1. A service flow processing method is characterized by comprising the following steps:

performing function segmentation processing on the image function model to obtain at least two image processing services;

determining an image processing service among the at least two image processing services, and querying an image processing model comprising the image processing service; wherein the image processing model comprises the image function model;

acquiring service flow information of the image processing service in the image processing model;

and carrying out service process processing on the image processing service according to the service process information to obtain a service execution process of the image processing model.

2. The service flow processing method according to claim 1, wherein the method further comprises:

and storing the image processing service in a service cluster to obtain service path information of the image processing service, and storing the service path information in a path information table.

3. The service flow processing method of claim 2, wherein the query includes an image processing model of the image processing service, comprising:

when it is monitored that the path information table stores the service path information, determining an image processing model of the image processing service storing the service path information.

4. The service flow processing method according to claim 2, wherein the method further comprises:

and generating an execution flow identification corresponding to the service execution flow for calling the service execution flow.

5. The service flow processing method according to claim 4, wherein the method further comprises:

receiving a service calling parameter; the service calling parameter comprises a service flow identifier;

and determining the service execution flow corresponding to the service flow identification according to the execution flow identification, and performing image processing on the image through the service execution flow corresponding to the service flow identification to generate an image processing result.

6. The service flow processing method according to claim 5, wherein the service invocation parameter further includes download address information and image processing information, and the image processing performed on the image through the service execution flow corresponding to the service flow identifier to generate an image processing result includes:

downloading the image according to the downloading address information;

based on the image processing information, performing image processing on the image through the image processing service included in the service execution flow corresponding to the service flow identification to obtain a service processing result;

and summarizing the service processing results to obtain image processing results.

7. The service flow processing method according to claim 6, wherein the image includes an image obtained by video frame extraction processing of a video, and a source of the image is determined by a category parameter in the service invocation parameter.

8. The service flow processing method according to claim 7, wherein the download address information, the image processing information and the category parameter are obtained by encoding processing.

9. The service flow processing method according to claim 5, wherein the service invocation parameter includes an identity parameter;

the determining the service execution flow corresponding to the service flow identifier according to the execution flow identifier includes:

carrying out authentication processing on the identity parameters to obtain an authentication processing result;

and determining the service execution flow corresponding to the service flow identification according to the execution flow identification based on the authentication processing result.

10. The service flow processing method according to claim 5, wherein the image processing the image through the service execution flow corresponding to the service flow identifier to generate an image processing result, includes:

determining the image processing service included in the service execution flow corresponding to the service flow identification as a service to be called, and determining the service path information of the service to be called in the path information table;

and calling the service to be called according to the service path information, and carrying out image processing on the image through the service to be called to generate an image processing result.

11. The service flow processing method according to claim 10, wherein the service path information includes a cluster identifier of the service cluster and network path information of the image processing service;

the calling the service to be called according to the service path information comprises the following steps:

determining the service cluster storing the service to be called according to the cluster identification;

and calling the service to be called in the service cluster according to the network path information.

12. The service flow processing method according to claim 5, wherein the method further comprises:

storing the image processing result in a content distribution network.

13. A service flow processing apparatus, the apparatus comprising:

the function segmentation module is configured to perform function segmentation processing on the image function model to obtain at least two image processing services;

a service determination module configured to determine an image processing service among the at least two image processing services and query an image processing model including the image processing service; wherein the image processing model comprises the image function model;

an information acquisition module configured to acquire service flow information of the image processing service in the image processing model;

and the flow processing module is configured to perform service flow processing on the image processing service according to the service flow information to obtain a service execution flow of the image processing model.

14. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the service flow processing method of any one of claims 1 to 12.

15. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the service flow processing method of any of claims 1 to 12 via execution of the executable instructions.

Background

Image processing services are widely used in a variety of image processing systems. When different services are accessed to the image processing system, the image processing service is required to be utilized to customize a dedicated image processing model, so that various service requirements are met conveniently, and rapid deployment and online are realized.

However, such a customization method takes a lot of manpower, so that the development period is long and the development cost is high. In addition, the interfaces of the different image processing models cannot be multiplexed, which also leads to a rapid increase in the maintenance costs of the image processing system.

In view of the above, there is a need in the art to develop a new service flow processing method and apparatus.

It should be noted that the information disclosed in the above background section is only for enhancement of understanding of the technical background of the present application, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure is directed to a service flow processing method, a service flow processing apparatus, a computer readable medium, and an electronic device, so as to overcome the technical problems of high labor cost and development cost and long development period, at least to some extent.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

According to an aspect of the embodiments of the present disclosure, there is provided a service-flow processing method, including:

performing function segmentation processing on the image function model to obtain at least two image processing services;

determining an image processing service among the at least two image processing services, and querying an image processing model comprising the image processing service; wherein the image processing model comprises the image function model;

acquiring service flow information of the image processing service in the image processing model;

and carrying out service process processing on the image processing service according to the service process information to obtain a service execution process of the image processing model.

According to an aspect of the embodiments of the present disclosure, there is provided a service-flow processing apparatus, including:

the function segmentation module is configured to perform function segmentation processing on the image function model to obtain at least two image processing services;

a service determination module configured to determine an image processing service among the at least two image processing services and query an image processing model including the image processing service; wherein the image processing model comprises the image function model or an image model other than the image function model;

an information acquisition module configured to acquire service flow information of the image processing service in the image processing model;

and the flow processing module is configured to perform service flow processing on the image processing service according to the service flow information to obtain a service execution flow of the image processing model.

In some embodiments of the present disclosure, based on the above technical solutions, the service-flow processing apparatus further includes:

the path storage module is configured to store the image processing service in a service cluster to obtain service path information of the image processing service, and store the service path information in a path information table.

In some embodiments of the present disclosure, based on the above technical solutions, the service determination module includes: an information monitoring sub-module configured to determine an image processing model including the image processing service in which the service path information is stored, when it is monitored that the path information table stores the service path information.

In some embodiments of the present disclosure, based on the above technical solutions, the service-flow processing apparatus further includes: and the identification generation module is configured to generate an execution flow identification corresponding to the service execution flow for calling the service execution flow.

In some embodiments of the present disclosure, based on the above technical solutions, the service-flow processing apparatus further includes: a parameter receiving module configured to receive a service invocation parameter; the service calling parameter comprises a service flow identifier;

and the flow determining module is configured to determine the service execution flow corresponding to the service flow identifier according to the execution flow identifier, and perform image processing on the image through the service execution flow corresponding to the service flow identifier to generate an image processing result.

In some embodiments of the present disclosure, based on the above technical solutions, the process determining module includes: an object download sub-module configured to download an image according to the download address information;

the service processing submodule is configured to perform image processing on the image through the image processing service included in the service execution flow corresponding to the service flow identification based on the image processing information to obtain a service processing result;

and the result summarizing submodule is configured to summarize the service processing result to obtain an image processing result.

In some embodiments of the present disclosure, based on the above technical solution, the image includes an image obtained by performing video frame extraction processing on a video, and a source of the image is determined by a category parameter in the service invocation parameter.

In some embodiments of the present disclosure, based on the above technical solution, the download address information, the image processing information, and the category parameter are obtained by encoding processing.

In some embodiments of the present disclosure, based on the above technical solutions, the process determining module includes: the authentication processing submodule is configured to perform authentication processing on the identity parameters to obtain an authentication processing result;

and the authentication success sub-module is configured to determine the service execution flow corresponding to the service flow identifier according to the execution flow identifier based on the authentication processing result.

In some embodiments of the present disclosure, based on the above technical solutions, the process determining module includes: a path determination submodule configured to determine that the image processing service included in the service execution flow corresponding to the service flow identifier is a service to be called, and determine the service path information of the service to be called in the path information table;

and the path calling submodule is configured to call the service to be called according to the service path information, and perform image processing on the image through the service to be called to generate an image processing result.

In some embodiments of the present disclosure, based on the above technical solutions, the path invoking sub-module includes: the cluster determining unit is configured to determine the service cluster storing the service to be called according to the cluster identification;

and the service calling unit is configured to call the service to be called in the service cluster according to the network path information.

In some embodiments of the present disclosure, based on the above technical solutions, the service-flow processing apparatus further includes: a result storage sub-module configured to store the image processing result in a content distribution network.

According to an aspect of the embodiments of the present disclosure, there is provided a computer readable medium, on which a computer program is stored, which when executed by a processor implements a service flow processing method as in the above technical solution.

According to an aspect of an embodiment of the present disclosure, there is provided an electronic apparatus including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the service flow processing method as in the above technical solution via executing the executable instructions.

According to an aspect of an embodiment of the present disclosure, there is provided a computer program product or a computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the service flow processing method provided in the above-mentioned various optional embodiments.

In the technical scheme provided by the embodiment of the disclosure, the image processing service is obtained according to the function segmentation processing, and the reusability of the image processing service is ensured on the basis of ensuring the uniqueness of the image processing function. Furthermore, the image processing service of the function segmentation processing is subjected to service flow processing, so that the labor cost and development resources are saved, the maintenance cost is greatly reduced, various image processing systems can be accessed more flexibly, and the efficiency of accessing the image processing systems is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty. In the drawings:

fig. 1 schematically illustrates an architecture diagram of an exemplary system to which the disclosed solution applies;

FIG. 2 schematically illustrates a flow chart of steps of a method of service flow processing in some embodiments of the present disclosure;

FIG. 3 schematically illustrates a flow diagram of steps of a method of invoking a service execution flow in accordance with an execution flow identification in some embodiments of the present disclosure;

FIG. 4 schematically illustrates a flow chart of steps of a method of determining a service execution flow in some embodiments of the present disclosure;

FIG. 5 schematically illustrates a flow chart of steps of a method of invoking a service execution flow of a parallel structure in some embodiments of the present disclosure;

FIG. 6 schematically illustrates a flow chart of steps of a method of generating image processing results in some embodiments of the present disclosure;

FIG. 7 schematically illustrates a flow chart of steps of a method of determining a service to be invoked in some embodiments of the present disclosure;

FIG. 8 schematically illustrates a block diagram of a vulgar character recognition model in an application scenario in accordance with embodiments of the present disclosure;

FIG. 9 is a block diagram schematically illustrating a pornographic material detection model in an application scenario according to some embodiments of the present disclosure;

FIG. 10 is a schematic diagram illustrating the architecture of a service-streamlined processing system in an application scenario in accordance with some embodiments of the present disclosure;

FIG. 11 is a schematic diagram illustrating the structure of a service flow process of a parallel chained low-prevailing task recognition model in some embodiments of the present disclosure;

FIG. 12 schematically illustrates a block diagram of a service flow processing apparatus in some embodiments of the present disclosure;

FIG. 13 schematically illustrates a structural schematic diagram of a computer system suitable for use with an electronic device embodying embodiments of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

In the related art, the image processing system is widely applicable to various application scenarios. The Software as a Service (SaaS a Service) system of the news and video advertisement collaboration department mainly has a function of providing image processing capability for each module on an advertisement delivery link, an advertisement retrieval link, and an advertisement playing link, and mainly uses an image intelligent (AI) model Service to perform capability output.

In a traditional scheme, before each service is accessed to an image SaaS system, a dedicated image AI model service needs to be customized, and the technical means customized according to needs can quickly and effectively meet the requirements of various services and realize quick online deployment.

However, this solution also has various disadvantages, and firstly, each image model service needs to be developed in a customized manner when accessing the image SaaS system, including communication protocol and interface customization, which occupies a large labor and time cost, and has a long development period and a high development cost. Then, since the business logic is coupled with the model processing logic, the interfaces of different image model services cannot be multiplexed, which causes the number of interfaces and the number of image model services to increase explosively with the increase of the number of access businesses, thereby causing the rapid increase of the system maintenance cost.

Based on the problems existing in the above schemes, the present disclosure provides a service flow processing method, a service flow processing apparatus, a computer readable medium, and an electronic device based on artificial intelligence and cloud technology.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

Computer Vision technology (CV) is a science for researching how to make a machine see, and further means that a camera and a Computer are used for replacing human eyes to perform machine Vision such as identification, tracking and measurement on a target, and further image processing is performed, so that the Computer processing becomes an image more suitable for human eyes to observe or is transmitted to an instrument to detect. As a scientific discipline, computer vision research-related theories and techniques attempt to build artificial intelligence systems that can capture information from images or multidimensional data. Computer vision technologies generally include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D technologies, virtual reality, augmented reality, synchronous positioning, map construction, and other technologies, and also include common biometric technologies such as face recognition and fingerprint recognition.

Cloud technology refers to a hosting technology for unifying serial resources such as hardware, software, and network in a wide area network or a local area network to realize calculation, storage, processing, and sharing of data.

Cloud technology (Cloud technology) is based on a general term of network technology, information technology, integration technology, management platform technology, application technology and the like applied in a Cloud computing business model, can form a resource pool, is used as required, and is flexible and convenient. Cloud computing technology will become an important support. Background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture-like websites and more web portals. With the high development and application of the internet industry, each article may have its own identification mark and needs to be transmitted to a background system for logic processing, data in different levels are processed separately, and various industrial data need strong system background support and can only be realized through cloud computing.

Cloud computing (cloud computing) is a computing model that distributes computing tasks over a pool of resources formed by a large number of computers, enabling various application systems to obtain computing power, storage space, and information services as needed. The network that provides the resources is referred to as the "cloud". Resources in the "cloud" appear to the user as being infinitely expandable and available at any time, available on demand, expandable at any time, and paid for on-demand.

As a basic capability provider of cloud computing, a cloud computing resource pool (called as an ifas (Infrastructure as a Service) platform for short is established, and multiple types of virtual resources are deployed in the resource pool and are selectively used by external clients.

According to the logic function division, a PaaS (Platform as a Service) layer can be deployed on an IaaS (Infrastructure as a Service) layer, a SaaS (Software as a Service) layer is deployed on the PaaS layer, and the SaaS can be directly deployed on the IaaS. PaaS is a platform on which software runs, such as a database, a web container, etc. SaaS is a variety of business software, such as web portal, sms, and mass texting. Generally speaking, SaaS and PaaS are upper layers relative to IaaS.

The service flow processing method of the computer vision technology and the cloud technology in the artificial intelligence is utilized, so that the labor cost and the development and maintenance cost are saved, and the efficiency of accessing the image processing system is improved.

Fig. 1 shows an exemplary system architecture diagram to which the disclosed solution is applied.

As shown in fig. 1, the system architecture 100 may include a terminal 110, a network 120, and a server side 130. Wherein the terminal 110 and the server 130 are connected through the network 120.

The terminal 110 may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, and the like. Network 120 may be any type of communications medium capable of providing a communications link between terminal 110 and server 130, such as a wired communications link, a wireless communications link, or a fiber optic cable, and the like, without limitation. The server 130 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform, and the like.

Specifically, the server 130 performs function segmentation processing on the image function model to obtain at least two image processing services. Further, an image processing service is determined in the at least two image processing services, and an image processing model comprising the image processing service is inquired; wherein the image processing model comprises an image function model. Then, service flow information of the image processing service in the image processing model is obtained, and service flow processing is carried out on the image processing service according to the service flow information to obtain a service execution flow of the image processing model.

Furthermore, an execution flow identifier corresponding to the service execution flow may be generated, so that the terminal 110 may invoke the service execution flow.

In addition, the service flow processing method in the embodiment of the present disclosure may be applied to a terminal, and may also be applied to a server, which is not particularly limited in the present disclosure. The embodiment of the disclosure is mainly illustrated by applying the service flow processing method to the server 130.

The service flow processing method, the service flow processing device, the computer readable medium, and the electronic device provided by the present disclosure are described in detail below with reference to specific embodiments.

Fig. 2 schematically illustrates a flowchart of steps of a service flow processing method in some embodiments of the present disclosure, and as illustrated in fig. 2, the service flow processing method may mainly include the following steps:

and S210, performing function segmentation processing on the image function model to obtain at least two image processing services.

S220, determining an image processing service in at least two image processing services, and inquiring an image processing model comprising the image processing service; wherein the image processing model comprises an image function model.

And step S230, acquiring service flow information of the image processing service in the image processing model.

And S240, carrying out service flow processing on the image processing service according to the service flow information to obtain a service execution flow of the image processing model.

In the exemplary embodiment of the present disclosure, the image processing service is obtained according to the function division processing, and the reusability of the image processing service is ensured on the basis of ensuring the uniqueness of the image processing function. Furthermore, the image processing service of the function segmentation processing is subjected to service flow processing, so that the labor cost and development resources are saved, the maintenance cost is greatly reduced, various image processing systems can be accessed more flexibly, and the efficiency of accessing the image processing systems is improved.

The following describes each step of the service flow processing method in detail.

In step S210, the image function model is subjected to function segmentation processing to obtain at least two image processing services.

In an exemplary embodiment of the present disclosure, the image processing service is a service that can be provided by the image function module, and may include a plurality of service contents such as an image input service and an image detection service, and may also be provided by other manners, and this exemplary embodiment is not particularly limited to this.

Specifically, the image function model may be a model with image processing capability, such as a vulgar character recognition model and a pornographic material detection model, or another image function model on an advertisement delivery, an advertisement retrieval, or an advertisement playing link, which is not particularly limited in this exemplary embodiment.

And the image processing service may be a service provided by each functional module in the image functional model. And performing abstract processing on the image function model according to the image processing function, so that the image processing service corresponding to each function module can be determined.

For example, when the image function model is a vulgar character recognition model, the image processing service may be a service provided by a picture input module, a service provided by a character detection module, a service provided by a character vulgar classification module, a service provided by a discrimination result output module, and the like; when the image function model is the pornographic animation material detection model, the image processing service may be a service provided by the picture input module, a service provided by the character detection module, a service provided by the cartoon character discrimination module, a service provided by the pornographic character discrimination module, a service provided by the discrimination result output module, and the like. When the image function model is an advertisement delivery, an advertisement retrieval, or another image function model on an advertisement playing link, the image processing service may also be another image processing service corresponding to another image function model, which is not particularly limited in this exemplary embodiment.

When the image processing service is provided by each functional module in the image functional model, the image processing service can characterize each functional module. Therefore, in order to perform the function division processing on the image processing model according to the function, the image processing service may be obtained by performing the function division processing on the image function model according to the image processing service.

When the image processing service is the service provided by the image input module, the service provided by the person detection module, the service provided by the person low-custom classification module and the service provided by the judgment result output module, the image processing service can be subjected to functional segmentation processing according to the image processing service to obtain the image input service, the person detection service, the person low-custom classification service and the judgment result output service; when the image processing service is a service provided by the picture input module, a service provided by the character detection module, a service provided by the cartoon character discrimination module, a service provided by the pornographic character discrimination module and a service provided by the discrimination result output module, the picture input service, the character detection service, the cartoon character discrimination service, the pornographic character discrimination service and the discrimination result output service can be obtained by performing function segmentation processing according to the image processing service.

In the exemplary embodiment, the image function model is subjected to function segmentation processing according to the image processing service to obtain at least two image processing services, so that a data basis is provided for subsequent service flow processing, and the reusability of the image processing service is improved.

After determining the image processing services, respective image processing services may be deployed to generate service path information.

In an alternative embodiment, the image processing service is stored in the service cluster to obtain service path information of the image processing service, and the service path information is stored in the path information table.

The service cluster is used for storing the image processing services obtained by the function segmentation processing, and a plurality of image processing services can be stored in one service cluster. One or more service clusters may be provided, and this exemplary embodiment is not particularly limited to this.

In order to solve the load problem caused by excessive deployed image processing services, the service path information deployed by the image processing services can be specified through the cluster identification of the service cluster and the network path information of the image processing services. That is, the service path information includes cluster identification of the service cluster and network path information of the image processing service.

The cluster identifier may be identification information of a load-balanced cluster, one cluster identifier may specify a group of network path information, and one network path information may specify one image processing service. The network path information may be routing information of the image processing service, or may be other information, which is not particularly limited in this exemplary embodiment. The routing information may be a storage path of the image processing service, and the corresponding image processing service may be acquired through the routing information.

And the path information table may store service path information of a new image processing service every time a new image processing service is monitored.

The path information table may be a table storing service path information. When the service path information includes the cluster identifier of the service cluster and the network path information of the image processing service, the path information table stores the cluster identifier and the network path information corresponding to the image processing service. That is, the path information table may be searched for service path information corresponding to the image processing service.

In the exemplary embodiment, after determining the image processing service obtained by the function segmentation processing, the image processing service may be further deployed, and the service path information related to the deployment location is stored, so as to facilitate subsequent query and processing of the corresponding image processing service through the service path information.

In step S220, an image processing service is determined among the at least two image processing services, and an image processing model including the image processing service is queried; wherein the image processing model comprises an image function model.

In an exemplary embodiment of the present disclosure, to perform a flow process on a plurality of image processing services obtained by a function segmentation process, one image processing service to be subjected to the flow process may be first determined in at least two image processing services. The image processing service may be determined randomly or may be specified according to actual requirements, and this exemplary embodiment is not particularly limited thereto.

Further, an image processing model comprising the image processing service is determined to perform the flow processing on the image processing service.

Specifically, to perform the flow processing on the image processing service, the path information table may be monitored to determine the time for performing the flow processing.

In an alternative embodiment, when it is monitored that the service path information is stored in the path information table, an image processing model including the image processing service in which the service path information is stored is determined.

Since the service path information of the image processing service is stored in the path information table when the image processing service is deployed, the image processing model can be determined to perform service flow processing after the deployment is completed. In addition, other timing of the service flow processing may be set according to actual requirements, which is not particularly limited in the present exemplary embodiment.

Since the image processing service is obtained by performing function segmentation processing on the image function model, and the same image processing service exists in the image processing model to be subjected to the flow processing, and a specific image processing service also exists, the image processing model including the image processing service can be determined to perform service flow processing on the image processing service included in the image processing model.

When the image processing service is a general image processing service, it can be determined that there are at least two image processing models including the image processing service; when the image processing service is a unique image processing service, it may be determined that there is only one image processing model including the image processing service.

For example, the services commonly included by the vulgar character recognition model and the pornographic material detection model are a picture input service, a character detection service and a discrimination result output service. Therefore, the image processing models including the image input service, the character detection service, and the discrimination result output service may have a vulgar character recognition model and a pornographic material detection model.

In addition, the vulgar character recognition model also comprises a special character vulgar classification service, and the pornographic animation material detection model also comprises a special cartoon character judgment service and a pornographic cartoon character judgment service. Thus, the image processing model including the character vulgar classification service may have a vulgar character recognition model, and the image processing model including the anima character discrimination service and the pornographic character discrimination service may have a pornographic material detection model.

In step S230, service flow information of the image processing service in the image processing model is acquired.

In an exemplary embodiment of the present disclosure, since the respective image processing services in the image processing model are executed in order, each image processing service has its own execution order in the image processing model, which is represented using the service flow information.

The service flow information may be represented by numbers, characters, letters, or the like, may also be represented by referring to an execution sequence of one service, or may be information in other manners, which is not particularly limited in this exemplary embodiment.

For example, the service flow information of the image input service in the vulgar character recognition model is 1, the service flow information of the character detection service is 2, the service flow information of the character vulgar classification service is 3, and the service flow information of the discrimination result output service is 4; the service flow information of the picture input service in the pornographic cartoon material detection model is 1, the service flow information of the character detection service is 2, the service flow information of the cartoon character discrimination service is 3, the service flow information of the pornographic cartoon character discrimination service is 4, and the service flow information of the discrimination result output service is 5.

Therefore, the service flow information of the same image processing service in different image processing models may be the same or different.

In step S240, the image processing service is subjected to service flow processing according to the service flow information to obtain a service execution flow of the image processing model.

In an exemplary embodiment of the present disclosure, after determining the service flow information of the image processing service in the image processing model, the image processing service may be subjected to service flow processing according to the service flow information to obtain a service execution flow corresponding to the image processing model.

The service flow processing is a processing method for connecting and processing the image processing service in other image processing services in the image processing model according to service flow information of the image processing service to obtain a service execution flow of the image processing service, and the processing result of the previous image processing service is an input parameter of the next image processing service because each image processing service has a service connection relationship after the connection processing. Since all the image processing services included in the image processing model are subjected to service flow processing, a service execution flow of the image processing model can be obtained after all the image processing services complete the service flow processing, and the service image flow represents a service connection relationship between the image processing services in the image processing model.

It should be noted that, since the image processing model includes the image function model, the image processing model of the service process may be a model that performs the service process on the image function model that has been newly subjected to the function segmentation process, that is, the service process is performed directly after the image function model is subjected to the function segmentation process.

In addition, the image processing model for performing the service flow processing includes another image processing model other than the image function model, and the another image processing model is an image processing model including the determined image processing service.

Moreover, the image processing model of the service process may further include an image processing model obtained by updating an image processing model. That is, the image processing model is updated according to actual needs, and after the update, the service flow process can be performed according to the image processing service included in the updated image processing model. Moreover, the service execution flow of the image processing model that is not updated may be deleted according to actual situations to save storage space, and the service execution flow of the image processing model before being updated may also be saved as an extended manner, which is not particularly limited in this exemplary embodiment.

For example, the service flow information of the picture input service in the vulgar character recognition model is 1, the service flow information of the character detection service is 2, the service flow information of the character vulgar classification service is 3, and the service flow information of the discrimination result output service is 4, so that the service flow of the picture input service, the character detection service, the character vulgar classification service and the discrimination result output service included in the vulgar character recognition model is respectively processed in a service flow manner, and the service execution flow of the image processing service in the vulgar character recognition model can be obtained as the picture input service → the character detection service → the character vulgar classification service → the discrimination result output service; the service flow information of the picture input service in the pornographic cartoon material detection model is 1, the service flow information of the character detection service is 2, the service flow information of the cartoon character discrimination service is 3, the service flow information of the pornographic cartoon character discrimination service is 4, and the service flow information of the discrimination result output service is 5, so that the service flow processing is respectively carried out on the picture input service, the character detection service, the cartoon character discrimination service, the pornographic cartoon character discrimination service and the discrimination result output service which are included in the pornographic cartoon material detection model, and the service execution flow of the pornographic cartoon material detection model can be obtained as the picture input service → the character detection service → the cartoon character discrimination service → the pornographic cartoon character discrimination service → the discrimination result output service.

Moreover, the service execution flow may be in a chain structure, and the chain structure may be in a serial chain structure, a parallel chain structure, or other structures, which is not limited in this exemplary embodiment.

After the service execution flow of the image processing model is generated, corresponding execution identification information may be generated for invocation.

In an alternative embodiment, an execution flow identifier corresponding to the service execution flow is generated for invoking the service execution flow.

The execution flow identifier may be identification information of the service execution flow, and one service execution flow uniquely corresponds to one execution flow identifier. A service execution flow can be uniquely determined by the execution flow identification information.

In an alternative embodiment, fig. 3 shows a flow chart of the steps of a method of invoking a service execution flow based on an execution flow identification, as shown in fig. 3, the method comprising at least the steps of: in step S310, receiving a service invocation parameter; the service calling parameter comprises a service flow identification.

When the service end requests to call the service execution flow, a service request is sent. The service request carries a service invocation parameter, and in order to specify the service execution flow to be invoked, the service invocation parameter includes an execution flow identifier.

In step S320, a service execution flow corresponding to the service flow identifier is determined according to the execution flow identifier, and the image processing is performed on the image through the service execution flow corresponding to the service flow identifier to generate an image processing result.

Because the execution flow identifier and the service execution flow have a one-to-one correspondence relationship, after the service flow identifier in the service calling parameter is obtained, the service execution flow to be called can be determined according to the execution flow identifier which is the same as the service flow identifier, so that the image processing is performed on the image through the service execution flow to generate an image processing result.

When the service request is called, all the application programs initiating the service request do not have the qualification of calling the service execution flow, so the service request can be authenticated.

In an alternative embodiment, the service invocation parameter comprises an identity parameter. Fig. 4 shows a schematic flow chart of the steps of a method for determining a service execution flow, as shown in fig. 4, the method at least comprising the following steps: in step S410, the authentication processing is performed on the identity parameter to obtain an authentication processing result.

The identity parameters may be identification information and signature information, i.e., appid and app _ sign, of the application that initiated the service request. The signature information may be signature information corresponding to the service request generated when the service end initiates the service request, so as to send the identification information and the signature information for verification. The signature information may be generated by encrypting the access request according to the key, or may be generated according to other manners, which is not limited in this exemplary embodiment.

The authentication processing of the identity parameter may be to determine whether the identification information and the signature information of the application program that can invoke the service execution process include the identification information and the signature information carried in the service request, or may be performed in other authentication manners, which is not particularly limited in this exemplary embodiment.

In step S420, based on the authentication processing result, a service execution flow corresponding to the service flow identifier is determined according to the execution flow identifier.

And when the identification information and the signature information of the application program which can call the service execution flow comprise the identification information and the signature information carried in the service request, determining that the authentication processing result is authenticated, so as to further determine the service execution flow by using the execution flow identification.

In the exemplary embodiment, the identity parameter is used to authenticate the application program initiating the service request, so that the information security and privacy of the service execution flow are ensured.

It is worth to be noted that, if the service execution flow is in a serial structure, the image processing result can be obtained by directly calling the service execution flow to perform image processing on the image; when the service execution flow is of a parallel structure, after the service execution flow is called to perform image processing on the image, the processing results can be summarized to obtain an image processing result.

In an alternative embodiment, the service invocation parameters further include download address information and image processing information. Fig. 5 shows a schematic flow chart of the steps of a method for invoking a service execution flow of a parallel structure, as shown in fig. 5, the method at least comprises the following steps: in step S510, an image is downloaded according to the download address information.

The download address information is position information stored in the image to be processed, and the image can be downloaded according to the position information so as to perform subsequent image processing on the image.

In an alternative embodiment, the image includes an image obtained by performing video framing processing on a video, and the source of the image is determined by a category parameter in the service invocation parameter.

When the service end sends the service request, the service request also carries a category parameter, so that whether the downloaded image is obtained by performing video frame extraction processing on the video can be determined according to the category parameter. The video frame extraction processing is a processing mode of extracting a plurality of frames at certain intervals in a video to be processed and simulating to obtain an image at certain intervals.

One piece of image, namely the image obtained according to the video, can be obtained through the video frame extraction processing. And processing the image processing service in the image calling service execution flow to obtain an image processing result.

Of course, if the service execution flow is also configured in parallel, the picture processing result may be obtained in accordance with the processing method of steps S520 to S530.

In the present exemplary embodiment, if the image is obtained by performing video frame extraction processing on a video, a service execution flow may also be called to perform image processing, so that application scenarios of the service execution flow are enriched. In step S520, based on the image processing information, the image is processed by the image processing service included in the service execution flow corresponding to the service flow identifier to obtain a service processing result.

The image processing information may be an input parameter necessary for image processing of an image, or may be other necessary information, which is not particularly limited in the present exemplary embodiment.

After the image and the image processing information are determined, a service execution flow can be called to perform image processing on the image and the image processing information to obtain a service processing result.

It is to be noted that, when the image execution flow is a parallel structure, the service processing result may be a processing result of at least two sub-flows. Moreover, the image processing information may be the same or different for at least two sub-flows, and this exemplary embodiment is not particularly limited thereto.

In step S530, the service processing results are summarized to obtain an image processing result.

The summary processing may be a manner of merging processing results of at least two sub-flows, or may be other processing manners, which is not particularly limited in this exemplary embodiment.

For example, when the processing result of one sub-flow is result 1 and the processing result of the other sub-flow is result 2, the processing may be integrated as the image processing result in a collective manner of [ result 1, result 2 ].

In the exemplary embodiment, the image processing result can be obtained by calling the image processing service in the service execution flow with the parallel structure, so that the application mode of the service execution flow is enriched, and the calling scene of the service execution flow is enlarged.

In an alternative embodiment, the download address information, the image processing information and the category parameter are obtained by an encoding process.

The encoding method may be encoding processing using JSON (JSON Object Notation) protocol, or may be other encoding methods, which is not particularly limited in this exemplary embodiment.

JSON is an ideal data exchange format, is easy to read and write by people, is easy to analyze and generate by a machine, and is very common in interface data development and transmission. When the JSON protocol coding mode is used for coding the download address information, the image processing information and the category parameters, the information is conveniently carried and transmitted through the service request, and a more convenient information transmission mode is provided for determining the service execution flow.

Specifically, the content design of the service invocation parameters can be viewed with reference to table 1:

wherein appid and app _ sign are identification information and signature information of the application program, namely identity parameters; the model _ action is a flow identifier, namely the model _ action can be used for determining a service to be called to execute the flow; the model _ param is a parameter list which may include download address information, image processing information, category parameters, and the like, and the download address information, the image processing information, and the category parameters are transmitted by JSON protocol coding.

When the image processing service in the service execution flow is downloaded and called to perform image processing on the image and the image processing information, the image processing service can be acquired from the path information table and called.

In an alternative embodiment, fig. 6 shows a flow chart of the steps of a method of generating image processing results, which method comprises at least the following steps, as shown in fig. 6: in step S610, the image processing service included in the service execution flow corresponding to the service flow identifier is determined as a service to be called, and service path information of the service to be called is determined in the path information table.

The path information table may be a table storing service path information of the image processing service. Because the service path information stored in the path information table has a one-to-one correspondence relationship with the image processing services, the image processing services in the service execution flow can be determined one by one as the services to be called, and the service path information of the services to be called is determined so as to be called according to the sequence of the service execution flow.

In step S620, a service to be called is called according to the service path information, and the image is processed by the service to be called to generate an image processing result.

In an alternative embodiment, the service path information comprises a cluster identification of the service cluster and network path information of the image processing service. Fig. 7 shows a flow chart of the steps of a method of determining a service to be invoked, which method comprises at least the following steps, as shown in fig. 7: in step S710, a service cluster storing the service to be called is determined according to the cluster identifier.

The cluster identifier may be identification information of a load-balanced cluster, one cluster identifier may specify a group of network path information, and one network path information specifies one image processing service. Therefore, the service cluster where the image processing service in the service execution flow is located, that is, the service cluster where the service to be called is located, can be determined according to the cluster identifier in the service path information.

In step S720, the service to be called in the service cluster is called according to the network path information.

The network path information may be routing information of the image processing service, or may be other information, which is not particularly limited in this exemplary embodiment. The routing information may be a storage path of the image processing service, and the corresponding image processing service, that is, the service to be invoked, may be acquired through the routing information.

Further, after a service cluster is determined, the service to be called in the service execution flow can be acquired according to the network path information.

In the exemplary embodiment, the service to be called in the service execution flow can be called through the service path information, the calling process is meticulous in logic, the load balancing problem in the storage and calling processes is solved, and the practicability is strong.

After determining the service to be called, the image processing may be performed on the image by using the service to be called to generate an image processing result. Also, since the amount of image processing result data generated during image processing is large, the image processing result can be stored at a specified position.

In an alternative embodiment, the image processing results are stored in a content distribution network.

Among them, a Content Delivery Network (CDN) is a novel Network construction method, which is a Network overlay layer optimized particularly for delivering broadband rich media over a conventional IP (Internet Protocol). In a broad sense, the CDN represents a network service mode based on quality and order. In brief, the CDN is a strategically deployed overall system, and includes 4 requirements of distributed storage, load balancing, redirection of network requests, and content management, and the content management and global network traffic management are at the core of the CDN. By determining user proximity and server load, the CDN ensures that the content serves the user's request in an extremely efficient manner. In general, content services are based on cache servers, also called proxy caches, which are located at the edge of the network, just one Hop away (Single Hop) from the user. Meanwhile, the proxy cache is a transparent mirror image of the content provider origin server (typically located in the CDN service provider's data center). Such an architecture enables a CDN service provider to provide the best possible experience on behalf of the content provider to end users who are intolerant of any delay in request response time. According to statistics, by adopting the CDN technology, 70% -95% of content access amount of the whole website page can be processed, the pressure of a server is reduced, and the performance and the expandability of the website are improved. CDNs are becoming more widely used because of their high efficiency and high quality of service.

It should be noted that the image processing result stored in the CDN may be an intermediate processing result of the image processing service, or may be a final processing result of the image processing model, so as to satisfy a processing result in each process of the service end invoking service execution flow.

In the exemplary embodiment, the image processing result is stored in the content distribution network, which not only can meet the requirement of large data volume of the image processing result in the image processing process, but also can meet the requirement of the service end for rapidly obtaining the image processing result, and the response speed and success probability of the service end request are improved.

The service flow processing method provided in the embodiment of the present disclosure is described in detail below with reference to a specific application scenario.

Fig. 8 is a block diagram illustrating a structure of a vulgar character recognition model in an application scenario, where as shown in fig. 8, the vulgar character recognition model includes a picture input module, a character detection module, a character vulgar classification module, a discrimination result output module, and the like.

It should be noted that each functional module can provide image processing services, i.e., the functional module is an externalized representation of the services.

Fig. 9 shows a module structure diagram of a pornographic animation material detection model in an application scene, and as shown in fig. 9, the pornographic animation material detection model includes functional modules of a picture input module, a character detection module, an animation character discrimination module, a pornographic character discrimination module and a discrimination result output module.

The functional abstraction of the vulgar character recognition model and the pornographic cartoon material detection model can discover that the functional modules of the two models comprise the same module, such as a picture input module, a character detection model and a judgment result output module, and a special module, such as a vulgar character classification module in the vulgar character recognition model, and an animation character judgment module and a pornographic cartoon character judgment module in the pornographic cartoon material detection model.

Therefore, the vulgar character recognition model and the pornographic cartoon material detection model can be subjected to functional segmentation processing to obtain the universal module and the special module, and deployment can be carried out.

In order to avoid explosive growth of system interfaces and maintain the universality and functional singleness of functional modules in the image SaaS system, a service flow processing system can be deployed in the image SaaS system, and a service end is accessed into the image SaaS system in a more flexible mode.

The image SaaS system mainly provides image processing services for each module on an advertisement putting, advertisement retrieving and advertisement playing link. In particular, the image SaaS system of the news video advertisement cooperation department is mainly applied to an advertisement intelligent auditing module in advertisement putting.

The intelligent advertisement auditing module mainly aims to use a machine to replace manual work to automatically audit the advertisements submitted by advertisers, and avoid information such as low-custom pictures, infringement trademarks, prohibited articles and the like in the advertisements. Therefore, in the advertisement intelligent matching module, the image SaaS system mainly provides corresponding processing capability for automatic auditing and processing of pictures or videos in advertisement materials, including judging whether the pictures or videos are vulgar, contain infringement trademarks, contain contraband, and the like.

Fig. 10 shows a schematic structural diagram of a service-flow processing system in an application scenario, and as shown in fig. 10, the service-flow processing system includes a configuration center 1010, a service cluster module 1020, a service-flow processing module 1030 of an image SaaS system, and a business end 1040.

When each image processing service comes online, the corresponding service path information is registered in the configuration center 1010. The service flow processing module 1030 of the image SaaS system subscribes the service path information for subsequent calling. Specifically, the service cluster module 1020 sends a request to the configuration center 1010 after being online, and sends the cluster identifier of its service cluster and the network path information of the image processing service to the configuration center 1010. Further, the configuration center 1010 writes the cluster identifier of the service cluster and the network path information of the image processing service into the path information table, and provides the service flow processing module 1030 of the image SaaS system with subscription.

The service flow processing module 1030 of the image SaaS system monitors the path information table. When monitoring that the cluster identifier of the new service cluster and the network path information of the image processing service are written in the path information table, determining an image processing model of the image processing service corresponding to the cluster identifier of the service cluster and the network path information of the image processing service, performing service flow processing on the image processing service according to the service flow information in the image processing model to obtain a service execution flow, and issuing the service execution flow to the configuration center 1010. When the service flow processing module 1030 of the image SaaS system subscribes to the service execution flow, the service execution flow may be loaded into the memory for calling.

The service end 1040 sends a service request to the service flow processing module 1030 of the image SaaS system, and carries a service call parameter to determine a service execution flow to be called. The service flow processing module 1030 of the image SaaS system sequentially calls the image processing service in the service execution flow to obtain an image processing result.

When the service execution flow is of a parallel structure, the service processing results of the sub-flows are also summarized to obtain an image processing result, and the image processing result is returned to the service end 1040.

Fig. 11 is a schematic structural diagram illustrating a service flow process of an vulgar character recognition model with a parallel chain structure, as shown in fig. 11, the vulgar character recognition model is of a parallel chain structure and includes a picture input service, a character detection service, a character vulgar classification service, a key part detection service, a key part vulgar classification service and a discrimination result output service.

The service flow processing flow can also use JSON protocol coding processing, and the coding mode is as follows:

when the service execution flow is in a chain structure, a mesh diagram of the service execution flow may be gradually generated. Then, when each image processing service is accessed, the corresponding service execution flow is published to the configuration center only by using the JSON coding protocol, and the service flow processing module of the image SaaS system subscribes to the information to be loaded into the memory to call the service execution flow.

Specifically, the service path information corresponding to the vulgar character recognition model is as follows:

each image processing service of the vulgar character recognition model corresponds to a cluster identifier, such as a cluster identifier of a picture input service of 1981633:65536, a cluster identifier of a character detection model service of 1528065:720896, a cluster identifier of a key part detection service of 1570305:983040, a cluster identifier of a character vulgar classification service of 1528065:655360, and a cluster identifier of a key part vulgar classification service of 1528065: 589824. The cluster identifier corresponds to a set of network path information and a service port, i.e. a set of service clusters.

When a service flow processing module of the image SaaS system calls an image processing service, network path information and a service port are obtained through the cluster identifier, and the service request is sent to a corresponding service instance.

Based on the above application scenarios, the service-flow processing method provided by the embodiment of the present disclosure obtains the image processing service according to the function segmentation processing, and ensures the reusability of the image processing service on the basis of ensuring the uniqueness of the image processing function. Furthermore, the image processing service of the function segmentation processing is subjected to service flow processing, so that at least 50% of labor cost and at least 30% of development resources are saved, the maintenance cost is greatly reduced, meanwhile, various image processing systems can be accessed more flexibly, and the efficiency of accessing the image processing systems is improved.

It should be noted that although the various steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that these steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

The following describes an embodiment of an apparatus of the present disclosure, which may be used to execute a service flow processing method in the foregoing embodiment of the present disclosure. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the service-flow processing method described above in the present disclosure.

Fig. 12 schematically shows a block diagram of a service-flow processing apparatus in some embodiments of the present disclosure, and as shown in fig. 12, the service-flow processing apparatus 1200 mainly may include: a function segmentation module 1210, a service determination module 1220, an information acquisition module 1230, and a flow processing module 1240.

A function segmentation module 1210 configured to perform function segmentation processing on the image function model to obtain at least two image processing services; a service determination module 1220 configured to determine an image processing service among the at least two image processing services and query an image processing model including the image processing service; wherein the image processing model comprises an image function model; an information obtaining module 1230 configured to obtain service flow information of the image processing service in the image processing model; and the flow processing module 1240 is configured to perform service flow processing on the image processing service according to the service flow information to obtain a service execution flow of the image processing model.

In some embodiments of the present disclosure, the service-flow processing apparatus further includes:

and the path storage module is configured to store the image processing service in the service cluster to obtain service path information of the image processing service, and store the service path information in the path information table.

In some embodiments of the disclosure, the service determination module comprises: and the information monitoring sub-module is configured to determine an image processing model comprising the image processing service stored with the service path information when monitoring that the path information table stores the service path information.

In some embodiments of the present disclosure, the service-flow processing apparatus further includes: and the identification generation module is configured to generate an execution flow identification corresponding to the service execution flow for calling the service execution flow.

In some embodiments of the present disclosure, the service-flow processing apparatus further includes: a parameter receiving module configured to receive a service invocation parameter; the service calling parameter comprises a service flow identifier;

and the flow determining module is configured to determine a service execution flow corresponding to the service flow identifier according to the execution flow identifier, and perform image processing on the image through the service execution flow corresponding to the service flow identifier to generate an image processing result.

In some embodiments of the disclosure, the flow determination module comprises: an object download sub-module configured to download the image according to the download address information;

the service processing submodule is configured to perform image processing on the image through an image processing service included in a service execution flow corresponding to the service flow identification based on the image processing information to obtain a service processing result;

and the result summarizing submodule is configured to summarize the service processing result to obtain an image processing result.

In some embodiments of the present disclosure, the image includes an image obtained by video framing a video, and the source of the image is determined by a category parameter in the service invocation parameter.

In some embodiments of the present disclosure, the download address information, the image processing information, and the category parameter are obtained by an encoding process.

In some embodiments of the disclosure, the flow determination module comprises: the authentication processing submodule is configured to perform authentication processing on the identity parameters to obtain an authentication processing result;

and the authentication success sub-module is configured to determine a service execution flow corresponding to the service flow identifier according to the execution flow identifier based on the authentication processing result.

In some embodiments of the disclosure, the flow determination module comprises: the path determining submodule is configured to determine that the image processing service included in the service execution flow corresponding to the service flow identification is the service to be called, and determine service path information of the service to be called in a path information table;

and the path calling submodule is configured to call the service to be called according to the service path information, and perform image processing on the image through the service to be called to generate an image processing result.

In some embodiments of the disclosure, the path invocation submodule includes: the cluster determining unit is configured to determine a service cluster for storing the service to be called according to the cluster identifier;

and the service calling unit is configured to call the service to be called in the service cluster according to the network path information.

In some embodiments of the present disclosure, the service-flow processing apparatus further includes: a result storage sub-module configured to store the image processing result in the content distribution network.

The specific details of the service-flow processing apparatus provided in each embodiment of the present disclosure have been described in detail in the corresponding method embodiment, and therefore are not described herein again.

FIG. 13 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present disclosure.

It should be noted that the computer system 1300 of the electronic device shown in fig. 13 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments of the present disclosure.

As shown in fig. 13, a computer system 1300 includes a Central Processing Unit (CPU)1301 that can perform various appropriate actions and processes according to a program stored in a Read-Only Memory (ROM) 1302 or a program loaded from a storage portion 1308 into a Random Access Memory (RAM) 1303. In the RAM 1303, various programs and data necessary for system operation are also stored. The CPU 1301, the ROM 1302, and the RAM 1303 are connected to each other via a bus 1304. An Input/Output (I/O) interface 1305 is also connected to bus 1304.

The following components are connected to the I/O interface 1305: an input portion 1306 including a keyboard, a mouse, and the like; an output section 1307 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage portion 1308 including a hard disk and the like; and a communication section 1309 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 1309 performs communication processing via a network such as the internet. A drive 1310 is also connected to the I/O interface 1305 as needed. A removable medium 1311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1310 as necessary, so that a computer program read out therefrom is mounted into the storage portion 1308 as necessary.

In particular, the processes described in the various method flowcharts may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications component 1309 and/or installed from removable media 1311. The computer program executes various functions defined in the system of the present application when executed by a Central Processing Unit (CPU) 1301.

It should be noted that the computer readable medium shown in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.