1. An application recommendation method, comprising:

acquiring user information of a target user and characteristic data of an application to be recommended, and acquiring platform profit price information of the application to be recommended;

determining click rate evaluation values of the target users to the applications to be recommended according to the user information and the characteristic data;

determining a recommendation score of the application to be recommended according to the click rate evaluation value and the platform profit price information;

and recommending the application to be recommended according to the recommendation score.

2. The application recommendation method of claim 1, wherein the determining the click rate estimate of the target user for the application to be recommended according to the user information and the feature data comprises:

inputting the user information and the characteristic data into a trained click rate prediction model for processing to obtain the click rate estimated value of the target user to the application to be recommended.

3. The application recommendation method of claim 2, wherein before the inputting the user information and the feature data into the trained click-through rate prediction model for processing to obtain the click-through rate estimation value of the target user for the application to be recommended, the method further comprises:

acquiring a sample training set; the sample training set comprises sample user information, sample characteristic data applied by a sample and a click rate label corresponding to the sample characteristic data;

and training an initial neural network model by using the sample training set to obtain a trained click rate prediction model.

4. The application recommendation method of claim 3, wherein said obtaining a sample training set comprises:

acquiring sample user information, and acquiring categorical characteristic information and continuous value characteristic information of sample application;

and determining sample characteristic data applied to the sample according to the classification characteristic information and the continuous value characteristic information.

5. The application recommendation method of claim 3, wherein said training an initial neural network model using said sample training set, resulting in a trained click-through rate prediction model for processing, comprises:

inputting the sample user information and the sample characteristic data of the sample application into an initial neural network model for processing to obtain sample click rates corresponding to the sample user information and the sample application;

calculating a target loss value according to the sample click rate, the click rate label and a preset loss function;

if the target loss value does not meet the preset suspension condition, updating the initial neural network model according to the target loss value, returning to execute the step of inputting the sample user information and the sample characteristic data of the sample application into the initial neural network model for processing, and obtaining the sample click rate corresponding to the sample user information and the sample application;

and if the target loss value meets the preset suspension condition, outputting a trained click rate prediction model.

6. The application recommendation method according to claim 1, wherein the obtaining platform profit price information of the application to be recommended comprises:

acquiring the activation unit price of the application to be recommended;

and carrying out normalization processing on the activation unit price to obtain the platform profit price information of the application to be recommended.

7. The application recommendation method of claim 1, wherein said determining a recommendation score for said application to be recommended based on said click-through rate estimate and said platform profitability price information comprises:

and multiplying the click rate estimated value and the platform profit price information to obtain the recommendation score of the application to be recommended.

8. An application recommendation apparatus, comprising:

the system comprises an acquisition unit, a recommendation unit and a recommendation unit, wherein the acquisition unit is used for acquiring user information of a target user and feature data of an application to be recommended and acquiring platform profit price information of the application to be recommended;

the first determining unit is used for determining the click rate estimated value of the target user to the application to be recommended according to the user information and the characteristic data;

the second determining unit is used for determining the recommendation score of the application to be recommended according to the click rate estimation value and the platform profit price information;

and the recommending unit is used for recommending the application to be recommended according to the recommendation score.

9. An application recommendation device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.

Background

In the big data era, the application recommendation system can improve the commercial income of companies on one hand and improve the use experience of users on the other hand by mining the preference of the users. When application recommendation is performed, there are many common recommendation algorithms, such as association rule recommendation based on business, behavior recommendation based on big data, linear model recommendation based on machine learning, and neural network model recommendation based on deep learning. However, the recommendation method described above focuses more on analyzing user behavior from the user experience, does not consider the benefit of the recommendation platform, and cannot comprehensively recommend applications.

Disclosure of Invention

The embodiment of the application provides an application recommendation method, an application recommendation device, application recommendation equipment and a computer readable storage medium, and can solve the problems.

In a first aspect, an embodiment of the present application provides an application recommendation method, including:

acquiring user information of a target user and characteristic data of an application to be recommended, and acquiring platform profit price information of the application to be recommended;

determining click rate evaluation values of the target users to the applications to be recommended according to the user information and the characteristic data;

determining a recommendation score of the application to be recommended according to the click rate evaluation value and the platform profit price information;

and recommending the application to be recommended according to the recommendation score.

Further, the determining the click rate estimation value of the target user for the application to be recommended according to the user information and the feature data includes:

inputting the user information and the characteristic data into a trained click rate prediction model for processing to obtain the click rate estimated value of the target user to the application to be recommended.

Further, before the inputting the user information and the feature data into the trained click rate prediction model for processing to obtain the click rate estimation value of the target user on the application to be recommended, the method further includes:

acquiring a sample training set; the sample training set comprises sample user information, sample characteristic data applied by a sample and a click rate label corresponding to the sample characteristic data;

and training an initial neural network model by using the sample training set to obtain a trained click rate prediction model.

Further, the obtaining a training set of samples includes:

acquiring sample user information, and acquiring categorical characteristic information and continuous value characteristic information of sample application;

and determining sample characteristic data applied to the sample according to the classification characteristic information and the continuous value characteristic information.

Further, the training an initial neural network model by using the sample training set to obtain a trained click rate prediction model for processing, including:

inputting the sample user information and the sample characteristic data of the sample application into an initial neural network model for processing to obtain sample click rates corresponding to the sample user information and the sample application;

calculating a target loss value according to the sample click rate, the click rate label and a preset loss function;

if the target loss value does not meet the preset suspension condition, updating the initial neural network model according to the target loss value, returning to execute the step of inputting the sample user information and the sample characteristic data of the sample application into the initial neural network model for processing, and obtaining the sample click rate corresponding to the sample user information and the sample application;

and if the target loss value meets the preset suspension condition, outputting a trained click rate prediction model.

Further, the obtaining of the platform profit price information of the application to be recommended includes:

acquiring the activation unit price of the application to be recommended;

and carrying out normalization processing on the activation unit price to obtain the platform profit price information of the application to be recommended.

Further, the determining the recommendation score of the application to be recommended according to the click-through rate estimate and the platform profit price information includes:

and multiplying the click rate estimated value and the platform profit price information to obtain the recommendation score of the application to be recommended.

In a second aspect, an embodiment of the present application provides an application recommendation apparatus, including:

the system comprises an acquisition unit, a recommendation unit and a recommendation unit, wherein the acquisition unit is used for acquiring user information of a target user and feature data of an application to be recommended and acquiring platform profit price information of the application to be recommended;

the first determining unit is used for determining the click rate estimated value of the target user to the application to be recommended according to the user information and the characteristic data;

the second determining unit is used for determining the recommendation score of the application to be recommended according to the click rate estimation value and the platform profit price information;

and the recommending unit is used for recommending the application to be recommended according to the recommendation score.

Further, the first determining unit is specifically configured to:

inputting the user information and the characteristic data into a trained click rate prediction model for processing to obtain the click rate estimated value of the target user to the application to be recommended.

Further, the first determining unit is specifically further configured to:

acquiring a sample training set; the sample training set comprises sample user information, sample characteristic data applied by a sample and a click rate label corresponding to the sample characteristic data;

and training an initial neural network model by using the sample training set to obtain a trained click rate prediction model.

Further, the first determining unit is specifically further configured to:

acquiring sample user information, and acquiring categorical characteristic information and continuous value characteristic information of sample application;

and determining sample characteristic data applied to the sample according to the classification characteristic information and the continuous value characteristic information.

Further, the first determining unit is specifically further configured to:

inputting the sample user information and the sample characteristic data of the sample application into an initial neural network model for processing to obtain sample click rates corresponding to the sample user information and the sample application;

calculating a target loss value according to the sample click rate, the click rate label and a preset loss function;

if the target loss value does not meet the preset suspension condition, updating the initial neural network model according to the target loss value, returning to execute the step of inputting the sample user information and the sample characteristic data of the sample application into the initial neural network model for processing, and obtaining the sample click rate corresponding to the sample user information and the sample application;

and if the target loss value meets the preset suspension condition, outputting a trained click rate prediction model.

Further, the obtaining unit is specifically configured to:

acquiring the activation unit price of the application to be recommended;

and carrying out normalization processing on the activation unit price to obtain the platform profit price information of the application to be recommended.

Further, the second determining unit is specifically configured to:

and multiplying the click rate estimated value and the platform profit price information to obtain the recommendation score of the application to be recommended.

In a third aspect, an embodiment of the present application provides an application recommendation device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor, when executing the computer program, implements the application recommendation method according to the first aspect.

In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the application recommendation method according to the first aspect.

In the embodiment of the application, user information of a target user and characteristic data of an application to be recommended are obtained, and platform profit price information of the application to be recommended is obtained; determining click rate estimated values of applications to be recommended by a target user according to the user information and the characteristic data; determining a recommendation score of the application to be recommended according to the click rate evaluation value and the profit price information; and recommending the application to be recommended according to the recommendation score. According to the method, not only is the user experience taken as a starting point, but also the user behavior is analyzed during recommendation, the benefit of a recommendation platform is also considered, on one hand, the user experience is guaranteed, on the other hand, the limited recommendation position can be effectively utilized to promote commercial revenue, and more comprehensive application recommendation can be carried out.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a schematic flow chart of an application recommendation method according to a first embodiment of the present application;

fig. 2 is a schematic diagram of an application recommendation apparatus according to a second embodiment of the present application;

fig. 3 is a schematic diagram of an application recommendation device according to a third embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to" determining "or" in response to detecting ". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".

Furthermore, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.

Referring to fig. 1, fig. 1 is a schematic flowchart of an application recommendation method according to a first embodiment of the present application. In this embodiment, an execution subject of the application recommendation method is a device having an application recommendation function, such as a server, a desktop computer, and the like. In this embodiment, a platform is mounted on the device, and a user accesses the platform, and the platform recommends an application according to the application recommendation method in this embodiment. The platform may be a platform for recommending applications, or a platform with a composite function, for example, a browser platform may perform search browsing or application recommendation.

The data quality monitoring method shown in fig. 1 may include:

s101: the method comprises the steps of obtaining user information of a target user and feature data of an application to be recommended, and obtaining platform profit price information of the application to be recommended.

The device acquires user information of a target user, the target user is a user accessing an application recommendation platform on the device, the user information of the target user is information for identifying characteristics of the target user, and the user information of the target user can include user identification, user age, user gender, device model, use duration and the like.

The device can acquire the user information of the target user through the registration information of the user on the platform and the device information of the user login platform.

The device obtains feature data of the application to be recommended. In this embodiment, the recommendation score of the application to be recommended needs to be calculated, and a recommendation policy of the application to be recommended is determined according to the recommendation score, that is, how to recommend the application. The feature data of the application to be recommended may include all information and features of the application to be recommended, and specifically, may include an applicable group of the application to be recommended, a historical download number, an application size, a historical evaluation, and the like.

Therefore, the equipment acquires the user information of the target user and the feature data of the application to be recommended, so that the information from the perspective of the user is acquired, and the user experience can be guaranteed during recommendation.

And the equipment acquires the platform profit price information of the application to be recommended from the perspective of the platform. Specifically, the merchant of the application puts the application on the platform, and if the user downloads the application of the merchant through the platform, the merchant needs to pay a certain fee to the platform, and the device may determine, according to the fee, platform profit price information of the application to be recommended in this embodiment. In the embodiment, from the perspective of the user, by combining the platform profit price information of the application to be recommended, the experience of the user can be ensured, and the benefit of the platform can also be ensured when the application is recommended.

Because the platform profit unit prices of different applications are different greatly, in order to avoid the platform profit unit prices of the applications from affecting the final recommendation result too much, the platform profit unit prices are selected to be normalized in the embodiment, and the influence of the unit price difference on the recommendation result is reduced. Specifically, the device obtains the activation unit price of the application to be recommended, wherein, a user downloads the corresponding application once on the platform, and then the corresponding application merchant pays the platform according to the number of times, and the fee is called the activation unit price. And the equipment carries out normalization processing on the activation unit price to obtain the platform profit price information of the application to be recommended.

S102: and determining the click rate estimation value of the target user to the application to be recommended according to the user information and the characteristic data.

The device determines the click rate estimated value of the application to be recommended by the target user according to the user information and the characteristic data, wherein the click rate estimated value of the application to be recommended by the target user identifies the interest of the target user in the application to be recommended, and can also be understood as the probability that the target user likes the application to be recommended.

The device pre-stores a click rate estimation determining strategy, and determines the click rate estimation of the application to be recommended by the target user according to the click rate estimation determining strategy, the user information and the characteristic data.

In one embodiment, in order to improve the accuracy of the click rate estimation value of the application to be recommended by the target user, the device may determine the click rate estimation value of the application to be recommended by the target user through a neural network model. And the equipment inputs the user information and the characteristic data into the trained click rate prediction model for processing to obtain the click rate estimated value of the application to be recommended by the target user. The device stores a trained click rate prediction model in advance, and the trained click rate prediction model is used for predicting click rate estimation values of applications to be recommended of target users.

The click-through rate prediction model may be pre-trained by other devices and then the freeze-trained click-through rate prediction model is stored in the device. Or the equipment carries out personalized training through a sample training set to obtain a click rate prediction model.

The click rate prediction model may include an input layer, a hidden layer, and an output layer (loss function layer), among others. The input layer includes an input layer node for receiving input user information and characteristic data. The hidden layer is used for processing the user information and the characteristic data and predicting click rate estimated values corresponding to the user information and the characteristic data. The output layer is used for outputting click rate estimated values of applications to be recommended by the target users.

In a possible implementation manner, the click rate prediction model is trained in advance by the local device, and the training method of the click rate prediction model may be as follows:

the method comprises the steps that equipment obtains a sample training set, wherein the sample training set comprises sample user information, sample characteristic data applied by a sample and a click rate label corresponding to the sample characteristic data; and training the initial neural network model by using a sample training set to obtain a trained click rate prediction model.

In the training process, sample user information, sample characteristic data applied by the sample and a click rate label corresponding to the sample characteristic data are used as training data, the training data are input into an initial neural network model, and the model is continuously improved by adjusting a loss function and relevant parameters of the initial neural network model, so that a final click rate prediction model is obtained. The relevant parameters may include key parameters such as hidden layer values, learning rate, batch _ size, and the like of the initial neural network.

The initial neural network model can be a DCN model, and compared with the conventional model, the cross layer of the DCN model can better learn high-order parameters, and meanwhile, the calculation amount is small, and the calculation efficiency is high. During training, fitting training can be performed through a back propagation algorithm, so that model prediction obtained through training is more accurate.

Specifically, sample user information and sample characteristic data of the sample application are input into the initial neural network model to be processed, and sample click rates corresponding to the sample user information and the sample application are obtained. And the equipment pre-stores a preset loss function, and calculates a target loss value according to the sample click rate, the click rate label and the preset loss function. If the target loss value does not meet the preset suspension condition, updating the initial neural network model according to the target loss value, returning to execute the step of inputting the sample user information and the sample characteristic data of the sample application into the initial neural network model for processing, and obtaining the sample click rate corresponding to the sample user information and the sample application; and if the target loss value meets the preset suspension condition, outputting the trained click rate prediction model.

When a sample training set is obtained, obtaining sample user information, obtaining classification characteristic information and continuous value characteristic information of sample application, and then determining sample characteristic data of the sample application according to the classification characteristic information and the continuous value characteristic information.

The categorical characteristic information of the sample application is a group to which the sample application is applicable, for example, the group to which the sample application is applicable may include pupils, middle school students, elderly people, and the like. The device may perform class numbering on a group such as a pupil, a middle school student, an old person, and the like, and for example, if the word value suitable for the pupil is regarded as 0 and the word value suitable for the middle school student is regarded as 1, the corresponding class characteristic information is 0 or 1.

The continuous value feature information may include the historical download number of the sample application, for example, the download number of application 1 is 100, and the continuous value feature information is 100; the download number of application 2 is 200, and the continuous value characteristic information is 200. Since the fluctuation of the continuous value feature information is relatively large, the continuous value feature information may be normalized, specifically, the normalized value may be obtained by performing the normalization according to the following formula:

normalized value ═ value (continuous value feature information maximum value-continuous value feature information current value)/(continuous value feature information maximum value-continuous value feature information minimum value).

The device can store the categorical characteristic information and the continuous value characteristic information in a correlated mode to serve as sample characteristic data of the sample application.

It should be understood that both the categorical characteristic information and the continuous value characteristic information belong to the attribute information of the sample application, and the sample application may have a plurality of attribute information, for example, the size of the application, the applicable devices, and the like.

In addition, in order to ensure the richness of the samples and improve the accuracy of the finally obtained training model, the positive samples and the negative samples can be selected according to a certain proportion when the samples are selected. In this embodiment, the positive sample is a sample user having a click sample application behavior, and the negative sample is a sample user not having a click sample application behavior, specifically, the ratio of the positive sample to the negative sample may be about 1: 2.5.

S103: and determining the recommendation score of the application to be recommended according to the click rate evaluation value and the platform profit price information.

The equipment determines the recommendation score of the application to be recommended according to the click rate evaluation value and the platform profit price information, namely, the application to be recommended is scored by considering two angles of a user and a platform to obtain the recommendation score.

Specifically, the device may multiply the click-through rate estimate by the platform profit price information to obtain the recommendation score of the application to be recommended. In addition, the equipment can also set weights corresponding to click rate evaluation and platform profit price information, and calculate the recommendation score according to the preset weights.

S104: and recommending the application to be recommended according to the recommendation score.

The device recommends the application to be recommended according to the recommendation score, specifically, recommendation strategies corresponding to different score ranges can be set, and the score range to which the recommendation score belongs is judged, so that the recommendation strategy of the application to be recommended is determined. For example, the device may set the recommendation policy for the application with score 90-100 to be a top recommendation and pop up an application recommendation animation, then when the recommendation score is 95, the device may make a top recommendation for the application to be recommended and pop up an application recommendation animation. The device may also set the recommendation policy for applications with a score lower than 20 to recommend every three days, and when the recommendation score is 16, the device may set to recommend the application to be recommended every three days.

In the embodiment of the application, user information of a target user and characteristic data of an application to be recommended are obtained, and platform profit price information of the application to be recommended is obtained; determining click rate estimated values of applications to be recommended by a target user according to the user information and the characteristic data; determining a recommendation score of the application to be recommended according to the click rate evaluation value and the profit price information; and recommending the application to be recommended according to the recommendation score. According to the method, not only is the user experience taken as a starting point, but also the user behavior is analyzed during recommendation, the benefit of a recommendation platform is also considered, on one hand, the user experience is guaranteed, on the other hand, the limited recommendation position can be effectively utilized to promote commercial revenue, and more comprehensive application recommendation can be carried out.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Referring to fig. 2, fig. 2 is a schematic diagram of an application recommendation device according to a second embodiment of the present application. The units are included for performing the steps in the corresponding embodiment of fig. 1. Please refer to fig. 1 for the related description of the corresponding embodiment. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 2, the application recommendation apparatus 2 includes:

the obtaining unit 210 is configured to obtain user information of a target user and feature data of an application to be recommended, and obtain platform profit price information of the application to be recommended;

a first determining unit 220, configured to determine, according to the user information and the feature data, an estimated click rate of the target user for the application to be recommended;

a second determining unit 230, configured to determine, according to the click-through rate estimate and the platform profit price information, a recommendation score of the application to be recommended;

and the recommending unit 240 is configured to recommend the application to be recommended according to the recommendation score.

Further, the first determining unit 220 is specifically configured to:

inputting the user information and the characteristic data into a trained click rate prediction model for processing to obtain the click rate estimated value of the target user to the application to be recommended.

Further, the first determining unit 220 is specifically configured to:

acquiring a sample training set; the sample training set comprises sample user information, sample characteristic data applied by a sample and a click rate label corresponding to the sample characteristic data;

and training an initial neural network model by using the sample training set to obtain a trained click rate prediction model.

Further, the first determining unit 220 is specifically configured to:

acquiring sample user information, and acquiring categorical characteristic information and continuous value characteristic information of sample application;

and determining sample characteristic data applied to the sample according to the classification characteristic information and the continuous value characteristic information.

Further, the first determining unit 220 is specifically configured to:

inputting the sample user information and the sample characteristic data of the sample application into an initial neural network model for processing to obtain sample click rates corresponding to the sample user information and the sample application;

calculating a target loss value according to the sample click rate, the click rate label and a preset loss function;

if the target loss value does not meet the preset suspension condition, updating the initial neural network model according to the target loss value, returning to execute the step of inputting the sample user information and the sample characteristic data of the sample application into the initial neural network model for processing, and obtaining the sample click rate corresponding to the sample user information and the sample application;

and if the target loss value meets the preset suspension condition, outputting a trained click rate prediction model.

Further, the obtaining unit 210 is specifically configured to:

acquiring the activation unit price of the application to be recommended;

and carrying out normalization processing on the activation unit price to obtain the platform profit price information of the application to be recommended.

Further, the second determining unit 230 is specifically configured to:

and multiplying the click rate estimated value and the platform profit price information to obtain the recommendation score of the application to be recommended.

Fig. 3 is a schematic diagram of an application recommendation device according to a third embodiment of the present application. As shown in fig. 3, the application recommendation device 3 of this embodiment includes: a processor 30, a memory 31 and a computer program 32, such as an application recommendation program, stored in said memory 31 and executable on said processor 30. The processor 30, when executing the computer program 32, implements the steps in the above-described embodiments of the application recommendation method, such as the steps 101 to 104 shown in fig. 1. Alternatively, the processor 30, when executing the computer program 32, implements the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the modules 210 to 240 shown in fig. 2.

Illustratively, the computer program 32 may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 30 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 32 in the application recommendation device 3. For example, the computer program 32 may be divided into an acquisition unit, a first determination unit, a second determination unit, and a recommendation unit, and the specific functions of each unit are as follows:

the system comprises an acquisition unit, a recommendation unit and a recommendation unit, wherein the acquisition unit is used for acquiring user information of a target user and feature data of an application to be recommended and acquiring platform profit price information of the application to be recommended;

the first determining unit is used for determining the click rate estimated value of the target user to the application to be recommended according to the user information and the characteristic data;

the second determining unit is used for determining the recommendation score of the application to be recommended according to the click rate estimation value and the platform profit price information;

and the recommending unit is used for recommending the application to be recommended according to the recommendation score.

The application recommendation device may include, but is not limited to, a processor 30, a memory 31. Those skilled in the art will appreciate that fig. 3 is merely an example of the application recommendation device 3, and does not constitute a limitation of the application recommendation device 3, and may include more or less components than those shown, or combine certain components, or different components, for example, the application recommendation device may also include an input-output device, a network access device, a bus, etc.

The Processor 30 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 31 may be an internal storage unit of the application recommendation device 3, such as a hard disk or a memory of the application recommendation device 3. The memory 31 may also be an external storage device of the application recommendation device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like equipped on the application recommendation device 3. Further, the application recommendation device 3 may also include both an internal storage unit and an external storage device of the application recommendation device 3. The memory 31 is used for storing the computer program and other programs and data required by the application recommendation device. The memory 31 may also be used to temporarily store data that has been output or is to be output.

It should be noted that, for the information interaction, execution process, and other contents between the above-mentioned devices/units, the specific functions and technical effects thereof are based on the same concept as those of the embodiment of the method of the present application, and specific reference may be made to the part of the embodiment of the method, which is not described herein again.

An embodiment of the present application further provides a network device, where the network device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, the processor implementing the steps of any of the various method embodiments described above when executing the computer program.

The embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps in the above-mentioned method embodiments.

The embodiments of the present application provide a computer program product, which when running on a mobile terminal, enables the mobile terminal to implement the steps in the above method embodiments when executed.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium and can implement the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing apparatus/terminal apparatus, a recording medium, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a usb-disk, a removable hard disk, a magnetic or optical disk, etc. In certain jurisdictions, computer-readable media may not be an electrical carrier signal or a telecommunications signal in accordance with legislative and patent practice.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other ways. For example, the above-described apparatus/network device embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.