1. A transaction risk identification method, the method comprising:

obtaining a transaction risk score card model which is trained in advance, wherein the transaction risk score card model is obtained by training a plurality of groups of training samples through a machine learning algorithm, each group of training samples comprises target characteristic data samples and scores of the target characteristic data samples, and the target characteristic data samples comprise characteristic variables and variable values corresponding to the characteristic variables; the characteristic variable is an index for representing the operation behavior;

acquiring invoice data of an invoice on an invoice sales item of a financing requester, and determining target characteristic data from the invoice data of the invoice on the financing requester, wherein the target characteristic data comprises characteristic variables and variable values corresponding to the characteristic variables;

inputting the target characteristic data into the transaction risk scoring card model to obtain a score of the target characteristic data output by the transaction risk scoring card model;

and calculating the transaction risk score of the financing requester according to the score of the target characteristic data.

2. The method of claim 1, wherein the training step of the transaction risk score card model comprises:

acquiring a purchase and sale item invoice data sample, and determining the target characteristic data sample from the purchase and sale item invoice data sample;

performing box separation operation and WOE conversion on the target characteristic data sample to obtain a box separation coefficient and a WOE value of the target characteristic data sample;

taking the product of the binning coefficient and the WOE value of the target feature data sample as the score of the target feature data sample;

and adding the scores of the target characteristic data samples, and taking the obtained sum as a transaction risk score.

3. The method of claim 2, wherein said determining said target feature data sample from said invoice data sample comprises:

determining a plurality of candidate characteristic data samples from the invoice data samples of the purchase and sale items, wherein the candidate characteristic data samples comprise a first characteristic variable and a variable value corresponding to the first characteristic variable; the first characteristic variable is an index for representing the operation behavior;

setting FP-Tree for the first characteristic variable according to the support degree, the reliability and the action degree, and determining a second characteristic variable from the first characteristic variables according to the set FP-Tree;

performing box separation operation and WOE conversion on the second feature variables, and screening the second feature variables by using KS values, AR values, IV values and VIF values;

and fitting the relation between the second characteristic variables and the target characteristic variables through a logistic regression algorithm, determining the target characteristic variables from the second characteristic variables, and forming the target characteristic data samples by the target characteristic variables and the variable values corresponding to the target characteristic variables.

4. The method of claim 2, wherein after determining the target feature data sample from the invoice data sample, the method further comprises:

and performing data cleaning and/or data processing on the target characteristic data sample, wherein the data cleaning comprises missing value processing and/or abnormal value processing on the target characteristic data sample, and the data processing comprises data transposition and/or data summation on the target characteristic data sample.

5. The method of claim 1, wherein calculating a transaction risk score for the financing requester based on the score of the target feature data comprises:

and carrying out weighted summation on the scores of the target characteristic data, and taking the calculation result of the weighted summation as the transaction risk score of the financing requester.

6. The method of claim 1, wherein after calculating a transaction risk score for the financing requester based on the score of the target feature data, the method further comprises:

setting a plurality of grading segments, wherein each grading segment corresponds to a transaction risk degree grade;

and determining a target score segment where the transaction risk score of the financing requester is located, and determining the transaction risk degree grade corresponding to the target score segment as the transaction risk degree grade of the financing requester.

7. A transaction risk identification device, the device comprising:

the system comprises an acquisition unit, a calculation unit and a processing unit, wherein the acquisition unit is used for acquiring a transaction risk score card model which is trained in advance, the transaction risk score card model is obtained by training a plurality of groups of training samples through a machine learning algorithm, each group of training samples comprises target characteristic data samples and scores of the target characteristic data samples, and the target characteristic data samples comprise characteristic variables and variable values corresponding to the characteristic variables; the characteristic variable is an index for representing the operation behavior;

the acquisition unit is further used for acquiring invoice data of the purchase and sale items of the financing requester and determining target characteristic data from the invoice data of the purchase and sale items of the financing requester, wherein the target characteristic data comprises characteristic variables and variable values corresponding to the characteristic variables;

the data processing unit is used for inputting the target characteristic data into the transaction risk scoring card model so as to obtain a score of the target characteristic data output by the transaction risk scoring card model;

and the calculating unit is used for calculating the transaction risk score of the financing requester according to the score of the target characteristic data.

8. The apparatus of claim 7, further comprising:

a training unit for performing a training step of the transaction risk score card model; the training step of the transaction risk score card model comprises the following steps:

acquiring a purchase and sale item invoice data sample, and determining the target characteristic data sample from the purchase and sale item invoice data sample;

performing box separation operation and WOE conversion on the target characteristic data sample to obtain a box separation coefficient and a WOE value of the target characteristic data sample;

taking the product of the binning coefficient and the WOE value of the target feature data sample as the score of the target feature data sample;

and adding the scores of the target characteristic data samples, and taking the obtained sum as a transaction risk score.

9. A transaction risk identification device, the device comprising:

a memory for storing a computer program; a processor for implementing the steps of the financing admission risk assessment method according to any one of claims 1 to 6 when executing said computer program.

10. A computer storage medium having stored therein instructions that, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 6.

Background

Supply chain finance is a primary implementation of financial institutions to provide funding support for financing enterprises. How to assess the authenticity of the financing object and identify the transaction risk is a common problem in supply chain finance.

In the existing mode, the credit granting evaluation process mainly depends on manual invoice collection and invoice authenticity checking, the mode is time-consuming, labor-consuming, low in efficiency and prone to error, authenticity and compliance of invoice data taking cannot be completely guaranteed, manual evaluation and measurement are carried out subsequently, the credit granting amount is calculated based on simple rules and credit checking standards, real transaction risks are difficult to evaluate, fraud behaviors cannot be distinguished, operation risks cannot be identified, and overall evaluation of enterprise transaction risks is imperfect.

Disclosure of Invention

The embodiment of the application provides a transaction risk identification method, a transaction risk identification device and a computer storage medium, which are used for improving the identification and evaluation efficiency of transaction risks and improving the accuracy of risk identification and evaluation results.

In a first aspect, an embodiment of the present application provides a transaction risk identification method, where the method includes:

obtaining a transaction risk score card model which is trained in advance, wherein the transaction risk score card model is obtained by training a plurality of groups of training samples through a machine learning algorithm, each group of training samples comprises target characteristic data samples and scores of the target characteristic data samples, and the target characteristic data samples comprise characteristic variables and variable values corresponding to the characteristic variables; the characteristic variable is an index for representing the operation behavior;

acquiring invoice data of an invoice on an invoice sales item of a financing requester, and determining target characteristic data from the invoice data of the invoice on the financing requester, wherein the target characteristic data comprises characteristic variables and variable values corresponding to the characteristic variables;

inputting the target characteristic data into the transaction risk scoring card model to obtain a score of the target characteristic data output by the transaction risk scoring card model;

and calculating the transaction risk score of the financing requester according to the score of the target characteristic data.

A second aspect of the embodiments of the present application provides a transaction risk identification device, including:

the system comprises an acquisition unit, a calculation unit and a processing unit, wherein the acquisition unit is used for acquiring a transaction risk score card model which is trained in advance, the transaction risk score card model is obtained by training a plurality of groups of training samples through a machine learning algorithm, each group of training samples comprises target characteristic data samples and scores of the target characteristic data samples, and the target characteristic data samples comprise characteristic variables and variable values corresponding to the characteristic variables; the characteristic variable is an index for representing the operation behavior;

the acquisition unit is further used for acquiring invoice data of the purchase and sale items of the financing requester and determining target characteristic data from the invoice data of the purchase and sale items of the financing requester, wherein the target characteristic data comprises characteristic variables and variable values corresponding to the characteristic variables;

the data processing unit is used for inputting the target characteristic data into the transaction risk scoring card model so as to obtain a score of the target characteristic data output by the transaction risk scoring card model;

and the calculating unit is used for calculating the transaction risk score of the financing requester according to the score of the target characteristic data.

A third aspect of embodiments of the present application provides a transaction risk identification device, including:

a memory for storing a computer program; a processor for implementing the steps of the financing admission risk assessment method according to the aforementioned first aspect when executing the computer program.

A fourth aspect of embodiments of the present application provides a computer storage medium having instructions stored therein, which when executed on a computer, cause the computer to perform the method of the first aspect.

According to the technical scheme, the embodiment of the application has the following advantages:

in the embodiment of the application, the transaction risk identification device acquires the transaction risk score card model and the purchase and sale item invoice data of the financing request party, determines the target characteristic data from the purchase and sale item invoice data of the financing request party, inputs the target characteristic data into the transaction risk score card model, obtains the score of the target characteristic data output by the transaction risk score card model, and calculates the transaction risk score of the financing request party according to the score of the target characteristic data, so that the identification and evaluation of the transaction risk do not need to depend on manual field investigation, the transaction risk is determined by deep investigation analysis under a manual line, the work efficiency of transaction risk identification and evaluation can be improved, meanwhile, the subjective factor of the transaction risk evaluation doped with the manual work is avoided, and the accuracy of the transaction risk identification and evaluation result can be improved.

Drawings

FIG. 1 is a schematic flow chart illustrating a transaction risk identification method according to an embodiment of the present disclosure;

FIG. 2 is another schematic flow chart illustrating a transaction risk identification method according to an embodiment of the present disclosure;

FIG. 3 is a schematic structural diagram of a transaction risk identification device according to an embodiment of the present application;

fig. 4 is another schematic structural diagram of a transaction risk identification device in the embodiment of the present application.

Detailed Description

The embodiment of the application provides a transaction risk identification method, a transaction risk identification device and a computer storage medium, which are used for improving the identification and evaluation efficiency of transaction risks and improving the accuracy of risk identification and evaluation results.

Referring to fig. 1, an embodiment of a transaction risk identification method in the embodiment of the present application includes:

101. acquiring a transaction risk score card model trained in advance;

the method of the embodiment can be applied to a transaction risk identification device, which can be a computer device such as a terminal and a server. The method of the embodiment can identify and evaluate the transaction risk of the financing requester, wherein the financing requester can be any business entity in social and economic activities, such as business entities of enterprises, individual industrial and commercial enterprises and the like. When any business entity has financing requirement, it can send financing request to financial institution. The financial institution can use the transaction risk identification device to evaluate whether the financing requester has transaction risk, and the transaction risk identification device receives the financing request of the financing requester and executes the processing operation of the request in the subsequent steps.

Specifically, the present embodiment evaluates the transaction risk of the financing requester based on a transaction risk scoring card model. Therefore, the transaction risk identification device obtains a transaction risk score card model which is trained in advance, the transaction risk score card model is obtained by training a plurality of groups of training samples through a machine learning algorithm, each group of training samples comprises target characteristic data samples and scores of the target characteristic data samples, and the target characteristic data samples comprise characteristic variables and variable values corresponding to the characteristic variables; the characteristic variable is an index for representing the operation behavior, such as an operating income, an operating time, an invoicing record and the like, and the variable value corresponding to the characteristic variable is a value corresponding to the index, such as an operating income index, and the corresponding variable value is 100 ten thousand; the variable value corresponding to the operation time is 1 month and 1 day in 2020.

102. Acquiring the invoice data of the purchase and sale item of the financing requester, and determining target characteristic data from the invoice data of the purchase and sale item of the financing requester;

the present embodiment identifies transaction risks for financing requestors based on the invoice data for the underwriting requestors. Therefore, the transaction risk identification device also acquires the invoice data of the financing requester, and determines the target characteristic data from the invoice data of the financing requester. Similarly, the target feature data includes feature variables and variable values corresponding to the feature variables.

103. Inputting the target characteristic data into the transaction risk scoring card model to obtain the score of the target characteristic data output by the transaction risk scoring card model;

after the target characteristic data are determined, the target characteristic data are input into a transaction risk scoring card model, and the transaction risk scoring card model outputs the score of the target characteristic data based on data processing logic obtained through pre-training.

104. Calculating to obtain a transaction risk score of the financing requester according to the score of the target characteristic data;

after the score of the target characteristic data is obtained, the score of the target characteristic data can be converted into a transaction risk score of the financing requester according to a preset calculation mode. The preset calculation method may be a weighted sum, or other calculation methods capable of converting the score of the target feature data into the transaction risk score, which is not limited herein.

In this embodiment, the transaction risk identification device obtains the transaction risk score card model and the invoice data of the purchase and sale item of the financing requester, determines the target feature data from the invoice data of the purchase and sale item of the financing requester, inputs the target feature data into the transaction risk score card model, obtains the score of the target feature data output by the transaction risk score card model, and calculates the transaction risk score of the financing requester according to the score of the target feature data.

The embodiments of the present application will be described in further detail below on the basis of the aforementioned embodiment shown in fig. 1. Referring to fig. 2, another embodiment of the transaction risk identification method in the embodiment of the present application includes:

201. acquiring a transaction risk score card model trained in advance;

in this embodiment, the training step of the transaction risk score card model includes: acquiring a purchase and sale item invoice data sample, and determining a target characteristic data sample from the purchase and sale item invoice data sample; performing box separation operation and evidence weight conversion (WOE) conversion on the target characteristic data sample to obtain a box separation coefficient and a WOE value of the target characteristic data sample; taking the product of the binning coefficient and the WOE value of the target characteristic data sample as the score of the target characteristic data sample; and adding the scores of the plurality of target characteristic data samples, and taking the obtained sum as a transaction risk score.

The target characteristic data sample is determined from the invoice data samples of the purchase and sale items, and the specific mode can be that a plurality of candidate characteristic data samples are determined from the invoice data samples of the purchase and sale items, and the candidate characteristic data samples comprise a first characteristic variable and a variable value corresponding to the first characteristic variable; the first characteristic variable is an index for representing the operation behavior; setting a frequent pattern Tree (FP-Tree) for the first characteristic variables according to the support degree, the credibility and the action degree, and determining second characteristic variables from the plurality of first characteristic variables according to the set FP-Tree; performing box separation operation and WOE conversion on the plurality of second characteristic variables, and screening the plurality of second characteristic variables by using KS values, AR values, IV values and VIF values; and fitting the relation between the second characteristic variables and the target characteristic variables through a logistic regression algorithm, determining the target characteristic variables from the second characteristic variables, and forming target characteristic data samples by the target characteristic variables and variable values corresponding to the target characteristic variables. Therefore, the target characteristic data sample determined by the specific method can truly reflect the operation condition and the transaction condition of the financing requester, so that the transaction risk of the financing requester can be more accurately evaluated according to the target characteristic data sample.

For convenience of data processing and model training, after a target characteristic data sample is determined from the invoice data sample, a preprocessing operation may be further performed on the target characteristic data sample, and the preprocessing operation may be specifically, performing data cleaning and/or data processing on the target characteristic data sample, where the data cleaning includes missing value processing and/or abnormal value processing on the target characteristic data sample, and the data processing includes data transposition and/or data summation on the target characteristic data sample. The preprocessing operation on the target characteristic data sample can be various, as long as the data can be more conveniently used in the subsequent processing process.

202. Acquiring the invoice data of the purchase and sale item of the financing requester, and determining target characteristic data from the invoice data of the purchase and sale item of the financing requester;

in this embodiment, the financing requester may send a financing request to the transaction risk identification device through its own terminal, where the financing request carries personal information of the financing requester and an authorization identifier, and the authorization identifier is used to indicate an right granted to the transaction risk identification device to obtain invoice data of an invoice on a purchase and sale item of the financing requester.

Specifically, the financing request may be a request for financing equipment, a request for financing product, or a request for financing assets in other forms, and the specific financing form is not limited.

The specific implementation of determining the target feature data from the invoice data of the purchase and sales items of the financing requester is similar to the specific implementation of determining the target feature data sample from the invoice data sample of the purchase and sales items, and the specific implementation of determining the target feature data sample from the invoice data sample of the purchase and sales items has been mentioned above, and the specific implementation of determining the target feature data from the invoice data of the purchase and sales items of the financing requester is not described herein again.

203. Inputting the target characteristic data into the transaction risk scoring card model to obtain the score of the target characteristic data output by the transaction risk scoring card model;

because the transaction risk score card model is trained based on the target feature data sample and the score of the target feature data sample, in the training process, the transaction risk score card model fits the functional relationship between the target feature data sample and the score of the target feature data sample, and the functional relationship can be applied to other scenes for calculating the score of the feature data. Therefore, when the score of the target characteristic data needs to be calculated subsequently, the transaction risk scoring card model calculates the score of the target characteristic data according to the fitted functional relationship and outputs the calculated score only by inputting the target characteristic data into the transaction risk scoring card model.

204. Calculating to obtain a transaction risk score of the financing requester according to the score of the target characteristic data;

in this embodiment, the transaction risk score is calculated according to the score of the target feature data, and there may be a plurality of calculation methods. In one calculation, the scores of the target feature data may be weighted and summed, and the weighted and summed calculation result is used as the transaction risk score of the financing requester.

In addition, the scores of the target feature data may not need to be weighted and summed, and the sum may be used as the transaction risk score by directly adding the scores of the target feature data. The embodiment does not limit the specific calculation mode for calculating the transaction risk score according to the score of the target feature data.

205. Setting a plurality of grading segments, determining a target grading segment where a transaction risk grade of a financing requester is located, and determining a transaction risk degree grade corresponding to the target grading segment as a transaction risk degree grade of the financing requester;

after the transaction risk score of the financing requester is obtained, the transaction risk degree grade of the financing requester can be further determined. Specifically, a plurality of scoring segments may be preset, where each scoring segment corresponds to one transaction risk degree level, so as to determine a target scoring segment where the transaction risk score of the financing requester is located, and determine the transaction risk degree level corresponding to the target scoring segment as the transaction risk degree level of the financing requester.

For example, if the scoring segment of the transaction risk score of the financing requester is 80-90 points, and the transaction risk degree grade corresponding to the scoring segment is a greater risk, it can be determined that the transaction risk degree grade of the financing requester is a greater risk, indicating that the financing requester has a greater transaction risk.

In the embodiment, a specific training mode of the transaction risk scoring card model and a specific implementation mode of determining the target characteristic data sample from the invoice data sample of the purchase and sale item are provided, so that the transaction risk scoring card model obtained through training can be ensured to calculate the transaction risk score more accurately, and the accuracy and the authenticity of the transaction risk identification and evaluation result are further improved.

The above describes the transaction risk identification method in the embodiment of the present application, and the following describes the transaction risk identification device in the embodiment of the present application, referring to fig. 3, an embodiment of the transaction risk identification device in the embodiment of the present application includes:

the acquiring unit 301 is configured to acquire a transaction risk score card model which is trained in advance, where the transaction risk score card model is obtained by training multiple sets of training samples through a machine learning algorithm, each set of training samples includes a target feature data sample and a score of the target feature data sample, and the target feature data sample includes a feature variable and a variable value corresponding to the feature variable; the characteristic variable is an index for representing the operation behavior;

the obtaining unit 301 is further configured to obtain invoice data of an invoice on an invoice sales item of a financing requester, and determine target feature data from the invoice data on the invoice on the financing requester, where the target feature data includes a feature variable and a variable value corresponding to the feature variable;

the data processing unit 302 is configured to input the target feature data into the transaction risk scoring card model to obtain a score of the target feature data output by the transaction risk scoring card model;

and the calculating unit 303 is configured to calculate a transaction risk score of the financing requester according to the score of the target feature data.

In a preferred implementation manner of this embodiment, the apparatus further includes:

a training unit 304 for performing a training step of the transaction risk score card model; the training step of the transaction risk score card model comprises the following steps:

acquiring a purchase and sale item invoice data sample, and determining a target characteristic data sample from the purchase and sale item invoice data sample;

performing box separation operation and WOE conversion on the target characteristic data sample to obtain a box separation coefficient and a WOE value of the target characteristic data sample;

taking the product of the binning coefficient and the WOE value of the target characteristic data sample as the score of the target characteristic data sample;

and adding the scores of the plurality of target characteristic data samples, and taking the obtained sum as a transaction risk score.

In a preferred implementation manner of this embodiment, when the step of determining the target feature data sample from the invoice data sample of the invoice, the training unit 304 is specifically configured to determine a plurality of candidate feature data samples from the invoice data sample of the invoice, where the candidate feature data samples include a first feature variable and a variable value corresponding to the first feature variable; the first characteristic variable is an index for representing the operation behavior; setting an FP-Tree for the first characteristic variable according to the support degree, the reliability and the action degree, and determining a second characteristic variable from the plurality of first characteristic variables according to the set FP-Tree; performing box separation operation and WOE conversion on the plurality of second characteristic variables, and screening the plurality of second characteristic variables by using KS values, AR values, IV values and VIF values; and fitting the relation between the second characteristic variables and the target characteristic variables through a logistic regression algorithm, determining the target characteristic variables from the second characteristic variables, and forming target characteristic data samples by the target characteristic variables and variable values corresponding to the target characteristic variables.

In a preferred implementation manner of this embodiment, the apparatus further includes:

the preprocessing unit 305 is used for performing data cleaning and/or data processing on the target characteristic data sample, wherein the data cleaning comprises missing value processing and/or abnormal value processing on the target characteristic data sample, and the data processing comprises data transposition and/or data summation on the target characteristic data sample.

In a preferred implementation manner of this embodiment, the calculating unit 303 is specifically configured to perform weighted summation on the scores of the multiple target feature data, and use a calculation result of the weighted summation as a transaction risk score of the financing requester.

In a preferred implementation manner of this embodiment, the apparatus further includes:

a risk rating unit 306, configured to set a plurality of score segments, where each score segment corresponds to a transaction risk degree level; and determining a target score segment where the transaction risk score of the financing requester is located, and determining the transaction risk degree grade corresponding to the target score segment as the transaction risk degree grade of the financing requester.

In this embodiment, the operations performed by the units in the transaction risk recognition device are similar to those described in the embodiments shown in fig. 1 to 2, and are not repeated herein.

In this embodiment, the obtaining unit 301 obtains the transaction risk score card model and the invoice data of the financing requester for the purchase and sale terms, determines the target feature data from the invoice data of the financing requester for the purchase and sale terms, the data processing unit 302 inputs the target feature data to the transaction risk score card model for the score of the target feature data output by the transaction risk score card model, the calculating unit 303 calculates the transaction risk score of the financing requester according to the score of the target feature data, therefore, the identification and evaluation of the transaction risk do not need to depend on manual field investigation on the spot, compared with the manual in-depth investigation analysis to determine the transaction risk, the work efficiency of the identification and evaluation of the transaction risk can be improved, meanwhile, artificial subjective factors doped in transaction risk assessment are avoided, and the accuracy of the transaction risk identification and assessment result can be improved.

Referring to fig. 4, the transaction risk identification apparatus in the embodiment of the present application is described below, where an embodiment of the transaction risk identification apparatus in the embodiment of the present application includes:

the transaction risk identification device 400 may include one or more Central Processing Units (CPUs) 401 and a memory 405, where the memory 405 stores one or more applications or data.

Memory 405 may be volatile storage or persistent storage, among other things. The program stored in memory 405 may include one or more modules, each of which may include a series of instructions operating on a transaction risk identification device. Still further, the central processor 401 may be arranged to communicate with the memory 405, and to execute a series of instruction operations in the memory 405 on the transaction risk identification device 400.

The transaction risk identification device 400 may also include one or more power supplies 402, one or more wired or wireless network interfaces 403, one or more input-output interfaces 404, and/or one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

The central processing unit 401 may perform the operations performed by the transaction risk recognition device in the embodiments shown in fig. 1 to fig. 2, which are not described herein again.

An embodiment of the present application further provides a computer storage medium, where one embodiment includes: the computer storage medium has stored therein instructions that, when executed on a computer, cause the computer to perform the operations performed by the transaction risk identification device in the embodiments of fig. 1-2.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. 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.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

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, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.