Method, device and equipment for pushing target user information

Abstract

The present application provides a method, device and equipment for pushing target user information, wherein the method comprises: obtaining target stock data and a data set of the target user; performing data integration on the target stock data and the data set of the target user to obtain resource transfer data related to the target user; wherein the resource transfer data represents the resource transfer situation of the target user; according to the resource transfer data related to the target user, determining the resource source category of the target user using a feature database and a preset classification model; and when the resource source category of the target user is a preset category, sending information related to the target user to a processing object corresponding to the target user. In an embodiment of the present application, the target stock data, the feature database and the preset classification model can be used to quickly and accurately determine the resource source category of the target user, so that the filtered data can be pushed in a timely and effective manner and processed in a timely manner.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and equipment for pushing target user information. Background Art

[0002] Currently, most banking business is concentrated online. Not only is the business volume huge and user information numerous, but many users will cooperate with illegal personnel to conduct transactions through informal channels, which brings many high-risk problems to banks.

[0003] The bank audit system in the existing technology only provides functional support for the process, such as data entry and data storage. It is necessary to use account managers or special auditors to conduct data mining and screening to screen out data that may be risky. Account managers or special auditors need to spend a lot of cost and time to screen, and cannot effectively screen the data of a large number of users. In addition, the use of the human model requires high work experience and professional quality of business personnel. It can be seen that the solution in the existing technology cannot meet the needs of timely screening and pushing risk data when the online business volume is huge.

[0004] To address the above problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method, device and equipment for pushing target user information to solve the problem in the prior art that it is impossible to meet the demand for timely screening and pushing of risk data when the online business volume is huge.

[0006] An embodiment of the present application provides a method for pushing target user information, comprising: obtaining target stock data and a data set of the target user; wherein the data set of the target user comprises: basic information of the target user, and the target stock data represents previously generated and stored data related to the target user; integrating the target stock data and the data set of the target user to obtain resource transfer data related to the target user; wherein the resource transfer data characterizes the resource transfer situation of the target user; according to the resource transfer data related to the target user, determining the resource source category of the target user using a feature database and a preset classification model; wherein the feature database is used to characterize the judgment standard of the resource source category, and the preset classification model is used to judge the category of the resource source according to the feature database; when the resource source category of the target user is a preset category, sending information related to the target user to the processing object corresponding to the target user.

[0007] In one embodiment, obtaining target stock data includes: obtaining historical data of the target user, wherein the historical data includes: wage payment data, provident fund data, and resource transfer data; determining a counterparty having a resource transfer relationship with the target user based on the resource transfer data in the historical data; obtaining relevant data of the counterparty; and using the historical data and relevant data of the counterparty as the target stock data.

[0008] In one embodiment, data integration is performed on the target stock data and the data set of the target user to obtain resource transfer data related to the target user, including: using unique ID technology to associate the data set of the target user with the data related to the target user in the target stock data; and determining the resource transfer data related to the target user based on the associated data.

[0009] In one embodiment, based on resource transfer data related to the target user, a feature database and a preset classification model are used to determine the resource source category of the target user, including: determining a feature transaction counterparty portrait and a feature user portrait based on the feature database; inputting the resource transfer data, feature transaction counterparty portrait and feature user portrait related to the target user into the preset classification model; and receiving the resource source category of the target user output by the preset classification model.

[0010] In one embodiment, after the resource transfer data, characteristic counterparty portrait and characteristic user portrait related to the target user are input into the preset classification model, it also includes: the preset classification model determines the counterparty information of the target user and the relevant information of the target user based on the resource transfer data related to the target user; the preset classification model matches the counterparty information of the target user with the characteristic counterparty portrait, and matches the relevant information of the target user with the characteristic user portrait to obtain a matching result; the preset classification model determines the resource source category of the target user based on the matching result.

[0011] In one embodiment, when the matching result is that the counterparty information of the target user does not match the characteristic counterparty portrait, it also includes: obtaining characteristic counterparty list data; determining the resource transfer amount between the target user and the characteristic counterparty within a preset time period based on the resource transfer data related to the target user and the characteristic counterparty list data; determining whether the resource source category of the target user is a preset category based on the resource transfer amount within the preset time period; when it is determined that the resource source category of the target user is a preset category, sending information related to the target user to the processing object corresponding to the target user.

[0012] In one embodiment, obtaining characteristic transaction counterparty list data includes: obtaining full industrial and commercial data; inputting the full industrial and commercial data into a classifier trained using a logistic regression model to obtain the characteristic transaction counterparty list data, wherein the characteristic transaction counterparty list data includes: the name of the intermediary company, the name of the intermediary employee, the intermediary employee ID number, and the intermediary employee account number.

[0013] The embodiment of the present application also provides a device for pushing target user information, including: an acquisition module, used to acquire target stock data and a data set of the target user; wherein the data set of the target user includes: basic information of the target user, and the target stock data represents previously generated and stored data related to the target user; a data integration module, used to integrate the target stock data and the data set of the target user to obtain resource transfer data related to the target user; wherein the resource transfer data characterizes the resource transfer situation of the target user; a risk level determination module, used to determine the resource source category of the target user based on the resource transfer data related to the target user, using a feature database and a preset classification model; wherein the feature database is used to characterize the judgment standard of the resource source category, and the preset classification model is used to judge the category of the resource source based on the feature database; a risk warning module, used to send information related to the target user to the processing object corresponding to the target user when the resource source category of the target user is a preset category.

[0014] An embodiment of the present application also provides a device for pushing target user information, including a processor and a memory for storing processor executable instructions, wherein the processor implements the steps of the method for pushing target user information when executing the instructions.

[0015] The embodiment of the present application also provides a computer-readable storage medium on which computer instructions are stored, and when the instructions are executed, the steps of the method for pushing target user information are implemented.

[0016] The embodiment of the present application provides a method for pushing target user information. The target stock data and the target user's data set can be obtained, and the target stock data and the target user's data set can be integrated to obtain resource transfer data related to the target user. The resource transfer data related to the target user can be obtained efficiently and accurately by using the stock data for data integration, which provides a good data foundation for data mining. Furthermore, the resource source category of the target user can be determined based on the resource transfer data related to the target user using a feature database and a preset classification model. Since the data volume of the resource transfer data related to the target user is large, the resource source category of the target user can be quickly and accurately determined using the feature database and the preset classification model. When the resource source category of the target user is a preset category, the information related to the target user is sent to the processing object corresponding to the target user, so that the information of the target user can be processed in a timely and effective manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application, constitute a part of the present application, and do not constitute a limitation of the present application. In the drawings:

[0018] Figure 1 is a schematic diagram of a system for pushing target user information provided according to an embodiment of the present application;

[0019] Figure 2 It is a schematic diagram of the steps of a method for pushing target user information provided in an embodiment of the present application;

[0020] Figure 3 It is a structural diagram of a device for pushing target user information provided in an embodiment of the present application;

[0021] Figure 4 It is a structural diagram of a device for pushing target user information provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present application, and are not intended to limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the disclosure of the present application more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0023] Those skilled in the art know that the embodiments of the present application can be implemented as a system, device, method or computer program product. Therefore, the present application can be implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0024] Although the processes described below include multiple operations that occur in a particular order, it should be clear that these processes may include more or fewer operations, which may be performed sequentially or in parallel (eg, using parallel processors or a multi-threaded environment).

[0025] In a scenario example of the present application, a system for pushing target user information is provided, such as Figure 1 As shown, it may include: a terminal device 101 and a bank server 102. The target user may initiate a resource transfer application in the bank system through the terminal device 101. The bank server 102 may determine the resource source category of the target user based on the resource transfer request submitted by the target user, and send information related to the target user to the processing object corresponding to the target user when the resource source category of the target user is a preset category. Furthermore, the determination result of the resource source category of the target user may also be fed back to the terminal device 101.

[0026] The terminal device 101 may be a terminal device or software operated by a user. Specifically, the terminal device may be a terminal device such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart watch or other wearable device, or a robot device, etc. Of course, the terminal device 101 may also be software that can run in the terminal device. For example: application software such as a banking system application, a payment application, a browser, and a WeChat applet.

[0027] The bank server 102 can be a single server or a server cluster. Of course, the server function can also be realized through cloud computing technology. The bank server 102 can be connected to multiple terminal devices, or it can be a server with a powerful bank transaction database, which can perform data mining based on user-initiated resource transfer requests and stock data in the bank database.

[0028] See also Figure 2 This embodiment can provide a method for pushing target user information. The push of the target user information can be used to review the resource transfer request submitted by the target user online, and prompt in time when it is confirmed that the resource source category of the target user is a preset category. The above-mentioned method for pushing target user information can include the following steps.

[0029] S201: Acquire target stock data and a data set of a target user, wherein the data set of the target user includes: basic information of the target user, and the target stock data represents previously generated and stored data related to the target user.

[0030] In this embodiment, the target stock data and target user data sets can be obtained. The stock data can refer to various types of activity data previously generated and stored in banks or other financial institutions, including: resource transfer data, wage payment data, user basic information, provident fund data, corporate customer data, personal customer data, industrial and commercial data, and credit data of the People's Bank of China.

[0031] The above-mentioned target stock data is data that can be used for risk mining, for example: the activity data of the target user before applying for resource transfer, and the relevant data of the counterparty with whom the target user has a resource transfer relationship. The above-mentioned target user may be a user who has submitted a resource transfer application and needs to be reviewed. The above-mentioned target user's data set may be a collection of relevant data of the resource transfer application submitted by the target user. In one embodiment, the above-mentioned target user's data set may include: basic information of the target user, and in some embodiments, may also include: the type of resource transfer application submitted by the target user, the total amount of resource transfer applied by the target user, and the date on which the target user applied for resource transfer. Specifically, the above-mentioned target user's data set may include: ID number, reserved telephone number, work unit, loan account number, down payment amount, loan amount, resource transfer application date, bank account opening date, loan application approval date, and housing information.

[0032] In this embodiment, the above resources may include: virtual currency, account funds, gold, real estate and other fixed assets, etc. Resource transfer may be the transfer of resources between users or between users and banks, or between users and products. In one embodiment, resource transfer may include: transfer, loan, loan repayment, purchase of financial products, etc.

[0033] In this embodiment, the target stock data and target user data sets may be obtained by pulling them from a preset database or mining them from text descriptions using a rule extraction method in combination with a corpus. The preset database may be a database in a bank or other financial institution that stores historical data and data submitted and generated by users in real time.

[0034] In one embodiment, obtaining the target stock data may include: obtaining the historical data of the target user before applying for fund transfer, wherein the historical data may include: wage payment data, provident fund data, and resource transfer data. Furthermore, the counterparty with a resource transfer relationship with the target user may be determined based on the resource transfer data in the historical data, and the relevant data of the counterparty may be obtained, and the historical data and the relevant data of the counterparty may be used as the target stock data. The relevant data of the counterparty may include all historical activity data of the counterparty, and may include: identity card number, reserved telephone number, work unit, bank account number, resource transfer data, etc.

[0035] In this embodiment, the above-mentioned counterparty refers to the user who has resource transfer with the target account. Therefore, the counterparty of the target user can be determined based on the resource transfer data of the target user. Since the user may only have abnormal transactions within a period of time before applying for resource transfer, for example, 3 months or 6 months, the historical data that is more than 6 months away from the current resource transfer application will generally have a relatively small impact on the risk of the target user's current resource transfer application. Therefore, in some embodiments, it is not necessary to obtain all the historical data of the target user before applying for resource transfer. Only the historical data of the target user within a period of time before applying for a loan can be obtained, thereby reducing the amount of data processing and improving the efficiency of data processing.

[0036] S202: Integrate the target stock data and the target user's data set to obtain resource transfer data related to the target user; wherein the resource transfer data represents the resource transfer situation of the target user.

[0037] Since the target user's data set does not contain all the target user's data, in some cases the target user may have other accounts besides the bank account included in the data set. Therefore, in one embodiment, the target stock data and the target user's data set may be integrated to obtain resource transfer data related to the target user.

[0038] In this embodiment, the target stock data and the target user's data set are integrated, and the data related to the target user in the target stock data is associated with the target user's data set, so as to obtain the resource transfer data related to the target user. The resource transfer data related to the target user can be used to characterize the resource transfer situation of the target user, so as to reflect the resource transfer situation between the target user and the transaction counterparty.

[0039] In one embodiment, the target user's data set can be associated with the target user's data in the target stock data using a unique ID technology, and the resource transfer data related to the target user can be determined based on the associated data. The above unique ID technology can associate different data using a unique ID key, and the unique ID key can be an ID number, a phone number, a product number, etc.

[0040] In this embodiment, the target user's ID card number can be used to associate the target user with other unprovided in-bank debit cards in the target stock data, thereby obtaining resource transfer data related to the target user. Of course, it is understandable that other possible unique ID keys can also be used to establish the association between data, which can be determined according to actual conditions, and this application does not limit this.

[0041] S203: Determine the resource source category of the target user based on the resource transfer data related to the target user using a feature database and a preset classification model; wherein the feature database is used to characterize the judgment criteria for the resource source category, and the preset classification model is used to judge the resource source category based on the feature database.

[0042] The resource transfer data related to the target user can reflect the resource source of the target user. Therefore, in this embodiment, the resource source category of the target user can be determined based on the resource transfer data related to the target user using a feature database and a preset classification model. The feature database can be used to characterize the judgment criteria for the resource source category. The feature database can store historical risk events and information related to feature users and feature transaction counterparties involved in historical risk events. Specifically, it can be formed based on the accumulated historical data and information about users involved in the historical data. The users involved in the historical data can include: feature users, intermediary companies, P2P network companies, etc.

[0043] In this embodiment, the above-mentioned preset classification model can be used to determine the category of resource sources according to the feature database, and can be a classification model pre-trained using supervised classification technology. The above-mentioned preset classification model can determine the resource source category of the target user based on the data in the feature database. In some embodiments, the risk level corresponding to the resource source category of the target user can also be determined. The risk level can include: no risk, low risk, medium risk and high risk, etc., and of course other risk levels can also be included, such as: medium-low risk, extremely high risk, etc., which can be set according to actual conditions, and this application does not limit this. In this embodiment, the resource source category of the target user can include: salary payment, transfer of users with social attribute relationships, transfer of feature transaction counterparties (users, companies), loans or borrowing.

[0044] Since the feature database stores the accumulated historical data and the information of the users involved in the historical data, in one embodiment, the resource transfer data related to the target user can be matched with the data in the feature database using the preset classification model, and the category of the target user's resource source can be determined based on the matching result. Furthermore, the risk level corresponding to the resource source category of the target user can be determined based on the frequency of occurrence of the determined resource source category and the number of times the target user and the target user's counterparty have experienced risks.

[0045] S204: When the resource source category of the target user is a preset category, information related to the target user is sent to a processing object corresponding to the target user.

[0046] In this embodiment, when the resource source category of the target user is a preset category, information related to the target user can be sent to the processing object corresponding to the target user. Among them, the preset category can be that the resource source of the target user is a transfer, loan, etc. of a characteristic counterparty (user, company), which can be determined according to actual conditions, and this application does not limit this. The above information related to the target user can be used to characterize the overall situation of the source of funds of the target user. The information related to the target user may include: the target user's ID number, reserved telephone number, work unit, loan account number, down payment amount, loan amount, resource transfer application date, loan application approval date, risk level, resource source category type, and relevant information of the user or company involved in the resource source.

[0047] In this embodiment, when it is determined that the resource source category of the target user is a preset category, it means that the target user may be at risk, and the target user's loan needs to be processed in a timely manner. Since each user is assigned a corresponding processing object when applying for resource transfer, the generated information related to the target user can be sent to the processing object corresponding to the target user, so that the processing object can process the target user's resource transfer application, thereby effectively avoiding the occurrence of risks.

[0048] In this implementation, the above-mentioned processing object can be a customer manager or other staff responsible for loan review, and the specific one can be determined according to actual conditions, and this application does not limit this.

[0049] From the above description, it can be seen that the embodiment of the present application achieves the following technical effects: by acquiring the target stock data and the target user's data set, the target stock data and the target user's data set are integrated to obtain the resource transfer data related to the target user, wherein the resource transfer data related to the target user can be obtained efficiently and accurately by using the stock data for data integration, providing a good data basis for data mining. Further, the resource source category of the target user can be determined based on the resource transfer data related to the target user using the feature database and the preset classification model. Since the data volume of the resource transfer data related to the target user is large, the resource source category of the target user can be quickly and accurately determined from it using the feature database and the preset classification model. In the case where the resource source category of the target user is a preset category, information related to the target user is sent to the processing object corresponding to the target user, so that the information of the target user can be processed in a timely and effective manner.

[0050] In one embodiment, according to the resource transfer data related to the target user, the resource source category of the target user is determined using a feature database and a preset classification model, which may include: determining a feature transaction counterparty portrait and a feature user portrait based on the feature database, and inputting the resource transfer data related to the target user, the feature transaction counterparty portrait, and the feature user portrait into the preset classification model. Further, the resource source category of the target user output by the preset classification model may be received.

[0051] In this embodiment, the characteristic user may be a user who has engaged in risky behavior in the past, and the characteristic transaction counterparty may be a transaction counterparty that has transferred resources with the user in historical data, thereby generating risky behavior.

[0052] In this embodiment, the above-mentioned characteristic counterparty portrait can be the attributes, behaviors and other information of the characteristic counterparty, and the attributes, behaviors and the like of the characteristic counterparty can be linked together by using text, graph and other technologies to form the characteristic counterparty portrait. Furthermore, the above-mentioned characteristic counterparty portrait can also include the risk index of the characteristic counterparty, which can be used to describe the frequency of risk hits of the characteristic counterparty, and can include at least one of the following: the number of risk hits in the past month, the number of risk hits in the past three months, the number of risk hits in the past year, the number of risk applications in the past month, etc., so as to comprehensively describe the characteristic counterparty to explore whether there is risk in the counterparty that has a resource transfer relationship with the target user.

[0053] In this embodiment, the above-mentioned characteristic user portrait can be the attributes, behaviors and other information of the characteristic user, and the attributes, behaviors and the like of the characteristic user can be linked together by using text, graph and other technologies to form the characteristic user portrait. Furthermore, the above-mentioned characteristic user portrait can also include the risk characteristics of the user, which can be used to describe the risks involved in the characteristic user, and can include: the user's multiple loan risk characteristics, the characteristics of the down payment coming from other loan risks, the number of transactions with the risk counterparty in the past month, the transaction amount with the risk counterparty in the past month, the ratio of the transaction amount with the characteristic transaction counterparty in the past month to the user's down payment, etc., so as to comprehensively describe the characteristic user and explore the possible risks of the target user.

[0054] In this embodiment, the resource source category of the target user can be determined by using a preset classification model. Specifically, the preset classification model can determine the target user's counterparty information and the target user's related information based on the resource transfer data related to the target user, wherein the target user's counterparty information may include: the counterparty's account number, the counterparty's basic information, the amount of resource transfer between the counterparty and the target user, etc., and the target user's related information may include: the number of transactions between the target user and the counterparty, the amount of resource transfer between the target user and the counterparty, the amount of resource transfer applied by the target user, the target user's down payment amount, and the total number of loans under the target user's name. In some embodiments, when determining the target user's counterparty information and the target user's related information, the target user's data set and other information can be combined, and the specific information can be determined according to actual conditions, and this application does not limit this.

[0055] Further, the preset classification model can match the target user's counterparty information with the characteristic counterparty portrait, and match the target user's relevant information with the characteristic user portrait, so as to obtain a matching result, and the resource source category of the target user can be determined according to the above matching result. Among them, the above matching result can include at least one of the following: the target user's counterparty information successfully matches the characteristic counterparty portrait, the target user's counterparty information fails to match the characteristic counterparty portrait, the target user's relevant information successfully matches the characteristic user portrait, the target user's relevant information fails to match the characteristic user portrait, etc. It can be understood that in some embodiments, the above matching result can also include other information, for example: the matching rate of the target user's relevant information and the characteristic user portrait is 50%, the matching rate of the target user's counterparty information and the characteristic counterparty portrait is 20%, etc., which can be set according to actual conditions, and this application does not limit this.

[0056] In this embodiment, matching the target user's counterparty information with the characteristic counterparty portrait can determine whether the target user's counterparty matches the characteristic counterparty in the characteristic database who has had risky behavior, that is, determine whether the target user's counterparty is a user who has had risky behavior. In one embodiment, it can be determined whether the target user's counterparty's account number or ID number matches the characteristic counterparty portrait, or whether the transaction behavior between the target user's counterparty and the target user matches the description in the characteristic counterparty portrait. Of course, it can be understood that matching can also be performed from other angles, which can be determined specifically based on actual conditions, and this application does not limit this.

[0057] In this embodiment, matching the relevant information of the target user with the characteristic user portrait can determine whether the target user is a user who has engaged in risky behavior, or whether the target user has the risk characteristics of a characteristic user who has engaged in risky behavior. In one embodiment, it can be determined whether the target user's account number or ID card number matches the characteristic user portrait, or whether the target user has the risk characteristics contained in the characteristic user portrait. Of course, it can be understood that matching can also be performed from other angles, which can be determined specifically according to actual conditions, and this application does not limit this.

[0058] Since the above matching results contain the matching information of the target user and the counterparty of the target user, it is possible to determine whether the target user is risky based on the above matching results, and further determine the resource source category and risk type of the target user. Furthermore, the risk level corresponding to the resource source category can be comprehensively determined based on the frequency of the corresponding resource source category in history, the amount involved, etc. Specifically, it can be determined based on actual conditions, and this application does not limit this.

[0059] In one embodiment, if the above matching result is that the target user's counterparty information does not match the characteristic counterparty portrait, that is, there is no data matching the target user's counterparty in the characteristic database, then it means that the target user's counterparty is safe from the perspective of historical data. However, in some embodiments, there may be a risk of the target user's counterparty, but there is no record in the characteristic database, resulting in omissions. Therefore, the characteristic counterparty list data can be obtained, and the transaction amount between the target user and the characteristic counterparty within a preset time period can be determined based on the resource transfer data related to the target user and the characteristic counterparty list data. Furthermore, it can be determined whether the target user's resources are at risk based on the resource transfer amount within the preset time period. In the case of determining that the target user's resources are at risk, information related to the target user can be sent to the processing object corresponding to the target user.

[0060] In one embodiment, since the counterparty may cooperate with the target user, risk behaviors such as loan fraud, loan arbitrage and money laundering may occur. In the process, it is necessary to transfer all or part of the resources required for cooperation with the counterparty to the target user. In a specific scenario, the counterparty will package the identity of users who do not meet the loan qualifications so that they can apply for mortgages that do not match their own consumption ability, or borrow the identities of multiple loan-qualified users from the counterparty to apply for multiple mortgages to hoard houses. Since the target user itself does not have the corresponding down payment payment ability or does not actually pay and repay the target user itself, the counterparty is required to provide part or all of the down payment or repayment funds to the target user before and after the loan. Therefore, the resource transfer data of the borrowing user within the preset time period can effectively reflect the resource transfer between the target user and the counterparty before and after the loan, thereby effectively tracking the source of the down payment or repayment funds. The counterparty that may have the above-mentioned behavior can be called a characteristic counterparty, which may include: financial institutions, employees of financial institutions, intermediary employees and intermediary companies in some embodiments.

[0061] The above-mentioned characteristic transaction counterparty list data is a list data containing all possible characteristic transaction counterparty information, wherein the list data may include: basic information and account number of the characteristic transaction counterparty. Since the above-mentioned characteristic transaction counterparty list data cannot be directly obtained from the database, data mining is required. In one embodiment, the full amount of industrial and commercial data can be obtained, wherein the full amount of industrial and commercial data can be a text description, for example: the business scope of a certain company is "enterprise management, computer system services, computer animation design, economic information consulting services..."

[0062] Furthermore, supervised classification technology can be used to extract some data from the above-mentioned full industrial and commercial data, and then manually mark whether it is a risky counterparty as training data. The training input feature is the business scope description text in the industrial and commercial data, and the business scope description text in the industrial and commercial data is vectorized using the TF-IDF algorithm (term frequency-inverse document frequency) and input into the classification algorithm model. The classification algorithm model can use a logistic regression model. After the training is completed, a trained classifier can be obtained, and the above-mentioned full industrial and commercial data can be input into the classifier trained using the logistic regression model to obtain the feature counterparty list data.

[0063] In this embodiment, the industrial and commercial data is used, so the output data is mainly company data. Therefore, in some embodiments, the corresponding employee data can be further mined through the wage data, provident fund data and private customer data, so as to obtain the ID number, account number and other information of the intermediary employee. It can be seen that the above-mentioned characteristic transaction counterparty list data may include: the name of the intermediary company, the name of the intermediary employee, the ID number of the intermediary employee, and the account number of the intermediary employee.

[0064] In this embodiment, if the amount of the target user's resources coming from the characteristic transaction counterparty is small within the preset time period, it can be determined that the target user's resources are not at risk. In this case, it is necessary to first determine the proportion of the target user's resources coming from the characteristic transaction counterparty. In one embodiment, the following formula can be used to determine whether the target user's source of funds is at risk:

[0065]

[0066] Among them, trans T It represents the total amount of money transferred by the characteristic counterparty to the target user within the preset time period T; baseAmt represents the base amount for comparison, such as the down payment or repayment amount (monthly payment, etc.); β and α are threshold parameters, which can be any values ​​greater than 0, such as 0.5, 0.83, 1.0, etc. The specific values ​​can be set according to actual needs, and are not limited in the comparison of this application.

[0067] When the calculation result is 1, it indicates that there is a risk in the source of funds of the target user. If the calculation result is 0, it indicates that there is no risk. In one embodiment, the parameter T can be used to control whether the risk warning calculation scenario is the risk of the source of the down payment or the risk of the source of the repayment funds. For example, when the data of the target user N months before submitting the loan application is selected, the risk of the source of the down payment is calculated; when the data of the target user N months after opening the account is selected, the risk of the source of the repayment funds is calculated. Generally, the preset time period T is three months or six months before the target user submits the loan application or after opening the account. The above formula can indicate that when the transfer amount received by the target user from the characteristic transaction counterparty within the T time range is within the range of β to α times the baseAmt amount, it is judged that the target user's loan funds are at risk.

[0068] Based on the same inventive concept, a device for pushing target user information is also provided in the embodiments of the present application, such as the following embodiments. Since the principle of solving the problem by the device for pushing target user information is similar to that of the method for pushing target user information, the implementation of the device for pushing target user information can refer to the implementation of the method for pushing target user information, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived. Figure 3 is a structural block diagram of a device for pushing target user information in an embodiment of the present application, such as Figure 3 As shown, it may include: an acquisition module 301, a data integration module 302, a risk level determination module 303, and a risk warning module 304. The structure is described below.

[0069] The acquisition module 301 may be used to acquire target stock data and a target user's data set; wherein the target user's data set includes: basic information of the target user, and the target stock data represents previously generated and stored data related to the target user.

[0070] The data integration module 302 may be used to integrate the target stock data and the target user's data set to obtain resource transfer data related to the target user; wherein the resource transfer data represents the resource transfer situation of the target user.

[0071] The risk level determination module 303 can be used to determine the resource source category of the target user based on the resource transfer data related to the target user, using a feature database and a preset classification model; wherein the feature database is used to characterize the judgment criteria for the resource source category, and the preset classification model is used to judge the resource source category based on the feature database.

[0072] The risk warning module 304 may be used to send information related to the target user to a processing object corresponding to the target user when the resource source category of the target user is a preset category.

[0073] The present application also provides an electronic device. Figure 4The electronic device composition structure diagram of the push method of target user information provided by the embodiment of the present application is shown, and the electronic device may specifically include an input device 41, a processor 42, and a memory 43. Among them, the input device 41 can be specifically used to input the target stock data and the target user's data set. The processor 42 can be specifically used to obtain the target stock data and the target user's data set; wherein the target user's data set includes: basic information of the target user, and the target stock data represents the previously generated and stored data related to the target user; the target stock data and the target user's data set are integrated to obtain the resource transfer data related to the target user; wherein the resource transfer data represents the resource transfer situation of the target user; according to the resource transfer data related to the target user, the resource source category of the target user is determined using a feature database and a preset classification model; wherein the feature database is used to represent the judgment standard of the resource source category, and the preset classification model is used to judge the category of the resource source according to the feature database; when the resource source category of the target user is a preset category, the information related to the target user is sent to the processing object corresponding to the target user. The memory 43 can be specifically used to store parameters such as the resource source category of the target user.

[0074] In this embodiment, the input device can specifically be one of the main devices for information exchange between the user and the computer system. The input device can include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input the original data and the program for processing these numbers into the computer. The input device can also obtain and receive data transmitted from other modules, units, and devices. The processor can be implemented in any appropriate manner. For example, the processor can take the form of a computer-readable medium, a logic gate, a switch, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a programmable logic controller, and an embedded microcontroller, etc., such as a microprocessor or a processor and a computer-readable program code (such as software or firmware) that can be executed by the (micro) processor. The memory can specifically be a memory device used to store information in modern information technology. The memory can include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function without a physical form is also called a memory, such as a RAM, a FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, a TF card, etc.

[0075] In this embodiment, the functions and effects specifically realized by the electronic device can be explained in comparison with other embodiments and will not be described in detail here.

[0076] In an embodiment of the present application, a computer storage medium of a push method based on target user information is also provided, and the computer storage medium stores computer program instructions, which can achieve the following when the computer program instructions are executed: obtaining target stock data and a data set of the target user; wherein the data set of the target user includes: basic information of the target user, and the target stock data represents previously generated and stored data related to the target user; integrating the target stock data and the data set of the target user to obtain resource transfer data related to the target user; wherein the resource transfer data represents the resource transfer situation of the target user; according to the resource transfer data related to the target user, determining the resource source category of the target user using a feature database and a preset classification model; wherein the feature database is used to represent the judgment standard of the resource source category, and the preset classification model is used to judge the category of the resource source according to the feature database; when the resource source category of the target user is a preset category, sending information related to the target user to the processing object corresponding to the target user.

[0077] In this embodiment, the storage medium includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk (HDD), or a memory card. The memory can be used to store computer program instructions. The network communication unit can be an interface for network connection communication set in accordance with the standard specified by the communication protocol.

[0078] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer storage medium can be explained in comparison with other embodiments and will not be repeated here.

[0079] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0080] Although the present application provides method operation steps such as the above-mentioned embodiments or flowcharts, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the embodiments of the present application. When the method is executed in an actual device or terminal product, it can be executed in the order of the method shown in the embodiment or the accompanying drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0081] It should be understood that the above description is for illustration and not for limitation. By reading the above description, many embodiments and many applications beyond the examples provided will be apparent to those skilled in the art. Therefore, the scope of the present application should not be determined with reference to the above description, but should be determined with reference to the aforementioned claims and the full scope of equivalents possessed by these claims.

[0082] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for pushing target user information, characterized in that: include: Acquire target stock data and a data set of a target user; wherein the data set of the target user includes: basic information of the target user, and the target stock data represents previously generated and stored data related to the target user; Integrate the target stock data and the target user's data set to obtain resource transfer data related to the target user; wherein the resource transfer data represents the resource transfer situation of the target user; According to the resource transfer data related to the target user, the resource source category of the target user is determined by using a feature database and a preset classification model; wherein the feature database is used to characterize the judgment criteria for the resource source category, the feature database stores historical risk events and relevant information of feature users and feature trading counterparties involved in the historical risk events, the feature database is formed based on the accumulated historical data and the information of users involved in the historical data, and the preset classification model is used to judge the category of the resource source based on the feature database; When the resource source category of the target user is a preset category, sending information related to the target user to a processing object corresponding to the target user; According to the resource transfer data related to the target user, the resource source category of the target user is determined by using a feature database and a preset classification model, including: The resource transfer data related to the target user is matched with the data in the feature database using a preset classification model, and the category of the resource source of the target user is determined based on the matching result.

2. The method according to claim 1, characterized in that Obtain target inventory data, including: Acquire historical data of the target user, wherein the historical data includes: wage payment data, provident fund data, and resource transfer data; Determining a transaction counterparty having a resource transfer relationship with the target user according to the resource transfer data in the historical data; Obtain relevant data of the transaction counterparty; The historical data and the relevant data of the transaction counterparty are used as the target inventory data.

3. The method according to claim 1, characterized in that Integrate the target stock data and the target user's data set to obtain resource transfer data related to the target user, including: Associating the target user's data set with the target user's related data in the target stock data using unique ID technology; The resource transfer data related to the target user is determined according to the associated data.

4. The method according to claim 1, characterized in that: According to the resource transfer data related to the target user, the resource source category of the target user is determined by using a feature database and a preset classification model, including: Determine a characteristic transaction counterparty portrait and a characteristic user portrait based on the characteristic database; Inputting the resource transfer data, characteristic transaction counterparty portrait and characteristic user portrait related to the target user into the preset classification model; Receive the resource source category of the target user output by the preset classification model.

5. The method according to claim 4, characterized in that After inputting the resource transfer data, the characteristic transaction counterparty portrait and the characteristic user portrait related to the target user into the preset classification model, the method further includes: The preset classification model determines the transaction counterparty information of the target user and the relevant information of the target user according to the resource transfer data related to the target user; The preset classification model matches the transaction counterparty information of the target user with the characteristic transaction counterparty portrait, and matches the relevant information of the target user with the characteristic user portrait to obtain a matching result; The preset classification model determines the resource source category of the target user according to the matching result.

6. The method according to claim 5, characterized in that When the matching result is that the transaction counterparty information of the target user does not match the characteristic transaction counterparty portrait, the method further includes: Obtain the characteristic counterparty list data; Determine the resource transfer amount between the target user and the characteristic transaction counterparty within a preset time period according to the resource transfer data related to the target user and the characteristic transaction counterparty list data; Determining whether the resource source category of the target user is a preset category according to the resource transfer amount within the preset time period; When it is determined that the resource source category of the target user is a preset category, information related to the target user is sent to a processing object corresponding to the target user.

7. The method according to claim 6, characterized in that Obtain the characteristic counterparty list data, including: Obtain full industrial and commercial data; The full amount of industrial and commercial data is input into a classifier trained using a logistic regression model to obtain the characteristic transaction counterparty list data, wherein the characteristic transaction counterparty list data includes: the name of the intermediary company, the name of the intermediary employee, the intermediary employee ID number, and the intermediary employee account number.

8. A device for pushing target user information, characterized in that: include: An acquisition module, used to acquire target stock data and a data set of a target user; wherein the data set of the target user includes: basic information of the target user, and the target stock data represents previously generated and stored data related to the target user; A data integration module, used to integrate the target stock data and the target user's data set to obtain resource transfer data related to the target user; wherein the resource transfer data represents the resource transfer situation of the target user; A risk level determination module, used to determine the resource source category of the target user based on the resource transfer data related to the target user, using a feature database and a preset classification model; wherein the feature database is used to characterize the judgment criteria for the resource source category, the feature database stores historical risk events and relevant information of feature users and feature trading counterparties involved in the historical risk events, the feature database is formed based on the accumulated historical data and the information of users involved in the historical data, and the preset classification model is used to judge the category of the resource source based on the feature database; A risk warning module, configured to send information related to the target user to a processing object corresponding to the target user when the resource source category of the target user is a preset category; According to the resource transfer data related to the target user, the resource source category of the target user is determined by using a feature database and a preset classification model, including: The resource transfer data related to the target user is matched with the data in the feature database using a preset classification model, and the category of the resource source of the target user is determined based on the matching result.

9. A device for pushing target user information, characterized in that: The method comprises a processor and a memory for storing processor-executable instructions, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the instructions.

10. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed, the steps of the method according to any one of claims 1 to 7 are implemented.

Images