Method and device for opening a unit settlement card

Abstract

The application discloses a kind of establishment method and device of unit settlement card, it is related to the field of financial technology, wherein the method comprises: by obtaining the unit settlement card establishment information submitted by enterprise customer, according to enterprise customer information, through federal computing call relevant database interface of enterprise customer, the comparison result of the information stored by enterprise customer and enterprise customer information is obtained from the database related to enterprise customer;Using pre-constructed knowledge graph and graph data mining model, the audit result of unit settlement card establishment information is obtained;If the audit result of unit settlement card establishment information is audit passed, according to enterprise customer information, the transaction limit of enterprise customer has opened account and historical transaction data are obtained, and input decision tree model, predict account transaction behavior data;According to account transaction behavior data, determine the transaction limit of unit settlement card, the present application can improve the comprehensiveness of transaction limit coverage, reduce transaction risk.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of financial technology, in particular to a method and device for opening a unit settlement card. BACKGROUND

[0002] This section is intended to provide background or context to the embodiments of the application recited in the claims. The description herein does not constitute admission of prior art.

[0003] With the increasing convenience of transactions, the risk of enterprise and bank capital security has also increased. The existing transaction risk control method has the problem of customer information leakage in the process of opening and auditing the unit settlement card. The phenomenon of inconsistent customer identity information and false enterprise information occurs, resulting in certain risks in transactions. In addition, the existing transaction risk control method cannot set the transaction limit of the unit settlement card, resulting in incomplete coverage of the transaction limit and risks such as loss of funds. SUMMARY

[0004] The embodiments of the present application provide a method for opening a unit settlement card to set a transaction limit, improve the comprehensiveness of transaction limit coverage, and reduce transaction risk. The method comprises:

[0005] Obtaining unit settlement card opening information submitted by an enterprise customer, wherein the unit settlement card opening information comprises enterprise customer information;

[0006] According to the enterprise customer information, calling a database interface related to the enterprise customer through federated computing, and obtaining the comparison result of the information stored by the enterprise customer and the enterprise customer information from the database related to the enterprise customer;

[0007] After the comparison result is correct, using a pre-constructed knowledge graph and a graph data mining model to perform correlation analysis and authenticity verification on the enterprise customer information to obtain an audit result of the unit settlement card opening information; the knowledge graph is pre-constructed according to historical enterprise customer information; and the graph data mining model determines the correlation of the enterprise customer information through a community detection algorithm;

[0008] If the audit result of the unit settlement card opening information is passed, according to the enterprise customer information, obtaining the transaction limit and historical transaction data of the account opened by the enterprise customer;

[0009] Inputting the transaction limit and historical transaction data of the account opened by the enterprise customer into a decision tree model to predict the dynamic account transaction behavior data of the unit settlement card of the enterprise customer;

[0010] According to the dynamic account transaction behavior data of the unit settlement card of the enterprise customer, determining the transaction limit of the unit settlement card, and completing the opening process of the unit settlement card.

[0011] The application also provides a unit settlement card opening device for setting a transaction limit, improving the comprehensiveness of the transaction limit coverage, and reducing transaction risks.

[0012] A unit settlement card opening information acquisition module is configured to acquire unit settlement card opening information submitted by the enterprise client, wherein the unit settlement card opening information comprises enterprise client information.

[0013] An enterprise client information comparison module is configured to compare the enterprise client information with information stored by the enterprise client in a database related to the enterprise client by calling a database interface related to the enterprise client through federated computing.

[0014] A unit settlement card opening information auditing module is configured to, after the comparison, perform correlation analysis and authenticity verification on the enterprise client information by using a pre-constructed knowledge graph and a graph data mining model to obtain an auditing result of the unit settlement card opening information, wherein the knowledge graph is pre-constructed according to historical enterprise client information, and the graph data mining model determines the correlation of the enterprise client information by using a community detection algorithm.

[0015] A transaction limit and historical transaction data acquisition module is configured to, if the auditing result of the unit settlement card opening information is passed, acquire a transaction limit and historical transaction data of an account opened by the enterprise client according to the enterprise client information.

[0016] A dynamic account transaction behavior data prediction module is configured to input the transaction limit and historical transaction data of the account opened by the enterprise client into a decision tree model to predict dynamic account transaction behavior data of the unit settlement card of the enterprise client.

[0017] A transaction limit determination module is configured to determine the transaction limit of the unit settlement card according to the dynamic account transaction behavior data of the unit settlement card of the enterprise client to complete the opening process of the unit settlement card.

[0018] The application also provides a computer device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the unit settlement card opening method when executing the computer program.

[0019] The application also provides a computer readable storage medium, which stores a computer program, wherein the computer program is executable on a processor to implement the unit settlement card opening method.

[0020] The application also provides a computer program product, which comprises a computer program, wherein the computer program is executable on a processor to implement the unit settlement card opening method.

[0021] In the embodiment of the present application, by obtaining the unit settlement card opening information submitted by the enterprise customer, the unit settlement card opening information includes enterprise customer information; according to the enterprise customer information, the database interface related to the enterprise customer is called through federated computing, and the comparison result of the information stored by the enterprise customer and the enterprise customer information is obtained from the database related to the enterprise customer; after the comparison result is correct, the pre-constructed knowledge graph and the graph data mining model are used to perform correlation analysis and authenticity verification on the enterprise customer information, and the audit result of the unit settlement card opening information is obtained; the knowledge graph is pre-constructed according to historical enterprise customer information; the graph data mining model determines the correlation of the enterprise customer information through a community detection algorithm; if the audit result of the unit settlement card opening information is passed, according to the enterprise customer information, the transaction limit and historical transaction data of the account opened by the enterprise customer are obtained; the transaction limit and historical transaction data of the account opened by the enterprise customer are input into a decision tree model to predict the dynamic account transaction behavior data of the unit settlement card of the enterprise customer; according to the dynamic account transaction behavior data of the unit settlement card of the enterprise customer, the transaction limit of the unit settlement card is determined, and the opening process of the unit settlement card is completed. In the above process, the federated computing method is used to ensure the security of the unit settlement card opening information, and the transaction limit is used to control the transaction, thereby improving the comprehensiveness of the transaction limit coverage and reducing the transaction risk. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. In the drawings:

[0023] Figure 1 Flowchart of the unit settlement card opening method in the embodiment of the present application;

[0024] Figure 2 Flowchart of obtaining the enterprise customer information comparison result in the embodiment of the present application;

[0025] Figure 3 Flowchart of constructing the knowledge graph in the embodiment of the present application;

[0026] Figure 4 Flowchart of predicting the dynamic account transaction behavior data in the embodiment of the present application;

[0027] Figure 5 Schematic diagram of the unit settlement card opening device in the embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, further detailed description of the embodiments of the present application will be given below with reference to the drawings. Herein, the illustrative embodiments of the present application and their descriptions are used to explain the present application, but not as a limitation of the present application.

[0029] Figure 1 The flow chart of the method for opening the unit settlement card in the embodiments of the present application, the method comprises:

[0030] Step 101, obtaining the unit settlement card opening information submitted by the enterprise client, the unit settlement card opening information comprising enterprise client information;

[0031] Step 102, according to the enterprise client information, calling the database interface related to the enterprise client through the federal calculation, obtaining the comparison result of the information stored by the enterprise client and the enterprise client information from the database related to the enterprise client;

[0032] Step 103, after the comparison result is correct, using the pre-constructed knowledge graph and the graph data mining model to perform correlation analysis and authenticity verification on the enterprise client information, obtaining the audit result of the unit settlement card opening information; the knowledge graph is pre-constructed according to historical enterprise client information; the graph data mining model determines the correlation of the enterprise client information through a community detection algorithm;

[0033] Step 104, if the audit result of the unit settlement card opening information is passed, according to the enterprise client information, obtaining the transaction limit and historical transaction data of the account opened by the enterprise client;

[0034] Step 105, inputting the transaction limit and historical transaction data of the account opened by the enterprise client into the decision tree model to predict the dynamic account transaction behavior data of the unit settlement card of the enterprise client;

[0035] Step 106, according to the dynamic account transaction behavior data of the unit settlement card of the enterprise client, determining the transaction limit of the unit settlement card, and completing the opening process of the unit settlement card.

[0036] Each step will be explained in detail below.

[0037] In step 101, the unit settlement card opening information submitted by the enterprise client is obtained, and the unit settlement card opening information comprises enterprise client information.

[0038] In specific embodiments, the enterprise client information comprises one or any combination of enterprise information, legal person identity information and agent identity information.

[0039] In specific embodiments, the unit settlement card opening information is encrypted by using an asymmetric encryption algorithm.

[0040] In step 102, according to the enterprise customer information, the database interface related to the enterprise customer is called through federated computing, and the comparison result of the enterprise customer stored information and the enterprise customer information is obtained from the database related to the enterprise customer.

[0041] As shown in Figure 2 In an embodiment, according to the enterprise customer information, the database interface related to the enterprise customer is called through federated computing, and the comparison result of the enterprise customer stored information and the enterprise customer information is obtained from the database related to the enterprise customer, including:

[0042] Step 201, encrypting the enterprise customer information to obtain encrypted enterprise customer information;

[0043] Step 202, sending the encrypted enterprise customer information to the database related to the enterprise customer through the federated computing to call the database interface, so that the database related to the enterprise customer decrypts to obtain the enterprise customer information, obtains the enterprise customer stored information according to the enterprise customer information, and compares the enterprise customer stored information with the enterprise customer information;

[0044] Step 203, obtaining the comparison result of the enterprise customer stored information and the enterprise customer information from the database related to the enterprise customer.

[0045] In specific embodiments, the unit settlement card opening information submitted by the enterprise customer is processed through federated computing, the interface of the database related to the enterprise customer, such as the market supervision database, the tax database, and the bank transaction database, is called using federated computing technology, the local decryption of the encrypted enterprise customer information is completed, the information stored in the database related to the enterprise customer is calculated and compared, and the information is verified to be correct. The enterprise customer information is associated and verified.

[0046] Among them, the interface of the database related to the enterprise customer, such as the interface of the market supervision database, the tax database, and the bank transaction database, is called using federated computing technology, including: using Federated Averaging algorithm to obtain encrypted unit settlement card opening information, and then sending the encrypted enterprise customer information to other federated computing nodes established in the database related to the enterprise customer, such as the market supervision database, the tax database, and the bank transaction database. Other federated computing nodes jointly use encryption technology to decrypt the unit settlement card opening information, compare the unit settlement card opening information submitted by the customer with the enterprise customer stored information in the database related to the enterprise customer, and obtain the comparison result.

[0047] In step 103, after the comparison result is correct, the enterprise customer information is analyzed for correlation and authenticity by using a pre-built knowledge graph and graph data mining model to obtain the audit result of the unit settlement card opening information; the knowledge graph is pre-built based on historical enterprise customer information; the graph data mining model determines the correlation relationship of enterprise customer information through community detection algorithm.

[0048] In a specific embodiment, the association relationship of the enterprise customer information includes one or any combination of the following: the association relationship between enterprise information and legal person identity information, the association relationship between the agent's identity information and legal person identity information, and the association relationship between enterprise information and agent's identity information.

[0049] like Figure 3 As shown, in one embodiment, before performing correlation analysis and authenticity verification on enterprise customer information using a pre-built knowledge graph and graph data mining model, the following steps are also included:

[0050] Step 301: Obtain historical enterprise customer information and analyze the relationships between historical enterprise customer information;

[0051] Step 302: Use historical enterprise customer information as entities in the knowledge graph, and use the relationships between historical enterprise customer information as relationships between entities in the knowledge graph to construct the knowledge graph.

[0052] In one embodiment, a pre-built knowledge graph and graph data mining model are used to perform association analysis and authenticity verification on enterprise customer information to obtain the audit results of the unit settlement card opening information, including:

[0053] The entities and relationships in the knowledge graph are compared and verified with the enterprise customer information to obtain the verification results of the authenticity of the enterprise customer information;

[0054] Using graph data mining models, determine the correlation analysis results of enterprise customer information;

[0055] The results of correlation analysis and authenticity verification of enterprise customer information constitute the audit results of the unit settlement card opening information.

[0056] In a specific embodiment, an audit report for the issuance of a unit settlement card is generated based on the audit results. The audit report includes the customer's risk score, audit conclusion, and audit opinions.

[0057] In step 104, if the audit result of the corporate settlement card opening information is approved, the transaction limit and historical transaction data of the corporate customer's opened account are obtained based on the corporate customer information.

[0058] In a specific embodiment, after the review result of the corporate settlement card opening information is approved, the system connects with the bank's internal corporate customer information system, corporate account system and historical transaction system to obtain the transaction limit of the corporate customer's opened bank account, historical transaction data such as account cash deposit and withdrawal, purchase, transfer, payroll, purchase of bond wealth management products, etc., and uses this information to assess the customer's payment ability and demand information.

[0059] In step 105, the transaction limits and historical transaction data of the enterprise customer's opened accounts are input into the decision tree model to predict the transaction behavior data of the enterprise customer's unit settlement card.

[0060] In one embodiment, before inputting the transaction limits and historical transaction data of the enterprise customer's existing accounts into the decision tree model, the following steps are included:

[0061] Perform one or more of the following actions on the transaction limits and historical transaction data of enterprise customers' existing accounts: data deduplication, data completion, and deletion of outliers.

[0062] like Figure 4 As shown, in one embodiment, the transaction limits and historical transaction data of the enterprise customer's opened accounts are input into a decision tree model to predict the transaction behavior data of the enterprise customer's corporate settlement card, including:

[0063] Step 401: Extract features from the transaction limits and historical transaction data of the enterprise customer's opened accounts to obtain feature data of the transaction limits and historical transaction data of the enterprise customer's opened accounts.

[0064] Step 402: Input the characteristic data of the transaction limits and historical transaction data of the enterprise customer's opened accounts into the decision tree model to predict the transaction behavior data of the enterprise customer's unit settlement card.

[0065] In a specific embodiment, feature values ​​such as single payment limit, daily cumulative payment limit, monthly cumulative payment limit, annual cumulative payment limit, and public-to-private transfer limit of the accounts opened by corporate clients are extracted. Simultaneously, feature values ​​are extracted and analyzed based on historical transaction data information (average daily transaction amount, maximum single transaction amount, transaction frequency, transaction type distribution, etc.) of accounts such as cash deposits and withdrawals, purchases, transfers, payroll disbursements, and purchases of bond wealth management products.

[0066] In specific embodiments, according to the account transaction limit and the account historical transaction data, the future consumption, transfer and other account transaction behaviors of the enterprise customer unit settlement card are predicted by a pre-constructed MARS model. The MARS model can automatically select a suitable segmented linear or nonlinear function to fit the data and generate a series of basis functions to approximate the data distribution. The transaction limit of the newly opened unit settlement card of the customer is calculated by the MARS model.

[0067] In step 106, according to the account transaction behavior data of the unit settlement card of the enterprise customer, the transaction limit of the unit settlement card is determined, and the opening process of the unit settlement card is completed.

[0068] In an embodiment, according to the account transaction behavior data of the unit settlement card of the enterprise customer, the transaction limit of the unit settlement card is determined, including:

[0069] According to the account transaction behavior data of the unit settlement card of the enterprise customer, the transaction limit system value of the unit settlement card of the enterprise customer is generated; for example, according to the result of the MARS model calculation, the transaction limit system value of the unit settlement card of the customer is generated, including the upper limit of the balance of the unit settlement card, the single payment limit, the daily cumulative payment limit, the monthly cumulative payment limit, the annual cumulative payment limit, the public to private limit, the public to public limit, the cash amount, the electronic bank channel cumulative payment limit, and the POS consumption limit.

[0070] According to the transaction limit system value of the unit settlement card of the enterprise customer, the self-adaptive matching of the transaction limit system setting of the unit settlement card of the enterprise customer is performed, and the transaction limit system suggestion result of the unit settlement card of the enterprise customer is formed.

[0071] The transaction limit system suggestion result is pushed to the enterprise customer, so that the enterprise customer sets the transaction limit of the unit settlement card according to the transaction limit system suggestion result.

[0072] In specific embodiments, the person in charge of the enterprise customer sets part of the limit of the unit settlement card in the transaction limit system suggestion result through the interactive interface, and the self-set limit cannot exceed the transaction limit system value.

[0073] In the embodiment of the application, a unit settlement card opening device is also provided, as described in the following embodiment. Since the principle of solving the problem of the device is similar to that of the unit settlement card opening method, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described again. As shown in Figure 5 The device includes:

[0074] The unit settlement card opening information acquisition module 501 is configured to acquire the unit settlement card opening information submitted by the enterprise customer, and the unit settlement card opening information includes enterprise customer information.

[0075] The enterprise customer information comparison module 502 is configured to, according to the enterprise customer information, call a database interface related to the enterprise customer through federated computing, and obtain a comparison result of the enterprise customer stored information and the enterprise customer information from the database related to the enterprise customer.

[0076] The unit settlement card opening information auditing module 503 is configured to, after the comparison is correct, perform correlation analysis and authenticity verification on the enterprise customer information by using a pre-constructed knowledge graph and a graph data mining model, and obtain an auditing result of the unit settlement card opening information; the knowledge graph is pre-constructed according to historical enterprise customer information; and the graph data mining model determines the correlation relationship of the enterprise customer information by a community detection algorithm.

[0077] The transaction limit and historical transaction data obtaining module 504 is configured to, if the auditing result of the unit settlement card opening information is passed, obtain the transaction limit and the historical transaction data of the account opened by the enterprise customer according to the enterprise customer information.

[0078] The account transaction behavior data prediction module 505 is configured to input the transaction limit and the historical transaction data of the account opened by the enterprise customer into a decision tree model, and predict the account transaction behavior data of the unit settlement card of the enterprise customer.

[0079] The transaction limit determining module 506 is configured to determine the transaction limit of the unit settlement card according to the account transaction behavior data of the unit settlement card of the enterprise customer, and complete the opening process of the unit settlement card.

[0080] In an embodiment, the enterprise customer information comparison module 502 is specifically configured to:

[0081] encrypt the enterprise customer information to obtain encrypted enterprise customer information;

[0082] call the database interface related to the enterprise customer through federated computing, and send the encrypted enterprise customer information to the database related to the enterprise customer, so that the database related to the enterprise customer: decrypts the enterprise customer information, obtains the enterprise customer stored information according to the enterprise customer information, and compares the enterprise customer stored information with the enterprise customer information.

[0083] obtain a comparison result of the enterprise customer stored information and the enterprise customer information from the database related to the enterprise customer.

[0084] In an embodiment, the method further includes a knowledge graph construction module, which is specifically configured to:

[0085] obtain historical enterprise customer information, and analyze the correlation relationship of the historical enterprise customer information.

[0086] The historical enterprise customer information is taken as an entity in the knowledge graph, and the association relationship of the historical enterprise customer information is taken as a relationship between entities in the knowledge graph, so as to construct the knowledge graph.

[0087] In an embodiment, the unit settlement card opening information auditing module 503 is specifically configured to:

[0088] The entity and the relationship in the knowledge graph are compared and verified with the enterprise customer information, so as to obtain a true and false verification result of the enterprise customer information.

[0089] The association analysis result of the enterprise customer information is determined by using a graph data mining model.

[0090] The association analysis result and the true and false verification result of the enterprise customer information are used to constitute an auditing result of the unit settlement card opening information.

[0091] In an embodiment, the preprocessing module is further included and is specifically configured to:

[0092] The transaction limit and the historical transaction data of the account opened by the enterprise customer are subjected to one or any combination of data deduplication, data completion and data outlier deletion.

[0093] In an embodiment, the dynamic account transaction behavior data prediction module 505 is specifically configured to:

[0094] The transaction limit and the historical transaction data of the account opened by the enterprise customer are subjected to feature extraction, so as to obtain feature data of the transaction limit and the historical transaction data of the account opened by the enterprise customer.

[0095] The feature data of the transaction limit and the historical transaction data of the account opened by the enterprise customer are input into a decision tree model, so as to predict dynamic account transaction behavior data of the unit settlement card of the enterprise customer.

[0096] In an embodiment, the transaction limit determination module 506 is specifically configured to:

[0097] According to the dynamic account transaction behavior data of the unit settlement card of the enterprise customer, a transaction limit system value of the unit settlement card of the enterprise customer is generated.

[0098] According to the transaction limit system value of the unit settlement card of the enterprise customer, adaptive matching is performed on the limit setting in the transaction limit system of the unit settlement card of the enterprise customer, so as to form a transaction limit system suggestion result of the unit settlement card of the enterprise customer.

[0099] The transaction limit system suggestion result is pushed to the enterprise customer, so that the enterprise customer sets the transaction limit of the unit settlement card according to the transaction limit system suggestion result.

[0100] The embodiment of the present application further provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the method for opening the unit settlement card when executing the computer program.

[0101] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program implements the method for opening the unit settlement card when executed by a processor.

[0102] The embodiment of the present application further provides a computer program product, which comprises a computer program, and the computer program implements the method for opening the unit settlement card when executed by a processor.

[0103] In the embodiment of the present application, by obtaining the unit settlement card opening information submitted by the enterprise client, the unit settlement card opening information comprises enterprise client information; according to the enterprise client information, a database interface related to the enterprise client is called through federated computing, and a comparison result of the information stored by the enterprise client and the enterprise client information is obtained from the database related to the enterprise client; after the comparison result is correct, the enterprise client information is analyzed and verified by using a pre-constructed knowledge graph and a graph data mining model, and an audit result of the unit settlement card opening information is obtained; the knowledge graph is pre-constructed according to historical enterprise client information; the graph data mining model determines the correlation of the enterprise client information through a community detection algorithm; if the audit result of the unit settlement card opening information is passed, according to the enterprise client information, transaction limits and historical transaction data of the account opened by the enterprise client are obtained; the transaction limits and the historical transaction data of the account opened by the enterprise client are input into a decision tree model, and the dynamic account transaction behavior data of the unit settlement card of the enterprise client is predicted; according to the dynamic account transaction behavior data of the unit settlement card of the enterprise client, the transaction limits of the unit settlement card are determined, and the opening process of the unit settlement card is completed. In the above process, the federated computing method is used to ensure the security of the unit settlement card opening information, and the transaction limits are used to control the transaction amount and frequency, so as to improve the comprehensiveness of the transaction limits and reduce the transaction risk.

[0104] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0105] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0106] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0107] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0108] The above-described specific embodiments, the purpose, technical solutions and advantages of the present application are further described in detail, it should be understood that the above-described only for the specific embodiments of the present application has, and is not used to limit the scope of protection of the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application, should be included within the scope of protection of the present application.

Claims

1. A method of opening a unit settlement card, characterized by, The method comprises the following steps: obtaining unit settlement card opening information submitted by an enterprise client, wherein the unit settlement card opening information comprises enterprise client information; obtaining comparison results of information stored by the enterprise client and the enterprise client information from a database related to the enterprise client by calling a database interface of the database related to the enterprise client through federated computing according to the enterprise client information; after the comparison results are correct, performing correlation analysis and authenticity verification on the enterprise client information by using a pre-constructed knowledge graph and a graph data mining model to obtain an audit result of the unit settlement card opening information, wherein the knowledge graph is pre-constructed according to historical enterprise client information, and the graph data mining model determines the correlation of the enterprise client information by a community detection algorithm; if the audit result of the unit settlement card opening information is passed, obtaining transaction limits and historical transaction data of an account opened by the enterprise client according to the enterprise client information; inputting the transaction limits and the historical transaction data of the account opened by the enterprise client into a decision tree model to predict dynamic account transaction behavior data of the unit settlement card of the enterprise client; determining transaction limits of the unit settlement card according to the dynamic account transaction behavior data of the unit settlement card of the enterprise client to complete the opening process of the unit settlement card.

2. The method of claim 1, wherein, According to the enterprise client information, the comparison results of the information stored by the enterprise client and the enterprise client information are obtained from a database related to the enterprise client by calling a database interface of the database related to the enterprise client through federated computing, comprising: encrypting the enterprise client information to obtain encrypted enterprise client information; sending the encrypted enterprise client information to the database related to the enterprise client through the database interface of the database related to the enterprise client by federated computing, so that the database related to the enterprise client decrypts the enterprise client information to obtain the enterprise client information, and obtains the information stored by the enterprise client according to the enterprise client information, and compares the information stored by the enterprise client with the enterprise client information; obtaining the comparison results of the information stored by the enterprise client and the enterprise client information from the database related to the enterprise client.

3. The method of claim 1, wherein, Before the correlation analysis and authenticity verification of the enterprise client information by using the pre-constructed knowledge graph and the graph data mining model, the method further comprises the following steps: obtaining historical enterprise client information and analyzing the correlation of the historical enterprise client information; constructing the knowledge graph by taking the historical enterprise client information as entities in the knowledge graph and taking the correlation of the historical enterprise client information as relationships between the entities in the knowledge graph.

4. The method of claim 3, wherein, The correlation analysis and authenticity verification of the enterprise client information by using the pre-constructed knowledge graph and the graph data mining model to obtain the audit result of the unit settlement card opening information, comprising: comparing the entities and the relationships in the knowledge graph with the enterprise client information to obtain authenticity verification results of the enterprise client information; determining correlation analysis results of the enterprise client information by using the graph data mining model; constructing the audit result of the unit settlement card opening information by using the correlation analysis results and the authenticity verification results of the enterprise client information.

5. The method of claim 1, wherein, Before the transaction limits and the historical transaction data of the account opened by the enterprise client are inputted into the decision tree model, the method comprises the following steps: The transaction limit and historical transaction data of the enterprise customer's opened account are processed by one or more of data deduplication, data completion, and data outlier deletion.

6. The method of claim 1, wherein, The transaction limit and historical transaction data of the enterprise customer's opened account are input into a decision tree model to predict the dynamic account transaction behavior data of the enterprise customer's unit settlement card, including: The transaction limit and historical transaction data of the enterprise customer's opened account are processed by one or more of data deduplication, data completion, and data outlier deletion. The transaction limit and historical transaction data of the enterprise customer's opened account are input into a decision tree model to predict the dynamic account transaction behavior data of the enterprise customer's unit settlement card.

7. The method of claim 1, wherein, According to the dynamic account transaction behavior data of the enterprise customer's unit settlement card, the transaction limit of the unit settlement card is determined, including: According to the dynamic account transaction behavior data of the enterprise customer's unit settlement card, the transaction limit system value of the enterprise customer's unit settlement card is generated. According to the transaction limit system value of the enterprise customer's unit settlement card, the transaction limit system settings of the enterprise customer's unit settlement card are adaptively matched to form a transaction limit system recommendation result of the enterprise customer's unit settlement card. The transaction limit system recommendation result is pushed to the enterprise customer for setting the transaction limit of the unit settlement card according to the transaction limit system recommendation result.

8. A device for issuing unit settlement cards, characterized in that, It includes: A unit settlement card opening information acquisition module is configured to acquire unit settlement card opening information submitted by an enterprise customer, wherein the unit settlement card opening information includes enterprise customer information. An enterprise customer information comparison module is configured to compare the enterprise customer information with the information stored by the enterprise customer in a database related to the enterprise customer by calling a database interface related to the enterprise customer through federated computing. A unit settlement card opening information audit module is configured to, after the comparison is correct, perform correlation analysis and authenticity verification on the enterprise customer information by using a pre-constructed knowledge graph and a graph data mining model to obtain an audit result of the unit settlement card opening information. A transaction limit and historical transaction data acquisition module is configured to, if the audit result of the unit settlement card opening information is passed, acquire the transaction limit and historical transaction data of the enterprise customer's opened account according to the enterprise customer information. A dynamic account transaction behavior data prediction module is configured to input the transaction limit and historical transaction data of the enterprise customer's opened account into a decision tree model to predict the dynamic account transaction behavior data of the enterprise customer's unit settlement card. A transaction limit determination module is configured to determine the transaction limit of the unit settlement card according to the dynamic account transaction behavior data of the enterprise customer's unit settlement card to complete the opening process of the unit settlement card.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the method of any one of claims 1 to 7.

Images