Risk verification method and device, computer equipment and storage medium

Abstract

The invention discloses a risk verification method and device, computer equipment and a storage medium. The method is used for verifying whether a preset financial system has a risk or not. The method comprises the following steps: firstly, obtaining to-be-verified business data in a financial system; analyzing the service data to obtain service information corresponding to the service data; the service information at least comprises a service identifier, a service type, a service content and a service amount; obtaining a payment amount corresponding to the service identifier in a preset financial system according to the service identifier; further, if the business amount is smaller than the payment amount, inputting the business type and the business content into a preset amount calculation model, and outputting a calculation amount corresponding to the business type and the business content by the amount calculation model; and finally, if the calculated amount is inconsistent with the business amount, determining that the business data has a risk. According to the method provided by the invention, heavy economic losses caused by model design, low code quality, low test discovery rate and the like can be reduced.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, which is applied in the financial field, and in particular to a risk verification method, device, equipment and medium. Background Art

[0002] In the financial system, due to the numerous related business lines, such as preservation, claims, contracts, medical care, renewal, channels, reinsurance, etc., there are many different business data to be managed in each business line. For example, in preservation, only business data such as fee-related preservation tasks, non-fee-related preservation tasks, long-term insurance preservation tasks, short-term insurance preservation tasks, annual payment preservation tasks, monthly payment preservation tasks, gift insurance preservation tasks, and non-gift insurance preservation tasks can be included. In the financial system, when any business data in each business line is sent to the corresponding financial system, the financial system will perform operations such as collection and payment based on the business data.

[0003] However, due to the large amount of business data in the financial system, it requires a huge amount of manpower and time to check the business data one by one, and it is still impossible to ensure that all business data are checked correctly, resulting in the risk of major losses in the financial system at any time due to errors in the business data reported to the financial system. Summary of the invention

[0004] The present application provides a risk verification method, device, computer equipment and storage medium, which aims to solve the problems of the current old insurance preservation acceptance method, such as single policy function, simple business scenario support, and the use of traditional single architecture in the system. However, there are many non-standard business process function interfaces, and each third-party channel has its own interface specifications and data requirements, which leads to frequent defects such as low automation, unstable service, and high system maintenance costs in the policy acceptance process in the financial system. Ultimately, it leads to major problems such as poor customer experience, inability to close the business loop, high complaint rates, and even inconsistent policy data accepted, resulting in asset losses. The provided method can reduce major economic losses caused by model design, low code quality, and low test discovery rate.

[0005] In a first aspect, the present application provides a risk verification method, which is used to verify whether a preset financial system has risks; comprising:

[0006] Obtain business data to be verified in the financial system;

[0007] Parse the business data and obtain the business information corresponding to the business data; the business information at least includes the business identification, business type, business content and business amount;

[0008] Obtain the payment amount corresponding to the business identifier in the preset financial system according to the business identifier;

[0009] If the business amount is less than the payment amount, the business type and business content are input into the preset amount calculation model, and the amount calculation model outputs the calculated amount corresponding to the business type and business content;

[0010] If the calculated amount is inconsistent with the business amount, there is a risk in the business data.

[0011] In some embodiments, after the business type, business amount and payment amount are input into a preset risk verification model, if the calculated amount is inconsistent with the business amount, then there is a risk in the business data, it also includes: parsing the business data, obtaining the associated data corresponding to the business data; obtaining the data identifier corresponding to the associated data; and stopping the operation of the business data and the associated data according to the business identifier and the data identifier.

[0012] Exemplarily, after stopping the operation of business data and associated data according to the business identifier and data identifier, it also includes: sending the business data, associated data and risk verification information to the verification terminal; if false alarm information sent by the verification terminal is received, resuming the operation of the business data and associated data.

[0013] In some embodiments, before inputting the business type and business content into a preset amount calculation model, it also includes: obtaining historical business data in the financial system, historical business types, historical business content and historical business amounts corresponding to the historical business data; inputting the historical business type and historical business content into the amount calculation model to be trained, and the amount calculation model outputs the predicted amount corresponding to the historical business type and historical business content; completing the training of the amount calculation model to be trained based on the historical business amount and the predicted amount.

[0014] In some embodiments, before the business type and business content are input into a preset amount calculation model, it also includes: parsing the business type to obtain a first coding vector corresponding to the business type; extracting from the business content according to preset keywords to obtain corresponding key fields in the business content; generating a second coding vector corresponding to the business content according to the key fields, so as to input the first coding vector and the second coding vector into the amount calculation model.

[0015] In some embodiments, business data includes fee-related business data and document business data; obtaining business data to be verified stored in a financial system includes: obtaining the fee-related business data before detecting that the financial system transmits the fee-related business data to the financial system, and uploading the fee-related business data to the financial system after confirming that the fee-related business data does not pose a risk; and / or, when detecting that document business data in the financial system is about to generate a document, obtaining the document business data, and generating a document corresponding to the document business data and sending it to the financial system after confirming that the document business data does not pose a risk.

[0016] In some embodiments, after obtaining the payment amount corresponding to the business identifier in the financial system according to the business identifier, it also includes: if the business amount is greater than or equal to the payment amount, confirming that there is a risk in the business data.

[0017] In a second aspect, the present application provides a risk verification device, comprising:

[0018] A data acquisition unit, used to acquire business data to be verified stored in the financial system;

[0019] A data parsing unit, used to parse business data and obtain business information corresponding to the business data; the business information at least includes business identification, business content and business amount;

[0020] An amount acquisition unit, used to acquire the payment amount corresponding to the business identifier in the financial system according to the business identifier;

[0021] An amount output unit, for inputting the business type and business content into a preset amount calculation model if the business amount is less than the payment amount, and the amount calculation model outputs the calculated amount corresponding to the business type and business content;

[0022] The risk calculation unit is used to determine if the calculated amount is inconsistent with the business amount, and that the business data is at risk.

[0023] In a third aspect, the present application further provides a computer device, including:

[0024] Memory and processor;

[0025] The memory is used to store computer programs;

[0026] The processor is used to execute the computer program and implement the steps of the risk verification method described in the first aspect above when executing the computer program.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the steps of the risk verification method described in the first aspect above.

[0028] The present application discloses a risk verification method, device, computer equipment and storage medium. The method is used to verify whether a preset financial system has risks; the method first obtains the business data to be verified stored in the financial system; then parses the business data to obtain the business information corresponding to the business data; the business information at least includes the business identifier, business type, business content and business amount; then, according to the business identifier, the payment amount corresponding to the business identifier is obtained in the preset financial system; further, if the business amount is less than the payment amount, the business type and business content are input into the preset amount calculation model, and the amount calculation model outputs the calculated amount corresponding to the business type and business content; finally, if the calculated amount is inconsistent with the business amount, the business data has risks.

[0029] Furthermore, the provided method obtains the paid amount corresponding to the business identifier according to the business identifier. When the current business amount is less than the payment amount, the business type and business content are input into the preset amount calculation model, and the amount calculation model outputs the calculated amount corresponding to the business type and business content. This allows the provided method to ensure that the business amount meets actual needs. The provided method can reduce significant economic losses caused by model design, low code quality, low test discovery rate, and other reasons.

[0030] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 is a schematic flow chart of the steps of a risk verification method provided by an embodiment of the present application;

[0033] Figure 2 is a schematic flow chart of the steps of a model training method provided in one embodiment of the present application;

[0034] Figure 3 is a schematic flow chart of the steps of a method for stopping operation provided in an embodiment of the present application;

[0035] Figure 4 It is a schematic diagram of the structure of a risk verification device provided by an embodiment of the present application;

[0036] Figure 5 It is a schematic block diagram of the structure of a computer device provided in one embodiment of the present application.

[0037] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0040] It should be understood that, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. For example, the first encoding vector and the second encoding vector are only used to illustrate two different encoding vectors. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the difference.

[0041] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0042] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0043] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0044] In the financial system, due to the numerous related business lines, such as preservation, claims, contracts, medical care, renewal, channels, reinsurance, etc., there are many different business data to be managed in each business line. For example, in preservation, only business data such as fee-related preservation tasks, non-fee-related preservation tasks, long-term insurance preservation tasks, short-term insurance preservation tasks, annual payment preservation tasks, monthly payment preservation tasks, gift insurance preservation tasks, and non-gift insurance preservation tasks can be included. In the financial system, when any business data in each business line is sent to the corresponding financial system, the financial system will perform operations such as collection and payment based on the business data.

[0045] However, due to the large amount of business data in the financial system, it requires a huge amount of manpower and time to check the business data one by one, and it is still impossible to ensure that all business data are checked correctly, resulting in the risk of major losses in the financial system at any time due to errors in the business data reported to the financial system.

[0046] To solve the above problems, please refer to Figure 1 , Figure 1 1 is a schematic flow chart of a risk verification method provided by an embodiment of the present application. The risk verification method can be implemented by a computer device, which can be deployed on a single server or a server cluster. It can also be deployed on a handheld terminal, a laptop computer, a wearable device or a robot, etc.

[0047] The provided method can be applied in the financial field to realize risk confirmation of each business data of different business lines in the financial system, ensuring that there are no security risks in each business data in the financial system.

[0048] To solve the above problems, please refer to Figure 1 Specifically, Figure 1 As shown, the provided method includes steps S101 to S105. The details are as follows:

[0049] S101. Obtain the business data to be verified stored in the financial system.

[0050] Specifically, when any business line in the financial system has business data that needs to be verified, such as business data that needs to be uploaded, reported, or has risks that need to be verified, the server equipped with the method provided in this application can intercept and verify it, and then execute the next step corresponding to the data after confirming that there are no risks in the business data. The embodiments of this application do not limit the type of business data to be verified.

[0051] In some embodiments, business data includes fee-related business data and document business data; obtaining business data to be verified stored in a financial system includes: obtaining the fee-related business data before detecting that the financial system transmits the fee-related business data to the financial system, and uploading the fee-related business data to the financial system after confirming that the fee-related business data does not pose a risk; and / or, when detecting that document business data in the financial system is about to generate a document, obtaining the document business data, and generating a document corresponding to the document business data and sending it to the financial system after confirming that the document business data does not pose a risk.

[0052] The provided method can then detect the risk of fee-related business data before uploading it to the financial system, and detect the document data when it is generated. The provided method can then detect the business data of different business lines at their key nodes, so as to avoid immeasurable losses caused by errors in fee-related or document-related data.

[0053] S102. Analyze the business data and obtain business information corresponding to the business data; the business information at least includes business identification, business type, business content and business amount.

[0054] Specifically, the server verifies the business data by first parsing the business data and obtaining the business information corresponding to the business data, namely the business identification, business content and business amount corresponding to the business data, thereby avoiding economic losses to the company corresponding to the financial system due to the business data.

[0055] In some embodiments, parsing business data and obtaining business information corresponding to the business data includes: obtaining historical data information of a business terminal corresponding to the business data; obtaining a communication protocol corresponding to the business terminal according to the historical data information; parsing the business data according to the communication protocol to extract a business identifier, business content, and business amount from the parsed business data. The provided method can quickly determine the corresponding parsing method for different types of business data, and can accurately obtain business information of each business data.

[0056] S103. Obtain the payment amount corresponding to the business identifier in a preset financial system according to the business identifier.

[0057] Specifically, based on the business identifier corresponding to the business data, the server can obtain the payment amount corresponding to the business identifier in the financial system corresponding to the financial system, such as the payment amount corresponding to the business line, salesperson or any other subject corresponding to the business data. The embodiment of the present application does not limit the type of business identifier. It can then quickly trace the historical payment situation of the business data to ensure that the business data verified this time is compliant in terms of amount.

[0058] S104. If the business amount is less than the payment amount, the business type and business content are input into a preset amount calculation model, and the amount calculation model outputs the calculated amount corresponding to the business type and business content.

[0059] Specifically, if the business amount is less than the payment amount, the server considers that the business data has passed the initial verification, and can then perform a secondary verification. That is, the business type and business content corresponding to the business data are input into a preset amount calculation model, such as a model built based on a convolutional neural network, and then the amount calculation model can determine the actual calculated amount corresponding to the business data in combination with the business type and business content corresponding to the business data, so as to quickly confirm whether there is a risk in this business data.

[0060] In some embodiments, Figure 2 As shown, before the business type and business content are input into the preset amount calculation model, steps S104a to S104c are also included.

[0061] like Figure 2 As shown, the provided method comprises the following steps

[0062] Step S104a. Obtain historical business data in the financial system, historical business types corresponding to the historical business data, historical business content and historical business amounts;

[0063] Step S104b. Input the historical business type and historical business content into the amount calculation model to be trained, and the amount calculation model outputs the predicted amount corresponding to the historical business type and historical business content;

[0064] Step S104c. Complete the training of the amount calculation model to be trained based on the historical business amount and the predicted amount.

[0065] The method provided in the embodiment of the present application uses the historical business data in the financial system and the historical business types, historical business contents and historical business amounts corresponding to the historical business data as training samples, so as to train the amount calculation model to be trained, and can complete the efficient training of the model in combination with a large amount of historical transaction data of the financial system. In addition, the model corresponding to different financial systems can be trained to improve the accuracy of the model amount calculation.

[0066] In some embodiments, before the business type and business content are input into a preset amount calculation model, it also includes: parsing the business type to obtain a first coding vector corresponding to the business type; extracting from the business content according to preset keywords to obtain corresponding key fields in the business content; generating a second coding vector corresponding to the business content according to the key fields, so as to input the first coding vector and the second coding vector into the amount calculation model.

[0067] The provided method parses the business type through the server, such as encoding, to obtain the first coding vector corresponding to the business type of the business data. Since the business content includes many characters that are irrelevant to the amount calculation, direct input will interfere with the final calculation. Therefore, the provided method can extract the corresponding key fields in the business content by setting keywords such as "amount, payment, date" based on the characteristics of the financial system. Then generate the corresponding second coding vector based on the key field. Then input the first coding vector and the second coding vector into the amount calculation model, which can improve the calculation accuracy of the amount calculation model.

[0068] S105. If the calculated amount is inconsistent with the business amount, there is a risk in the business data.

[0069] Specifically, when the server confirms that the calculated amount is inconsistent with the business amount, it can be determined that the business data has risks, that is, the payment amount of the business data does not match the actual business content of the business data, and then the business data is determined to have risks, and then manually reviewed or directly returned. This ensures that the financial system will not cause immeasurable losses due to incorrect business data caused by system loopholes.

[0070] In some embodiments, Figure 3 As shown, after the business type, business amount and payment amount are input into the preset risk verification model, if the calculated amount is inconsistent with the business amount, then there is a risk in the business data, it also includes steps S106 to S108.

[0071] like Figure 3 As shown, the provided method comprises the following steps:

[0072] Step S106. Analyze the business data and obtain the associated data corresponding to the business data;

[0073] Step S107. Obtain the data identifier corresponding to the associated data;

[0074] Step S108: Stop the operation of the business data and associated data according to the business identifier and the data identifier.

[0075] After confirming that the business data is at risk, the server obtains the business identifier of the associated data corresponding to the business data. The associated data can be data of the same business line as the business data, or data of other business lines that are coordinated with the business data. Then the server promptly stops the business data at risk and the associated data associated with it according to the business identifier corresponding to the business data and the data identifier corresponding to the associated data, thereby ensuring the security of the financial system.

[0076] Exemplarily, after stopping the operation of business data and associated data according to the business identifier and data identifier, it also includes: sending the business data, associated data and risk verification information to the verification terminal; if false alarm information sent by the verification terminal is received, resuming the operation of the business data and associated data.

[0077] Business data and related data are verified through verification terminals. In case of false alarms or until the risk is cleared, the operation of business data and / or related data will be restored, thereby ensuring the security of the financial system.

[0078] At the same time, the verification terminal can be operated by a technician or equipped with a preset verification model, which can then verify whether the risk confirmation of business data and related data is correct, so as to avoid affecting the operation of the business due to misconfirmation of risks.

[0079] In some embodiments, after obtaining the payment amount corresponding to the business identifier in the financial system according to the business identifier, it also includes: if the business amount is greater than or equal to the payment amount, confirming that there is a risk in the business data.

[0080] When the business amount is greater than the payment amount of the business identifier corresponding to the business data in the financial system, that is, the amount transmitted from upstream to the financial system is compared with the payment amount and payment amount already stored in the financial system for this business identifier (such as the business number), that is, the total amount of successful payments. If the amount transmitted from upstream to the finance is greater than the total amount of payment amount and successful payments already stored in the financial system for this business number, there is a risk and it needs to be reviewed or intercepted.

[0081] In some embodiments, the server constructs an anti-asset loss evidence immunity model based on the above method, and the model includes a calculation rule model for fee-related business items, and this calculation rule is derived from the rules set by the business needs of each business line. After the business data of each business line enters the anti-asset loss evidence immunity model, the anti-asset loss evidence immunity model determines which business line and which fee-related business data it belongs to based on the system code, business number, and business type, such as: total policy refund, claim settlement, etc. Then it enters the fee-related business data calculation rule model, and the fee-related business data calculation rule model returns the amount. The amount passed in by the business line is compared with the amount returned by the fee-related business data calculation rule model of the evidence immunity model. If they are inconsistent, there is a risk.

[0082] At the same time, for business data that triggers risk points in the asset loss prevention and certification immunity model, the transaction must be blocked, and a corresponding risk event record must be generated in the immunity center, and an email must be triggered to the R&D manager of the business line corresponding to the business data to manually verify and handle the risk event.

[0083] If after manual verification, it is found that the business data will indeed cause asset losses, the risk event will be handled manually and the business data will be closed.

[0084] If after manual verification, the business data will not cause capital loss, the manually processed risk event will be: false alarm, and the business data will continue to be sent to the bank.

[0085] Through the asset loss prevention and document immunity model, all fee-related business data passing through the finance department will be uniformly controlled, and at the same time, the interface for document-related business will be exposed to the outside world.

[0086] At the same time, before the fee-related business data is sent to the bank, the sent amount is automatically checked in the anti-loss and asset immunity model. Risks are proactively discovered and intercepted, and quickly responded and processed. This effectively reduces the company's major economic losses caused by model design, low code quality, and low test discovery rate.

[0087] For document-related businesses, real-time verification and risk interception can greatly reduce customer complaints and provide users with a better experience.

[0088] The present application discloses a risk verification method, device, computer equipment and storage medium. The method is used to verify whether a preset financial system has risks; the method first obtains the business data to be verified stored in the financial system; then parses the business data to obtain the business information corresponding to the business data; the business information at least includes the business identifier, business type, business content and business amount; then, according to the business identifier, the payment amount corresponding to the business identifier is obtained in the preset financial system; further, if the business amount is less than the payment amount, the business type and business content are input into the preset amount calculation model, and the amount calculation model outputs the calculated amount corresponding to the business type and business content; finally, if the calculated amount is inconsistent with the business amount, the business data has risks.

[0089] Furthermore, the provided method obtains the paid amount corresponding to the business identifier according to the business identifier. When the current business amount is less than the payment amount, the business type and business content are input into the preset amount calculation model, and the amount calculation model outputs the calculated amount corresponding to the business type and business content. This allows the provided method to ensure that the business amount meets actual needs. The provided method can reduce significant economic losses caused by model design, low code quality, low test discovery rate, and other reasons.

[0090] See also Figure 4 As shown, Figure 4 : is a schematic diagram of the structure of the risk verification device 200 provided in an embodiment of the present application. The risk verification device 200 is used to execute the steps of the risk verification method shown in the above embodiments. The risk verification device 200 can be a single server or a server cluster, or the risk verification device 200 can be a terminal, which can be a handheld terminal, a laptop computer, a wearable device or a robot, etc.

[0091] like Figure 4 As shown, the risk verification device 200 includes:

[0092] A data acquisition unit 201 is used to acquire business data to be verified stored in a financial system;

[0093] The data parsing unit 202 is used to parse the business data and obtain the business information corresponding to the business data; the business information at least includes the business identification, business content and business amount;

[0094] An amount acquisition unit 203 is used to acquire a payment amount corresponding to the business identifier in the financial system according to the business identifier;

[0095] The amount output unit 204 is used to input the business type and business content into a preset amount calculation model if the business amount is less than the payment amount, and the amount calculation model outputs the calculated amount corresponding to the business type and business content;

[0096] The risk calculation unit 205 is used to determine that if the calculated amount is inconsistent with the business amount, there is a risk in the business data.

[0097] In some embodiments, after the business type, business amount and payment amount are input into a preset risk verification model, if the calculated amount is inconsistent with the business amount, then there is a risk in the business data, it also includes: a stop operation unit, used to parse the business data and obtain the associated data corresponding to the business data; obtain the data identifier corresponding to the associated data; stop the operation of the business data and the associated data according to the business identifier and the data identifier.

[0098] Exemplarily, after stopping the operation of business data and associated data according to the business identifier and data identifier, it also includes: a recovery operation unit, used to send the business data, associated data and risk verification information to the verification terminal; if a false alarm information sent by the verification terminal is received, the operation of the business data and associated data is recovered.

[0099] In some embodiments, before the business type and business content are input into a preset amount calculation model, it also includes: a model training unit, which is used to obtain historical business data in the financial system, historical business types, historical business content and historical business amounts corresponding to the historical business data; input the historical business type and historical business content into the amount calculation model to be trained, and the amount calculation model outputs the predicted amount corresponding to the historical business type and historical business content; and complete the training of the amount calculation model to be trained based on the historical business amount and the predicted amount.

[0100] In some embodiments, before the business type and business content are input into a preset amount calculation model, it also includes: a vector input unit, used to parse the business type and obtain a first coding vector corresponding to the business type; extract the business content according to preset keywords to obtain the corresponding key fields in the business content; generate a second coding vector corresponding to the business content according to the key fields, so as to input the first coding vector and the second coding vector into the amount calculation model.

[0101] In some embodiments, the business data includes fee-related business data and document business data; the business data to be verified in the financial system is obtained, and the data acquisition unit 201 is also used to: before detecting that the financial system transmits the fee-related business data to the financial system, obtain the fee-related business data, and after confirming that the fee-related business data does not pose a risk, upload the fee-related business data to the financial system; and / or, when detecting that the document business data in the financial system is about to generate a document, obtain the document business data, and after confirming that the document business data does not pose a risk, generate a document corresponding to the document business data and send it to the financial system.

[0102] In some embodiments, after obtaining the payment amount corresponding to the business identifier in the financial system according to the business identifier, the risk calculation unit 205 is further used to: if the business amount is greater than or equal to the payment amount, confirm that the business data has a risk.

[0103] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the risk verification device and each module described above can refer to the corresponding process in the risk verification method embodiments described in the above embodiments, and will not be repeated here.

[0104] The risk verification method described above can be implemented in the form of a computer program. Figure 4 Run on the device shown.

[0105] See also Figure 5 , Figure 5 1 is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device includes a processor, a memory and a network interface connected via a device bus, wherein the memory may include a storage medium and an internal memory.

[0106] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any risk verification method.

[0107] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0108] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any risk verification method.

[0109] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the terminal to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0110] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0111] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0112] The method is used to verify whether the pre-set financial system has risks; it includes:

[0113] Obtain business data to be verified in the financial system;

[0114] Parse the business data and obtain the business information corresponding to the business data; the business information at least includes the business identification, business type, business content and business amount;

[0115] Obtain the payment amount corresponding to the business identifier in the preset financial system according to the business identifier;

[0116] If the business amount is less than the payment amount, the business type and business content are input into the preset amount calculation model, and the amount calculation model outputs the calculated amount corresponding to the business type and business content;

[0117] If the calculated amount is inconsistent with the business amount, there is a risk in the business data.

[0118] In some embodiments, after the business type, business amount and payment amount are input into a preset risk verification model, if the calculated amount is inconsistent with the business amount, then there is a risk in the business data, it also includes: parsing the business data, obtaining the associated data corresponding to the business data; obtaining the data identifier corresponding to the associated data; and stopping the operation of the business data and the associated data according to the business identifier and the data identifier.

[0119] Exemplarily, after stopping the operation of business data and associated data according to the business identifier and data identifier, it also includes: sending the business data, associated data and risk verification information to the verification terminal; if false alarm information sent by the verification terminal is received, resuming the operation of the business data and associated data.

[0120] In some embodiments, before inputting the business type and business content into a preset amount calculation model, it also includes: obtaining historical business data in the financial system, historical business types, historical business content and historical business amounts corresponding to the historical business data; inputting the historical business type and historical business content into the amount calculation model to be trained, and the amount calculation model outputs the predicted amount corresponding to the historical business type and historical business content; completing the training of the amount calculation model to be trained based on the historical business amount and the predicted amount.

[0121] In some embodiments, before the business type and business content are input into a preset amount calculation model, it also includes: parsing the business type to obtain a first coding vector corresponding to the business type; extracting from the business content according to preset keywords to obtain corresponding key fields in the business content; generating a second coding vector corresponding to the business content according to the key fields, so as to input the first coding vector and the second coding vector into the amount calculation model.

[0122] In some embodiments, business data includes fee-related business data and document business data; obtaining business data to be verified stored in a financial system includes: obtaining the fee-related business data before detecting that the financial system transmits the fee-related business data to the financial system, and uploading the fee-related business data to the financial system after confirming that the fee-related business data does not pose a risk; and / or, when detecting that document business data in the financial system is about to generate a document, obtaining the document business data, and generating a document corresponding to the document business data and sending it to the financial system after confirming that the document business data does not pose a risk.

[0123] In some embodiments, after obtaining the payment amount corresponding to the business identifier in the financial system according to the business identifier, it also includes: if the business amount is greater than or equal to the payment amount, confirming that there is a risk in the business data.

[0124] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement the steps of the risk verification method provided in the above-mentioned embodiments of the present application.

[0125] The computer-readable storage medium may be an internal storage unit of the computer device described in the above embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device.

[0126] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A risk verification method, characterized in that: The method is used to verify whether a preset financial system has risks; the method comprises: Obtaining the business data to be verified stored in the financial system; Parsing the business data to obtain business information corresponding to the business data; the business information at least includes a business identifier, a business type, a business content, and a business amount; Obtaining the payment amount corresponding to the business identifier in a preset financial system according to the business identifier; If the business amount is less than the payment amount, the business type and business content are input into a preset amount calculation model, and the amount calculation model outputs a calculated amount corresponding to the business type and business content; If the calculated amount is inconsistent with the business amount, the business data is at risk.

2. The method according to claim 1, characterized in that After inputting the business type, business amount and payment amount into a preset risk verification model, and if the calculated amount is inconsistent with the business amount, then the business data has a risk, the method further includes: Parsing the business data to obtain associated data corresponding to the business data; Obtaining a data identifier corresponding to the associated data; The operation of the service data and the associated data is stopped according to the service identifier and the data identifier.

3. The method according to claim 2, characterized in that The method according to claim 1, characterized in that after stopping the operation of the service data and the associated data according to the service identifier and the data identifier, it also includes: Sending the business data, the associated data and the risk verification information to a verification terminal; If false alarm information sent by the verification terminal is received, the operation of the business data and the associated data is restored.

4. The method according to claim 1, characterized in that: Before inputting the business type and business content into the preset amount calculation model, the method further includes: Acquire historical business data in the financial system, and historical business types, historical business contents, and historical business amounts corresponding to the historical business data; Inputting the historical business type and historical business content into the amount calculation model to be trained, and the amount calculation model outputs the predicted amount corresponding to the historical business type and historical business content; The training of the amount calculation model to be trained is completed according to the historical business amount and the predicted amount.

5. The method according to claim 1, characterized in that Before inputting the business type and business content into the preset amount calculation model, the method further includes: Parsing the service type, and obtaining a first encoding vector corresponding to the service type; Extract the business content according to preset keywords to obtain corresponding key fields in the business content; A second encoding vector corresponding to the business content is generated according to the key field, so as to input the first encoding vector and the second encoding vector into the amount calculation model.

6. The method according to claim 1, characterized in that The business data includes fee-related business data and document-related business data; the obtaining of the business data to be verified stored in the financial system includes: Before detecting that the financial system transmits the fee-related business data to the financial system, obtaining the fee-related business data, and uploading the fee-related business data to the financial system after confirming that the fee-related business data does not pose a risk; and / or, When it is detected that the document business data in the financial system will generate a document, the document business data is obtained, and after confirming that there is no risk in the document business data, a document corresponding to the document business data is generated and sent to the financial system.

7. The method according to claim 1, characterized in that After acquiring the payment amount corresponding to the service identifier in the financial system according to the service identifier, the method further includes: If the business amount is greater than or equal to the payment amount, it is confirmed that the business data is at risk.

8. A risk verification device, characterized in that: The following are used to verify whether the pre-set financial system is at risk: A data acquisition unit, used to acquire the business data to be verified stored in the financial system; A data parsing unit, used to parse the business data and obtain business information corresponding to the business data; the business information at least includes a business identifier, business content and business amount; An amount acquisition unit, used for acquiring, in the financial system according to the business identifier, a payment amount corresponding to the business identifier; an amount output unit, for inputting the business type and business content into a preset amount calculation model if the business amount is less than the payment amount, and the amount calculation model outputs a calculated amount corresponding to the business type and business content; The risk calculation unit is used to determine that if the calculated amount is inconsistent with the business amount, then there is a risk in the business data.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to implement the method according to any one of claims 1 to 7.

Images