Business data processing method and device, equipment, medium and program product

Abstract

The invention provides a business data processing method and device, equipment, a medium and a program product, which can be applied to the technical field of big data and financial science and technology. The service data processing method comprises the steps that in response to a received risk identification request from terminal equipment, a service data set matched with the terminal equipment is determined, and the service data set comprises multiple pieces of service data of multiple data types; calling a risk identification model matched with the business data, and performing risk identification on the plurality of business data to obtain a risk identification result; returning the risk identification result and a model identifier of the risk identification model to the terminal equipment; and in response to a received risk processing request from the terminal equipment, determining a risk processing strategy for the service data group according to the processing authority of the terminal equipment and the processing parameters in the risk processing request.

Description

Technical Field

[0001] The present disclosure relates to the field of big data and financial technology counting, and specifically to a business data processing method, device, equipment, medium and program product. Background Art

[0002] With the development of business diversification, the areas covered by the risk identification systems operated by bank branch staff are becoming increasingly broad, and the traditional risk identification model has been unable to adapt to the increasingly complex internal and external operating environment.

[0003] For example, the risk management of business data lacks direct and efficient risk identification methods, the identification level is too simple, the same event is repeatedly checked, and risk hot spots, difficulties, and pain points cannot be responded to quickly and promptly. In addition, the existing risk identification system lacks the necessary data storage and processing center, and the relevant data sources are scattered and unsystematic, making it difficult to form economies of scale, and risks cannot be effectively identified and handled.

[0004] In summary, the existing technologies have technical problems such as low risk identification accuracy, low risk identification efficiency, and imperfect risk handling methods. Summary of the invention

[0005] In view of the above problems, the present disclosure provides a business data processing method, apparatus, device, medium and program product.

[0006] According to a first aspect of the present disclosure, a business data processing method is provided, comprising: in response to receiving a risk identification request from a terminal device, determining a business data group that matches the terminal device, wherein the business data group includes multiple business data of multiple data types; calling a risk identification model that matches the business data, performing risk identification on the multiple business data, and obtaining a risk identification result; returning the risk identification result and a model identifier of the risk identification model to the terminal device; and in response to receiving a risk handling request from the terminal device, determining a risk handling strategy for the business data group according to the processing authority of the terminal device and the processing parameters in the risk handling request.

[0007] According to an embodiment of the present disclosure, in response to receiving a risk identification request from a terminal device, determining a business data group that matches the terminal device includes: in response to receiving a risk identification request from a terminal device, determining a plurality of business data newly added on the day from a data lake; calling a business volume allocation model to allocate the plurality of business data newly added on the day to each operating user in the daily schedule according to groups; determining a target operating user that matches the terminal device based on device information of the terminal device; and determining the business data group allocated to the target operating user as a business data group that matches the terminal device.

[0008] According to an embodiment of the present disclosure, a risk identification model matching business data is called to perform risk identification on multiple business data to obtain a risk identification result, including: determining at least one risk identification model matching the business data according to the data type of the business data; calling each risk identification model to perform risk identification on multiple business data to obtain a risk identification sub-result output by each risk identification model; and determining the risk identification result according to the risk identification sub-result output by each risk identification model.

[0009] According to an embodiment of the present disclosure, at least one risk identification model that matches the business data is determined based on the data type of the business data, including: when it is determined that the data type of the business data is a reconciliation type, multiple reconciliation risk identification models that match the business data are determined, wherein the reconciliation risk identification model includes at least one of the following: a first reconciliation risk identification model for risk identification in the reconciliation time dimension, a second reconciliation risk identification model for risk identification in the reconciliation method dimension, a third reconciliation risk identification model for risk identification in the reconciliation result dimension, and a fourth reconciliation risk identification model for risk identification in the reconciliation location dimension; when it is determined that the data type of the business data is an account opening type, an account opening risk identification model that matches the business data is determined.

[0010] According to an embodiment of the present disclosure, the first reconciliation risk identification model outputs a first risk identification sub-result, the second reconciliation risk identification model outputs a second risk identification sub-result, the third reconciliation risk identification model outputs a third risk identification sub-result, and the fourth reconciliation risk identification model outputs a fourth risk identification sub-result; determining the risk identification result based on the risk identification sub-result output by each risk identification model includes: determining the number of risk results based on the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result, and the fourth risk identification sub-result; and determining the risk identification result based on the number of risk results, the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result, and the fourth risk identification sub-result.

[0011] According to an embodiment of the present disclosure, each risk identification model is called to perform risk identification on multiple business data to obtain a risk identification sub-result output by each risk identification model, including: for the second reconciliation risk identification model, obtaining the reconciliation track information of the business users related to the business data; and inputting the reconciliation track information, the generation time of the business data and the reconciliation duration into the second reconciliation risk identification model to output the second risk identification sub-result.

[0012] According to an embodiment of the present disclosure, the processing parameters include institutional parameters and policy parameters; the risk handling strategy for the business data group is determined based on the processing authority of the terminal device and the processing parameters in the risk handling request, including: when it is determined that the processing authority is the same as the institutional parameter, the risk handling strategy for the business data group is determined based on the policy parameters; when it is determined that the processing authority is not the same as the institutional parameter, the risk handling strategy for the business data group is determined based on the policy parameters and the institutional parameters.

[0013] According to a second aspect of the present disclosure, a business data processing device is provided, comprising: a determination module, for determining a business data group matching a terminal device in response to receiving a risk identification request from a terminal device, wherein the business data group includes multiple business data of multiple data types; a calling module, for calling a risk identification model matching the business data, performing risk identification on the multiple business data, and obtaining a risk identification result; a return module, for returning the risk identification result and a model identifier of the risk identification model to the terminal device; and a processing module, for determining a risk handling strategy for the business data group according to the processing authority of the terminal device and the processing parameters in the risk handling request in response to receiving a risk handling request from the terminal device.

[0014] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0015] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.

[0016] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor.

[0017] In the embodiments of the present disclosure, a smart risk control platform based on big data is constructed. The smart risk control platform can respond to the risk identification request received from the terminal device, determine the business data group that matches the terminal device, automatically match and call the risk identification model to identify the multiple business data in the assigned business data group, and generate the corresponding risk handling strategy for risk handling based on the user's risk handling request. As a result, the embodiments of the present disclosure integrate multi-dimensional and multi-stage risk identification such as data allocation, model matching and policy processing, and can perform multi-granular risk handling based on processing parameters and processing permissions, thereby solving the technical problems of low risk identification accuracy, low risk identification efficiency, and imperfect risk handling means, and achieving the technical effect of more accurate and faster risk identification and risk handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0019] Figure 1 An application scenario diagram of the business data processing method and device according to an embodiment of the present disclosure is shown.

[0020] Figure 2 A flow chart of a business data processing method according to an embodiment of the present disclosure is shown.

[0021] Figure 3 A flow chart of a method for determining a service data group matching a terminal device according to an embodiment of the present disclosure is shown.

[0022] Figure 4 A flow chart of a method for determining risk identification results according to an embodiment of the present disclosure is shown.

[0023] Figure 5 A schematic diagram of a scenario for determining risk identification results according to an embodiment of the present disclosure is shown.

[0024] Figure 6 A scenario schematic diagram of a business data processing method according to a specific embodiment of the present disclosure is shown.

[0025] Figure 7 A schematic diagram of the system framework of a smart wind control system according to a specific embodiment of the present disclosure is shown.

[0026] Figure 8 A structural block diagram of a business data processing device according to an embodiment of the present disclosure is shown.

[0027] Fig. 9 A block diagram of an electronic device suitable for implementing a business data processing method according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0029] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0030] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0031] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0033] In order to at least partially solve the technical problems in the prior art of low risk identification accuracy, low risk identification efficiency, and imperfect risk handling methods, the embodiments of the present invention are based on data analysis, with risk models and management models as engines. By deeply exploring risk characteristics and management difficulties, various data are dynamically managed and utilized to create a highly integrated intelligent risk control system based on big data.

[0034] An embodiment of the present disclosure provides a business data processing method, which can be applied to the above-mentioned intelligent risk control system, the method comprising: in response to receiving a risk identification request from a terminal device, determining a business data group matching the terminal device, wherein the business data group includes multiple business data of multiple data types; calling a risk identification model matching the business data, performing risk identification on the multiple business data, and obtaining a risk identification result; returning the risk identification result and the model identifier of the risk identification model to the terminal device; and in response to receiving a risk handling request from the terminal device, determining a risk handling strategy for the business data group according to the processing authority of the terminal device and the processing parameters in the risk handling request.

[0035] Figure 1 The application scenario diagram of the business data processing method and device according to the embodiment of the present disclosure is shown. It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is schematic. Any number of terminal devices, networks and servers can be provided according to implementation requirements.

[0036] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0037] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples). The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, etc.

[0038] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0039] It should be noted that the business data processing method provided in the embodiment of the present disclosure can generally be executed by the server 105 or a server cluster. Accordingly, the business data processing device provided in the embodiment of the present disclosure can generally be set in the server 105 or a server cluster.

[0040] For example, a smart risk control system may be deployed in the server 105. A user may use a first terminal device 101, a second terminal device 102, a third terminal device 103, and other terminal devices to send a risk identification request. In response to receiving a risk identification request from a terminal device, the smart risk control system in the server 105 determines a business data group that matches the terminal device, wherein the business data group includes multiple business data of multiple data types; calls a risk identification model that matches the business data, performs risk identification on the multiple business data, and obtains a risk identification result; and returns the risk identification result and the model identifier of the risk identification model to the first terminal device 101, the second terminal device 102, and the third terminal device 103. The server 105 may also determine a risk handling strategy for the business data group in response to receiving a risk handling request from the first terminal device 101, the second terminal device 102, and the third terminal device 103 according to the processing authority of the terminal device and the processing parameters in the risk handling request.

[0041] Figure 2 A flow chart of a business data processing method according to an embodiment of the present disclosure is shown.

[0042] like Figure 2 As shown, the business data processing method 200 of this embodiment includes operations S210 to S240, and the business data processing method can be executed by an intelligent risk control system.

[0043] In operation S210 , in response to receiving a risk identification request from a terminal device, a business data group matching the terminal device is determined, wherein the business data group includes a plurality of business data of a plurality of data types.

[0044] According to an embodiment of the present disclosure, the terminal device may be a terminal device used by an operating user of the smart risk control system. The operating user may view and operate the smart risk system on the terminal device and initiate a risk identification request. The server begins to execute the risk identification process after receiving a risk identification request initiated by a terminal device.

[0045] According to an embodiment of the present disclosure, the service data group matching the terminal device may be specified by the terminal device, or may be randomly assigned to the terminal device based on daily service data.

[0046] For example, the business data that needs risk identification every day, every week, and every month is changing. Therefore, after receiving the risk identification request, the intelligent performance module of the smart risk control system first determines the corresponding business data group for each terminal device. It should be noted that the operating user of the terminal device can log in to the smart risk control system regularly every day, every week, and every month to perform routine risk identification.

[0047] Alternatively, the operating user can also specify multiple business data and identify risks for them. In this case, the risk identification request can include the identifier of the specified business data, such as the identifier of the business data group XX group. As a result, the smart risk control system can parse the risk identification request, obtain the identifier of the specified business data, and call this part of the specified business data from the data lake of the head office.

[0048] According to an embodiment of the present disclosure, a business type refers to the type of business being performed, such as a reconciliation business, a clearing business, etc. A large business type may include multiple small business types, such as a reconciliation business may include multiple types such as reconciliation failure, unreconciled, abnormal reconciliation account, abnormal reconciliation result, etc. The same business data group may include multiple business data, and multiple business data may include multiple data types.

[0049] In operation S220, a risk identification model matching the business data is called to perform risk identification on the plurality of business data to obtain a risk identification result.

[0050] According to an embodiment of the present disclosure, the risk identification model may be a risk identification model embedded in the intelligent risk control system, which is used to identify risks in business data and obtain risk identification results.

[0051] According to the embodiments of the present disclosure, different risk identification models may be provided for different business types, so as to specifically identify risks of business data of the specified business type.

[0052] According to an embodiment of the present disclosure, the risk identification model may be a model constructed based on machine learning, a model constructed based on expert rules, a classification model constructed based on deep learning, a decision tree, etc. The present disclosure does not limit the type of risk identification model.

[0053] In operation S230, the risk identification result and the model identifier of the risk identification model are returned to the terminal device.

[0054] According to an embodiment of the present disclosure, after the risk identification model identifies a risk identification result, the risk identification result and the model identifier of the risk identification model may be returned to the terminal device and visually displayed on the terminal device.

[0055] According to an embodiment of the present disclosure, an operating user can select corresponding processing parameters on a terminal device based on risk identification results and a model identifier of a risk identification model, and generate a risk processing request based on the processing parameters, so that the intelligent risk control system can generate a corresponding risk processing strategy based on the risk processing request.

[0056] In operation S240 , in response to receiving the risk handling request from the terminal device, a risk handling strategy for the business data group is determined according to the handling authority of the terminal device and the handling parameters in the risk handling request.

[0057] According to an embodiment of the present disclosure, processing authority refers to the authority to process the risk of the current business data group, and different terminal devices have different processing authorities. For example, processing authority may include: having processing authority for the business data of the affiliated organization, and having no processing authority for the business data of the affiliated organization.

[0058] According to an embodiment of the present disclosure, the processing parameters parsed from the risk processing request may include an organization parameter and a policy parameter. The organization parameter is used to characterize the source organization of the business data, and the policy parameter may be the policy information for handling the risk selected by the operating user, such as who to report to, who is allowed to handle, when to handle, etc.

[0059] In the embodiments of the present disclosure, a smart risk control platform based on big data is constructed. The smart risk control platform can respond to the risk identification request received from the terminal device, determine the business data group that matches the terminal device, automatically match and call the risk identification model to identify the multiple business data in the assigned business data group, and generate the corresponding risk handling strategy for risk handling based on the user's risk handling request. As a result, the embodiments of the present disclosure integrate multi-dimensional and multi-stage risk identification such as data allocation, model matching and policy processing, and can perform multi-granular risk handling based on processing parameters and processing permissions, thereby solving the technical problems of low risk identification accuracy, low risk identification efficiency, and imperfect risk handling means, and achieving the technical effect of more accurate and faster risk identification and risk handling.

[0060] Figure 3 A flow chart of a method for determining a service data group matching a terminal device according to an embodiment of the present disclosure is shown. Figure 3 As shown, the method 300 for determining a business data group that matches a terminal device in this embodiment includes operations S311 to S314. The method 300 for determining a business data group that matches a terminal device can be executed by the intelligent risk control system as a specific embodiment of operation S210.

[0061] In operation S311, in response to receiving a risk identification request from a terminal device, a plurality of business data newly added on the day is determined from the data lake.

[0062] In operation S312, the business volume distribution model is called to distribute the multiple business data newly added on the day to each operating user in the daily schedule according to the group.

[0063] In operation S313, a target operating user matching the terminal device is determined according to the device information of the terminal device.

[0064] In operation S314, the service data group assigned to the target operating user is determined as a service data group matching the terminal device.

[0065] According to an embodiment of the present disclosure, the time when the risk identification request is initiated, such as the time of the day, can be determined from the risk identification request. Thereafter, multiple newly added business data with the same time as the time of the day can be determined from the data lake of the head office based on the time of the day.

[0066] According to an embodiment of the present disclosure, a data lake may include data for a period of time, and the data in this part includes full data and incremental data. In this embodiment, the incremental data added daily can be calculated in advance through the big data processing software of the data lake. Thus, in response to receiving a risk identification request from a terminal device, multiple business data added on the day, that is, the incremental data of the day, can be directly determined from the data lake.

[0067] According to an embodiment of the present disclosure, the smart risk control system includes an intelligent duty performance module. The intelligent duty performance module includes five functions: business volume random allocation mechanism, management personnel workbench, regulatory matters, reconciliation duty performance and reconciliation maintenance.

[0068] The random distribution mechanism of business volume includes a business volume distribution model, which automatically distributes the daily added business data to each operating user, such as the inspection manager, through the system's automated calculations.

[0069] According to the embodiment of the present disclosure, the multiple business data added on the day can be sorted to obtain a task list, and then the order of the operating users on duty in the day's schedule can be disrupted. According to the order of the task list, the multiple business data added on the day are allocated to each operating user in the day's schedule one by one. After all the business data in the task list are allocated, a business data group can be encoded for the multiple business data allocated to each operating user, so that each operator obtains a business data group to be identified for risks.

[0070] According to the embodiments of the present disclosure, the management personnel workstation covers functions such as indicator supervision, network work log, and automatic report collection management. Normative matters are used to regulate the behavior of operating users. For businesses that have operational flaws but do not constitute the standards for assessing risk events, they can be recorded in the matters to be regulated. Reconciliation duties are used to supervise the reconciliation business that is not performed daily, so as to enter the reconciliation business data into the system in a timely manner. Reconciliation maintenance can provide a query function, and the reconciliation administrator can use this module to query the reconciliation progress and update the performance of duties.

[0071] According to the embodiments of the present disclosure, device information refers to the binding information between the operator who uses the terminal device and the terminal device. The terminal devices within the bank can be mobile. When performing risk identification every day, the operating user can log in the work number information on the terminal device, thereby binding the terminal device and the operating user to obtain the device information.

[0072] Since operation S312 has allocated a service data group to each operating user, operation S313 can determine the target operating user matching the terminal device based on the device information of the terminal device, and determine the service data group allocated to the target operating user as the service data group matching the terminal device.

[0073] In an embodiment of the present disclosure, by responding to a risk identification request received from a terminal device, multiple business data newly added on the day are determined from the data lake; the business volume allocation model is called to allocate the multiple business data newly added on the day to each operating user in the daily schedule according to groups, and based on the device information of the terminal device, the business data group of the target operating user matching the terminal device is used as the business data group matching the terminal device. This can automatically allocate business data to be risk identified to each terminal device, reduce the difficulty of resource allocation and management of risk business data, eliminate the need for repeated management of the same risk event, and save management resources.

[0074] Figure 4 A flow chart of a method for determining risk identification results according to an embodiment of the present disclosure is shown. Figure 4 As shown, the method 400 for determining the risk identification result of this embodiment includes operations S421 to S423. The method for determining the risk identification result can be executed by the intelligent risk control system as a specific embodiment of operation S220.

[0075] In operation S421, at least one risk identification model matching the business data is determined according to the data type of the business data.

[0076] In operation S422, each risk identification model is called to perform risk identification on a plurality of business data, and a risk identification sub-result output by each risk identification model is obtained.

[0077] In operation S423, a risk identification result is determined according to the risk identification sub-results output by each risk identification model.

[0078] According to an embodiment of the present disclosure, business data of each data type may correspond to one or more risk identification models. For example, business data of the reconciliation type may correspond to multiple risk identification models.

[0079] According to an embodiment of the present disclosure, the intelligent risk control system may include a model mapping table, which includes a correspondence between data types and risk identification models. For each business data, at least one risk identification model matching each business data may be determined according to the model mapping table.

[0080] According to an embodiment of the present disclosure, after determining the risk identification model, multiple business data in the business data group can be input as a whole, and each risk identification model can be called to perform an overall analysis on the multiple business data to obtain the risk identification sub-results output by each risk identification model.

[0081] According to an embodiment of the present disclosure, after obtaining the risk identification sub-result output by each risk identification model, the risk identification sub-result output by each risk identification model can be combined to determine the risk identification result. For example, the risk identification sub-result can be a numerical output of 0 to 1, where a risk identification sub-result of 0 means no risk and a risk identification sub-result of 1 means there is risk. The risk identification sub-result output by each risk identification model can be summed and the average value calculated as the risk identification result.

[0082] In the embodiments of the present disclosure, multiple risk identification models are embedded in the intelligent risk control system. When performing risk identification on multiple business data, the risk identification sub-result output by at least one risk identification model that matches the business data is called, and the risk identification result is determined based on the risk identification sub-result output by each risk identification model. This not only enables targeted management identification of each established data model to be more accurate, but also improves the internal risk identification rate.

[0083] According to an embodiment of the present disclosure, at least one risk identification model that matches the business data is determined based on the data type of the business data, including: when it is determined that the data type of the business data is a reconciliation type, multiple reconciliation risk identification models that match the business data are determined, wherein the reconciliation risk identification model includes at least one of the following: a first reconciliation risk identification model for risk identification in the reconciliation time dimension, a second reconciliation risk identification model for risk identification in the reconciliation method dimension, a third reconciliation risk identification model for risk identification in the reconciliation result dimension, and a fourth reconciliation risk identification model for risk identification in the reconciliation location dimension; when it is determined that the data type of the business data is an account opening type, an account opening risk identification model that matches the business data is determined.

[0084] According to an embodiment of the present disclosure, the first reconciliation risk identification model used for risk identification in the reconciliation time dimension can be a non-zero online banking limit model for long-term inactive accounts, which is used to screen accounts whose online banking limits of long-term (such as 7 days) inactive accounts have not been reduced to zero and issue early warnings to notify bank branches to complete the limit adjustment operation to fill the risk exposure.

[0085] According to an embodiment of the present disclosure, the second reconciliation risk identification model for risk identification in the dimension of reconciliation method can be a model for rectification warning of account information of unsuccessful reconciliation by mail. The model for rectification warning of account information of unsuccessful reconciliation by mail summarizes the accounts that failed to reconcile by mail due to incorrect reconciliation information, distributes and pushes them through the "rectification warning of account information of unsuccessful reconciliation by mail" model, and automatically establishes rectification tasks in the system, provides feedback in the system, and if the reconciliation is still not completed at the end of the quarter, the account will be controlled.

[0086] According to the embodiment of the present disclosure, the third reconciliation risk identification model used for risk identification in the reconciliation result dimension can be an unreconciled account control detection model. If the account fails to cooperate in the reconciliation within the specified time and fails to provide a reasonable reason, it will be identified as an unreconciled account, and the account will be subject to the control measures of only receiving but not paying. In addition, the branch can also actively push it to the sub-branch, generate rectification tasks, and urge the sub-branch to complete the control operation in a timely manner.

[0087] The third reconciliation risk identification model can also be an inefficient account high online banking limit model, which screens out accounts whose group online banking payment limit exceeds the actual payment limit by more than 3 times by comparing the daily maximum payment amount and the group daily cumulative limit of inefficient accounts with low stock transaction volume and low balance in the past three months, and issues early warnings, and requires outlets to set reasonable limits based on the actual payment amount of the account. The third reconciliation risk identification model can also be a public account automatic filing failure unprocessed model, which pushes accounts that have failed to be automatically filed to outlets, urging them to log in to the system in time to supplement the information of accounts that have failed to be filed, and reduce the occurrence of risk events.

[0088] According to an embodiment of the present disclosure, the fourth reconciliation risk identification model for risk identification in the reconciliation location dimension can be an off-site account maintenance detection model. The system actively detects newly opened off-site accounts and pushes them to the branch. After receiving the task, the branch feeds back the reconciliation information to the system for maintenance.

[0089] According to the embodiment of the present disclosure, when it is determined that the data type of the business data is an account opening type, an account opening risk identification model matching the business data is determined. The account opening risk identification model can establish 13 suspicious feature libraries starting from the basic account opening information, contact information, industrial and commercial information and address information in the business data, and dig out the subtle connections between different users in real time to find suspicious features of different user groups. The model uses an advanced risk quantification scoring card mechanism to establish 23 risk indicators based on the risk characteristics of suspicious accounts, and differentiates the account risks according to the different risk levels. This makes the account risk level a reference, and the abnormality level between accounts can be compared, avoiding the qualitative evaluation of black and white. This model uses the real-time early warning of "non-list" account risks for the first time. The risk scoring results can be provided before the account opening approval is enabled. After discovering abnormal problems, the outlets can promptly cancel the account opening application and refuse to open the account. When the outlets discover risky accounts and refuse to open the account, the assessment results can be entered in the scoring early warning model. When the user tries to submit an account opening application again at other outlets, the early warning model can call out the risk assessment results of the previous outlet account opening.

[0090] In the embodiments of the present disclosure, risk identification models of multiple dimensions such as reconciliation time, reconciliation method, reconciliation result and reconciliation location are constructed for the risk identification model of the reconciliation type, so that calling each risk identification model can output risk identification sub-results in the specific reconciliation time, reconciliation method, reconciliation result and reconciliation location dimensions, covering extensive and comprehensive risk identification with higher risk identification accuracy.

[0091] According to an embodiment of the present disclosure, before obtaining business data, the user's consent or authorization may be obtained. For example, before obtaining business data, a request may be issued to the user to obtain business data related to the executed business. When the user agrees or authorizes that the business data can be obtained, the operation of obtaining the business data is performed. According to an embodiment of the present disclosure, before risk identification processing / decision-making is performed on business data, the user's consent or authorization may also be obtained. In an embodiment of the present disclosure, a corresponding operation entry may be provided for the user to choose to agree or refuse the automated decision result. That is, before risk identification processing / decision-making is performed on business data, an instruction to agree or refuse to perform processing / decision-making input by the user through the corresponding operation entry may be obtained. If the user agrees to perform processing / decision-making, risk identification processing / decision-making is subsequently performed on the business data. If the user refuses to perform processing / decision-making, the expert decision-making process is entered.

[0092] According to an embodiment of the present disclosure, according to each risk identification model output risk identification sub-result, determining the risk identification result includes: determining the number of risk results according to the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result and the fourth risk identification sub-result; and determining the risk identification result according to the number of risk results, the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result and the fourth risk identification sub-result.

[0093] According to an embodiment of the present disclosure, multiple business data are input into a first reconciliation risk identification model, and a first risk identification sub-result of the reconciliation time dimension is output; multiple business data are input into a second reconciliation risk identification model, and a second risk identification sub-result of the reconciliation method dimension is output; multiple business data are input into a third reconciliation risk identification model, and a third risk identification sub-result of the reconciliation result dimension is output; multiple business data are input into a fourth reconciliation risk identification model, and a fourth risk identification sub-result of the reconciliation position dimension is output.

[0094] According to an embodiment of the present disclosure, the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result, and the fourth risk identification sub-result can all be represented by a numerical value of 0 to 1. For example, if it is greater than 0.8, it is considered that there is a risk and the risk identification does not pass; if it is less than 0.8, it is considered that there is no risk and the risk identification passes. According to the results corresponding to the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result, and the fourth risk identification sub-result, the number of risk results whose identification sub-results pass can be determined.

[0095] It is understandable that the more risk results with passed identification sub-results, the lower the possibility that multiple business data are at risk; conversely, the fewer the risk results, the higher the possibility that there is a risk. Therefore, the weights for weighted summation of the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result, and the fourth risk identification sub-result can be determined based on the number of risk results. For example, a separate weight adjustment parameter can be determined based on the number of risk results, and the parameters of the sum of the above four risk identification sub-results can be adjusted to obtain the final risk identification result. Alternatively, a separate weight adjustment parameter can be determined based on the number of risk results, and the weight of each risk identification sub-result can be determined based on the ratio between each identification sub-result and the weight adjustment parameter.

[0096] Figure 5 FIG. 2 is a schematic diagram showing a scenario for determining a risk identification result according to an embodiment of the present disclosure. Figure 5 As shown, in this embodiment 500, for the business data group 501, the first reconciliation risk identification model 502 is used to output the first risk identification sub-result 506, the second reconciliation risk identification model 503 is used to output the second risk identification sub-result 507, the third reconciliation risk identification model 504 is used to output the third risk identification sub-result 508, and the fourth reconciliation risk identification model 505 is used to output the fourth risk identification sub-result 509. The number of risk results is determined by combining the first risk identification sub-result 506, the second risk identification sub-result 507, the third risk identification sub-result 508, and the fourth risk identification sub-result 509, and the risk identification result 510 is determined according to the number of risk results and the above four risk identification sub-models.

[0097] In an embodiment of the present disclosure, based on the risk identification sub-results in the dimensions of comprehensive reconciliation time, reconciliation method, reconciliation result and reconciliation position, the weight used for weighted summation to obtain the risk identification result is determined according to the number of risk results that pass the identification sub-results, so that a more reasonable risk identification result can be obtained with higher risk identification accuracy.

[0098] According to an embodiment of the present disclosure, each risk analysis model is called to perform risk identification on multiple business data to obtain a risk identification sub-result output by each risk identification model, including: for the second reconciliation risk identification model, obtaining the reconciliation track information of the business users related to the business data; and inputting the reconciliation track information, the generation time of the business data and the reconciliation duration into the second reconciliation risk identification model to output the second risk identification sub-result.

[0099] According to an embodiment of the present disclosure, the second reconciliation risk identification model may also be a face-to-face reconciliation execution trajectory detection model.

[0100] In one embodiment, when a face-to-face reconciliation execution trajectory detection model matching the business data is determined, the intelligent risk control system generates a face-to-face reconciliation task through the face-to-face reconciliation execution trajectory detection model, and obtains the reconciliation trajectory information of the business users related to the business data. The business users related to the business data are also the reconciliation personnel when operating the business data, and the reconciliation trajectory information is also the electronic operation trajectory and corresponding operation photos of the reconciliation personnel when completing the current business data. After the reconciliation trajectory information, the generation time of the business data and the reconciliation duration are input into the face-to-face reconciliation execution trajectory detection model, the second risk identification sub-result can be output.

[0101] According to an embodiment of the present disclosure, the face-to-face reconciliation execution trajectory detection model can be a machine learning model, which abstracts the electronic operation trajectory in the reconciliation trajectory information into a trajectory operation sequence for operating controls, and uses the generation time of business data and the reconciliation duration as other input parameters. Thus, the second risk identification sub-result is obtained by analyzing the above three types of parameters.

[0102] In the embodiments of the present disclosure, for the face-to-face reconciliation in the reconciliation method, the special face-to-face reconciliation can be checked through the reconciliation track information, the generation time of the business data and the reconciliation duration to ensure the accuracy of risk identification under the face-to-face reconciliation method.

[0103] According to the embodiments of the present disclosure, the intelligent analysis module in the intelligent risk control system can embed the above-mentioned multiple risk identification models. In addition to the above-mentioned multiple risk identification models, there can also be an uncancelled teller number model, which determines the uncancelled teller number by comparing the teller number in the to-be-cancelled list with the teller number that still exists in the current system. If there is an uncancelled teller number, the fifth risk identification sub-result is not passed, and the outlet is warned to urge the outlet to make timely rectifications.

[0104] According to an embodiment of the present disclosure, for operation S240, a risk handling strategy for a business data group is determined based on the processing authority of the terminal device and the processing parameters in the risk handling request, including: when it is determined that the processing authority is the same as the institutional parameter, the risk handling strategy for the business data group is determined based on the policy parameters; when it is determined that the processing authority is not the same as the institutional parameter, the risk handling strategy for the business data group is determined based on the policy parameters and the institutional parameters.

[0105] According to an embodiment of the present disclosure, the processing parameters include an organization parameter and a policy parameter. The organization parameter may be the source organization of the business data, and the policy parameter may be the policy information for handling the risk selected by the operating user, such as who to report to, who is allowed to handle, when to handle, etc.

[0106] According to the embodiments of the present disclosure, in the process of risk handling, it is considered that the processing authority needs to be consistent with the source organization of the business data, so that the business data with risks can be handled in time. If they are inconsistent, repeated identification will lead to waste of risk handling resources. Therefore, in the embodiments of the present disclosure, in the process of risk handling, it is first determined whether the processing authority is the same as the organization parameter. If they are the same, the risk handling strategy for the business data group is determined according to the policy parameters, such as determining the risk handling strategy that matches the policy parameters as the risk handling strategy for the business data group.

[0107] In the case where it is determined that the processing authority is different from the institutional parameters, a risk processing strategy for the business data group is determined based on the policy parameters and the institutional parameters. For example, the generated risk processing strategy is: determine a risk processing strategy that matches the policy parameters, and push the risk processing strategy as a candidate processing strategy to the business data source institution corresponding to the institutional parameters.

[0108] In the embodiments of the present disclosure, by comparing the organizational parameters with the processing permissions, and based on the comparison results, determining the risk handling strategy for the business data group according to the policy parameters, or the policy parameters plus the organizational parameters, it is possible to ensure timely processing of risky business data and avoid repeated risk identification that leads to waste of risk handling resources.

[0109] Figure 6 FIG. 1 is a schematic diagram showing a scenario of a method for processing business data according to a specific embodiment of the present disclosure. Figure 6 As shown, this embodiment includes S601~S607.

[0110] Operation S601 can be performed through the model intelligent analysis module in the smart risk control system to add a new risk identification model, and operation S602 can be used to call the risk identification model warning. Among them, operation S602 can call a new or existing risk identification model warning. Operation S603 can be performed through the risk event management module in the smart risk control system to query risks, and operation S604 can be used to determine whether there is a risk. Operation S605 is performed when there is a risk, and operation S607 is performed to record the operation when there is no risk. Operation S605 can be performed through the intelligent performance module in the smart risk control system to check risks, and operation S606 can be used to process according to the risk handling strategy.

[0111] The risk event management module of the smart risk control system can include a quasi-risk event management module, a risk event query module, an internal risk event query module, and a cross-regional push query module. The quasi-risk event management module is used to provide multiple screening conditions such as date, model identification, event status of risk identification results, etc., covering query purposes of different needs. The risk event query module can filter by institutional dimension, and can also query by different calibers and dimensions, associate rectification measures, and provide complete and effective information for indicator calculation and risk governance. The internal risk event query module covers the full event information of internal risk events, and at the same time associates the internal risk subjects and the account serial numbers of risk events for secondary identity authentication and secondary risk verification. The cross-regional push query module summarizes and improves the relevant data of cross-regional push in risk identification, so as to timely push the risk handling strategy across regions to the corresponding institutions.

[0112] Figure 7 FIG. 1 is a schematic diagram showing the system framework of a smart wind control system according to a specific embodiment of the present disclosure. Figure 7 As shown in the system architecture 700, the smart risk control system includes a model intelligent analysis module, an intelligent performance module, a risk event management module and a graphical analysis module. The model intelligent analysis module is embedded with multiple risk identification models, which can perform model maintenance and call risk identification models for model warning. The intelligent performance module can support risk event query and risk event management. The risk event management module involves risk event allocation (such as determining the business data group that matches each terminal device), risk event supervision and risk event reporting. The graphical analysis module can perform business volume statistics, branch operation risk indicators and branch risk heat maps.

[0113] The embodiments of the present disclosure are based on data analysis, with risk models and management models as engines. By deeply exploring risk characteristics and management difficulties, and dynamically managing and utilizing various data, a highly integrated intelligent risk control system based on big data is created. By establishing an intelligent risk control system, the difficulty of performing risk identification duties is reduced, and monitoring resources are saved. Establishing a data model for risk identification in an intelligent risk control system can improve the accuracy of risk identification and increase the internal risk identification rate; by displaying dynamic charts of indicators, data, and risk events, more flexible, prepared, and intuitive decision-making basis is provided for managers at all levels, risk display is more intelligent, management is more refined, and strong support is provided for operational management.

[0114] Figure 8 FIG. 2 shows a structural block diagram of a service data processing device according to an embodiment of the present disclosure. Figure 8 As shown, the business data processing device 800 of this embodiment includes a determination module 810 , a calling module 820 , a return module 830 and a processing module 840 .

[0115] The determination module 810 is used to determine a business data group that matches the terminal device in response to receiving a risk identification request from the terminal device, wherein the business data group includes multiple business data of multiple data types. In one embodiment, the determination module 810 can be used to perform the operation S210 described above, which will not be repeated here.

[0116] The calling module 820 is used to call the risk identification model that matches the business data, perform risk identification on multiple business data, and obtain risk identification results. In one embodiment, the calling module 820 can be used to perform the operation S220 described above, which will not be repeated here.

[0117] The return module 830 is used to return the risk identification result and the model identifier of the risk identification model to the terminal device. In one embodiment, the return module 830 can be used to perform the operation S230 described above, which will not be repeated here.

[0118] The processing module 840 is used to determine the risk handling strategy for the business data group in response to receiving the risk handling request from the terminal device according to the processing authority of the terminal device and the processing parameters in the risk handling request. In one embodiment, the processing module 840 can be used to perform the operation S240 described above, which will not be repeated here.

[0119] According to an embodiment of the present disclosure, the determination module 810 includes: a first determination submodule, for determining a plurality of business data newly added on the day from the data lake in response to receiving a risk identification request from a terminal device; an allocation submodule, for calling a business volume allocation model to allocate the plurality of business data newly added on the day to each operating user in the daily schedule according to groups; a second determination submodule, for determining a target operating user matching the terminal device based on the device information of the terminal device; and a third determination submodule, for determining the business data group allocated to the target operating user as a business data group matching the terminal device.

[0120] According to an embodiment of the present disclosure, the calling module 820 includes: a fourth determination submodule, used to determine at least one risk identification model that matches the business data based on the data type of the business data; a calling submodule, used to call each risk identification model, perform risk identification on multiple business data, and obtain the risk identification sub-result output by each risk identification model; and a fifth determination submodule, used to determine the risk identification result based on the risk identification sub-result output by each risk identification model.

[0121] According to an embodiment of the present disclosure, the fourth determination submodule includes: a first determination unit, which is used to determine multiple reconciliation risk identification models that match the business data when it is determined that the data type of the business data is a reconciliation type, wherein the reconciliation risk identification model includes at least one of the following: a first reconciliation risk identification model for risk identification in the reconciliation time dimension, a second reconciliation risk identification model for risk identification in the reconciliation method dimension, a third reconciliation risk identification model for risk identification in the reconciliation result dimension, and a fourth reconciliation risk identification model for risk identification in the reconciliation location dimension; a second determination unit, which is used to determine an account opening risk identification model that matches the business data when it is determined that the data type of the business data is an account opening type.

[0122] According to an embodiment of the present disclosure, the first reconciliation risk identification model outputs a first risk identification sub-result, the second reconciliation risk identification model outputs a second risk identification sub-result, the third reconciliation risk identification model outputs a third risk identification sub-result, and the fourth reconciliation risk identification model outputs a fourth risk identification sub-result.

[0123] The fifth determination submodule includes: a third determination unit, used to determine the number of risk results based on the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result and the fourth risk identification sub-result; a fourth determination unit, used to determine the risk identification result based on the number of risk results, the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result and the fourth risk identification sub-result.

[0124] According to an embodiment of the present disclosure, a calling submodule includes: for the second reconciliation risk identification model, an acquisition unit is used to obtain the reconciliation track information of the business users related to the business data; an input unit is used to input the reconciliation track information, the generation time of the business data and the reconciliation duration into the second reconciliation risk identification model, and output a second risk identification sub-result.

[0125] According to an embodiment of the present disclosure, the processing parameters include an institutional parameter and a policy parameter. The processing module 840 includes: a sixth determination submodule, which is used to determine the risk processing strategy for the business data group according to the policy parameter when it is determined that the processing authority is the same as the institutional parameter; and a seventh determination submodule, which is used to determine the risk processing strategy for the business data group according to the policy parameter and the institutional parameter when it is determined that the processing authority is not the same as the institutional parameter.

[0126] According to an embodiment of the present disclosure, any multiple modules of the determination module 810, the call module 820, the return module 830 and the processing module 840 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the determination module 810, the call module 820, the return module 830 and the processing module 840 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the determination module 810, the call module 820, the return module 830 and the processing module 840 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0127] Fig. 9 A block diagram of an electronic device suitable for implementing a business data processing method according to an embodiment of the present disclosure is shown.

[0128] like Fig. 9As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 to a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0129] In RAM 903, various programs and data required for the operation of electronic device 900 are stored. Processor 901, ROM 902 and RAM 903 are connected to each other via bus 904. Processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 902 and / or RAM 903. It should be noted that the program can also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0130] According to an embodiment of the present disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to the bus 904. The electronic device 900 may further include one or more of the following components connected to the input / output (I / O) interface 905: an input portion 906 including a keyboard, a mouse, etc.; an output portion 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 908 including a hard disk, etc.; and a communication portion 909 including a network interface card such as a LAN card, a modem, etc. The communication portion 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage portion 908 as needed.

[0131] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or it may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented. According to the embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 902 and / or RAM 903 described above and / or one or more memories other than ROM 902 and RAM 903.

[0132] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the business data processing method provided by the embodiment of the present disclosure.

[0133] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 901. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0134] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 909, and / or installed from a removable medium 911. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0135] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0136] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0137] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0138] Those skilled in the art will appreciate that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure. The embodiments of the present disclosure are described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, and these substitutions and modifications should all fall within the scope of the present disclosure.

Claims

1. A business data processing method, characterized in that: The method comprises: In response to receiving a risk identification request from a terminal device, determining a business data group matching the terminal device, wherein the business data group includes a plurality of business data of a plurality of data types; Invoking a risk identification model that matches the business data, performing risk identification on a plurality of the business data, and obtaining a risk identification result; Returning the risk identification result and the model identifier of the risk identification model to the terminal device; and In response to receiving the risk handling request from the terminal device, a risk handling strategy for the business data group is determined according to the handling authority of the terminal device and the handling parameters in the risk handling request.

2. The method according to claim 1, characterized in that The step of determining, in response to receiving a risk identification request from a terminal device, a business data group matching the terminal device comprises: In response to receiving a risk identification request from a terminal device, determining multiple business data newly added on the day from the data lake; Call the business volume allocation model to allocate multiple newly added business data of the day to each operating user in the daily shift schedule according to groups; Determining a target operating user matching the terminal device according to the device information of the terminal device; and The service data group assigned to the target operating user is determined as a service data group matching the terminal device.

3. The method according to claim 1, characterized in that The calling of the risk identification model matching the business data to perform risk identification on the plurality of business data to obtain the risk identification result includes: Determining, according to the data type of the business data, at least one risk identification model that matches the business data; Calling each of the risk identification models to perform risk identification on the plurality of business data, and obtaining a risk identification sub-result output by each of the risk identification models; and The risk identification result is determined according to the risk identification sub-result output by each of the risk identification models.

4. The method according to claim 3, characterized in that The step of determining, according to the data type of the business data, at least one risk identification model that matches the business data comprises: In the case where it is determined that the data type of the business data is a reconciliation type, a plurality of reconciliation risk identification models matching the business data are determined, wherein the reconciliation risk identification model comprises at least one of the following: a first reconciliation risk identification model for risk identification in the reconciliation time dimension, a second reconciliation risk identification model for risk identification in the reconciliation method dimension, a third reconciliation risk identification model for risk identification in the reconciliation result dimension, and a fourth reconciliation risk identification model for risk identification in the reconciliation position dimension; When it is determined that the data type of the business data is an account opening type, an account opening risk identification model matching the business data is determined.

5. The method according to claim 4, characterized in that The first reconciliation risk identification model outputs a first risk identification sub-result, the second reconciliation risk identification model outputs a second risk identification sub-result, the third reconciliation risk identification model outputs a third risk identification sub-result, and the fourth reconciliation risk identification model outputs a fourth risk identification sub-result; Determining the risk identification result according to the risk identification sub-result output by each of the risk identification models includes: Determining the number of risk results according to the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result, and the fourth risk identification sub-result; as well as The risk identification result is determined according to the number of risk results, the first risk identification sub-result, the second risk identification sub-result, the third risk identification sub-result, and the fourth risk identification sub-result.

6. The method according to claim 4, characterized in that The calling of each of the risk identification models to perform risk identification on the plurality of business data to obtain the risk identification sub-result output by each of the risk identification models includes: For the second account reconciliation risk identification model, obtaining account reconciliation track information of business users related to the business data; and The reconciliation track information, the generation time of the business data and the reconciliation duration are input into the second reconciliation risk identification model, and a second risk identification sub-result is output.

7. The method according to claim 1, characterized in that The processing parameters include an organization parameter and a policy parameter; the step of determining the risk processing policy for the business data group according to the processing authority of the terminal device and the processing parameters in the risk processing request includes: In the case where it is determined that the processing authority is the same as the organization parameter, determining a risk processing strategy for the business data group according to the strategy parameter; In the case where it is determined that the processing authority is different from the organizational parameter, a risk processing strategy for the business data group is determined according to the strategy parameter and the organizational parameter.

8. A business data processing device, characterized in that: The device comprises: a determination module, configured to determine, in response to receiving a risk identification request from a terminal device, a business data group matching the terminal device, wherein the business data group includes a plurality of business data of a plurality of data types; A calling module, used to call a risk identification model that matches the business data, perform risk identification on a plurality of the business data, and obtain a risk identification result; a returning module, configured to return the risk identification result and the model identifier of the risk identification model to the terminal device; and The processing module is used to determine a risk processing strategy for the business data group in response to receiving a risk processing request from the terminal device according to the processing authority of the terminal device and the processing parameters in the risk processing request.

9. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images