A risk detection method, apparatus and device

Abstract

Embodiments of the present specification provide a risk detection method, device and equipment, wherein the method comprises: in response to an execution request triggered by a target user for a target service, obtaining credit evaluation requirements corresponding to a scene to which the target service belongs, and obtaining credit evaluation data of the target user collected based on multiple data sources; determining credit evaluation weights corresponding to the credit evaluation data based on the credit evaluation requirements, identity information of the target user triggering execution of the target service, and credit evaluation dimensions corresponding to the credit evaluation data; determining a target credit evaluation result of the target user based on the credit evaluation data and corresponding credit evaluation weights by using a preset fusion algorithm; and determining whether there is a risk in executing the target service based on the target credit evaluation result.

Description

Technical Field

[0001] This document relates to the field of computer technology, and in particular to a risk detection method, apparatus, and equipment. Background Technology

[0002] With the rapid development of the data economy, credit has become an important factor in the generation of credit. Businesses based on user credit, such as credit leasing and credit lending, are becoming increasingly common. To improve the success rate of credit-related businesses, multiple different credit assessment platforms can be used to assess user credit data.

[0003] For example, when users need to use credit services, they can access different credit assessment platforms by switching accounts to obtain credit assessment data that matches the current business. However, when there are many credit assessment platforms and the differences between credit assessment data are large, the time cost of obtaining credit data through the multi-account login mechanism is high, and the matching degree between the obtained credit assessment data and the current business needs is low, which affects the success rate of business processing. Therefore, it is necessary to provide a faster and more reliable solution for obtaining credit assessment data to improve the success rate of credit-related business processing. Summary of the Invention

[0004] The purpose of the embodiments in this specification is to provide a faster and more reliable method for obtaining credit assessment data, so as to improve the success rate of credit-related business transactions.

[0005] To achieve the above technical solution, the embodiments in this specification are implemented as follows: This specification provides a risk detection method, comprising: responding to an execution request for a target business triggered by a target user; obtaining a credit assessment requirement corresponding to the scenario to which the target business belongs, and obtaining credit assessment data for the target user collected from multiple data sources; determining a credit assessment weight corresponding to the credit assessment data based on the credit assessment requirement, the identity information of the target user triggering the execution of the target business, and the credit assessment dimension corresponding to the credit assessment data; determining a target credit assessment result for the target user based on the credit assessment data and the corresponding credit assessment weight using a preset fusion algorithm; and determining whether there is a risk in executing the target business based on the target credit assessment result.

[0006] This specification provides a risk detection device, comprising: a data acquisition module for acquiring sample data corresponding to financial transactions and risk labels corresponding to the sample data; a first detection module for performing risk detection on the sample data using a preset large language model to obtain a first risk detection result and a probability value of the first risk detection result belonging to each preset confidence interval; a loss determination module for determining a first loss value based on the first risk detection result and the risk labels, and determining a second loss value based on the matching degree between the first risk detection result and the risk labels, and the probability value of the first risk detection result belonging to each preset confidence interval; and a model training module for training the preset large language model based on the first loss value and the second loss value to obtain a trained large language model, wherein the trained large language model is used to determine the risk detection result and confidence level corresponding to the execution of financial transactions, and the risk detection result and confidence level are used to determine whether there is a risk in executing the financial transactions.

[0007] This specification provides an embodiment of a risk detection device, comprising: a processor; and a memory arranged to store computer-executable instructions, wherein, when executed, the processor: responds to an execution request triggered by a target user for a target service, acquires a credit assessment requirement corresponding to the scenario to which the target service belongs, and acquires credit assessment data for the target user collected from multiple data sources; determines a credit assessment weight corresponding to the credit assessment data based on the credit assessment requirement, the identity information of the target user triggering the execution of the target service, and the credit assessment dimension corresponding to the credit assessment data; uses a preset fusion algorithm to determine a target credit assessment result for the target user based on the credit assessment data and the corresponding credit assessment weight; and determines whether there is a risk in executing the target service based on the target credit assessment result.

[0008] This specification also provides a storage medium for storing computer-executable instructions. When executed by a processor, the executable instructions implement the following process: in response to an execution request for a target service triggered by a target user, obtaining the credit assessment requirement corresponding to the scenario to which the target service belongs, and obtaining credit assessment data for the target user collected from multiple data sources; determining the credit assessment weight corresponding to the credit assessment data based on the credit assessment requirement, the identity information of the target user triggering the execution of the target service, and the credit assessment dimension corresponding to the credit assessment data; using a preset fusion algorithm, determining the target credit assessment result for the target user based on the credit assessment data and the corresponding credit assessment weight; and determining whether there is a risk in executing the target service based on the target credit assessment result.

[0009] This specification also provides a computer program product, including a computer program that, when executed by a processor, implements the following process: in response to an execution request for a target business triggered by a target user, obtaining a credit assessment requirement corresponding to the scenario to which the target business belongs, and obtaining credit assessment data for the target user collected from multiple data sources; determining a credit assessment weight corresponding to the credit assessment data based on the credit assessment requirement, the identity information of the target user triggering the execution of the target business, and the credit assessment dimension corresponding to the credit assessment data; determining a target credit assessment result for the target user based on the credit assessment data and the corresponding credit assessment weight using a preset fusion algorithm; and determining whether there is a risk in executing the target business based on the target credit assessment result. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 This is a schematic diagram of the implementation environment for one of the risk detection methods described in this specification; Figure 2 This is a flowchart illustrating the processing procedure of one risk detection method described in this specification. Figure 3 This is a flowchart illustrating the process of determining credit assessment weights as described in this specification. Figure 4 This is a schematic diagram of the system architecture of a multi-dimensional credit account fusion system as described in this specification; Figure 5 This is a flowchart illustrating the process for determining another credit assessment weight in this specification. Figure 6 This is a flowchart illustrating the process of determining credit assessment data as described in this specification. Figure 7 This is a schematic diagram of the data processing flow of a one-dimensional credit account fusion system as described in this specification; Figure 8 This is a flowchart illustrating the process of determining a target credit assessment result as described in this specification. Figure 9 This is a schematic diagram of a risk detection device described in this specification; Figure 10 This is a schematic diagram of a risk detection device described in this manual. Detailed Implementation

[0011] This specification provides a risk detection method, apparatus, and device through its embodiments.

[0012] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0013] This specification provides a faster and more reliable solution for obtaining credit assessment data to improve the success rate of credit-related business processing. In practical applications, a multi-account login switching mechanism can be used to obtain credit assessment data matching the currently pending business. For example, when a user triggers the execution of credit-related business, they can access different credit assessment platforms by switching accounts. For instance, after applying for loan resources using credit assessment data 1 provided by a personal credit platform, a user can log in to a corporate credit platform to obtain credit assessment data 2, and then execute credit-related business based on credit assessment data 1 and / or credit assessment data 2. However, in this solution, users need to frequently switch and log in repeatedly between multiple credit assessment platforms, making the operation process cumbersome. Furthermore, due to the lack of a unified identity identifier, the identification results of the same user by different credit assessment platforms may be inconsistent, posing a risk of identity conflict. In addition, since the data between different credit assessment platforms cannot be linked in real time, the data update of one account cannot automatically synchronize and affect the credit assessment judgment of another account. In complex business processing scenarios involving multiple credit assessment dimensions, it is difficult to accurately determine credit assessment data, resulting in low scenario adaptability. Alternatively, a single-dimensional credit assessment system can be used to handle credit-related business. For example, credit-related business can be processed using credit assessment data from only one system, such as personal credit assessment data from a personal credit assessment platform or corporate credit assessment data from a corporate credit assessment platform. However, because each credit assessment platform independently maintains its own credit assessment model and user credit data, a user's credit performance on platform A cannot be obtained and referenced by platform B. This results in relatively one-sided credit assessment data that cannot fully reflect the user's true credit status. For example, a business owner with good credit may find it difficult to obtain personal credit services due to a limited personal credit record. Furthermore, users need to rebuild their credit profiles on each credit assessment platform, which is costly, inefficient, and data cannot be reused. In addition, malicious third parties may use different identities on different credit assessment platforms, making it difficult for a single credit assessment platform to identify cross-dimensional risks. Moreover, in complex scenarios (such as those involving multiple credit assessment dimensions), it is difficult to determine which credit assessment dimension's data to use.

[0014] In summary, due to the independent operation of various credit assessment platforms and the fragmented nature of their data, users lack a unified view of their credit accounts, making it difficult to fully understand their own credit status. This results in data silos. Furthermore, existing solutions, based on only a single credit assessment dimension (such as individual or corporate credit assessment only), fail to reflect a user's true overall credit value, and this singular assessment dimension prevents the maximization of service benefits. Additionally, switching between different credit assessment platforms requires separate logins and repeated authentications, leading to cumbersome procedures, a poor user experience, and a fragmented authentication experience. Moreover, single-dimensional credit assessment data is insufficient to support the risk control needs of complex scenarios, resulting in inadequate accuracy and comprehensiveness in credit assessments. To address this, this specification provides a faster and more reliable method for acquiring credit assessment data. This method calculates a weight allocation scheme in real time based on the credit assessment needs of the current service scenario, combined with user identity attributes and credit assessment dimensions corresponding to credit assessment data collected from multiple data sources. Specifically, it calculates the credit assessment weight corresponding to each piece of credit assessment data. A preset fusion algorithm is then used to combine these credit assessment weights to quickly and accurately determine the target credit assessment result. This avoids the problem of low accuracy in determining assessment results inherent in static weight assessment schemes, thereby improving the success rate of credit-related business transactions. Specific processing details can be found in the following embodiments.

[0015] The risk detection methods described in one or more embodiments of this specification are applicable to the risk detection implementation environment, such as... Figure 1 As shown, the implementation environment includes at least: Client 100 and server 200. Furthermore, server 200 can be configured with various network models and algorithms, among which: Client 100 can run on terminal devices, which can be mobile phones, personal computers, tablets, e-book readers, wearable devices, devices that interact with information based on AR (Augmented Reality) and VR (Virtual Reality), and laptop computers, etc. Client 100 can be installed on terminal devices, and Client 100 can be an application, a browser, or a subroutine embedded in an application, etc.

[0016] Server 200 can run on a server, which can be one or more servers, a server cluster consisting of several servers, or a cloud server on a cloud computing platform. Server 200 can be installed on the server. Server 200 can be an application or a subroutine embedded in an application. Various network models and algorithms can be integrated into server 200, or server 200 can call one or more of various network models and algorithms to perform corresponding operations.

[0017] In addition, it may include a database 300, which may be set in the server on which the server 200 runs, or outside the server on which the server 200 runs. The database 300 may store user assessment requirements, credit assessment requirements, model parameters of the weight determination model, credit assessment dimensions corresponding to the credit assessment data, etc.

[0018] In this implementation environment, a target user can trigger an execution request for a target business through client 100. In response to the execution request, server 200 can obtain the credit assessment requirements corresponding to the scenario to which the target business belongs, and obtain credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data, server 200 can determine the credit assessment weight corresponding to the credit assessment data. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weight, server 200 can determine the target credit assessment result for the target user. Based on the target credit assessment result, server 200 can determine whether there is a risk in executing the target business and return the risk assessment result to client 100.

[0019] like Figure 2 As shown in the embodiments of this specification, a risk detection method is provided. The execution subject of this method can be a server, which can be a single independent server or a server cluster composed of multiple servers. The server can be a backend server for financial businesses such as resource transfer or resource lending, or a backend server for financial business applications. The method specifically includes the following steps: In step S202, in response to the execution request for the target business triggered by the target user, the credit assessment requirements corresponding to the scenario to which the target business belongs are obtained, and the credit assessment data for the target user is obtained based on multiple data sources.

[0020] The target business can be credit-related business, such as credit lending, cross-border business (such as visa application, cross-border resource transfer, etc.), corporate financing, government services, etc., which require credit. Credit assessment requirements can include credit assessment dimensions, credit rating, data acquisition time, etc., and data sources can include personal credit assessment sources, corporate credit assessment sources, third-party credit reporting sources, etc.

[0021] In implementation, target users can trigger execution requests for the target business on the client side. The client can then send these execution requests to the server, which can receive and respond to them. Based on a pre-defined correspondence between scenarios and requirements, the server can determine the credit assessment requirements corresponding to the scenario of the target business. For example, taking credit lending as the target business, the pre-defined correspondence between scenarios and requirements can determine that the credit assessment requirements corresponding to the credit lending scenario may include personal credit assessment requirements and / or corporate credit assessment requirements. The server can determine multiple data sources based on the credit assessment requirements and send the target user's user identifier to these multiple data sources to conduct credit assessments of the target user based on the data collected from these multiple data sources.

[0022] For example, the multiple data sources for credit assessment in credit lending operations could include data source 1 and data source 2 related to personal credit assessment dimensions, and data source 3 related to corporate credit assessment dimensions. The server can send the target user's user identifier to these three data sources and receive the credit assessment data for the target user returned by these three data sources. Furthermore, the server can filter and process the acquired credit assessment data based on factors such as data acquisition time limits in the credit assessment requirements.

[0023] The above-mentioned method for determining credit assessment requirements and credit assessment data is an optional and feasible method. In actual application scenarios, there can be a variety of different methods. Different methods can be selected according to different actual application scenarios. This specification does not specifically limit the embodiments in this way.

[0024] In step S204, the credit assessment weight corresponding to the credit assessment data is determined based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, and the credit assessment dimension corresponding to the credit assessment data.

[0025] The identity information of the target user that triggers the execution of the target business can include identity information of various roles such as personal identity, corporate identity, employee identity, and manager identity. The credit assessment dimensions can include personal credit assessment dimensions, corporate credit assessment dimensions, and third-party credit assessment dimensions.

[0026] In implementation, the server can use a pre-trained target model to determine the credit assessment weights corresponding to the credit assessment data based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data. The target model can be a model built based on a preset machine learning algorithm.

[0027] Alternatively, the server can obtain the source level of the data source corresponding to each credit assessment data (which can be determined based on the credibility of the data source channel, data update cycle, data collection method, etc.), and use a pre-trained target model to determine the credit assessment weight corresponding to the credit assessment data based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, the credit assessment dimension corresponding to the credit assessment data, and the source level of the data source corresponding to each credit assessment data.

[0028] Alternatively, the server can also obtain the amount of credit assessment data corresponding to each data source, as well as the data credibility feedback information corresponding to each data source, and determine the credibility of each data source based on the amount of data and the credibility feedback information. Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, the credit assessment dimension corresponding to the credit assessment data, and the source level and credibility of the data source corresponding to each credit assessment data, the credit assessment weight corresponding to the credit assessment data can be determined.

[0029] Furthermore, the method for determining the credit assessment weights described above is an optional and feasible method. In practical application scenarios, there can be a variety of different methods. Different methods can be selected according to different practical application scenarios. This specification does not specifically limit the embodiments in this regard.

[0030] An innovative fusion calculation mechanism was designed to dynamically adjust the weights of various credit dimensions. Based on the feature tags of the current service scenario (such as personal consumption, corporate financing, cross-border services, etc.), combined with user identity attributes and data quality scores for each dimension, the algorithm calculates the weight allocation scheme in real time, ultimately generating a scenario-adapted comprehensive credit assessment result. The algorithm supports hot updates of weight configurations, allowing strategy adjustments without a system restart.

[0031] Technical Results: This approach overcomes the limitations of traditional static weighting assessments, making credit evaluation results more aligned with real-world needs. Experimental data shows that compared to fixed-weighting schemes, dynamic weighting schemes improve service matching accuracy by 25% and reduce user complaint rates by 35%.

[0032] In step S206, a preset fusion algorithm is used to determine the target credit assessment result for the target user based on the credit assessment data and the corresponding credit assessment weights.

[0033] Among them, fusion algorithms can be used to dynamically adjust the calculation method of the proportion coefficient of each credit assessment data in the comprehensive assessment, and can be used to integrate and process data from different sources to achieve more accurate information understanding. For example, fusion algorithms can include multimodal fusion algorithms, multi-model fusion algorithms, etc.

[0034] In implementation, the server can determine the preset fusion algorithm based on the number of data modalities (such as text modalities, table modalities, web page modalities, etc.) contained in the credit assessment data, as well as the number of credit assessment data corresponding to each data modality.

[0035] For example, when the number of data modalities contained in the credit assessment data exceeds the modality threshold, the server can use a multimodal fusion algorithm to determine the target credit assessment result for the target user based on the credit assessment data and the corresponding credit assessment weights. Specifically, the server can construct a first deterministic model based on the multimodal fusion algorithm, and train the first deterministic model based on historical data to obtain a trained first deterministic model. Then, using the trained first deterministic model, the server can determine the target credit assessment result for the target user based on the credit assessment data and the corresponding credit assessment weights.

[0036] Alternatively, if the number of data modalities in the credit assessment data exceeds a modality threshold, and the number of credit assessment data corresponding to multiple data modalities exceeds a preset threshold, the server can utilize a multi-model fusion algorithm to determine the target credit assessment result for the target user based on the credit assessment data and corresponding credit assessment weights. For example, the server can construct a sub-module based on a machine learning algorithm corresponding to each data modality, and construct a second deterministic model based on multiple sub-modules and a fusion module. The sub-modules can process the credit assessment data and corresponding credit assessment weights corresponding to the data modality to obtain the credit assessment result corresponding to that data modality. The fusion module can fuse the credit assessment results from multiple sub-modules. The server can then use the trained second deterministic model to determine the target credit assessment result for the target user based on the credit assessment data and corresponding credit assessment weights.

[0037] Furthermore, the method for determining the target credit assessment result described above is an optional and feasible method. In practical application scenarios, there can be a variety of different methods. Different methods can be selected according to different practical application scenarios. This specification does not specifically limit the embodiments in this way.

[0038] In step S208, based on the target credit assessment results, it is determined whether there is a risk in performing the target business.

[0039] In implementation, the server can determine whether there is a risk in executing the target business based on the target credit assessment result and the credit requirements of the target business. For example, taking the target business as a credit lending business, assuming that the credit requirement for this credit lending business is 200 credit points, while the credit score corresponding to the target credit assessment result is 80, since the difference in credit scores between the credit requirement and the target credit assessment result is 200-80=120, which is greater than the preset score difference (assuming it is 50), then the server can determine that there is a risk in executing the target business.

[0040] Alternatively, the server can send the credit assessment results to the pre-defined management entity corresponding to the target business, so as to determine whether there is any risk in executing the target business through manual review.

[0041] Furthermore, if it is determined that there is no risk in executing the target business, the server can execute the target business based on the target credit assessment results. For example, the server can quantify the credit value based on the target credit assessment results (that is, convert the integrated credit data into a quantifiable range of service rights and credit limits), and execute the target business according to the credit value quantification results. Specifically, taking the target business as a credit lending business as an example, assuming that it is determined that there is no risk in executing the target business, the server can determine the amount of resources that the target user can borrow based on the target credit assessment results, and execute the credit lending business corresponding to the amount of resources that can be borrowed.

[0042] The server can quantify the credit value of the target credit assessment result by using a pre-built mathematical mapping relationship between the credit assessment result and the scope of service rights. By transforming the integrated target credit assessment result into a visualized credit value, the abstract credit assessment result can be converted into specific rights indicators such as service limits, deposit-free scope, and priority rights that users can intuitively understand. It also supports real-time calculation and dynamic adjustment of rights, which can help users clearly perceive their own credit value, improve credit awareness, and increase the usage rate of credit services. The mathematical mapping relationship between the credit assessment result and the scope of service rights can also provide standardized docking specifications for partner institutions and expand the application scenarios of credit services.

[0043] This specification provides a risk detection method that, in response to an execution request for a target service triggered by a target user, obtains the credit assessment requirements corresponding to the scenario of the target service and acquires credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target service, and the credit assessment dimensions corresponding to the credit assessment data, the method determines the credit assessment weights corresponding to the credit assessment data. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, the method determines the target credit assessment result for the target user. Based on the target credit assessment result, the method determines whether there is a risk in executing the target service. In this way, based on the credit assessment requirements of the current service scenario, combined with the user's identity attributes and the credit assessment dimensions corresponding to the credit assessment data collected from multiple data sources, a weight allocation scheme can be calculated in real time, i.e., the credit assessment weights corresponding to each piece of credit assessment data. By using a preset fusion algorithm combined with the credit assessment weights, the target credit assessment result can be quickly and accurately determined, avoiding the problem of low accuracy in determining the assessment result in static weight assessment schemes, and improving the success rate of credit-related business processing.

[0044] In practical applications, the specific processing methods for determining the credit assessment weights corresponding to the credit assessment data in step S204 above, based on credit assessment needs, the identity information of the target user triggering the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data, can vary. The following provides one optional processing method, such as... Figure 3 As shown, the specific process may include the following steps S2042 to S2044.

[0045] In step S2042, based on the data source corresponding to the credit assessment data, the validity information and timeliness information corresponding to the credit assessment data are determined.

[0046] Among them, validity information can be determined based on the source level and credibility of the data source corresponding to the credit assessment data, while timeliness information can be determined based on the assessment time (or update time) of the credit assessment data and the data generation time of the assessment data used in the credit assessment data.

[0047] In implementation, such as Figure 4 As shown, the server can build a multi-dimensional credit account fusion system, which may include a multi-source data acquisition module, a credit dimension standardization module, a dynamic weight fusion calculation module, an identity management module, and a scenario-based service routing module.

[0048] For example, taking data sources including personal credit systems, corporate credit systems, and third-party credit reporting systems, the multi-source data collection module can collect credit assessment data from these three data sources, as well as information such as the source level and credibility of each data source and the assessment time of each credit assessment data.

[0049] Then, the credit dimension standardization module can be used to transform heterogeneous raw credit assessment data into a unified internal data model. This module can predefine standardized credit dimension data models, including personal credit dimensions, corporate credit dimensions, and third-party credit reporting dimensions. The server can use the above credit dimension models to perform data standardization processing on the raw credit assessment data to obtain credit assessment data. Among them, data standardization processing can include field mapping, format conversion, numerical normalization, and missing value handling.

[0050] In this way, the dynamic weight fusion calculation module can obtain standardized credit assessment data, as well as the validity and timeliness information corresponding to each credit assessment data.

[0051] The validity information of credit assessment data can be determined based on the source level and credibility of the data source, while the timeliness information of credit assessment data can be determined based on the assessment time (or update time) and the data generation time of the assessment data used in the credit assessment data.

[0052] The multi-source data acquisition module can map heterogeneous data corresponding to credit assessment dimensions such as personal credit assessment, corporate credit assessment, and third-party credit reporting to a standardized dimensional structure. Through a common credit dimension metadata specification, this mechanism can support flexible data field mapping, numerical normalization, and intelligent completion of missing values. It can achieve automated and standardized processing of credit data from different data sources and in different formats, solve the technical problem of "language barriers" in multi-source credit data, improve data access efficiency, and shorten the new data source access cycle from weekly to hourly, laying a data foundation for multi-dimensional credit integration.

[0053] In step S2044, the credit assessment weight corresponding to the credit assessment data is determined based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, the nature and validity information of the credit assessment data, and the credit assessment dimensions corresponding to the credit assessment data.

[0054] In implementation, the dynamic weight fusion calculation module can use a pre-trained third-party determination model to determine the credit assessment weights corresponding to the credit assessment data based on credit assessment requirements, the identity information of the target user triggering the execution of the target business, the nature and validity information of the credit assessment data, and the credit assessment dimensions corresponding to the credit assessment data.

[0055] The third determined model can be a model built based on a preset deep learning algorithm.

[0056] In practical applications, the specific processing methods for determining whether there is a risk in the execution of financial business based on the second detection result and the corresponding confidence level in step S2044 above can be varied. The following provides an optional processing method, which may specifically include the processing of steps A1 to A2.

[0057] In step A1, the user evaluation needs of the target users for the target business are obtained.

[0058] User assessment requirements can include the importance of credit assessment dimensions set by the user, business execution requirements input by the user, etc. For example, user assessment requirements can include that the importance of personal credit assessment dimensions is higher than that of corporate credit assessment dimensions.

[0059] In step A2, the pre-trained weight determination model is used to determine the credit assessment weights corresponding to the credit assessment data based on user assessment needs, credit assessment needs, identity information of the target user triggering the execution of the target business, the nature and validity information of the credit assessment data, and the credit assessment dimensions corresponding to the credit assessment data.

[0060] The weight determination model can be a model built based on a preset deep learning algorithm.

[0061] In implementation, the dynamic weight fusion calculation module can receive standardized multi-dimensional credit assessment data and use a pre-trained weight determination model to dynamically determine the weight coefficients of each credit assessment dimension based on the current scenario's credit assessment needs, user assessment needs, etc., so as to determine the credit assessment weights corresponding to the credit assessment data based on the weight coefficients of each credit assessment dimension.

[0062] In practical applications, the specific processing methods for determining the credit assessment weights corresponding to the credit assessment data in step S204 above, based on credit assessment needs, the identity information of the target user triggering the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data, can vary. The following provides one optional processing method, such as... Figure 5 As shown, the specific process may include the following steps S2046 to S2048.

[0063] In step S2046, the credit assessment data is obtained as follows: the first assessment data, which matches the credit assessment dimension with the credit assessment requirement and / or the identity information of the target user triggering the execution of the target business, and the second assessment data, which is not the first assessment data, is obtained from the credit assessment data.

[0064] In practice, for example, assuming the credit assessment requirement is a personal credit assessment dimension requirement, the server can determine the credit assessment data of the personal credit assessment dimension in the credit assessment data as the first assessment data, and determine the credit assessment data corresponding to assessment dimensions other than the personal credit assessment dimension (such as corporate credit assessment dimension, third-party credit investigation dimension, etc.) as the second assessment data.

[0065] In step S2048, the credit assessment weight corresponding to the first assessment data is determined as the first assessment weight, and the credit assessment weight corresponding to the second assessment data is determined as the second assessment weight.

[0066] The weight of the first evaluation can be greater than that of the second evaluation.

[0067] In implementation, the server can determine the credit assessment data that matches the identity information of the target user that triggers the execution of the target business as the main dimension assessment data. That is, the first assessment data of the main dimension can be given a higher credit assessment weight, while the second assessment data of other dimensions can be given a lower credit assessment weight.

[0068] In practical applications, the specific processing methods for obtaining credit assessment data for the target user based on multiple data sources in step S202 above can vary. The following provides one optional processing method, such as... Figure 6 As shown, the specific process may include the following steps S2022 to S2026.

[0069] In step S2022, first credit assessment data for the target user is obtained based on multiple data sources.

[0070] In implementation, such as Figure 7 As shown, the target user can trigger an account fusion application. In response to the application, the multi-dimensional credit account fusion system can collect multi-source credit data based on the target user's authorization information, that is, obtain the first credit assessment data for the target user based on multiple data sources.

[0071] The multi-source data acquisition module also supports various data access methods, including API interface calls, data file synchronization, and real-time message subscription.

[0072] In practical applications, the specific processing methods for obtaining the first credit assessment data for the target user based on multiple data sources in step S2022 above can be varied. The following provides an optional processing method, which may specifically include the following steps B1 to B3.

[0073] In step B1, the target user identifier of the target user is obtained.

[0074] Among them, the target user identifier can be irreversible information generated based on the user information of the target user using a preset encryption algorithm.

[0075] In implementation, such as Figure 7 As shown, when a user uses the multi-dimensional credit account integration system for the first time, they can initiate a credit account integration application through the preset application corresponding to the multi-dimensional credit account integration system (or a mini-program embedded in the main program). The multi-dimensional credit account integration system can guide users to authorize and bind multiple credit assessment platforms such as personal credit accounts, corporate credit accounts, and third-party credit data.

[0076] In this way, the multi-dimensional credit account fusion system can use the multi-source data acquisition module to obtain credit assessment data within the authorized scope from the above-mentioned authorized data sources. Then, the credit dimension standardization module can convert the collected raw credit assessment data into a standard format and store it in the unified account center. At the same time, the identity management module can generate a unique fusion account identity for the user and establish an association mapping with each sub-account.

[0077] The target user can initiate a service request. That is, when the server receives an execution request for the target business triggered by the target user, it can obtain the target user's target user identifier, which is a unique integrated account identity identifier.

[0078] In step B2, the mapping relationship between account identifiers and user identifiers for each data source is obtained from multiple data sources, and the target account identifier corresponding to the target user in each data source is determined.

[0079] In practice, the server can determine the target account identifier corresponding to the target user in each data source based on the mapping relationship between the account identifier and the user identifier of the data source.

[0080] In step B3, based on the target account identifier and the target user's authorization information for each data source, the first credit assessment data for the target user is obtained from multiple data sources.

[0081] In implementation, the identity management module can generate and manage a unique identity identifier (i.e., target user identifier) ​​for each integrated account (i.e., each user). This identifier can serve as a globally unique identity credential for the user in the multi-dimensional credit account integration system, establishing a mapping relationship with the user's various credit dimension sub-accounts. Furthermore, the identity identifier is generated using an irreversible encryption algorithm, ensuring the privacy protection of the user's true identity.

[0082] Specifically, the target user's identifier can be generated using an irreversible hash algorithm, establishing a many-to-one mapping relationship with the target user's sub-accounts across various credit dimensions. Furthermore, the identity authentication process can support a token-based single sign-on mechanism. After completing authentication once using the unified identifier, the target user can seamlessly access different credit dimensions without repeated login verification. This achieves a "one-time authentication, all-scenario access" user experience, shortening the average authentication process time, increasing the authentication success rate, and improving the convenience for users to use credit services across different dimensions.

[0083] In step S2024, the first credit assessment data is subjected to data quality verification based on one or more of the following verification rules to obtain the data quality verification results: integrity verification, timeliness verification, and source legality verification.

[0084] In practice, the multi-source data acquisition module can perform preliminary data quality checks on the collected credit assessment data based on rules such as integrity verification, timeliness verification, and source legality verification, and obtain data quality verification results.

[0085] In step S2026, based on the data quality verification results, the first credit assessment data is filtered to obtain the credit assessment data.

[0086] In implementation, the server can filter the first credit assessment data based on the data quality verification results and the data quality requirements in the credit assessment requirements corresponding to the target user (or target business) to obtain the credit assessment data.

[0087] In practical applications, the specific processing method for determining the target credit assessment result for the target user in step S206 above, using a preset fusion algorithm based on credit assessment data and corresponding credit assessment weights, can vary. One optional processing method is provided below, such as... Figure 8 As shown, the specific process may include the following steps S2062 to S2064.

[0088] In step S2062, the pre-trained credit assessment model is used to perform consistency verification on the credit assessment data to obtain the first verification result.

[0089] Among them, the credit assessment model can be a model built based on a preset machine learning algorithm.

[0090] In implementation, the server can use a pre-trained credit assessment model to verify the temporal consistency and logical consistency between credit assessment data, and obtain the first verification result. Based on this constructed multi-dimensional consistency cross-validation mechanism, abnormal data (such as abnormal accounts, abnormal credit assessment data, etc.) can be identified through data consistency verification.

[0091] In step S2064, a target credit assessment result for the target user is determined using a preset fusion algorithm, the first verification result, the credit assessment data, and the corresponding credit assessment weight.

[0092] In implementation, when a target user initiates a service request, the scenario-based service routing module of the multi-dimensional credit account fusion system can analyze the scenario characteristics of the request to determine the primary dimension for credit assessment. Based on the primary and secondary dimensions, the system determines the corresponding credit assessment weight for the credit assessment data. In this way, the dynamic weight fusion calculation module can mobilize relevant dimension data (i.e., the first verification result, credit assessment data, and corresponding credit assessment weights) according to scenario requirements to perform comprehensive assessment calculations and output a comprehensive credit result, which is the target credit assessment result for the target user.

[0093] In addition, the multi-dimensional credit account fusion system may also include a scenario-based service routing module. This module can be used to intelligently match the combination of credit dimensions (i.e., credit assessment data and corresponding credit assessment weights) according to the service scenario requested by the user (i.e. the scenario to which the target business belongs) and route the request to the corresponding service processing channel. The routing decision is based on the preset scenario-dimensional mapping rules and the real-time credit data status.

[0094] The scenario-based service routing module can be configured with a scenario-based credit service routing engine. This engine has a built-in scenario-dimension matching rule library and can automatically identify credit dimension combinations based on scenario characteristics in the user request (such as transaction amount, service type, and purpose of use). Furthermore, the engine can also have a fallback strategy, automatically switching to alternative dimension combinations when the selected dimension data is insufficient, ensuring service continuity. This enables precise "personalized" credit service adaptation. The system can automatically complete dimension selection decisions, eliminating the need for users to understand complex credit dimension concepts. Service routing response time can be controlled within a preset time range, improving the accuracy of routing decisions.

[0095] Thus, a multi-dimensional credit account fusion system, capable of integrating multiple credit accounts and providing unified identity authentication, can address technical issues in existing technologies, such as the isolation between personal and corporate credit, the lack of integration mechanisms between third-party credit data and platform credit systems, the need for repeated authentication when switching between different credit dimensions, and the inability to comprehensively assess a user's overall credit value through independent calculation of data from each credit dimension. Specifically, the multi-dimensional credit account fusion system can establish a unified credit account center, mapping personal credit, corporate credit, and third-party credit assessment data to the same account system. Simultaneously, it can utilize a unified credit dimension data model to standardize and structure credit assessment data from different sources. Based on scenarios and credit assessment needs, a dynamic weighted fusion algorithm calculates the corresponding credit assessment weights for each credit assessment data point, generating a comprehensive credit assessment result (i.e., the target credit assessment result). Furthermore, it can generate a unique identity identifier (i.e., the target user identifier) ​​for the fused credit account, supporting one-click cross-dimensional identity authentication. It can also intelligently match credit dimensions based on user request scenarios and automatically route to the appropriate service channel. By building a dedicated, comprehensive credit account for users, unified management and display of personal credit, corporate credit, and third-party credit data can be achieved, maximizing the credit value of users, improving the efficiency of identity authentication and the accuracy of credit service matching, and making risk control more comprehensive.

[0096] In practical applications, credit assessment data can include first sub-data, second sub-data, and third sub-data. The first sub-data can include personal credit assessment results, performance record data, and behavioral preference data corresponding to the user assessment dimension. The second sub-data can include organizational qualification information and business status information corresponding to the organizational assessment dimension. The third sub-data can include third-party credit assessment results, credit information, and historical credit records corresponding to the third-party credit reporting dimension.

[0097] Among them, the user assessment dimension, also known as the individual assessment dimension, is mainly based on the user's transaction behavior and performance records on the platform to conduct personal credit assessment. The organization assessment dimension, also known as the enterprise assessment dimension, is used to characterize the enterprise credit system and is mainly based on the enterprise's operating status, business information, legal risks, etc. to conduct enterprise credit assessment. The third-party credit reporting dimension can be the credit reporting services (such as the collection, collation, storage and processing of credit information) provided by third-party credit reporting agencies in accordance with the law for individuals and / or enterprises.

[0098] Because credit assessment systems across different dimensions operate relatively independently, users need to manage their credit information separately on different platforms. Business users also find it difficult to easily access the personal credit information of business owners, and there is a lack of effective sharing and integration mechanisms for credit assessment data between platforms. Therefore, a unified credit account center established using a multi-dimensional credit account fusion system can standardize, map, and integrate credit assessment data from multiple dimensions, including scattered personal credit, business credit, and third-party credit reporting data. This generates unique identifiers for cross-dimensional authentication and intelligently matches credit dimensions based on service scenarios, thereby maximizing the release of user credit value and improving the overall identity authentication experience.

[0099] In addition, the credit account center can also serve as an aggregation layer and unified service outlet for various credit data sources. It is responsible for receiving data inputs from multiple data sources such as personal credit systems, corporate credit systems, and third-party credit reporting agencies. After standardized mapping and fusion calculation, it provides integrated credit services and unified identity authentication capabilities to the outside world.

[0100] Users can manage their personal and corporate credit information through a single entry point, eliminating the need to switch between multiple platforms. The multi-dimensional credit account integration system provides a unified identity authentication system, allowing users to access services across all credit assessment dimensions with a single login. Based on the integrated comprehensive credit assessment, users can obtain higher credit limits, a wider range of services, and more precise rights matching. Specifically, upon first use, the multi-dimensional credit account integration system guides users through the process of binding their multi-dimensional credit accounts. On the account management page, users can view data overviews for each credit assessment dimension and the overall credit assessment results. When users utilize specific services, the system automatically matches the appropriate credit dimension based on the scenario, allowing users to quickly complete service applications through unified identity authentication.

[0101] For example, taking personal consumption scenarios as an example, when a target user applies for credit consumption services, the multi-dimensional credit account integration system can not only evaluate their personal credit assessment data, but also comprehensively consider their corporate credit assessment data as a business owner, and ultimately give a higher credit limit than a single dimension, thereby improving the success rate of credit consumption services.

[0102] Alternatively, taking corporate financing as an example, the target user's identity information can be that of a business owner. When the target user applies for a corporate loan, their credit assessment data based on their good personal assessment dimension is integrated with the credit assessment data based on the corporate assessment dimension, which can result in a more favorable financing rate and improve the success rate of corporate loan applications.

[0103] Alternatively, for government service scenarios, target users can complete real-name authentication on the government service platform through a unified identity identifier, and the multi-dimensional credit account integration system can automatically retrieve multiple relevant credit assessment data to support the "credit-integrated government service" scenario.

[0104] In cross-border service scenarios, outbound travelers can apply for visa services through a unified credit account. The multi-dimensional credit account integration system can generate credit certificates by integrating multi-dimensional credit assessment data, which can simplify the visa application process.

[0105] In addition, to ensure data security and privacy compliance, the multi-dimensional credit account integration system can implement strict security measures at each stage. For example, data transmission can use encrypted channels, sensitive data needs to be de-identified before storage, the use and sharing of users' credit assessment data must be clearly authorized, and complete data access logs need to be recorded to support audit traceability.

[0106] To address the issue that single-dimensional credit assessments are incomplete and fail to reflect a user's overall credit value, the multi-dimensional credit account fusion system establishes a multi-dimensional credit account fusion architecture. This integrates data from multiple sources, including individuals, businesses, and credit reporting agencies, into a unified assessment system, improving the accuracy and comprehensiveness of credit assessments and expanding the range of service benefits users can unlock. Furthermore, to address the data silos between different credit systems, which previously required users to manage credit assessment data separately on different platforms, the multi-dimensional credit account fusion system constructs a unified credit account center. This enables automatic collection, standardized mapping, and centralized management of data from various dimensions, unifying the user's credit account view, improving data management efficiency, and simplifying operational processes.

[0107] To address the issue of repeated authentication and fragmented user experience when switching between platforms, the multi-dimensional credit account fusion system uses a unified identity management mechanism. Users can achieve one-click authentication across dimensions based on a unique identity credential, which improves the efficiency of identity authentication. Furthermore, users do not need to remember multiple account passwords, which can increase the success rate of authentication.

[0108] To address the challenge of determining the appropriate credit dimensions in complex scenarios, the scenario-based service routing module of the multi-dimensional credit account fusion system can intelligently match combinations of credit dimensions based on a rule engine, thereby improving service matching accuracy, reducing scenario adaptation error rates, and enhancing user experience smoothness.

[0109] To address the issue of low utilization rate and insufficient value release of credit data, the multi-dimensional credit account fusion system introduces a dynamic weight fusion algorithm. By dynamically adjusting the weight of each dimension based on scenario requirements, it can maximize credit value, allowing users to obtain higher credit limits and better service conditions than with a single dimension.

[0110] To address the issue of limited risk control capabilities and difficulty in identifying cross-dimensional fraud, the multi-dimensional credit account fusion system uses a multi-dimensional cross-verification mechanism to identify abnormal identities through data consistency checks, which can improve the accuracy of identifying fake identities and reduce fraud risks.

[0111] This specification provides a risk detection method that, in response to an execution request for a target service triggered by a target user, obtains the credit assessment requirements corresponding to the scenario of the target service and acquires credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target service, and the credit assessment dimensions corresponding to the credit assessment data, the method determines the credit assessment weights corresponding to the credit assessment data. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, the method determines the target credit assessment result for the target user. Based on the target credit assessment result, the method determines whether there is a risk in executing the target service. In this way, based on the credit assessment requirements of the current service scenario, combined with the user's identity attributes and the credit assessment dimensions corresponding to the credit assessment data collected from multiple data sources, a weight allocation scheme can be calculated in real time, i.e., the credit assessment weights corresponding to each piece of credit assessment data. By using a preset fusion algorithm combined with the credit assessment weights, the target credit assessment result can be quickly and accurately determined, avoiding the problem of low accuracy in determining the assessment result in static weight assessment schemes, and improving the success rate of credit-related business processing.

[0112] The above describes the risk detection method provided in the embodiments of this specification. Based on the same idea, the embodiments of this specification also provide a risk detection device, such as... Figure 9 As shown.

[0113] The risk detection device includes: a data acquisition module 901, a weight determination module 902, a comprehensive evaluation module 903, and a risk detection module 904, wherein: The data acquisition module 901, in response to the execution request for the target business triggered by the target user, acquires the credit assessment requirements corresponding to the scenario to which the target business belongs, and acquires the credit assessment data for the target user based on multiple data sources. The weight determination module 902 determines the credit assessment weight corresponding to the credit assessment data based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, and the credit assessment dimension corresponding to the credit assessment data. The comprehensive evaluation module 903 uses a preset fusion algorithm to determine the target credit evaluation result for the target user based on the credit evaluation data and the corresponding credit evaluation weights. The risk detection module 904 determines, based on the target credit assessment results, whether there is a risk in executing the target business.

[0114] In this embodiment of the specification, the weight determination module 902 is used for: Based on the data source corresponding to the credit assessment data, determine the validity and timeliness information corresponding to the credit assessment data; Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, the nature and validity information of the credit assessment data, and the credit assessment dimensions corresponding to the credit assessment data, the credit assessment weight corresponding to the credit assessment data is determined.

[0115] In this embodiment of the specification, the weight determination module 902 is used for: Obtain the user evaluation needs of the target users for the target service; Using a pre-trained weight determination model, the credit assessment weights corresponding to the credit assessment data are determined based on the user assessment needs, the credit assessment needs, the identity information of the target user triggering the execution of the target business, the nature and validity information of the credit assessment data, and the credit assessment dimensions corresponding to the credit assessment data.

[0116] In this embodiment of the specification, the weight determination module 902 is used for: The credit assessment data includes first assessment data that matches the credit assessment dimension with the credit assessment requirement and / or the identity information of the target user triggering the execution of the target business, and second assessment data other than the first assessment data. The credit assessment weight corresponding to the first assessment data is determined as the first assessment weight, and the credit assessment weight corresponding to the second assessment data is determined as the second assessment weight, wherein the first assessment weight is greater than the second assessment weight.

[0117] In this embodiment of the specification, the data acquisition module 901 is used for: Based on the multiple data sources, obtain the first credit assessment data for the target user; The first credit assessment data is subjected to data quality verification based on one or more of the following verification rules to obtain data quality verification results: integrity verification, timeliness verification, and source legality verification. Based on the data quality verification results, the first credit assessment data is filtered to obtain the credit assessment data.

[0118] In this embodiment of the specification, the data acquisition module 901 is used for: Obtain the target user identifier of the target user, wherein the target user identifier is irreversible information generated based on the user information of the target user using a preset encryption algorithm; Obtain the mapping relationship between account identifiers and user identifiers for each of the multiple data sources, and determine the target account identifier corresponding to the target user in each data source; Based on the target account identifier and the target user's authorization information for each data source, first credit assessment data for the target user is obtained from the multiple data sources.

[0119] In the embodiments described in this specification, the comprehensive evaluation module 903 is used for: Using a pre-trained credit assessment model, the consistency of the credit assessment data is checked to obtain a first verification result; Using the preset fusion algorithm, based on the first verification result, the credit assessment data, and the corresponding credit assessment weight, a target credit assessment result is determined for the target user.

[0120] In this embodiment of the specification, the credit assessment data includes a first sub-data, a second sub-data, and a third sub-data. The first sub-data includes personal credit assessment results, performance record data, and behavioral preference data corresponding to the user assessment dimension. The second sub-data includes organizational qualification information and business status information corresponding to the organizational assessment dimension. The third sub-data includes third-party credit assessment results, credit information, and historical credit records corresponding to the third-party credit reporting dimension.

[0121] This specification provides a risk detection device that, in response to an execution request for a target service triggered by a target user, acquires the credit assessment requirement corresponding to the scenario of the target service and obtains credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirement, the identity information of the target user triggering the execution of the target service, and the credit assessment dimensions corresponding to the credit assessment data, it determines the credit assessment weights corresponding to the credit assessment data. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, it determines the target credit assessment result for the target user. Based on the target credit assessment result, it determines whether there is a risk in executing the target service. In this way, based on the credit assessment requirement of the current service scenario, combined with the user's identity attributes and the credit assessment dimensions corresponding to the credit assessment data collected from multiple data sources, a weight allocation scheme can be calculated in real time, i.e., the credit assessment weights corresponding to each credit assessment data. By using a preset fusion algorithm combined with the credit assessment weights, the target credit assessment result can be quickly and accurately determined, avoiding the problem of low accuracy in determining the assessment result of static weight assessment schemes, and improving the success rate of credit-related business processing.

[0122] The above are risk detection devices provided in the embodiments of this specification. Based on the same idea, the embodiments of this specification also provide a risk detection device, such as... Figure 10 As shown.

[0123] The risk detection device can provide terminal equipment or servers, etc., for the above embodiments.

[0124] like Figure 10 As shown, device 1000 mainly consists of a communication interface 1002, a user interface 1004, a processor 1006, and a data storage 1008. These components are interconnected and communicate with each other via a system bus, network, or other connection mechanism 1010. The communication interface 1002 enables device 1000 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, the communication interface 1002 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, the communication interface 1002 can be a wired interface such as Ethernet, Token Ring, or a USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or a wide-area wireless interface (e.g., WiMAX or LTE). Of course, the communication interface 1002 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. The communication interface 1002 may also include multiple physical communication interfaces, such as Wi-Fi interfaces, Bluetooth interfaces, and wide-area wireless interfaces.

[0125] User interface 1004 includes receiving user input and providing output to the user. Therefore, user interface 1004 may include input components such as a keypad, keyboard, touch-sensitive or presence-sensitive panel, computer mouse, trackball, joystick, microphone, still camera, and video camera, and output components such as a display screen (which may be combined with a touch-sensitive panel), CRT, LCD, LED, display using DLP technology, printer, and other similar devices known or developed in the future. User interface 1004 may also generate auditory output via speakers, speaker jacks, audio output ports, audio output devices, headphones, and other similar devices known or developed in the future. In some embodiments, user interface 1004 may include software, circuitry, or other forms of logic capable of transmitting and receiving data from external user input / output devices. Additionally or alternatively, device 1000 may support remote access from other devices via communication interface 1002 or another physical interface (not shown). User interface 1004 may be configured to receive user input, the position and movement of which may be indicated by indicators or cursors described herein. User interface 1004 can also be configured as a display device for rendering or displaying text fragments.

[0126] Processor 1006 may contain one or more general-purpose processors and / or special-purpose processors.

[0127] Data storage 1008 may include one or more volatile storage components and may be integrated wholly or partially with processor 1006. Data storage 1008 may include removable and non-removable components.

[0128] Processor 1006 is capable of executing program instructions 1018 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 1008 to perform the various functions described herein. Data storage 1008 may contain a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 1000, enable device 1000 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Execution of program instructions 1018 by processor 1006 may result in processor 1006 using data 1012.

[0129] For example, program instructions 1018 may include an operating system 1022 (e.g., an operating system kernel, device drivers, and / or other modules) installed on device 1000 and one or more applications 1020 (e.g., a browser, social media application, or game application). Similarly, data 1012 may include operating system data 1016 and application data 1014. Operating system data 1016 is primarily accessible to the operating system 1022, while application data 1014 is primarily accessible to one or more applications 1020. Application data 1014 may reside in a file system visible or hidden from the user of device 1000.

[0130] Application 1020 can communicate with operating system 1012 through one or more application programming interfaces (APIs). These APIs help application 1020 read and / or write application data 1014, transmit or receive information via communication interface 1002, receive or display information on user interface 1004, etc.

[0131] In some terminology, application 1020 may be simply referred to as "app". Furthermore, application 1020 can be downloaded to device 1000 through one or more online app stores or app markets. However, applications can also be installed on device 1000 in other ways, such as through a web browser or a physical interface on device 1000 (e.g., a USB port).

[0132] Specifically, in this embodiment, the risk detection device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the risk detection device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: In response to an execution request for a target business triggered by a target user, the system obtains the credit assessment requirements corresponding to the scenario to which the target business belongs, and obtains credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user who triggers the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data, the credit assessment weight corresponding to the credit assessment data is determined. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, a target credit assessment result is determined for the target user. Based on the target credit assessment results, determine whether there is any risk in performing the target business.

[0133] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, the risk detection device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0134] This specification provides a risk detection device that, in response to an execution request for a target service triggered by a target user, acquires the credit assessment requirements corresponding to the scenario of the target service and obtains credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target service, and the credit assessment dimensions corresponding to the credit assessment data, it determines the credit assessment weights corresponding to the credit assessment data. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, it determines the target credit assessment result for the target user. Based on the target credit assessment result, it determines whether there is a risk in executing the target service. In this way, based on the credit assessment requirements of the current service scenario, combined with the user's identity attributes and the credit assessment dimensions corresponding to the credit assessment data collected from multiple data sources, a weight allocation scheme can be calculated in real time, i.e., the credit assessment weights corresponding to each credit assessment data. By using a preset fusion algorithm combined with the credit assessment weights, the target credit assessment result can be quickly and accurately determined, avoiding the problem of low accuracy in determining the assessment result of static weight assessment schemes, and improving the success rate of credit-related business processing.

[0135] Furthermore, based on the above Figures 1 to 8 This specification also provides a storage medium for storing computer-executable instruction information in one or more embodiments. In one specific embodiment, the storage medium may be a USB flash drive, optical disc, hard disk, etc. When the computer-executable instruction information stored in the storage medium is executed by a processor, it can realize the following process: In response to an execution request for a target business triggered by a target user, the system obtains the credit assessment requirements corresponding to the scenario to which the target business belongs, and obtains credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user who triggers the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data, the credit assessment weight corresponding to the credit assessment data is determined. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, a target credit assessment result is determined for the target user. Based on the target credit assessment results, determine whether there is any risk in performing the target business.

[0136] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the above-described storage medium embodiment is basically similar to the method embodiment, so the description is relatively simple; relevant parts can be referred to the description of the method embodiment.

[0137] This specification provides a storage medium that, in response to an execution request for a target service triggered by a target user, acquires the credit assessment requirements corresponding to the scenario of the target service, and acquires credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target service, and the credit assessment dimensions corresponding to the credit assessment data, it determines the credit assessment weights corresponding to the credit assessment data. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, it determines the target credit assessment result for the target user. Based on the target credit assessment result, it determines whether there is a risk in executing the target service. In this way, based on the credit assessment requirements of the current service scenario, combined with the user's identity attributes and the credit assessment dimensions corresponding to the credit assessment data collected from multiple data sources, a weight allocation scheme can be calculated in real time, i.e., the credit assessment weights corresponding to each credit assessment data. By using a preset fusion algorithm combined with the credit assessment weights, the target credit assessment result can be quickly and accurately determined, avoiding the problem of low accuracy in determining the assessment result in static weight assessment schemes, and improving the success rate of credit-related business processing.

[0138] Furthermore, based on the above Figures 1 to 8 This specification also provides one or more embodiments of a computer program product, including a computer program, which, when executed by a processor, can perform the following processes: In response to an execution request for a target business triggered by a target user, the system obtains the credit assessment requirements corresponding to the scenario to which the target business belongs, and obtains credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user who triggers the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data, the credit assessment weight corresponding to the credit assessment data is determined. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, a target credit assessment result is determined for the target user. Based on the target credit assessment results, determine whether there is any risk in performing the target business.

[0139] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the above-described embodiment of a computer program product is relatively simple in description because it is fundamentally similar to the method embodiment; relevant parts can be referred to the description of the method embodiment.

[0140] This specification provides a computer program product that, in response to an execution request for a target service triggered by a target user, acquires the credit assessment requirements corresponding to the scenario of the target service, and acquires credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target service, and the credit assessment dimensions corresponding to the credit assessment data, it determines the credit assessment weights corresponding to the credit assessment data. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, it determines the target credit assessment result for the target user. Based on the target credit assessment result, it determines whether there is a risk in executing the target service. In this way, based on the credit assessment requirements of the current service scenario, combined with the user's identity attributes and the credit assessment dimensions corresponding to the credit assessment data collected from multiple data sources, a weight allocation scheme can be calculated in real time, i.e., the credit assessment weights corresponding to each credit assessment data. By using a preset fusion algorithm combined with the credit assessment weights, the target credit assessment result can be quickly and accurately determined, avoiding the problem of low accuracy in determining the assessment result of static weight assessment schemes, and improving the success rate of credit-related business processing.

[0141] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0142] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using a hardware physical module. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0143] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0144] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0145] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0146] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] The embodiments described herein are illustrated with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0148] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0149] These computer program instructions may also be loaded onto a computer or other programmable device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0150] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0151] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0152] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0153] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Without further limitations, the presence of additional identical elements in the process, method, article, or apparatus that includes said elements is not excluded.

[0154] It should also be noted that the terms "one," "an," and "the" do not specifically refer to the singular; they can also include the plural. Ordinal numbers such as "first," "second," etc., do not necessarily indicate order; often they are used to distinguish between objects. For example, "first server" and "second server" usually refer to two servers. To differentiate between these two servers, they are described as "first server" and "second server." Of course, sometimes these two servers may be the same server.

[0155] In this specification, unless explicitly stated otherwise, "receiving and sending data" does not necessarily mean direct receiving and sending; it can also mean indirect receiving and sending. For example, A receiving data sent by B can be understood as A directly receiving data sent by B, or it can be understood as A indirectly receiving data sent by B through other entities such as C. Similarly, B sending data to A can be understood as B sending data directly to A, or it can be understood as B indirectly sending data to A through other entities such as C. Here, C can be a single subject, or two or more subjects.

[0156] This specification uses specific terms to describe embodiments thereof. Terms such as "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations within this specification do not necessarily refer to the same embodiment. Furthermore, those skilled in the art can combine and integrate the different embodiments or examples described herein, as well as the features of those different embodiments or examples, without contradiction.

[0157] Although one or more embodiments of this specification provide method steps as described in the embodiments or flowcharts, it is understood that the order of steps listed in the embodiments or flowcharts is only one of many possible execution orders and does not represent the only execution order. Therefore, when the claims involve method steps, any changes or adjustments to the order of such steps, or the parallelism between steps, are also within the scope of protection of the claims.

[0158] It should be noted that the user data obtained in this manual is authorized by the user and does not involve user privacy.

[0159] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0160] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0161] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0162] The above description is merely an embodiment of this specification and is not intended to limit this document. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A risk detection method, comprising: In response to an execution request for a target business triggered by a target user, the system obtains the credit assessment requirements corresponding to the scenario to which the target business belongs, and obtains credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user who triggers the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data, the credit assessment weight corresponding to the credit assessment data is determined. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, a target credit assessment result is determined for the target user. Based on the target credit assessment results, determine whether there is any risk in performing the target business.

2. The method according to claim 1, wherein determining the credit assessment weight corresponding to the credit assessment data based on the credit assessment requirement, the identity information of the target user triggering the execution of the target business, and the credit assessment dimension corresponding to the credit assessment data includes: Based on the data source corresponding to the credit assessment data, determine the validity and timeliness information corresponding to the credit assessment data; Based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, the nature and validity information of the credit assessment data, and the credit assessment dimensions corresponding to the credit assessment data, the credit assessment weight corresponding to the credit assessment data is determined.

3. The method according to claim 2, wherein determining the credit assessment weight corresponding to the credit assessment data based on the credit assessment requirement, the identity information of the target user triggering the execution of the target business, the nature and validity information of the credit assessment data, and the credit assessment dimension corresponding to the credit assessment data includes: Obtain the user evaluation needs of the target users for the target business; Using a pre-trained weight determination model, the credit assessment weights corresponding to the credit assessment data are determined based on the user assessment needs, the credit assessment needs, the identity information of the target user triggering the execution of the target business, the nature and validity information of the credit assessment data, and the credit assessment dimensions corresponding to the credit assessment data.

4. The method according to claim 1, wherein determining the credit assessment weight corresponding to the credit assessment data based on the credit assessment requirement, the identity information of the target user triggering the execution of the target business, and the credit assessment dimension corresponding to the credit assessment data includes: The credit assessment data includes first assessment data that matches the credit assessment dimension with the credit assessment requirement and / or the identity information of the target user triggering the execution of the target business, and second assessment data other than the first assessment data. The credit assessment weight corresponding to the first assessment data is determined as the first assessment weight, and the credit assessment weight corresponding to the second assessment data is determined as the second assessment weight, wherein the first assessment weight is greater than the second assessment weight.

5. The method according to claim 1, wherein obtaining credit assessment data for the target user based on multiple data sources includes: Based on the multiple data sources, obtain the first credit assessment data for the target user; The first credit assessment data is subjected to data quality verification based on one or more of the following verification rules to obtain data quality verification results: integrity verification, timeliness verification, and source legality verification. Based on the data quality verification results, the first credit assessment data is filtered to obtain the credit assessment data.

6. The method according to claim 5, wherein obtaining the first credit assessment data for the target user based on the plurality of data sources includes: Obtain the target user identifier of the target user, wherein the target user identifier is irreversible information generated based on the user information of the target user using a preset encryption algorithm; Obtain the mapping relationship between account identifiers and user identifiers for each of the multiple data sources, and determine the target account identifier corresponding to the target user in each data source; Based on the target account identifier and the target user's authorization information for each data source, first credit assessment data for the target user is obtained from the multiple data sources.

7. The method according to claim 1, wherein determining the target credit assessment result for the target user based on the credit assessment data and the corresponding credit assessment weights using a preset fusion algorithm includes: Using a pre-trained credit assessment model, the consistency of the credit assessment data is checked to obtain a first verification result; Using the preset fusion algorithm, based on the first verification result, the credit assessment data, and the corresponding credit assessment weight, a target credit assessment result is determined for the target user.

8. The method according to claim 1, wherein the credit assessment data includes a first sub-data, a second sub-data, and a third sub-data, wherein the first sub-data includes personal credit assessment results, performance record data, and behavioral preference data corresponding to the user assessment dimension, the second sub-data includes organizational qualification information and business status information corresponding to the organizational assessment dimension, and the third sub-data includes third-party credit assessment results, credit information, and historical credit records corresponding to the third-party credit reporting dimension.

9. A risk detection device, comprising: The data acquisition module, in response to the execution request triggered by the target user for the target business, acquires the credit assessment requirements corresponding to the scenario to which the target business belongs, and acquires the credit assessment data for the target user based on multiple data sources; The weight determination module determines the credit assessment weight corresponding to the credit assessment data based on the credit assessment requirements, the identity information of the target user triggering the execution of the target business, and the credit assessment dimension corresponding to the credit assessment data. The comprehensive evaluation module uses a preset fusion algorithm to determine the target credit evaluation result for the target user based on the credit evaluation data and the corresponding credit evaluation weights. The risk detection module determines whether there is a risk in performing the target business based on the target credit assessment results.

10. A risk detection device, wherein the risk detection includes: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to: In response to an execution request for a target business triggered by a target user, the system obtains the credit assessment requirements corresponding to the scenario to which the target business belongs, and obtains credit assessment data for the target user collected from multiple data sources. Based on the credit assessment requirements, the identity information of the target user who triggers the execution of the target business, and the credit assessment dimensions corresponding to the credit assessment data, the credit assessment weight corresponding to the credit assessment data is determined. Using a preset fusion algorithm, based on the credit assessment data and the corresponding credit assessment weights, a target credit assessment result is determined for the target user. Based on the target credit assessment results, determine whether there is any risk in performing the target business.

Images