Risk monitoring method based on dynamic threshold early warning and multi-scene adaptation system

Abstract

The invention relates to the technical field of data monitoring. The risk monitoring method based on dynamic threshold early warning comprises the following steps: acquiring risk triggering information under multiple scenes, acquiring a credit scene, a transaction scene and an association scene according to the risk triggering information, judging whether the credit scene, the transaction scene and the association scene enter a risk monitoring state or not, and if the credit scene, the transaction scene and the association scene enter the risk monitoring state, performing risk monitoring on the credit scene, the transaction scene and the association scene. If yes, obtaining structured monitoring data of multiple scenes, and obtaining historical credit change data of a credit scene, real-time transaction flow data of a transaction scene and associated party risk exposure data of an associated scene according to the structured monitoring data; and cross-scene risk features are acquired according to the historical credit change data and the real-time transaction flow data. According to the invention, by integrating credit type, transaction type and association type scene data, a multi-dimensional risk source is covered, risk missed judgment caused by single data source analysis is avoided, and comprehensive control of systematic risks is realized.

Description

Technical Field

[0001] This application relates to the field of data monitoring technology, and in particular to a risk monitoring method and multi-scenario adaptation system based on dynamic threshold early warning. Background Technology

[0002] With the deepening development of the digital economy, the digital transformation of finance, commerce and trade, supply chain management and other fields continues to deepen, showing significant characteristics of diversified scenarios, massive data, and interconnected risks. On the one hand, scenarios such as credit business of financial institutions, transaction processes of e-commerce platforms, and upstream and downstream collaboration of industrial chains are becoming increasingly segmented. In the financial field alone, dozens of sub-scenarios are covered, including personal credit, corporate financing, and cross-border payments, and the risk manifestations of each scenario are fundamentally different. On the other hand, the flow of data between multiple scenarios has been significantly enhanced, and risks are no longer limited to a single field, but present a complex situation of "cross-scenario transmission, temporal evolution, and multi-source triggering".

[0003] Traditional risk monitoring methods often use fixed risk thresholds (such as the upper limit of a single transaction amount or a fixed credit scoring standard). However, the market environment, user behavior, and related networks are all in dynamic change. Static thresholds are prone to "false warnings" when risks fluctuate in the short term or "missed warnings" when risks evolve in the long term (such as missing the opportunity to intervene when credit deteriorates slowly without reaching the fixed threshold), which seriously reduces the reliability of warnings. Summary of the Invention

[0004] This application provides a risk monitoring method based on dynamic threshold early warning to solve the problem that single-modal data cannot handle the correlation analysis of multi-dimensional information, such as the problem that contradictions between voice content and facial expressions can easily lead to a break in the interaction logic.

[0005] This application provides a risk monitoring method based on dynamic threshold early warning, including: Obtain risk trigger information in multiple scenarios, and based on the risk trigger information, identify credit-related scenarios, transaction-related scenarios, and association-related scenarios. Determine whether credit-related scenarios, transaction-related scenarios, and association-related scenarios have entered a risk monitoring state. If they have entered a risk monitoring state, obtain structured monitoring data for multiple scenarios, and obtain historical credit change data for credit-related scenarios, real-time transaction flow data for transaction-related scenarios, and related party risk exposure data for association-related scenarios based on the structured monitoring data. Cross-scenario risk characteristics are obtained based on historical credit change data and real-time transaction flow data, and multi-scenario basic risk characteristics are obtained based on the cross-scenario risk characteristics. Based on the historical credit change data and related party risk exposure data, obtain the associated risk characteristics, and based on the associated risk characteristics, obtain the trend characteristic quantity; generate a comprehensive risk index according to the multi-scene basic risk features and trend feature quantities; determine whether the comprehensive risk index is greater than a preset safety threshold value; if less than, continue to monitor; if greater than, obtain a sub-risk level according to the comprehensive risk index, and obtain a multi-scene adaptive sub-level early warning information according to the sub-risk level.

[0006] Preferably, the step of determining whether the credit scene, the transaction scene, and the correlation scene enter the risk monitoring state comprises: split the risk trigger information under the multi-scene according to the scene categories to obtain credit state data corresponding to credit scene exclusive trigger indicators, transaction behavior data corresponding to transaction scene exclusive trigger indicators, and correlation party risk transmission data corresponding to correlation scene exclusive trigger indicators; integrate the credit state data, the transaction behavior data, and the correlation party risk transmission data to obtain scene-indicator association relationship data; obtain associated risk transmission abnormal information according to the scene-indicator association relationship data; respectively compare the real-time trigger indicator data of the credit scene, the transaction scene, and the correlation scene with the scene trigger condition data according to the associated risk transmission abnormal information to obtain indicator-condition fit degree data; obtain scene risk monitoring start determination result data according to the indicator-condition fit degree data; determine whether the scene risk monitoring start determination result data meets a preset regulation; if meeting, the determination result is that the fit degree meets the requirement, and it is determined that the corresponding scene enters the risk monitoring state; if not meeting, the determination result is that the fit degree does not meet the requirement, and it is determined that the scene does not enter the risk monitoring state.

[0007] Preferably, the step of obtaining the multi-scene structured monitoring data, and obtaining the historical credit change data of the credit scene, the real-time transaction flow data of the transaction scene, and the correlation party risk exposure data of the correlation scene according to the structured monitoring data comprises: obtain credit scene, transaction scene, and correlation scene corresponding structured monitoring data collection dimension data according to the structured monitoring data; obtain credit scene data storage source information, transaction scene data storage source information, and correlation scene data storage source information according to the credit scene, the transaction scene, and the correlation scene corresponding structured monitoring data collection dimension data; According to the credit class scene data storage source information, the transaction class scene data storage source information, and the association class scene data storage source information, corresponding credit class scene original data, transaction class scene original data, and association class scene original data are obtained. Field integrity verification is performed on the credit class scene original data, the transaction class scene original data, and the association class scene original data, to obtain credit class scene standardized data, transaction class scene standardized data, and association class scene standardized data. According to the credit class scene standardized data, historical credit change data is obtained. According to the transaction class scene standardized data, real-time transaction flow data is obtained. According to the association class scene standardized data, associated party risk exposure data is obtained.

[0008] Preferably, the step of obtaining cross-scene risk features according to the historical credit change data and the real-time transaction flow data, and obtaining multi-scene basic risk features according to the cross-scene risk features, comprises: According to the historical credit change data, a change trajectory of the credit state in different time periods is obtained, to obtain credit change trajectory data. According to the credit change trajectory data, trend direction and change amplitude features of the credit state are identified, to obtain credit trend feature data. According to the real-time transaction flow data of the transaction class scene, transaction amount distribution, transaction object party distribution, and time distribution behavior features are extracted, to obtain transaction behavior feature data. According to the credit trend feature data and the transaction behavior feature data, cross-scene feature correlation data is obtained. According to the cross-scene feature correlation data, core correlation features that can jointly reflect risks are screened out, to obtain cross-scene risk feature data. According to the cross-scene risk feature data, multi-scene basic risk feature data is obtained.

[0009] Preferably, the step of obtaining association risk features according to the historical credit change data and the associated party risk exposure data, and obtaining trend feature quantities according to the association risk features, comprises: According to the historical credit change data, credit state and association dimension of the associated party are extracted, to obtain credit association dimension data. According to the associated party risk exposure data, risk type, exposure scale, and influence range risk dimension of the associated party are extracted, to obtain associated risk dimension data. According to the credit association dimension data and the associated risk dimension data, association risk transmission analysis data is obtained. According to the association risk transmission analysis data, association risk feature data is obtained. According to the correlation risk characteristic data, the correlation risk characteristics in different time periods are arranged in time sequence to form time sequence data of the correlation risk characteristics. According to the correlation risk characteristic time sequence data, trend characteristic quantity data is generated.

[0010] Preferably, the step of generating the comprehensive risk index according to the multi-scene basic risk characteristics and the trend characteristic quantity comprises: According to the multi-scene basic risk characteristic data, basic risk dimension data reflecting credit and basic risk dimension data of transaction cross-scene risk are extracted. According to the trend characteristic quantity data, trend risk dimension data reflecting the change trend of the correlation risk are extracted. According to the basic risk dimension data reflecting credit, the basic risk dimension data of transaction cross-scene risk and the trend risk dimension data, risk data fusion data is generated. According to the risk data fusion data, fused risk data is acquired. According to the fused risk data, risk quantization data is acquired. According to the risk quantization data, comprehensive risk index data is acquired.

[0011] The application discloses a risk monitoring and multi-scene adaptation system based on dynamic threshold early warning, which comprises: A data acquisition module is used for acquiring risk trigger information under multiple scenes, and acquiring credit type scenes, transaction type scenes and correlation type scenes according to the risk trigger information. A first judgment module is used for judging whether the credit type scenes, the transaction type scenes and the correlation type scenes enter a risk monitoring state, and if yes, acquiring structured monitoring data of the multiple scenes, and acquiring historical credit change data of the credit type scenes, real-time transaction flow data of the transaction type scenes and correlation party risk exposure data of the correlation type scenes according to the structured monitoring data. A multi-scene basic risk characteristic acquisition module is used for acquiring cross-scene risk characteristics according to the historical credit change data and the real-time transaction flow data, and acquiring multi-scene basic risk characteristics according to the cross-scene risk characteristics. A trend characteristic quantity acquisition module is used for acquiring correlation risk characteristics according to the historical credit change data and the correlation party risk exposure data, and acquiring trend characteristic quantities according to the correlation risk characteristics. A comprehensive risk index generation module is used for generating a comprehensive risk index according to the multi-scene basic risk characteristics and the trend characteristic quantities. A second judgment module is used for judging whether the comprehensive risk index is greater than a preset safety threshold. If no, continuous monitoring is performed. If greater, a sub-risk level is obtained according to the comprehensive risk index, and a multi-scenario adaptive sub-level early warning information is obtained according to the sub-risk level.

[0012] Preferably, the first judging module comprises; The data acquisition unit is configured to split the risk trigger information under the multiple scenes according to the scene categories to obtain credit status data corresponding to credit-scene-specific trigger indicators, transaction behavior data corresponding to transaction-scene-specific trigger indicators, and associated party risk transmission data corresponding to associated-scene-specific trigger indicators. The correlation relationship data acquisition unit is configured to integrate the credit status data, the transaction behavior data, and the associated party risk transmission data to obtain scene-indicator correlation relationship data. The associated risk transmission abnormal information acquisition unit is configured to acquire associated risk transmission abnormal information according to the scene-indicator correlation relationship data. The fitting degree data acquisition unit is configured to compare the fitting degrees of real-time trigger indicator data of the credit scene, the transaction scene, and the associated scene with scene trigger condition data according to the associated risk transmission abnormal information to obtain indicator-condition fitting degree data. The determination result data acquisition unit is configured to acquire scene risk monitoring start determination result data according to the indicator-condition fitting degree data. The judging unit is configured to determine whether the scene risk monitoring start determination result data meets a preset regulation. If the determination result is that the fitting degree meets the requirement, it is determined that the corresponding scene enters a risk monitoring state. If the determination result is that the fitting degree does not meet the requirement, it is determined that the scene does not enter the risk monitoring state.

[0013] The application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the risk monitoring method based on dynamic threshold early warning.

[0014] The application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the risk monitoring method based on dynamic threshold early warning.

[0015] Compared with the related art, the risk monitoring method based on dynamic threshold early warning provided by the application has at least the following technical effects: The application integrates credit, transaction and correlation scenarios, covers multi-dimensional risk sources, avoids risk omissions caused by single data source analysis, realizes comprehensive control of systemic risk, captures risk transmission rules through cross-scenario risk feature correlation analysis and trend feature quantity extraction, can dynamically predict the evolution direction of risk compared with traditional static evaluation, greatly improves the forward-looking of early warning, improves the accuracy of risk assessment through data standardization processing, multi-dimensional fusion and comprehensive risk indicator quantification, the grading early warning mechanism can accurately adapt to the needs of multiple scenarios, and avoids excessive response or insufficient response.

[0016] The details of one or more embodiments of the present application are presented in the following drawings and description to make other features, objects and advantages of the present application more apparent. BRIEF DESCRIPTION OF DRAWINGS

[0017] The drawings described herein are intended to provide further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute an improper limitation on the present application. In the drawings: Figure 1 The method flowchart of an embodiment of the present application.

[0018] Figure 2 The system structure schematic diagram of an embodiment of the present application.

[0019] Figure 3 The internal structure schematic diagram of a computer device of an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical scheme and advantages of the present application more clear and apparent, the present application is described and explained below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application. Based on the embodiments provided by the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0021] Obviously, the drawings in the following description are only some examples or embodiments of the present application, and for those of ordinary skill in the art, the present application can be applied to other similar scenarios without creative labor. In addition, it can be understood that although the efforts made in this development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacture or production changes based on the technical content disclosed in the present application are only routine technical means, and should not be understood as insufficient disclosure of the content disclosed in the present application.

[0022] Reference to an "embodiment" in this application means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of other embodiments. It is expressly understood that the embodiments described in this application are open-ended and that additional embodiments that are presently unforeseeable over and above the described embodiments, such as modifications and improvements, will occur to one skilled in the art upon a careful reading of the disclosure.

[0023] Unless otherwise defined, all technical and scientific terms used in the application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terms "comprise", "comprising", "comprises" and "comprising" as used herein are used in their broadest sense, and are used in conjunction with open-ended language such as "comprising" and "including", but also include the more restrictive terms, such as "consisting of", "consisting essentially of" and "substantially comprised of". The terms "comprise", "comprising", "comprises" and "comprising" as used herein are used in their broadest sense, and are used in conjunction with open-ended language such as "comprising" and "including", but also include the more restrictive terms, such as "consisting of", "consisting essentially of" and "substantially comprised of". The terms "connected", "coupled", "attached", and the like, unless otherwise defined, are used in their broadest sense and encompass both direct and indirect connections, couplings, attachments, and the like. The term "multiple" means two or more. The term "and / or" describes association between name objects. It indicates that there are three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects. The terms "first", "second", "third", and the like are merely used to distinguish similar objects, and do not represent a specific order of the objects.

[0024] Embodiment 1 The embodiment of the application provides a risk monitoring method based on dynamic threshold early warning. Figure 1 is a flow chart according to an exemplary embodiment. As shown in Figure 1 , it comprises: S1, acquiring risk trigger information in multiple scenarios, and acquiring credit type scenarios, transaction type scenarios, and association type scenarios according to the risk trigger information, S2, judging whether the credit type scenarios, the transaction type scenarios, and the association type scenarios enter a risk monitoring state, if entering the risk monitoring state, acquiring structured monitoring data of the multiple scenarios, and acquiring historical credit change data of the credit type scenarios, real-time transaction flow data of the transaction type scenarios, and association party risk exposure data of the association type scenarios according to the structured monitoring data; S3, acquiring cross-scenario risk features according to the historical credit change data and real-time transaction flow data, and acquiring multi-scenario basic risk features according to the cross-scenario risk features; S4, acquiring associated risk features according to the historical credit change data and associated party risk exposure data, and acquiring trend feature quantities according to the associated risk features; S5, generating a comprehensive risk index according to the multi-scenario basic risk features and the trend feature quantities; S6, judging whether the comprehensive risk index is greater than a preset safety threshold; If less, continuously monitoring; If greater, acquiring a risk level according to the comprehensive risk index, and acquiring a multi-scenario adaptive graded early warning information according to the risk level.

[0025] As described in S1-S6 above, the present application integrates risk trigger information of credit scenarios, transaction scenarios and associated scenarios, extracts cross-scenario risk features and trend feature quantities, generates a comprehensive risk index, and then determines whether to start risk monitoring, graded early warning or response measures according to the index, solves the problem that single-scenario risk assessment cannot comprehensively cope with systemic risks, and realizes accurate identification and timely disposal of multi-dimensional risks. From a physical point of view, risk management is a dynamic and complex process. With the continuous change of credit environment, market transaction mode and associated party behavior, single-scenario assessment cannot cover potential systemic risks, especially in the case of high correlation of multi-scenario data, traditional methods cannot accurately identify risk transmission effects, therefore a forward-looking dynamic monitoring system integrating multi-scenario data needs to be built to timely capture risk signs and prevent spread. The deficiency of the prior art is that traditional risk monitoring focuses on a single scenario, lacks deep integration of cross-scenario risk correlation effects, and can only judge risks within a specific scenario, and cannot comprehensively and real-time assess multi-dimensional systemic risks. The present application integrates multi-scenario risk trigger information, and each step is based on cross-scenario data integration ideas, ensuring the comprehensiveness and accuracy of risk monitoring.

[0026] Multi-scenario risk trigger information is collected from API interfaces, internal databases, data scraping tools and other channels, including historical transaction data, credit data, associated party behavior data, etc. Then the information is classified by clustering algorithm, rule engine, etc. into credit, transaction and association scenarios; risk trigger information is the basis of risk assessment, and the information of each scenario is the preliminary signal of potential risk. Classification and extraction can lay a data foundation for subsequent monitoring, for example, in the financial scenario, large high-frequency transactions of accounts can trigger transaction class alarms, and credit score fluctuations trigger credit class monitoring.

[0027] By decision tree, random forest model or rule logic, according to the risk trigger information of each scene, the threshold is set to judge whether to enter the risk monitoring state, if the information exceeds the threshold, the monitoring is started; The preliminary screening of the risk state prevents the spread of high-risk scenarios to other fields, such as when a user transfers a large amount of money to an unknown account, the transaction scenario will automatically enter the monitoring state.

[0028] Based on historical credit change data and real-time transaction flow data, principal component analysis (PCA), neural network and other feature extraction algorithms are used to fuse data and extract cross-scene risk features; The physical meaning of this step is to mine the potential correlation of multiple scenes, and the risk of a single scene may not be significant, but joint analysis can discover deep risk patterns, for example, a user's transaction and credit are abnormal in multiple scenes, and the cross-scene risk features will be higher than normal.

[0029] Extract historical credit change data and associated risk exposure data, and then fuse the data through time series analysis, clustering and other methods to extract associated risk features and finally calculate trend feature quantities; Capture the dynamic changes of credit risk and the risk transmission effect of associated parties, for example, a certain enterprise credit score fluctuates greatly within three months, and the associated supplier's financial situation deteriorates, which can generate a "credit risk transmission index" to predict risk evolution.

[0030] Quantify the basic risk features of each scene, and then synthesize the comprehensive risk index by weighted average or machine learning algorithm according to the contribution of the scene to the overall risk; Reflect the overall risk level of the subject comprehensively, avoid one-sidedness of single scene evaluation, for example, the market, credit and operational risk indexes of a certain enterprise are 0.6, 0.7 and 0.5 respectively, and the weighted comprehensive index is 0.6, which provides a comprehensive basis for decision-making.

[0031] Based on historical data and industry standards, set a safety threshold, and then compare the comprehensive risk index with the threshold, if the index exceeds the threshold, intervention is needed, otherwise continuous monitoring; The physical meaning is that the threshold is the safety boundary of risk bearing, which can avoid unnecessary intervention, the threshold setting of traditional method is rough and static, while the dynamic comparison realizes intelligent control, ensuring that the response is started only when the risk is truly exceeded, for example, the index exceeds the threshold to trigger a graded early warning, otherwise keep regular monitoring. Through the integration and dynamic analysis of multi-scene data, the risk assessment is significantly improved in terms of forward-looking and accuracy, providing scientific support for risk management.

[0032] In one embodiment, the step of judging whether the credit scenario, transaction scenario, and associated scenario enter the risk monitoring state comprises: S201, split the risk trigger information under multiple scenes according to the scene category to obtain credit state data corresponding to credit scenario exclusive trigger indicators, transaction behavior data corresponding to transaction scenario exclusive trigger indicators, and associated party risk transmission data corresponding to associated scenario exclusive trigger indicators; S202, scene-index association relationship data is obtained according to the credit status data, the transaction behavior data and the associated party risk transmission data integration; S203, associated risk transmission abnormal information is obtained according to the scene-index association relationship data; S204, index-condition fit degree data is obtained by respectively comparing the real-time trigger index data of the credit type scene, the transaction type scene and the association type scene with the scene trigger condition data according to the associated risk transmission abnormal information; S205, scene risk monitoring start determination result data is obtained according to the index-condition fit degree data; S206, whether the scene risk monitoring start determination result data meets the preset regulation or not; If yes, the determination result is that the fit degree meets the requirement, and it is determined that the corresponding scene enters the risk monitoring state; If no, the determination result is that the fit degree does not meet the requirement, and it is determined that the scene does not enter the risk monitoring state.

[0033] In summary, the present application can accurately determine the risk monitoring start condition of each scene by fine splitting, integrating and multi-dimensional comparison of multiple types of risk data, identify and respond to potential risks in time, and avoid the spread of single scene risk or cross-scene risk transmission causing systemic problems. From step S201, the risk characteristics of each scene need to be embodied by exclusive trigger indexes and data types. Only by extracting risk trigger information according to scene classification can a foundation be laid for subsequent targeted analysis. The deficiency of traditional technology is that it adopts a global unified data processing method, ignores the differences in risk performance of different scenes, and leads to information disorder and fuzzy analysis, which cannot accurately locate the risk source. The solution is to first collect multiple scene risk trigger information from API interfaces, internal databases and other channels, and then split the information according to scene categories through clustering algorithms, rule engines and other technologies to form credit status data exclusive to credit type scenes, transaction behavior data exclusive to transaction type scenes and associated party risk transmission data exclusive to association type scenes. For example, in the financial field, credit score fluctuations of an account can be classified as credit status data, and large high-frequency transfers can be classified as transaction behavior data, which clearly defines the data boundary for subsequent analysis.

[0034] By integrating the split data of different scenarios, the correlation between scenarios and risk indicators is established, forming a unified analysis perspective to explore the potential connection of cross-scenario risks. The defect of traditional technology is that it processes different types of data sources separately, lacks cross-scenario and cross-indicator data fusion and correlation analysis capability, and cannot identify the transmission path between risks, reducing the accuracy of risk monitoring. Through data integration algorithm, trigger data of credit, transaction and association scenarios are included in a unified correlation model. This model can reflect the internal relationship between risk indicators in different scenarios, such as using historical credit data of credit scenarios to predict the risk occurrence probability of transaction scenarios, and identifying cross-border risk transmission risks through association scenarios' fund flow information, providing integrated data support for subsequent anomaly detection.

[0035] From the integrated scenario-indicator correlation data, abnormal correlation patterns are mined. These abnormal patterns often represent potential risk transmission paths and are important signals of risk hazards. Traditional technology relies on a single data source or simple statistical models for anomaly detection, which cannot cover multi-dimensional and cross-scenario risk transmission anomalies, and is prone to miss deep risks. Through complex anomaly detection algorithm, the abnormal rules in scenario-indicator correlation data are analyzed, such as in association scenarios, by analyzing the fund flow frequency and amount changes between different enterprises, it can be found that the credit deterioration of an enterprise may be transmitted to its partners through the fund chain, thus identifying the abnormal transmission chain of "credit problem-fund flow-risk diffusion", and providing key basis for risk prediction.

[0036] By comparing real-time trigger indicator data with preset scenario trigger conditions, the degree of fit is calculated to dynamically judge the risk occurrence probability of the scenario. The higher the degree of fit, the greater the risk possibility. This provides a dynamic reference for risk monitoring start. Traditional technology relies on fixed preset risk thresholds, which is difficult to adapt to real-time changes in scenario conditions and data fluctuations, and is prone to false positives or false negatives. Combined with dynamic threshold adjustment mechanism, real-time trigger indicator data and scenario trigger condition data are compared, and the degree of fit is calculated through cosine similarity, Euclidean distance, etc. If the degree of fit reaches the set standard (such as the real-time frequency of a transaction scenario and the abnormal trigger condition fit degree exceeds 80%), it is preliminarily determined that the risk possibility of this scenario is high, providing quantitative basis for subsequent start decision.

[0037] Based on the index-condition matching degree data, multiple factors need to be considered to ensure accuracy; traditional technology often uses a single index threshold to determine the monitoring start, which may cause errors due to the complexity of risk factors being ignored in multiple scenarios and multiple data environments; by using a weighted average algorithm, multiple dimension risk trigger indicators (such as credit scenario score fluctuation range, transaction scenario amount abnormality degree, and correlation scenario conduction speed) are combined to optimize the matching degree data, for example, higher weight is given to high-impact indicators (such as sudden credit score drop), and finally the scenario risk monitoring start determination result data is generated to avoid decision bias caused by a single indicator.

[0038] The scenario risk monitoring start determination result is finally compared with the preset monitoring start condition to determine whether the scenario enters the risk monitoring state, which is the final decision link of the risk monitoring process; traditional risk monitoring systems rely on static rules and lack flexibility and dynamic adjustment capability, and are prone to fail to respond to new risks due to rule lag; by comparing the determination result with the preset risk monitoring standard and adjusting the strategy flexibly according to real-time data changes, if the determination result meets the preset regulation (such as the matching degree exceeding the threshold for 5 minutes and the risk trend rising), it is determined that the corresponding scenario enters the risk monitoring state; if it does not meet the condition, it is determined that the scenario does not enter the monitoring state, thereby avoiding unnecessary resource waste and misjudgment.

[0039] In one embodiment, the step of acquiring structured monitoring data of multiple scenarios and acquiring historical credit change data of credit scenarios, real-time transaction flow data of transaction scenarios, and associated party risk exposure data of associated scenarios according to the structured monitoring data comprises: S207, acquiring structured monitoring data collection dimension data corresponding to credit scenarios, transaction scenarios, and associated scenarios according to the structured monitoring data; S208, acquiring credit scenario data storage source information, transaction scenario data storage source information, and associated scenario data storage source information according to the collection dimension data of the structured monitoring data of credit scenarios, transaction scenarios, and associated scenarios; S209, acquiring corresponding credit scenario original data, transaction scenario original data, and associated scenario original data according to the credit scenario data storage source information, transaction scenario data storage source information, and associated scenario data storage source information; S210, performing field integrity check on the credit scenario original data, transaction scenario original data, and associated scenario original data to obtain credit scenario standardized data, transaction scenario standardized data, and associated scenario standardized data; S211, acquiring historical credit change data according to the credit scenario standardized data; S212, acquiring real-time transaction flow data according to the transaction scenario standardized data; S213, obtaining associated party risk exposure data according to the associated scenario standardized data.

[0040] In summary, the present application identifies the structured monitoring data collection dimensions of credit, transaction and association scenarios according to the system preset rules. These dimensions clearly define the boundaries and core content of data collection for each scenario. The credit scenario collection dimensions include historical credit score, overdue records, loan repayment, etc. The transaction scenario collection dimensions include transaction time, transaction amount, transaction party identity information, transaction purpose, etc. The association scenario collection dimensions include associated party fund flow record, cooperation time, guarantee relationship, associated party credit status, etc. This step clearly defines the collection dimensions to ensure that the subsequent collected data is complete and has analysis value, avoiding data loss or redundancy due to ambiguous dimensions. For example, in the financial field, the credit scenario needs to collect the credit score change dimension in the past three years to ensure accurate analysis of credit trends.

[0041] Based on the determined collection dimensions of each scenario, the corresponding data storage source information is further obtained. These information includes data storage location, data format, access permission and data update frequency. Since multi-scenario data is often scattered in different database systems or even across data centers, the mapping and matching of collection dimensions and storage sources is realized through automated means.

[0042] According to the obtained data storage source information of each scenario, the original data is extracted from the corresponding storage source. The credit scenario original data is extracted from the credit database or third-party credit platform, the transaction scenario original data is extracted from the bank transaction system and e-commerce platform transaction log, and the association scenario original data is extracted from the association business management system and enterprise cooperation archives. The technical core of this step is to design an efficient and secure data retrieval mechanism. For example, distributed data synchronization technology is used to extract data from multiple storage sources in parallel, encrypted transmission protocols are used to ensure data security, and data integrity check points are set to avoid data omission or incorrect acquisition, ensuring that the original data can fully reflect the actual situation of each scenario.

[0043] Field integrity verification and standardization processing are carried out on the original data of the three types of scenarios: field integrity verification checks whether the data has missing key fields, format errors, numerical abnormalities, and missing fields are filled by interpolation of the same scenario and dimension data, format error data is converted in batches, and numerical abnormality data is marked and re-extracted; standardization processing unifies data of different formats and units into system standard format, and finally outputs standardized data of credit, transaction and association scenarios.

[0044] The historical credit change data is extracted from the credit type scene standardized data, the fields related to the credit state change in the standardized data are screened, and the historical credit change data set is arranged in time sequence, for example, the credit score, overdue times, and unpaid loan amount of a subject in the past 24 months are monthly summarized, and the data can intuitively present the evolution trend of the credit status of the subject, and provide time sequence data support for subsequent analysis of the credit risk change rule and prediction of future credit behavior.

[0045] For the transaction type scene standardized data, real-time transaction flow data is extracted, the transaction timestamp, transaction amount, transaction party, transaction type and other fields in the standardized data are analyzed in real time, the real-time transaction flow list is generated according to the transaction occurrence order, the list includes the unique identification, occurrence time, core information and risk label of each transaction, the core of this step is to ensure real-time, the real-time analysis and flow generation of standardized data are realized through stream processing technology, and a data error correction mechanism is set to ensure that the real-time transaction flow data can accurately reflect the current transaction behavior of the subject, and provide data support for real-time monitoring of abnormal transactions and timely blocking of risks.

[0046] The associated party risk exposure data is extracted from the associated type scene standardized data, the risk related fields of the associated party in the standardized data are identified, the associated party risk exposure data set is screened and integrated according to the risk exposure definition, for example, the credit rating of an associated supplier of a subject is reduced from A level to C level, and the supplier still owes 1 million yuan of overdue goods to the subject, and this information will be included in the associated party risk exposure data. The technical difficulty of this step lies in comprehensive identification of associated parties and accurate definition of risk exposure, the associated party relationship graph is constructed to avoid missing associated parties, and the preset risk exposure judgment rule is used to ensure the accuracy, and finally the associated party risk exposure data can help to identify potential indirect risks and provide basis for preventing cross-subject risk transmission.

[0047] In one embodiment, the step of acquiring cross-scene risk features according to the historical credit change data and the real-time transaction flow data, and acquiring multi-scene basic risk features according to the cross-scene risk features, comprises: S301, acquiring the change trajectory of the credit state in different time periods according to the historical credit change data, to obtain credit change trajectory data; S302, identifying the trend direction and change amplitude features of the credit state according to the credit change trajectory data, to obtain credit trend feature data; S303, extracting the amount distribution, transaction object party distribution, and time distribution behavior features of the transaction according to the real-time transaction flow data of the transaction type scene, to obtain transaction behavior feature data; S304, acquiring cross-scene feature correlation data according to the credit trend feature data and the transaction behavior feature data; S305, according to the cross-scene feature association data, core associated features capable of jointly reflecting risks are screened out, and cross-scene risk feature data is obtained; S306, according to the cross-scene risk feature data, multi-scene basic risk feature data is obtained.

[0048] In summary, the application extracts credit trend features and transaction behavior features through multi-dimensional analysis of credit scene historical data and transaction scene real-time data, screens out core risk features through cross-scene association analysis, and finally generates multi-scene basic risk feature data, which provides core data support for subsequent comprehensive and accurate risk assessment and early warning, and solves the problem of incomplete and inaccurate risk identification caused by traditional technology relying on single scene or single dimension data. From the physical meaning, the change of credit status has time sequence regularity, and the transaction behavior directly reflects the real-time activity of the subject. Both of them carry different scene risk information. Through time sequence tracing of credit data, trend extraction, and multi-dimensional feature extraction of transaction data, the potential risk patterns (such as the linkage of credit deterioration and abnormal transactions) that cannot be found in a single scene can be mined by integrating the two types of scene features. The screening of core risk features and the generation of basic risk features can further focus on key risk signals, reduce redundant data interference, and lay a precise data foundation for risk assessment.

[0049] Credit change trajectory data in different time periods is obtained through historical credit change data: technically, time series analysis techniques such as autoregressive model (AR), moving average method (MA), and exponential smoothing method are used to decompose historical credit data by period, fit the credit fluctuation trend of each period, mark the credit rising, falling or stable mode, and form a continuous trajectory; for example, a user's credit score dropped from 820 to 650 in 12 months due to multiple credit card overdue, and the time series model can capture this continuous decline trajectory and the sharp drop node after each overdue. This step traces the time sequence evolution of credit status, provides original time sequence data for subsequent trend analysis, and makes up for the limitations of traditional single time window data.

[0050] Credit trend feature data is generated based on credit change trajectory data to identify credit trend direction and change amplitude features: technically, linear regression model is used to judge long-term trend, moving average method and Holt-Winters exponential smoothing method are used to filter short-term noise, and standard deviation, variance and other indicators are calculated to evaluate fluctuation amplitude; distinguish the long-term trend (such as continuous deterioration) and short-term fluctuation of credit change, solve the problem that traditional static data cannot distinguish the nature of risk.

[0051] The transaction amount distribution, transaction object party distribution, and time distribution characteristics are extracted from the real-time transaction flow data of the transaction type scene to generate transaction behavior characteristic data: in terms of technology, the interval distribution of the transaction amount is counted to identify abnormal consumption, the transaction object type is analyzed to determine the transaction object risk, and the transaction time distribution is extracted to find time anomalies; the multi-dimensional transaction characteristics depict the subject's consumption habits and potential risks, such as a user transferring a high frequency of transactions to a stranger network merchant at night within a week, and the amount, object, and time distribution characteristics of the transaction will collectively point to abnormal transaction risks, making up for the one-sidedness of traditional single-dimensional transaction analysis.

[0052] Cross-scene characteristic association data is obtained through correlation analysis of the credit trend characteristic data and the transaction behavior characteristic data: in terms of technology, correlation analysis, collaborative filtering and other methods are used to obtain the correlation of the two types of characteristics, such as finding that “continuous decline in credit score” and “increase in large transaction frequency” and “increase in proportion of transactions with strangers” have strong correlation; the potential linkage between credit status and transaction behavior is revealed, breaking the traditional separation between credit and transaction analysis, such as a user's credit deterioration accompanied by an increase in abnormal transactions, which can be used as an important risk signal to provide direction for subsequent core feature selection.

[0053] Cross-scene risk characteristic data is generated by screening core associated features that can reflect risks together from cross-scene characteristic association data: in terms of technology, the data is first standardized to ensure comparability, and then chi-square test, mutual information, Pearson correlation coefficient and other methods are used to calculate the correlation between features, and features with strong correlation in multiple scenes are screened out to eliminate redundant features; focus on multi-scene common risk features to reduce irrelevant data interference, such as the selected “credit score monthly drop over 50 points and proportion of transactions with strangers over 30%”, which can accurately point to the situation where high credit risk and transaction risk coexist, solving the problem of narrow coverage of traditional single-scene features.

[0054] Multi-scene basic risk characteristic data is obtained based on cross-scene risk characteristic data: in terms of technology, the core feature data is first integrated into a unified data set, then principal component analysis is used for dimensionality reduction to reduce redundancy, similar features are aggregated through clustering analysis, and finally standardized processing is performed to generate basic risk feature data that adapts to multiple scenes; the cross-scene core risk features are further integrated and optimized to form a simple and unified risk data set, such as “credit-transaction linkage risk factor 0.85” which can directly represent a high risk level, providing standardized input for subsequent comprehensive risk index calculation, solving the problem of traditional multi-scene data integration and poor comparability.

[0055] In one embodiment, the step of obtaining the associated risk features according to the historical credit change data and the associated party risk exposure data, and obtaining the trend feature quantity according to the associated risk features, comprises: S401, extracting a credit state and an association dimension of the associated party according to the historical credit change data, to obtain credit association dimension data; S402, extracting a risk type, exposure scale and influence range risk dimension of the associated party according to the associated party risk exposure data, to obtain associated risk dimension data; S403, obtaining associated risk conduction analysis data according to the credit association dimension data and the associated risk dimension data; S404, obtaining associated risk feature data according to the associated risk conduction analysis data; S405, arranging the associated risk features in different time periods in time sequence according to the associated risk feature data, to form time sequence data of the associated risk features; S406, generating trend feature quantity data according to the associated risk feature time sequence data.

[0056] In summary, the application extracts the associated risk features that can reflect the linkage between the historical credit change data and the associated party risk exposure data, and then generates the trend feature quantity data of the quantifiable risk change law through the time sequence processing of these features, to finally provide accurate and comprehensive data support for subsequent risk analysis, early warning and decision making. The core is to solve the problems of single data source dependence, weak time sequence modeling capability and simplified risk dimension extraction in traditional risk analysis, to realize dynamic and deep control of the associated party risk conduction effect. From the physical meaning, with the increasing complexity of the financial market and the business environment, the risk conduction between the associated parties has become a key factor affecting the stable operation of enterprises. The historical credit change data is the "time sequence archive" of the credit status of enterprises, and the associated party risk exposure data is the "mapping carrier" of the risk conduction path. Combining the two types of data can not only discover potential associated risk signals (such as the linkage between the decline of enterprise credit score and the default of associated party debt) that cannot be found by single data source, but also can quantify the future evolution direction of risk through trend feature quantity, so as to optimize the foresight and pertinence of risk management, and avoid the risk of missed judgment caused by incomplete coverage in traditional single data dimension analysis.

[0057] According to historical credit change data, the credit state and the association dimension of the associated party are extracted, and credit association dimension data is generated The credit state of an enterprise is not isolated, and the financial health degree and cooperation stability of the associated party will directly affect the credit change of the enterprise, and vice versa, the credit fluctuation of the enterprise may also be transmitted to the associated party, and the extraction of the association dimension of the two can clearly define the basic association path of risk transmission; static credit data is mostly used to analyze the credit status of an enterprise, and the dynamic interaction relationship between the credit and the associated party is completely ignored, so that the potential influence of credit change on the risk exposure of the associated party cannot be captured; the solution of the present application is to extract the credit score, default record, debt repayment progress and other time sequence credit information of the enterprise at multiple time nodes from the historical credit change data, and then match the financial health score, cooperation business default situation, abnormal fund flow record and other information of the associated party at the corresponding time node from the associated party risk exposure data, align the two types of time sequence data according to the time dimension through the establishment of a mapping model of "enterprise credit index and associated party risk index", and finally form credit association dimension data that can reflect the dynamic association relationship between the two, laying a foundation for subsequent analysis of how credit change affects associated risk transmission.

[0058] According to the associated party risk exposure data, the risk type, exposure scale and influence range risk dimension of the associated party are extracted, and associated risk dimension data is obtained The risk of the associated party is not a single form, and the risk impact on the enterprise is greatly different for different risk types, different exposure scales and different influence ranges, and the real characteristics of the associated party risk can be completely described by comprehensively extracting these dimensions; risk analysis is often only dependent on a single risk indicator, which ignores the comprehensive effect of different types of risks such as market risk and credit risk, and also fails to consider the transmission chain of risks among different associated parties; the solution of the present application is to realize multi-dimensional extraction through multi-channel data analysis: for the risk type, analyze the profit fluctuation reason, contract default clause, regulatory penalty record and the like in the financial statements of the associated party, and define the risk category; for the exposure scale, the cumulative debt amount, unfulfilled contract amount, abnormal fund occupation amount and the like of the associated party in the cooperation period are counted, and the specific risk exposure value is calculated; for the influence range, combined with industry database, market research report and enterprise cooperation network atlas, the cooperation business range, upstream and downstream enterprise quantity and industry field that may be affected by the risk of the associated party are evaluated, and finally these information is integrated to generate associated risk dimension data, and the overall risk characteristics of the associated party are completely presented.

[0059] The two types of dimension data extracted in the first two steps of obtaining the correlation risk transmission analysis data according to the credit correlation dimension data and the correlation risk dimension data provide basic information from the perspectives of "credit correlation" and "correlation risk". Only by analyzing the two can the specific risk transmission mechanism between the enterprise and the associated party be revealed, such as whether the decrease of the enterprise credit score will lead to the tightening of the cooperation and credit of the associated party, or whether the credit risk of the associated party will affect the debt repayment ability of the enterprise. The credit analysis and risk exposure analysis are generally carried out separately, that is, only the credit risk of the enterprise is evaluated, or only the risk exposure of the associated party is analyzed, lacking systematic research on the interaction between the two, and unable to deeply explore the deep influence of credit change on correlation risk transmission. The solution of the present application is to build a multi-dimensional correlation analysis model, to correlate the indicators such as "enterprise credit change amplitude, credit deterioration duration" in the credit correlation dimension data with the indicators such as "associated party risk type, exposure scale growth rate" in the correlation risk dimension data: to analyze the linear correlation between the two by using Pearson correlation coefficient, to determine the causal direction of credit change and correlation risk exposure by using causality test (such as Granger causality test), to quantify the influence coefficient of credit change on correlation risk exposure by regression analysis, and finally to generate correlation risk transmission analysis data containing risk transmission path, transmission strength and transmission cycle, to provide basis for accurately predicting risk transmission trend.

[0060] Although the correlation risk transmission analysis data reveals the transmission mechanism, it still belongs to multi-dimensional original analysis results, and the core features with clear risk indication significance need to be extracted from it. These features are the key basis for judging the severity of correlation risk and formulating countermeasures. Limited to identifying a single risk source, lacking comprehensive and deep analysis of correlation risk features, and unable to extract effective early warning signals for future risks from the transmission data. The solution of the present application is to extract features from the correlation risk transmission analysis data by data mining technology: for risk fluctuation characteristics, calculate the standard deviation and coefficient of variation of the exposure scale of correlation risk in different time periods to obtain the risk fluctuation amplitude; for risk transmission efficiency characteristics, calculate the average time from the occurrence of credit change to the appearance of correlation risk exposure to obtain the risk transmission time delay; for risk periodicity characteristics, analyze the periodicity of the change of risk exposure scale with time by Fourier transform to obtain the risk fluctuation period; integrate these extracted features into structured correlation risk feature data to provide clear feature dimensions for subsequent time series analysis.

[0061] According to the correlation risk characteristic data, the correlation risk characteristics in different time periods are arranged in time sequence to form time sequence data of the correlation risk characteristics. The correlation risk characteristics are not fixed and unchangeable, but dynamically evolve over time. Arranging the characteristics into time sequence data according to time periods can intuitively show the evolution trajectory of the risk characteristics, and provide support for discovering long-term trends and short-term abnormalities. The processing of time sequence data is extremely rough, and most of the analysis is performed using quarterly or annual summary data, which cannot capture the details of the changes of the correlation risk characteristics in a finer time dimension, resulting in the inability to accurately identify the turning point of the risk trend. The solution of the present application is to first determine a reasonable time period, and then arrange the characteristic indicators such as 'amplitude of fluctuation, conduction time delay, periodicity' in the correlation risk characteristic data in time sequence according to the time period to form the time sequence corresponding to each characteristic indicator. Then, the sequence is optimized using time sequence preprocessing technology, and algorithms such as ARIMA model and LSTM network are used to mine the time dependence and potential change pattern in the sequence, and finally the correlation risk characteristic time sequence data that can clearly reflect the evolution law of the correlation risk characteristics over time is generated.

[0062] The trend characteristic quantity data generated according to the correlation risk characteristic time sequence data is a quantitative presentation of the correlation risk change trend, which can convert abstract time sequence data into intuitive and quantitative information that can be used for decision-making, provide timely and accurate trend signals for the risk early warning system, and help decision-makers to develop response measures in advance. The prediction of the risk trend mostly relies on artificial experience or simple rules, lacks systematic and scientific prediction based on historical time sequence data, and has low prediction accuracy and strong subjectivity. The solution of the present application is to process the correlation risk characteristic time sequence data using various trend analysis algorithms: for linear trend characteristics, a trend line is fitted using the least squares method to calculate the trend slope; for nonlinear trend characteristics, exponential smoothing method is used to process the seasonal and periodic fluctuations in the sequence to predict future trend changes; the trend quantitative results output by these algorithms are integrated to generate trend characteristic quantity data, which can not only accurately predict the change direction and amplitude of the correlation risk in a period of time in the future, but also provide reliability evaluation of trend prediction, and provide scientific and reliable basis for subsequent risk monitoring and decision-making.

[0063] In one embodiment, the step of generating a comprehensive risk index according to the multi-scene basic risk characteristics and trend characteristics includes: S501, extracting basic risk dimension data reflecting credit and basic risk dimension data of transaction cross-scene risk according to multi-scene basic risk characteristic data; S502, extracting trend risk dimension data reflecting the trend of correlation risk change according to trend characteristic quantity data; S503, generating risk data fusion data according to the credit reflecting basic risk dimension data, the transaction cross-scene risk basic risk dimension data and the trend risk dimension data; S504, obtaining the fused risk data according to the risk data fusion data; S505, obtaining the risk quantification data according to the fused risk data; S506, obtaining the comprehensive risk index data according to the risk quantification data.

[0064] To sum up, the application generates comprehensive risk index data according to multi-scene basic risk characteristics and trend characteristic quantity, and finally obtains comprehensive risk index data reflecting the overall risk situation through multi-step data fusion and quantification processing, thereby providing quantitative basis for risk management and assisting decision support. In the face of complex and variable risk environment, a single risk dimension cannot fully present the overall risk situation, especially in the fields of credit and transaction cross-scene, multi-dimensional fusion data is needed to obtain a more representative risk index to accurately assess risks and respond to variable market conditions and complex business scenarios. In the prior art, risk index generation often relies on single-dimensional evaluation or only focuses on specific scenes, ignoring the interaction of multi-scene and trend characteristics, and can only give static evaluation, which is difficult to cope with dynamic complex situations. Therefore, the application innovatively proposes a comprehensive risk assessment method based on multi-scene basic risk characteristic data and trend characteristic data, which extracts multi-dimensional risk data, integrates multi-source data using fusion algorithm and quantifies it into comprehensive risk index, thereby solving the problem of insufficient integration of multi-scene multi-dimensional risk information in traditional technology and improving the accuracy and dynamic adaptability of risk assessment.

[0065] According to the multi-scene basic risk characteristic data, the credit reflecting basic risk dimension data and the transaction cross-scene risk basic risk dimension data are extracted: the basic risk dimension data is a preliminary measurement of risk, which can reflect the core factors affecting risk, and the credit and transaction cross-scene dimension data are extracted specifically, which can ensure the coverage of two key risk sources; the extraction of multi-scene basic risk characteristics is relatively extensive, and the core risk dimensions of different scenes are not accurately distinguished, which is easy to miss the key risk information of credit or transaction cross-scene; the technical implementation needs to collect multi-scene original data first, clean and denoise the data to ensure accuracy, and then use feature extraction technologies such as principal component analysis and clustering algorithm, and adjust the extraction strategy flexibly according to the needs of different scenes, analyze user credit history, payment ability and other information for credit basic risk dimension data; for transaction cross-scene risk basic risk dimension data, focus on mining risk interaction and transmission characteristics between different scenes, and finally obtain two types of basic risk dimension data.

[0066] According to the trend characteristic quantity data, trend risk dimension data reflecting the change trend of the associated risk is extracted: the risk change trend can reveal the evolution law of the risk at different times and scenes, and is the key basis for predicting the future risk trend; although the traditional technology can make trend judgment through time series analysis, it can only capture short-term data fluctuations and cannot comprehensively cover long-term change trends, especially in a multi-scene and multi-dimensional data environment, it is difficult to identify potential associated risk trends; the technical implementation adopts a method combining time series analysis and machine learning, first processes the historical trend characteristic quantity data, extracts long-term and short-term risk trend information through moving average, exponential smoothing and other methods, then introduces decision tree, support vector machine and other machine learning algorithms to analyze the relevance of these trend information and historical risk events, and finally forms trend risk dimension data that can reflect the evolution law of the associated risk over time, providing reliable support for subsequent risk prediction.

[0067] According to the basic risk dimension data reflecting credit, the basic risk dimension data of transaction cross-scene risk and the trend risk dimension data, risk data fusion data is generated: through multi-dimensional data fusion, the local limitations of single data source can be eliminated, and different dimensional risk information can be integrated, so that the comprehensive state of the risk can be more comprehensively and accurately reflected, and the comprehensiveness and prediction accuracy of risk assessment can be improved; the data fusion method of the traditional technology is relatively simple, and is mostly focused on a single dimension or scene, and the correlation between dimensions is not fully utilized, resulting in insufficient precision of the fusion result; the technical implementation adopts a weighted fusion algorithm, first determines the weighted coefficients of the dimensional data through regression analysis according to the historical risk data and expert experience, for example, the credit basic risk dimension weight is 0.4, the transaction cross-scene risk dimension weight is 0.3, and the trend risk dimension weight is 0.3; then the three types of dimensional data are weighted and summed according to the weighted coefficients, the correlation between the dimensions is fully utilized, and finally the risk data fusion data covering the multi-scene and trend change characteristics is obtained.

[0068] According to the risk data fusion data, the fused risk data is obtained: the fused risk data is the basic input for subsequent risk quantification analysis, and needs to comprehensively reflect the comprehensive influence of different dimensional risks to ensure that it can provide a real and consistent data source for quantification processing; the technical implementation needs to further process the risk data fusion data, first carries out data normalization, standardization and other preprocessing to eliminate data format and magnitude differences; then adopts a fusion method with strong numerical stability to check and correct abnormal values that may occur in the fusion process, ensures the accuracy and consistency of the data in the calculation process, and finally outputs the fused risk data that can truly reflect the risk status.

[0069] According to the risk data after fusion, risk quantitative data is obtained: the risk quantitative data converts abstract risk information into operable digital indicators, can clearly present the severity of risk, and provides a scientific basis for the actual operation of risk management; the technical implementation adopts professional quantitative algorithms, such as converting the risk data after fusion into standardized risk values through risk coefficient calculation, so that the manager can intuitively understand the risk size, for example, the risk quantitative score of a certain subject is 75 points, indicating that it is at a high risk level.

[0070] According to the risk quantitative data, comprehensive risk index data is obtained: the comprehensive risk index data is the final quantitative result of all risk data, and is the core tool of risk management decision, which needs to accurately quantify the comprehensive risk level in different scenarios, and provides a direct basis for enterprise risk decision; the technical implementation adopts weighted average or multi-dimensional fusion method, based on risk quantitative data, combined with risk preference of different business scenarios, to calculate the comprehensive risk index, for example, when using the weighted average method, the quantitative sub-items related to credit, transaction and correlation trend in the risk quantitative data are weighted according to the preset weight, and finally the comprehensive risk index data is generated; the index can uniformly quantify the comprehensive risk level in multiple scenarios, help enterprises clearly identify the risk level, and then make accurate risk response decisions.

[0071] Embodiment 2 The application also provides a risk monitoring and multi-scenario adaptation system based on dynamic threshold early warning, as shown in Figure 2 , comprising: A data acquisition module 1 is used for acquiring risk trigger information in multiple scenarios, and acquiring historical credit change data of a credit scenario, real-time transaction flow data of a transaction scenario, and correlation party risk exposure data of a correlation scenario according to the risk trigger information. A first judgment module 2 is used for judging whether the credit scenario, the transaction scenario and the correlation scenario enter a risk monitoring state, if entering the risk monitoring state, acquiring structured monitoring data of multiple scenarios, and acquiring historical credit change data of the credit scenario, real-time transaction flow data of the transaction scenario, and correlation party risk exposure data of the correlation scenario according to the structured monitoring data. A multi-scenario basic risk feature acquisition module 3 is used for acquiring cross-scenario risk features according to the historical credit change data and the real-time transaction flow data, and acquiring multi-scenario basic risk features according to the cross-scenario risk features. A trend feature quantity acquisition module 4 is used for acquiring correlation risk features according to the historical credit change data and the correlation party risk exposure data, and acquiring trend feature quantities according to the correlation risk features. A comprehensive risk index generation module 5 is used for generating a comprehensive risk index according to the multi-scenario basic risk features and the trend feature quantities. A second judgment module 6 is used for judging whether the comprehensive risk index is greater than a preset safety threshold. If it is less than, continue monitoring; If the risk level is greater than the comprehensive risk index, then a risk level is obtained based on the comprehensive risk index, and a graded early warning information matching multiple scenarios is obtained based on the risk level.

[0072] In one embodiment, the first determination module 2 includes: The data acquisition unit is used to break down risk trigger information in multiple scenarios into credit status data corresponding to credit-related scenario-specific trigger indicators, transaction behavior data corresponding to transaction-related scenario-specific trigger indicators, and related party risk transmission data corresponding to related scenario-specific trigger indicators. The correlation data acquisition unit is used to integrate credit status data, transaction behavior data, and risk transmission data of related parties to obtain scenario-indicator correlation data. The associated risk transmission anomaly information acquisition unit is used to acquire associated risk transmission anomaly information based on scenario-indicator correlation data; The matching data acquisition unit is used to compare the matching degree between real-time trigger indicator data and scenario trigger condition data of credit scenario, transaction scenario and related scenario based on the abnormal information of related risk transmission, and to obtain indicator-condition matching degree data. The judgment result data acquisition unit is used to acquire the scenario risk monitoring start judgment result data based on the indicator-condition fit data. The judgment unit is used to determine whether the data from the scenario risk monitoring startup meets the preset requirements. If the conditions are met, the result is that the fit meets the requirements, and the corresponding scenario is determined to enter the risk monitoring state. If it does not meet the requirements, the result is that the fit is not met, and the scenario will not be put into risk monitoring for the time being.

[0073] Example 3 like Figure 3 As shown, Embodiment 3 of the present invention provides a computer device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the risk monitoring method for dynamic threshold early warning described above.

[0074] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the risk monitoring method for dynamic threshold-based early warning described above.

[0075] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific and detailed manner, but should not be construed as limiting the scope of the patent. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these are all within the scope of the present application. Therefore, the scope of protection of the patent of the present application should be subject to the appended claims.

Claims

1. A method of risk monitoring based on dynamic threshold early warning, characterized in that, Comprise: acquire risk trigger information under multiple scenes, and acquire credit type scene, transaction type scene, and correlation type scene according to the risk trigger information, determine whether the credit type scene, the transaction type scene, and the correlation type scene enter a risk monitoring state, if the risk monitoring state is entered, acquire structured monitoring data of multiple scenes, and acquire historical credit change data of the credit type scene, real-time transaction flow data of the transaction type scene, and correlation party risk exposure data of the correlation type scene according to the structured monitoring data; acquire cross-scene risk characteristics according to the historical credit change data and the real-time transaction flow data, and acquire multiple scene basic risk characteristics according to the cross-scene risk characteristics; acquire correlation risk characteristics according to the historical credit change data and the correlation party risk exposure data, and acquire trend characteristic quantities according to the correlation risk characteristics; generate a comprehensive risk index according to the multiple scene basic risk characteristics and the trend characteristic quantities; determine whether the comprehensive risk index is greater than a preset safety threshold; if less than, continue to monitor; if greater than, acquire a sub-risk level according to the comprehensive risk index, and acquire a sub-level early warning information matched with multiple scene adaptation according to the sub-risk level.

2. The risk monitoring method based on dynamic threshold early warning according to claim 1, characterized in that, The step of determining whether the credit type scene, the transaction type scene, and the correlation type scene enter a risk monitoring state comprises: splitting risk trigger information under multiple scenes according to scene categories to obtain credit state data corresponding to credit type scene exclusive trigger indexes, transaction behavior data corresponding to transaction type scene exclusive trigger indexes, and correlation party risk transmission data corresponding to correlation type scene exclusive trigger indexes; integrating the credit state data, the transaction behavior data, and the correlation party risk transmission data to obtain scene-index correlation relationship data; acquiring correlation risk transmission abnormal information according to the scene-index correlation relationship data; respectively comparing the real-time trigger index data of the credit type scene, the transaction type scene, and the correlation type scene with the scene trigger condition data according to the correlation risk transmission abnormal information to obtain index-condition fit degree data; acquiring scene risk monitoring start determination result data according to the index-condition fit degree data; determining whether the scene risk monitoring start determination result data meets a preset regulation; if meeting, determining that the corresponding scene enters a risk monitoring state because the fit degree meets the requirement; if not meeting, determining that the scene does not enter a risk monitoring state because the fit degree does not meet the requirement.

3. The risk monitoring method based on dynamic threshold early warning according to claim 1, characterized in that, The step of acquiring structured monitoring data of multiple scenes, and acquiring historical credit change data of the credit type scene, real-time transaction flow data of the transaction type scene, and correlation party risk exposure data of the correlation type scene according to the structured monitoring data comprises: acquiring credit type, transaction type, and correlation type scene corresponding structured monitoring data collection dimension data according to the structured monitoring data; acquiring credit type scene data storage source information, transaction type scene data storage source information, and correlation type scene data storage source information according to the collection dimension data of the credit type scene, the transaction type scene, and the correlation type scene corresponding structured monitoring data; According to the credit class scene data storage source information, the transaction class scene data storage source information, and the association class scene data storage source information, corresponding credit class scene original data, transaction class scene original data, and association class scene original data are obtained. Field integrity verification is performed on the credit class scene original data, the transaction class scene original data, and the association class scene original data to obtain credit class scene standardized data, transaction class scene standardized data, and association class scene standardized data. According to the credit class scene standardized data, historical credit change data is obtained. According to the transaction class scene standardized data, real-time transaction flow data is obtained. According to the association class scene standardized data, associated party risk exposure data is obtained.

4. The risk monitoring method based on dynamic threshold early warning according to claim 1, characterized in that, The step of obtaining cross-scene risk features according to the historical credit change data and the real-time transaction flow data, and obtaining multi-scene basic risk features according to the cross-scene risk features, includes: According to the historical credit change data, the change trajectory of the credit state in different time periods is obtained to obtain credit change trajectory data. According to the credit change trajectory data, the trend of the credit state and the change amplitude feature are identified to obtain credit trend feature data. According to the real-time transaction flow data of the transaction class scene, the amount distribution, the transaction object party distribution, and the time distribution behavior feature of the transaction are extracted to obtain transaction behavior feature data. According to the credit trend feature data and the transaction behavior feature data, cross-scene feature correlation data is obtained. According to the cross-scene feature correlation data, core correlation features that can jointly reflect risks are screened out to obtain cross-scene risk feature data. According to the cross-scene risk feature data, multi-scene basic risk feature data is obtained.

5. The risk monitoring method based on dynamic threshold early warning according to claim 1, characterized in that, The step of obtaining association risk features according to the historical credit change data and the associated party risk exposure data, and obtaining trend feature quantities according to the association risk features, includes: According to the historical credit change data, the association dimension of the credit state and the associated party is extracted to obtain credit association dimension data. According to the associated party risk exposure data, the risk type, exposure scale, and influence range risk dimension of the associated party are extracted to obtain association risk dimension data. According to the credit association dimension data and the association risk dimension data, association risk transmission analysis data is obtained. According to the association risk transmission analysis data, association risk feature data is obtained. According to the association risk feature data, the association risk features in different time periods are arranged in time sequence to form time series data of the association risk features. According to the association risk feature time series data, trend feature quantity data is generated.

6. The risk monitoring method based on dynamic threshold early warning according to claim 1, characterized in that, The step of generating a comprehensive risk index according to the multi-scene basic risk features and the trend feature quantities, includes: According to the multi-scene basic risk feature data, basic risk dimension data reflecting the credit and basic risk dimension data of transaction cross-scene risk are extracted. According to the trend feature quantity data, trend risk dimension data reflecting the change trend of the association risk are extracted. According to the basic risk dimension data reflecting the credit, the basic risk dimension data of transaction cross-scene risk, and the trend risk dimension data, risk data fusion data is generated. According to the risk data fusion data, fused risk data is obtained. According to the risk data after fusion, risk quantitative data is acquired; According to the risk quantitative data, comprehensive risk index data is acquired.

7. The risk monitoring and multi-scenario adaptation system based on dynamic threshold early warning, characterized in that, It comprises: A data acquisition module is configured to acquire risk trigger information in multiple scenarios, and acquire credit scenarios, transaction scenarios, and correlation scenarios according to the risk trigger information, A first judgment module is configured to judge whether the credit scenarios, transaction scenarios, and correlation scenarios enter a risk monitoring state, and if so, acquire structured monitoring data in multiple scenarios, and acquire historical credit change data of the credit scenarios, real-time transaction flow data of the transaction scenarios, and correlation party risk exposure data of the correlation scenarios according to the structured monitoring data; A multi-scenario basic risk feature acquisition module is configured to acquire cross-scenario risk features according to the historical credit change data and real-time transaction flow data, and acquire multi-scenario basic risk features according to the cross-scenario risk features; A trend feature quantity acquisition module is configured to acquire correlation risk features according to the historical credit change data and correlation party risk exposure data, and acquire trend feature quantities according to the correlation risk features; A comprehensive risk index generation module is configured to generate a comprehensive risk index according to the multi-scenario basic risk features and trend feature quantities; A second judgment module is configured to judge whether the comprehensive risk index is greater than a preset safety threshold; If less than, continue to monitor; If greater than, acquire a sub-risk level according to the comprehensive risk index, and acquire a sub-level early warning information matched with multi-scenario adaptation according to the sub-risk level.

8. The risk monitoring and multi-scene adapting system based on dynamic threshold early warning according to claim 7, characterized in that, The first judgment module comprises: A data acquisition unit is configured to split risk trigger information in multiple scenarios according to scenario categories to obtain credit state data corresponding to credit scenario-specific trigger indicators, transaction behavior data corresponding to transaction scenario-specific trigger indicators, and correlation party risk transmission data corresponding to correlation scenario-specific trigger indicators; An association relationship data acquisition unit is configured to integrate the credit state data, transaction behavior data, and correlation party risk transmission data to obtain scenario-indicator association relationship data; An associated risk transmission abnormal information acquisition unit is configured to acquire associated risk transmission abnormal information according to the scenario-indicator association relationship data; A fit degree data acquisition unit is configured to compare the real-time trigger indicator data of the credit scenarios, transaction scenarios, and correlation scenarios with the scenario trigger condition data according to the associated risk transmission abnormal information to obtain indicator-condition fit degree data; A determination result data acquisition unit is configured to acquire scenario risk monitoring start determination result data according to the indicator-condition fit degree data; A judgment unit is configured to judge whether the scenario risk monitoring start determination result data meets a preset regulation; If so, the determination result is that the fit degree meets the requirement, and it is determined that the corresponding scenario enters the risk monitoring state; If not, the determination result is that the fit degree does not meet the requirement, and it is determined that the scenario does not enter the risk monitoring state. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the method in any one of claims 1 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 6.

Images