Risk monitoring method and device based on equity relation thematic database and medium

Abstract

The embodiment of the invention discloses a risk monitoring method and device based on an equity relation thematic database and a medium, and relates to the technical field of e-commerce, and the method comprises the steps: determining an admission data source corresponding to an e-commerce platform through the pre-obtained registration information of a plurality of e-commerce, carrying out the data extraction and data mining in the admission data source, and carrying out the data extraction and mining in the admission data source; determining the equity structure data of each e-commerce and the equity association relationship data among the plurality of e-commerce; evaluating the equity structure data of each e-commerce, determining an e-commerce equity evaluation index corresponding to each e-commerce, and constructing an e-commerce equity relationship thematic database corresponding to the e-commerce platform based on the e-commerce equity evaluation index and the equity association relationship data; determining at least one target monitoring e-commerce, and determining a plurality of associated e-commerce; and setting a corresponding risk monitoring strategy, collecting real-time transaction activity data of the target monitoring e-commerce and the associated e-commerce on the e-commerce platform based on the risk monitoring strategy, and performing risk early warning by using the real-time transaction activity data.

Description

Technical Field

[0001] The present invention relates to the field of e-commerce technology, and in particular to a risk monitoring method, device and medium based on an equity relationship subject library. Background Art

[0002] In today's booming digital economy, the e-commerce industry is experiencing explosive growth. With the popularization of Internet technology and the change in consumer shopping habits, more and more merchants are flocking to e-commerce platforms, and the number of e-commerce companies is growing exponentially. The surge in the number of e-commerce companies has also brought unprecedented challenges to the management of e-commerce platforms. As a bridge connecting merchants and consumers, the management quality of e-commerce platforms is directly related to the platform's operating efficiency, user experience, and market competitiveness.

[0003] Among many management links, the equity structure directly affects the decision-making mechanism, business stability and future development direction of e-commerce. If there are hidden dangers in the equity structure of e-commerce on the e-commerce platform, such as excessive concentration of equity, frequent changes or pledge risks, it may lead to store management decision-making errors, broken capital chain or even sudden closure, which will have a serious impact on the platform. In addition, there may be situations where the equity relationships of multiple e-commerce companies are related in the e-commerce platform, which increases the systemic risk of the e-commerce platform. For example, there may be mutual guarantees or fund borrowing between related stores. Once a store cannot repay its debts, it may trigger a chain reaction, causing multiple related stores to fall into financial difficulties at the same time. Therefore, once the equity problem occurs, the loss and impact on the e-commerce platform are relatively large. When conducting risk monitoring of e-commerce, it is extremely important to conduct risk assessment of e-commerce through equity relationships. There are a large number of e-commerce companies and transaction activity data on the e-commerce platform. In the process of monitoring e-commerce, unified monitoring is prone to untimely monitoring and missed detection. In the case of e-commerce companies with high-risk equity relationships, the timeliness and accuracy of monitoring cannot be met.

[0004] Therefore, traditional risk monitoring methods do not consider the risks of e-commerce equity and lack targeted monitoring methods for e-commerce, resulting in risks in the management of e-commerce platforms. Summary of the invention

[0005] One or more embodiments of this specification provide a risk monitoring method, device and medium based on an equity relationship subject library, which is used to solve the following technical problems: traditional risk monitoring methods do not consider the risks of e-commerce equity and lack e-commerce targeted monitoring methods, resulting in risks in the management of e-commerce platforms.

[0006] One or more embodiments of this specification adopt the following technical solutions:

[0007] One or more embodiments of the present specification provide a risk monitoring method based on an equity relationship thematic library, the method comprising: determining an access data source corresponding to an e-commerce platform through pre-acquired registration information of multiple e-commerce companies, and using DataWorks to perform data extraction and data mining in the access data source to determine the equity structure data of each of the e-commerce companies and the equity relationship data between the multiple e-commerce companies; evaluating the equity structure data of each of the e-commerce companies through a pre-set equity evaluation index system, determining an e-commerce equity evaluation index corresponding to each of the e-commerce companies, and constructing an e-commerce equity relationship thematic library corresponding to the e-commerce platform based on the e-commerce equity evaluation index and the equity relationship data; under the triggering of a management node of the e-commerce platform, screening the multiple e-commerce companies through the e-commerce equity relationship thematic library to determine at least one target monitored e-commerce company, and determining multiple associated e-commerce companies based on the equity relationship data between the multiple e-commerce companies and the target monitored e-commerce company; setting corresponding risk monitoring strategies for the target monitored e-commerce companies and the associated e-commerce companies, collecting real-time transaction activity data of the target monitored e-commerce companies and the associated e-commerce companies on the e-commerce platform based on the risk monitoring strategies, and using the real-time transaction activity data for risk warning.

[0008] One or more embodiments of this specification provide a risk monitoring device based on an equity relationship subject library, including:

[0009] at least one processor; and,

[0010] a memory communicatively connected to the at least one processor; wherein,

[0011] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the above method.

[0012] One or more embodiments of the present specification provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the above method.

[0013] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects: through the technical solution of the embodiments of this specification, the access data source is determined by using the pre-acquired multiple e-commerce registration information, and data extraction and mining are performed through DataWorks, so as to comprehensively integrate various data sources, break the data silos, and ensure that complete data covering the equity structure and relationship of e-commerce is obtained. Compared with the traditional method, it is no longer limited to a single data source or limited data dimensions, and solves the problem of one-sided risk assessment caused by data loss. In the case that the flow of massive equity relationship data is prone to jamming and delay, DataWorks is used to achieve fast data extraction and mining to ensure the timeliness of data, so that the platform can obtain the latest equity information in a timely manner; the equity structure data is evaluated through a pre-set equity evaluation index system, and the e-commerce equity evaluation index is determined from multiple dimensions such as equity concentration, stability and pledge risk, which changes the limitation of traditional risk monitoring that does not fully consider equity risks and realizes the refined evaluation of e-commerce equity risks; based on the e-commerce equity evaluation index and equity relationship data, an e-commerce equity relationship subject library is constructed, and the traditional monitoring It is difficult to find the complex mutual guarantee or fund borrowing and lending between related stores by traditional monitoring methods, while the thematic database can clearly present the equity relationship context and obtain the risk transmission path; under the trigger of the e-commerce platform management node, the target monitoring e-commerce and related e-commerce are screened with the help of the e-commerce equity relationship thematic database, which changes the problems of untimely monitoring and missed detection caused by traditional unified monitoring. Through in-depth analysis of equity data, e-commerce with high-risk equity relationships are accurately located to avoid unnecessary excessive monitoring of a large number of low-risk e-commerce, while ensuring that no high-risk objects are missed; corresponding risk monitoring strategies are set for target monitoring e-commerce and related e-commerce, fully considering the unique risk characteristics of different e-commerce. Different from the traditional lack of targeted monitoring methods, the risk monitoring plan is customized according to the equity evaluation results and the closeness of the relationship of each e-commerce. Personalized monitoring significantly improves the timeliness and accuracy of monitoring, effectively meets the monitoring needs of e-commerce platforms for e-commerce with different risk levels, collects real-time transaction activity data of target monitoring e-commerce and related e-commerce based on risk monitoring strategies, and uses these data for risk warning, solving the problem that traditional monitoring methods cannot meet timeliness requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0015] Figure 1A schematic diagram of a risk monitoring method based on an equity relationship subject database provided in an embodiment of this specification;

[0016] Figure 2 A schematic diagram of the structure of a risk monitoring device based on an equity relationship subject library provided in an embodiment of this specification. DETAILED DESCRIPTION

[0017] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0018] The embodiment of this specification provides a risk monitoring method based on an equity relationship subject library. It should be noted that the execution subject in the embodiment of this specification can be a server or any device with data processing capabilities. Figure 1 A flow chart of a risk monitoring method based on an equity relationship subject library provided in an embodiment of this specification is as follows: Figure 1 As shown, it mainly includes the following steps:

[0019] In step S101, the access data source corresponding to the e-commerce platform is determined by pre-acquired registration information of multiple e-commerce companies, and data extraction and data mining are performed in the access data source using DataWorks to determine the equity structure data of each e-commerce company and the equity relationship data between multiple e-commerce companies.

[0020] In one embodiment of the present specification, generally, when an e-commerce company settles in an e-commerce platform, the e-commerce company sends a settlement request to the e-commerce platform by authorizing the e-commerce platform to query information and submit registration information. The e-commerce platform can only allow the e-commerce company that meets the requirements to settle in the platform after reviewing the e-commerce company. In this case, the registration information of the e-commerce company at the platform registration node is obtained. The registration information here includes the registration information submitted by the e-commerce company, and also includes the database permissions that the platform authorized by the e-commerce company can query. The registration information includes the registered name and business scope of the e-commerce company. In the application scenario of a large e-commerce platform, the database permissions authorized to access can be the industrial and commercial registration information permissions, as well as the e-commerce fund flow information obtained with the authorization of the e-commerce company. Through the above information, the access data source corresponding to the e-commerce platform is determined, and the data source information of the access data source is obtained, such as the data source type, database address, port, database name and other information.

[0021] DataWorks is used to extract and mine data in the access data source to determine the equity structure data of each e-commerce company and the equity relationship data between multiple e-commerce companies, specifically including: determining the data source type of the access data source, configuring database connection information according to the data source type, and establishing a connection relationship between the access data source and the DataWorks system through the database connection information; creating a data synchronization task, and importing the e-commerce equity data in the access data source into a pre-set data warehouse through the synchronization node of the DataWorks system; in the data warehouse, performing direct shareholding relationship mining on the e-commerce equity data to determine the equity structure data corresponding to each e-commerce company, and constructing an equity structure data table corresponding to each e-commerce company, wherein the equity structure data includes shareholder information, shareholding ratio, and equity pledge information; and associating the equity structure data table corresponding to each e-commerce company to determine the equity relationship data between multiple e-commerce companies.

[0022] In one embodiment of this specification, the type of access data source is first determined. Common data sources include relational databases (such as MySQL, Oracle), file systems (such as HDFS, local files), message queues (such as Kafka), and various API interfaces. For e-commerce platforms, the database here can be the platform's own business database, a third-party business registration information database, an e-commerce financial data database provided by a financial institution, etc. It should be noted that DataWorks (Data Workshop, formerly the Big Data Development Kit) is a PaaS (Platform-as-a-Service) platform product, which is applied to various scenarios that require data processing and analysis, such as e-commerce, finance, logistics, etc. Through DataWorks, data warehouses, data lakes, lake warehouses, and other solutions can be built to achieve data integration, development, governance, and analysis, thereby mining the value of data and improving business decision-making efficiency. In DataWorks, different types of data sources are connected to the system through the data source management function. For example, for a MySQL data source, the database host address, port, user name, password, database name, and other information need to be configured so that DataWorks can establish a connection with it. Create a data synchronization task for each connected data source. Here, you can choose full synchronization or incremental synchronization based on the amount of data and the frequency of data updates. For full synchronization, use the synchronization node of DataWorks to import the data of the entire table into the target storage location (such as a data warehouse) at one time by writing SQL statements or using built-in tools. For incremental synchronization, set filtering conditions to synchronize only the most recently updated data, such as using timestamp fields for filtering.

[0023] During the data synchronization process, data quality issues may occur, such as missing values, duplicate data, and erroneous data. In DataWorks, you can use the data cleaning node to process them. Missing values ​​can be filled with default values ​​or according to business rules. For example, if the shareholder's contact information is missing, you can use "unknown" to fill it. Duplicate data can be removed by using the deduplication function, and duplicate records can be deleted based on unique keys (such as e-commerce ID and shareholder ID). Erroneous data can be filtered or modified by writing custom functions or using built-in functions to filter or modify data that does not conform to business logic. For example, if the equity ratio exceeds 100%, it can be corrected to 100%. The data format and encoding of different data sources may be different, and data conversion is required. You can use the conversion node of DataWorks to convert the data into a unified format. For example, the date field can be unified from different formats to the YYYY-MM-DD format, and the character encoding can be unified to UTF-8. Restructure the data and integrate related fields from multiple source data into one data set. For example, the shareholder name from the industrial and commercial registration information and the equity ratio data from the e-commerce platform can be integrated into one table for subsequent analysis.

[0024] In one embodiment of the present specification, a data warehouse is an integrated, subject-oriented, time-varying data set used to support decision making, storing e-commerce equity-related data from multiple data sources, and after pre-processing steps such as extraction, cleaning, and conversion, it is stored in a form that is easy to analyze. Direct shareholding relationship refers to shareholders directly holding shares in e-commerce companies. Mining direct shareholding relationships in a data warehouse is achieved by querying related tables that store equity data. For example, suppose there is a table called ecommerce_equity in the data warehouse, which records fields such as e-commerce ID, shareholder ID, and shareholding ratio. By executing SQL query statements such as SELECT ecommerce_id, shareholder_id, shareholding_ratio FROM ecommerce_equity, the shareholding relationship information between each e-commerce and its direct shareholders can be extracted from the table. The data obtained by mining the above direct shareholding relationship is further used to determine the complete equity structure data corresponding to each e-commerce. In addition to shareholder information (such as shareholder name, shareholder type, etc., detailed information can be obtained in other related tables through shareholder ID) and shareholding ratio, equity pledge information is also included. Equity pledge information may be stored in another related table, such as the equity_pledge table. Through the association fields such as the e-commerce ID and shareholder ID, the equity pledge information can be associated with the direct shareholding relationship data to determine the complete equity structure data of each e-commerce company. A separate equity structure data table is constructed for each e-commerce company to more clearly organize and display the equity structure information of the e-commerce company. For example, the equity structure data table of e-commerce company A can be named ecommerce_A_equity_structure.

[0025] Through the above technical solution, the access data source type is determined and the corresponding database connection information is configured, so that DataWorks can establish connections with various types of data sources, expanding the scope of data acquisition. E-commerce platforms can collect equity-related data from various channels, including internal corporate financial systems, third-party business registration databases, financial institution data interfaces, etc., and fully integrate equity information; by configuring database connection information to establish a connection relationship with the DataWorks system, seamless docking between the data source and the analysis system is achieved. When the data source changes (such as database migration, changing the storage location), only the connection information needs to be adjusted, without large-scale modifications to the entire data processing process. Ensure the stability and sustainability of data extraction; create data synchronization tasks and use the synchronization nodes of the DataWorks system to automatically import e-commerce equity data in the access data source into the pre-set data warehouse. This process does not require frequent manual intervention and is automatically executed according to preset scheduling rules (such as timed extraction and event-triggered extraction), greatly saving labor costs and improving the timeliness and accuracy of data updates; conduct direct shareholding relationship mining on e-commerce equity data in the data warehouse, accurately determine the equity structure data of each e-commerce company, and construct corresponding data tables, which record shareholder information, shareholding ratios, and equity pledge information in detail, providing a clear and intuitive equity structure view for e-commerce platforms.

[0026] The equity structure data table corresponding to each e-commerce company is associated to determine the equity relationship data between multiple e-commerce companies, specifically including: in the first equity structure data table corresponding to the first e-commerce company, the first shareholder information is used as the first target associated entity, and multiple equity structure data tables are queried through the first target associated entity to determine the second associated e-commerce company with the first target associated entity; the second shareholder information other than the first target associated entity in the equity structure data table of the second associated e-commerce company is used as the second target associated entity, and the multiple equity structure data tables are queried through the second target associated entity to determine the third associated e-commerce company with the second target associated entity; the equity relationship data between multiple e-commerce companies are determined through the first e-commerce company, the second associated e-commerce company and the third associated e-commerce company.

[0027] In one embodiment of the present specification, by gradually associating each e-commerce company's separate equity structure data table, the direct or indirect equity relationship between multiple e-commerce companies is mined. First, the first shareholder information is selected as the first target associated entity in the first equity structure data table corresponding to the first e-commerce company. For example, suppose there are multiple e-commerce companies such as e-commerce company A, e-commerce company B, and e-commerce company C and their respective equity structure data tables. In the equity structure data table of e-commerce company A, shareholder A is selected as the first target associated entity. This first target associated entity is used to query multiple equity structure data tables, that is, to find out whether shareholder A exists in the equity structure data tables of all other e-commerce companies such as e-commerce company B and e-commerce company C. If shareholder A is found in the equity structure data table of e-commerce company B, then e-commerce company B is the second associated e-commerce company with the first target associated entity. It is thus determined that e-commerce company A and e-commerce company B have an equity relationship through shareholder A, which is a direct relationship because shareholder A directly holds shares of e-commerce company A and e-commerce company B. The second shareholder information other than the first target associated entity (shareholder A) in the equity structure data table of the second associated e-commerce company (e-commerce company B) is used as the second target associated entity. For example, shareholder B in the equity structure data table of e-commerce company B is selected as the second target associated entity. This second target associated entity is used to query again in multiple equity structure data tables. That is, check whether shareholder B exists in the equity structure data tables of other e-commerce companies such as e-commerce company A and e-commerce company C. If shareholder B is found in the equity structure data table of e-commerce company C, then e-commerce company C is the third associated e-commerce company with the second target associated entity. In this way, an associated chain is constructed: e-commerce company A-shareholder A-e-commerce company B-shareholder B-e-commerce company C. This shows that e-commerce company A and e-commerce company C have formed an indirect equity association relationship through e-commerce company B and shareholders A and B, that is, e-commerce company A has controlled e-commerce company C through e-commerce company C, forming a controlling link, which can also be called an equity link, and the link length is 1 (e-commerce company C), and so on, until the target associated entity cannot be found in other e-commerce companies. Through the above-mentioned sorting out of the relationship between the first e-commerce company, the second associated e-commerce company and the third associated e-commerce company, the equity association relationship data between multiple e-commerce companies are determined.

[0028] Through the above technical solution, by gradually associating the equity structure data table of each e-commerce company, the complex equity relationship network between e-commerce companies can be deeply excavated, and not only e-commerce companies with direct shareholding relationships can be discovered, but also the relationship formed through multiple layers of indirect shareholding can be traced; querying with shareholder information as the associated entity can accurately identify the e-commerce companies and shareholders involved in the equity relationship; the determined equity relationship data provides a basis for risk transmission analysis. When an e-commerce company encounters equity risk (such as equity pledge risk, control risk caused by equity change, etc.), the path of possible risk transmission can be traced through equity relationship; in addition to contributing to risk monitoring, e-commerce platforms can better allocate resources based on equity relationship data. For e-commerce companies with stable equity structure and low association risk, more platform resource support can be given, such as advertising space recommendation, promotion activity participation opportunities, etc., to promote their development; and for e-commerce companies with complex equity relationships and higher risks, some high-risk businesses can be restricted or supervision can be strengthened to ensure the overall stability of the platform.

[0029] Step S102, through the pre-set equity evaluation index system, the equity structure data of each e-commerce company is evaluated, and the e-commerce equity evaluation index corresponding to each e-commerce company is determined, so as to construct the e-commerce equity relationship subject library corresponding to the e-commerce platform based on the e-commerce equity evaluation index and equity relationship data.

[0030] The equity structure data of each e-commerce company is evaluated through a pre-set equity evaluation index system to determine the e-commerce equity evaluation index corresponding to each e-commerce company, specifically including: determining the equity evaluation index system, wherein the equity evaluation index system includes an equity concentration index, an equity stability index and a pledge risk index; through the shareholding ratio and equity pledge information corresponding to each shareholder in the equity structure data, the equity concentration index, the equity stability index and the pledge risk index are quantified respectively to determine the e-commerce equity evaluation index corresponding to each e-commerce company.

[0031] In one embodiment of this specification, the equity evaluation index system consists of an equity concentration index, an equity stability index, and a pledge risk index, which reflect the characteristics and potential risks of the equity structure of e-commerce companies from different dimensions. The equity concentration index is used to measure the degree of concentration of e-commerce equity among shareholders. The equity stability index mainly reflects the stability of the equity structure of e-commerce companies. Frequent changes in equity may indicate that there are unstable factors within the company, affecting operational stability. The pledge risk index focuses on the pledge of e-commerce equity. Equity pledge may bring funds to shareholders, but it is also accompanied by risks such as stock price fluctuations and failure to repay on time. Once a problem occurs, it may lead to major changes in the equity structure and affect normal operations.

[0032] The shareholding ratio of each shareholder is obtained from the equity structure data, and the equity concentration index value is determined by the Herfindahl-Hirschman Index (HHI). The equity concentration is measured by calculating the sum of the squares of all shareholders' shareholding ratios. Assuming that e-commerce company A has three shareholders, with shareholding ratios of 40%, 30%, and 30% respectively, then HHI = 0.4 2 +0.3 2 +0.3 2 =0.34. The larger the HHI value, the more concentrated the equity is, while a lower HHI indicates that the equity is relatively dispersed, which may lead to problems such as low decision-making efficiency and competition for control.

[0033] The quantification of equity stability indicators includes the frequency of equity changes and the scope of equity changes. The number of changes in e-commerce shareholders within a certain period of time (such as the past year) is counted. For example, if e-commerce company B has changed its shareholders three times in the past year, the equity stability indicator value of the equity change frequency of the e-commerce company is 3 times / year. The more changes there are, the lower the equity stability. The change range of the shareholding ratio of a single or multiple shareholders in the latest equity change is obtained. The larger the scope of equity change, the greater the change range of the equity structure and the lower the stability. The quantification of pledge risk indicators calculates the proportion of pledged equity of the e-commerce company to the total share capital of the company through the equity pledge information in the equity structure data. For example, if the equity pledge ratio is 40%, it means that a large proportion of the company's equity has been pledged. When the value of the pledged equity decreases due to a fall in stock prices or other unfavorable factors, it may trigger a series of risks, such as shareholders needing to add collateral, or even forced liquidation of pledged equity, thereby affecting the equity structure and normal operations.

[0034] The values ​​obtained by quantifying the equity concentration index, equity stability index and pledge risk index are used as the equity evaluation index of each e-commerce company. It can comprehensively and systematically reflect the status and potential risks of the equity structure of e-commerce companies, and provide an intuitive and quantitative decision-making basis for e-commerce platforms and other related parties. For example, the equity concentration index (HHI) of e-commerce company A is 0.34, the equity stability index (equity change frequency) is 1 time / year, and the pledge risk index (equity pledge ratio) is 20%. These index values ​​together constitute the e-commerce equity evaluation index of e-commerce company A. Through the e-commerce equity evaluation index and equity association relationship data, the e-commerce equity relationship subject library corresponding to the e-commerce platform is constructed. The e-commerce equity evaluation index obtained by evaluating the equity structure data of each e-commerce company is sorted out. The indicators cover equity concentration index (Herfindahl-Hirschman index), equity stability index (equity change frequency, equity change scope, etc.) and pledge risk index (equity pledge ratio, etc.). Take e-commerce as a unit and store these indicators in the data storage layer of the subject library. For example, you can create a table named ecommerce_equity_evaluation to associate the e-commerce equity evaluation indicator data with the unique identifier of the e-commerce (such as the e-commerce ID). When you need to obtain the equity evaluation of a certain e-commerce, you can quickly locate and query the relevant indicator data through the e-commerce ID. Sort out the equity relationship data between multiple e-commerce companies determined through mining, including direct shareholding relationships (such as e-commerce A directly holds shares of e-commerce B) and indirect shareholding relationships (such as e-commerce A indirectly holds shares of e-commerce B through e-commerce C). For example, create a table named equity_relationship to store equity relationship data. In the subject library, the equity relationship data is integrated with the e-commerce equity evaluation indicator data through common identifiers such as e-commerce ID.

[0035] By integrating e-commerce equity evaluation indicators and equity relationship data, a comprehensive risk profile can be drawn for each e-commerce company. The risks of the e-commerce company's own equity structure can be determined based on equity evaluation indicators (such as equity concentration, equity stability and pledge risk). In addition, the equity relationship data can be combined to analyze the transmission risks that may be brought about by related e-commerce companies. Since the equity structure and relationship of e-commerce companies may change dynamically over time, the constructed subject database facilitates the continuous tracking of these changes. By regularly updating the data, the evolution of e-commerce equity risks can be monitored in real time.

[0036] Step S103, under the triggering of the management node of the e-commerce platform, screen multiple e-commerce companies through the e-commerce equity relationship database to determine at least one target monitored e-commerce company, and determine multiple associated e-commerce companies based on the equity relationship data between the multiple e-commerce companies and the target monitored e-commerce company.

[0037] In one embodiment of the present specification, the management node of the e-commerce platform can initiate screening operations based on a variety of business needs or events. For example, the management node may conduct regular reviews according to a preset time period (such as monthly or quarterly), or it may immediately trigger screening when certain abnormal situations are detected (such as a decline in the overall performance of the platform, a surge in the number of complaints, etc.). When triggered by the management node of the e-commerce platform, the data of the e-commerce equity relationship subject library will be called, and through the e-commerce equity relationship subject library, screening will be performed among multiple e-commerce companies to determine at least one target monitoring e-commerce company. After the target monitoring e-commerce company is determined, the e-commerce company associated with it will be found based on the equity relationship data in the subject library.

[0038] Through the e-commerce equity relationship subject database, screening is performed among the multiple e-commerce companies to determine at least one target monitored e-commerce company, specifically including: determining the e-commerce equity evaluation index set corresponding to each e-commerce company through the e-commerce equity relationship subject database, wherein the e-commerce equity evaluation index set includes an equity concentration index, an equity stability index and a pledge risk index; determining the indicator screening threshold corresponding to the e-commerce equity evaluation index set, wherein the indicator screening threshold includes a concentration reference threshold pair, an equity change frequency threshold, an equity change range threshold and an equity pledge ratio threshold; setting a risk identifier for each e-commerce company according to the e-commerce equity evaluation index set corresponding to each e-commerce company and the indicator screening threshold, so as to determine at least one target monitored e-commerce company through the risk identifier.

[0039] In one embodiment of the present specification, a set of e-commerce equity evaluation indicators corresponding to each e-commerce company is determined through an e-commerce equity relationship subject database, and a risk indicator is set for the e-commerce company by using the relationship between a preset indicator screening threshold and the evaluation indicator to screen out target monitored e-commerce companies with risks.

[0040] According to the set of e-commerce equity evaluation indicators corresponding to each e-commerce company and the screening threshold of the indicator, a risk indicator is set for each e-commerce company, so as to determine at least one target monitored e-commerce company through the risk indicator, specifically including: according to the equity concentration indicator and the preset equity concentration reference threshold pair, an e-commerce company that is higher than the maximum threshold of the equity concentration reference threshold pair, or lower than the minimum threshold of the equity concentration reference threshold pair is determined as a concentration screening e-commerce company, so as to set a concentration risk indicator for the e-commerce company; an e-commerce company whose equity change frequency in the equity stability indicator is greater than the equity change frequency threshold, and whose equity change range in the equity stability indicator is higher than the equity change range threshold, is determined as a stability screening e-commerce company, so as to set a stability risk indicator for the e-commerce company; an e-commerce company whose equity pledge ratio in the equity stability indicator is higher than the equity pledge ratio threshold is determined as a pledge risk screening e-commerce company, so as to set a pledge risk indicator for the e-commerce company; and an e-commerce company with at least one risk indicator is determined as a target monitored e-commerce company.

[0041] In one embodiment of the present specification, in order to identify potential risk e-commerce companies based on the e-commerce equity evaluation index set, it is necessary to determine the corresponding index screening threshold. Different threshold settings will affect the sensitivity and accuracy of risk identification, and the index screening threshold can be adjusted according to needs. The concentration reference threshold pair includes two thresholds, a maximum threshold and a minimum threshold. For example, when the HHI is greater than the maximum threshold (such as 0.25), it may indicate that the equity is over-concentrated, and there is a risk of major shareholders controlling the company, damaging the interests of small shareholders, or lack of diversification in decision-making; while a lower HHI (below the minimum threshold) indicates that the equity is relatively dispersed, and there may be problems such as low decision-making efficiency and control rights competition. The equity change frequency threshold can be set to 3 times / year. If the equity change frequency of an e-commerce company is higher than the threshold, it means that its equity structure is unstable and there may be potential risks. The equity change range threshold refers to the proportion range involved in the equity change, such as the equity change range exceeds 20%. When the equity change range of an e-commerce company exceeds this threshold, it means that the equity structure has changed significantly, which may have an impact on the company's operations. The equity pledge ratio threshold is a percentage, such as 40%. If the equity pledge ratio of an e-commerce company is higher than the threshold, it means that it faces a higher pledge risk. Once problems arise, it may lead to changes in the equity structure and financial risks.

[0042] According to the e-commerce equity evaluation index set and index screening threshold corresponding to each e-commerce company, a risk indicator is set for each e-commerce company. For the equity concentration index, if the shareholding ratio of the largest shareholder is higher than the maximum threshold of the concentration reference threshold pair or lower than the minimum threshold, a "concentration risk indicator" is set. When the equity change frequency is greater than the equity change frequency threshold, or when the equity change range is higher than the equity change range threshold, a "stability risk indicator" is set. If the equity pledge ratio is higher than the equity pledge ratio threshold, a "pledge risk indicator" is set. It should be noted that when setting the stability risk indicator, if the equity change frequency is greater than the equity change frequency threshold and the equity change range is higher than the equity change range threshold, two stability risk indicators are set. Based on the number of risk indicators of each e-commerce company, the e-commerce company with a non-zero number of indicators is determined as the target monitoring e-commerce company. After determining the target monitoring e-commerce company, multiple associated e-commerce companies corresponding to each target monitoring e-commerce company are determined based on the equity association relationship data between multiple e-commerce companies and the target monitoring e-commerce company.

[0043] Through the above technical solution, the e-commerce risks are assessed using indicators of multiple dimensions such as equity concentration, equity stability and pledge risk, which is more comprehensive and accurate than the assessment of a single indicator. Specific screening thresholds are set for each indicator to make risk judgment more targeted, and target monitoring e-commerce is determined among many e-commerce companies, so that platforms or regulatory agencies can concentrate limited resources on objects that need attention. After the target monitoring e-commerce is determined, equity-related relationships may lead to the spread of risks. E-commerce companies that may have risks are locked in advance, and the transmission of risks in the e-commerce network is prevented in advance, which can cut off the risk transmission path in time.

[0044] Step S104, setting corresponding risk monitoring strategies for the target monitored e-commerce and the associated e-commerce, collecting real-time transaction activity data of the target monitored e-commerce and the associated e-commerce on the e-commerce platform based on the risk monitoring strategies, and using the real-time transaction activity data for risk warning.

[0045] There are a large number of e-commerce companies on the e-commerce platform, and the amount of data generated is large. If a unified risk monitoring method is adopted for all e-commerce companies, due to the huge amount of e-commerce data, the unified risk monitoring method may not be able to quickly process all the data. Moreover, under the unified monitoring method, if the warning threshold is set improperly, it will lead to a large number of invalid warnings or missed risks.

[0046] The corresponding risk monitoring strategies are set for the target monitored e-commerce and the associated e-commerce, specifically including: obtaining the number of risk identifications of the target monitored e-commerce, and setting the risk level of the target monitored e-commerce according to the number of risk identifications, wherein the number of risk identifications and the risk level are positively correlated; setting the first risk monitoring strategy of the target monitored e-commerce through the risk level, wherein the first risk monitoring strategy includes a collection period of real-time transaction activity data and a transaction risk trigger threshold; determining the equity link parameters between each of the associated e-commerce and the target monitored e-commerce according to the equity association relationship data; and determining the second risk monitoring strategy corresponding to each of the associated e-commerce through the equity link parameters, wherein the collection period in the second risk monitoring strategy is not less than the collection period of the first risk monitoring strategy.

[0047] In one embodiment of the present specification, the number of risk identifications of the target monitored e-commerce is obtained. The more risk identifications there are, the more and more complex the potential risks of the e-commerce are. Here, the number of risk identifications and the risk level are set to be positively correlated, that is, the more risk identifications there are, the higher the risk level of the target monitored e-commerce. For example, if the number of risk identifications is 1, it can be set to a low risk level, 2-3 to a medium risk level, and 4 to a high risk level. This setting method can intuitively reflect the risk level of the target monitored e-commerce and provide a basis for the subsequent formulation of targeted risk monitoring strategies.

[0048] According to the set risk level, the first risk monitoring strategy is set for the target monitored e-commerce, which mainly includes the collection cycle of real-time transaction activity data and the transaction risk triggering threshold. For the target monitored e-commerce with a high risk level, due to its high potential risk, it is necessary to obtain real-time transaction activity data more frequently to detect risk signs as early as possible, so the collection cycle will be set shorter, such as collecting data once an hour. For e-commerce with a low risk level, the collection cycle can be relatively long, such as collecting data once a day. In this way, while effectively monitoring risks, data collection resources can be reasonably allocated to avoid unnecessary frequent data collection for low-risk e-commerce. It is also set according to the risk level. For e-commerce with a high risk level, its transaction risk triggering threshold will be set relatively low so as to more sensitively capture risk signals in transaction activities. For example, for high-risk e-commerce, when sales drop by 10% in a short period of time, a risk warning is triggered; while for low-risk e-commerce, it may be set that sales drop by 20% to trigger a warning. This method of setting trigger thresholds according to risk levels can improve the accuracy and pertinence of risk monitoring.

[0049] According to the equity association data, the equity link parameters between each associated e-commerce company and the target monitored e-commerce company are determined. For example, e-commerce company A controls e-commerce company B through e-commerce companies C, D, and E, indicating that the link length is 3 (e-commerce company C, e-commerce company D, e-commerce company E). The shorter the equity link length, the higher the risk of the associated e-commerce company. On the basis of the first risk monitoring strategy of the target monitored e-commerce company, the risk monitoring strategy of the associated e-commerce company is adjusted according to the equity link parameters, so as to determine the second risk monitoring strategy corresponding to each associated e-commerce company. Since the risk of each associated e-commerce company is generated under the risk of the target monitored e-commerce company, and is transmitted from the target monitored e-commerce company through the equity link, the directness and urgency of the risk are relatively lower, that is, the risk of the associated e-commerce company is lower than that of the target monitored e-commerce company, and the collection cycle in the second risk monitoring strategy is set to be no less than the collection cycle of the first risk monitoring strategy. For associated e-commerce companies with close equity associations with the target monitored e-commerce company, their collection cycle may be slightly longer than that of the target monitored e-commerce company to pay close attention to the risk transmission situation; while for associated e-commerce companies with relatively loose equity associations (longer link lengths), the collection cycle can be extended, but will not be lower than the collection cycle of the target monitored e-commerce company. For example, the target monitored e-commerce collects data once an hour, the closely related e-commerce also collects data once every 1.5 hours, and the loosely related e-commerce can collect data once every 3 hours. In addition to the collection cycle, other risk monitoring parameters such as transaction risk trigger thresholds can also be adjusted according to the equity link parameters. For closely related e-commerce with equity ties, their transaction risk trigger thresholds may be closer to the target monitored e-commerce in order to detect risk transmission more promptly; while for loosely related e-commerce, the trigger threshold can be appropriately relaxed.

[0050] Through the above technical solution, the risk level of the target monitored e-commerce is determined by the number of risk identifiers. The evaluation method based on multi-dimensional risk identifiers avoids the one-sidedness of single indicator evaluation, making the risk level division more scientific and reasonable; the corresponding first risk monitoring strategy is set according to different risk levels, and monitoring resources are reasonably allocated; the real-time transaction activity data collection cycle and transaction risk trigger threshold in the first risk monitoring strategy are customized according to the risk level, which makes the risk monitoring of the target monitored e-commerce more efficient; considering the equity link parameters to set the second risk monitoring strategy for the associated e-commerce, it can fully consider the transmission characteristics of risks in the equity relationship, which not only ensures the effective monitoring of the risks of the associated e-commerce, but also can reasonably adjust the monitoring intensity according to the degree of association, avoiding excessive The system can eliminate excessive monitoring or insufficient monitoring, thereby improving the risk early warning capability of the entire e-commerce network; provide personalized first risk monitoring strategies for target monitored e-commerce companies according to risk levels, which can better adapt to the risk conditions of different e-commerce companies. Personalized strategies make risk monitoring more in line with the actual conditions of e-commerce companies, improve the pertinence and effectiveness of monitoring strategies, and help to more accurately discover and respond to the risks of target monitored e-commerce companies; determine the second risk monitoring strategy for associated e-commerce companies through equity link parameters, fully consider the diversity and complexity of equity relationships between associated e-commerce companies and target monitored e-commerce companies, and formulate targeted monitoring strategies for each associated e-commerce company according to the different degrees of equity relationship, which can better respond to the risk transmission problems caused by equity relationships and provide more accurate risk monitoring services for associated e-commerce companies.

[0051] Using the real-time transaction activity data for risk warning specifically includes: determining the transaction risk trigger threshold in the risk monitoring strategy of each e-commerce company; generating risk warning information for the e-commerce company through the real-time transaction activity data and the transaction risk trigger threshold, and sending the risk warning information to the management node of the e-commerce platform.

[0052] In one embodiment of the present specification, the transaction risk trigger threshold in the risk monitoring strategy corresponding to each e-commerce company is determined. After the real-time transaction activity data of the user is collected according to the real-time transaction activity data collection cycle in the risk monitoring strategy, these data are compared and analyzed with the predetermined transaction risk trigger threshold to determine whether the risk trigger threshold is reached. Real-time transaction activity data contains many aspects of information, such as key indicators such as sales, order volume, average customer price, refund rate, and complaint rate. If the real-time transaction activity data shows that the refund rate of an e-commerce company reaches 15%, and the refund rate trigger threshold set in the risk monitoring strategy of the e-commerce company is 10%, then it means that the e-commerce company has triggered the risk warning condition on the refund rate indicator. When any transaction activity information reaches the risk trigger threshold, risk warning information is generated, and the generated risk warning information is sent to the management node of the e-commerce platform.

[0053] Through the above technical solution, data collection is carried out according to the real-time transaction activity data collection cycle, so as to obtain the latest transaction dynamics of e-commerce in a timely manner, compare the real-time transaction activity data with the transaction risk trigger threshold determined in advance according to the risk monitoring strategy, and accurately judge the risk. After the risk warning information is sent to the management node of the e-commerce platform, it provides a decision-making basis for the platform management. According to the risk indicators involved in the warning information (such as sales, refund rate, complaint rate, etc.), the specific problems faced by e-commerce can be quickly understood, so as to formulate targeted management strategies.

[0054] Through the technical solution of the embodiments of this specification, the access data source is determined by using the pre-acquired multiple e-commerce registration information, and data extraction and mining are performed through DataWorks, which comprehensively integrates various data sources, breaks down data silos, and ensures that complete data covering the equity structure and relationship of e-commerce is obtained. Compared with traditional methods, it is no longer limited to a single data source or limited data dimensions, and solves the problem of one-sided risk assessment caused by data loss. In the case that the flow of massive equity relationship data is prone to jamming and delay, DataWorks is used to achieve fast data extraction and mining to ensure the timeliness of data, so that the platform can obtain the latest equity information in a timely manner; the equity structure data is evaluated through a pre-set equity evaluation index system, and the e-commerce equity evaluation index is determined from multiple dimensions such as equity concentration, stability and pledge risk, which changes the limitation of traditional risk monitoring that does not fully consider equity risks and realizes a refined assessment of e-commerce equity risks; based on e-commerce equity evaluation indicators and equity relationship data, an e-commerce equity relationship database is constructed, and traditional monitoring methods are difficult to discover complex relationships between related stores. The database can clearly present the equity relationship context and obtain the risk transmission path; under the trigger of the e-commerce platform management node, the target monitored e-commerce and related e-commerce are screened with the help of the e-commerce equity relationship database, which changes the problems of untimely monitoring and missed detection caused by traditional unified monitoring. Through in-depth analysis of equity data, e-commerce with high-risk equity relationships are accurately located to avoid unnecessary excessive monitoring of a large number of low-risk e-commerce companies, while ensuring that no high-risk objects are missed; corresponding risk monitoring strategies are set for target monitored e-commerce and related e-commerce, fully considering the unique risk characteristics of different e-commerce companies. Different from the traditional lack of targeted monitoring methods, the risk monitoring plan is customized according to the equity evaluation results and the closeness of the relationship of each e-commerce company. Personalized monitoring significantly improves the timeliness and accuracy of monitoring, effectively meets the monitoring needs of e-commerce platforms for e-commerce companies of different risk levels, collects real-time transaction activity data of target monitored e-commerce and related e-commerce companies based on risk monitoring strategies, and uses these data for risk warning, solving the problem that traditional monitoring methods cannot meet timeliness requirements.

[0055] The embodiment of this specification also provides a risk monitoring device based on the equity relationship database, such as Figure 2 As shown, the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method.

[0056] The embodiments of the present specification also provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the above method.

[0057] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0058] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] The devices and media provided in the embodiments of this specification correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0060] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0061] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0064] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0065] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0066] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0067] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0068] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A risk monitoring method based on a special database of equity relations, characterized in that: The method comprises: By obtaining the registration information of multiple e-commerce companies in advance, determine the access data source corresponding to the e-commerce platform, and use DataWorks to perform data extraction and data mining in the access data source to determine the equity structure data of each e-commerce company and the equity relationship data between multiple e-commerce companies; By using a pre-set equity evaluation index system, the equity structure data of each e-commerce company is evaluated to determine the e-commerce equity evaluation index corresponding to each e-commerce company, so as to construct an e-commerce equity relationship subject database corresponding to the e-commerce platform based on the e-commerce equity evaluation index and the equity association relationship data; Under the triggering of the management node of the e-commerce platform, the plurality of e-commerce companies are screened through the e-commerce equity relationship subject database to determine at least one target monitoring e-commerce company, and a plurality of associated e-commerce companies are determined based on the equity relationship data between the plurality of e-commerce companies and the target monitoring e-commerce company; Corresponding risk monitoring strategies are set for the target monitored e-commerce and the associated e-commerce, so as to collect real-time transaction activity data of the target monitored e-commerce and the associated e-commerce on the e-commerce platform based on the risk monitoring strategies, and use the real-time transaction activity data for risk warning.

2. The risk monitoring method based on the equity relationship database according to claim 1 is characterized in that: DataWorks is used to extract and mine data from the access data source to determine the equity structure data of each e-commerce company and the equity relationship data between multiple e-commerce companies, including: Determine a data source type of the access data source, and configure database connection information according to the data source type, so as to establish a connection relationship between the access data source and the DataWorks system through the database connection information; Create a data synchronization task to import the e-commerce equity data in the access data source into the pre-set data warehouse through the synchronization node of the DataWorks system; In the data warehouse, the direct shareholding relationship mining is performed on the equity data of the e-commerce companies to determine the equity structure data corresponding to each e-commerce company, and an equity structure data table corresponding to each e-commerce company is constructed, wherein the equity structure data includes shareholder information, shareholding ratio and equity pledge information; The equity structure data table corresponding to each e-commerce company is associated to determine the equity relationship data between multiple e-commerce companies.

3. The risk monitoring method based on the equity relationship database according to claim 2 is characterized in that: The equity structure data table corresponding to each e-commerce company is associated to determine the equity association relationship data between multiple e-commerce companies, specifically including: In the first equity structure data table corresponding to the first e-commerce company, the first shareholder information is used as the first target associated entity, and the first target associated entity is used to query multiple equity structure data tables to determine the second associated e-commerce company that has the first target associated entity; The second shareholder information other than the first target associated entity in the equity structure data table of the second associated e-commerce company is used as the second target associated entity, so as to query the plurality of equity structure data tables through the second target associated entity to determine the third associated e-commerce company where the second target associated entity exists; The equity relationship data among the plurality of e-commerce companies are determined through the first e-commerce company, the second associated e-commerce company and the third associated e-commerce company.

4. The risk monitoring method based on the equity relationship database according to claim 1 is characterized in that: The equity structure data of each e-commerce company is evaluated through a pre-set equity evaluation index system to determine the e-commerce equity evaluation index corresponding to each e-commerce company, specifically including: Determining the equity evaluation index system, wherein the equity evaluation index system includes an equity concentration index, an equity stability index and a pledge risk index; Through the shareholding ratio and equity pledge information corresponding to each shareholder in the equity structure data, the equity concentration index, equity stability index and pledge risk index are quantified respectively to determine the e-commerce equity evaluation index corresponding to each of the e-commerce companies.

5. The risk monitoring method based on the equity relationship subject database according to claim 1 is characterized in that: Through the e-commerce equity relationship database, the multiple e-commerce companies are screened to determine at least one target monitoring e-commerce company, specifically including: Determine the e-commerce equity evaluation index set corresponding to each e-commerce company through the e-commerce equity relationship subject database, wherein the e-commerce equity evaluation index set includes an equity concentration index, an equity stability index, and a pledge risk index; Determine an indicator screening threshold corresponding to the e-commerce equity evaluation indicator set, wherein the indicator screening threshold includes a concentration reference threshold pair, an equity change frequency threshold, an equity change range threshold, and an equity pledge ratio threshold; According to the e-commerce equity evaluation index set corresponding to each e-commerce company and the index screening threshold, a risk identifier is set for each e-commerce company, so as to determine at least one target monitored e-commerce company through the risk identifier.

6. The risk monitoring method based on the equity relationship database according to claim 5 is characterized in that: According to the e-commerce equity evaluation index set corresponding to each e-commerce company and the index screening threshold, a risk identifier is set for each e-commerce company, so as to determine at least one target monitoring e-commerce company through the risk identifier, specifically including: According to the equity concentration index and the preset equity concentration reference threshold pair, e-commerce companies with a value higher than the maximum threshold of the equity concentration reference threshold pair, or lower than the minimum threshold of the equity concentration reference threshold pair, are determined as concentration screening e-commerce companies, so as to set a concentration risk flag for the e-commerce companies; Determine an e-commerce company whose equity change frequency in the equity stability index is greater than the equity change frequency threshold, and whose equity change range in the equity stability index is higher than the equity change range threshold as a stability screening e-commerce company, so as to set a stability risk flag for the e-commerce company; Determine an e-commerce company whose equity pledge ratio in the equity stability index is higher than the equity pledge ratio threshold as a pledge risk screening e-commerce company, so as to set a pledge risk flag for the e-commerce company; An e-commerce company with at least one risk indicator is identified as a target monitored e-commerce company.

7. The risk monitoring method based on the equity relationship database according to claim 5 is characterized in that: The corresponding risk monitoring strategies are set for the target monitored e-commerce company and the associated e-commerce company, specifically including: Acquire the number of risk identifiers of the target monitored e-commerce company, and set the risk level of the target monitored e-commerce company according to the number of risk identifiers, wherein the number of risk identifiers and the risk level are positively correlated; According to the risk level, a first risk monitoring strategy of the target monitored e-commerce company is set, wherein the first risk monitoring strategy includes a collection period of real-time transaction activity data and a transaction risk triggering threshold; Determining the equity link parameters between each of the associated e-commerce companies and the target monitored e-commerce company according to the equity association relationship data; By using the equity link parameters, adjustments are made on the basis of the first risk monitoring strategy to determine a second risk monitoring strategy corresponding to each of the associated e-commerce companies, wherein the collection period in the second risk monitoring strategy is not less than the collection period of the first risk monitoring strategy.

8. The risk monitoring method based on the equity relationship subject database according to claim 1 is characterized in that: Using the real-time transaction activity data to conduct risk warning, specifically including: Determining a transaction risk trigger threshold in a risk monitoring strategy for each of the e-commerce companies; Through the real-time transaction activity data and the transaction risk trigger threshold, risk warning information is generated for the e-commerce company, so as to send the risk warning information to the management node of the e-commerce platform.

9. A risk monitoring device based on a special database of equity relations, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the method according to any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to execute the method according to any one of claims 1 to 8.

Images