Knowledge graph-based Internet lease risk control method and system, and medium

Abstract

The invention provides an Internet lease risk control method and system based on a knowledge graph, and a medium, and belongs to the technical field of artificial intelligence and financial science and technology. The method comprises the steps of obtaining rental item information, rental mode information and basic information of a rental object through an Internet rental system platform, constructing a rental behavior recognition knowledge graph, extracting repayment capability information and credit behavior information, and querying through a corresponding preset database to obtain debt payment capability stability data and behavior reliability data. Market behavior change information is obtained and processed through a preset market risk evaluation model, and market behavior change data is obtained. And finally carrying out risk evaluation processing to obtain an Internet lease risk index and judge an Internet lease risk control condition. According to the method and the device, rapid and accurate calculation of the real-time indexes of the Internet lease risk control business data is realized, index updating can be completed at the moment when the business data is generated or in an extremely short time, and powerful support is provided for real-time risk control decision making.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and financial technology, and specifically to Internet leasing risk control methods, systems, and media based on knowledge graphs. Background Art

[0002] With the booming development of the internet leasing industry and the continuous expansion of business scale, the importance of risk management has become increasingly prominent. Massive amounts of leasing business data are constantly being generated, including tenant information, leasing order details, and equipment usage data. Accurate and real-time calculation of risk indicators is crucial for promptly identifying potential risks, formulating appropriate risk control strategies, and ensuring the healthy and stable operation of the leasing business. However, traditional risk control data indicator calculation often relies on periodic data batch processing, which is subject to lags and cannot meet the rapid changes and real-time decision-making needs of internet businesses. Furthermore, data integration and processing are challenging due to the complex and diverse data sources and formats, which can easily lead to inaccurate and incomplete indicator calculations. There is a lack of a technical approach that uses knowledge graphs to deeply mine the complex relationships between multi-source data, comprehensively improve the accuracy and completeness of indicator calculations, and more accurately characterize risk characteristics.

[0003] In response to the above problems, effective technical solutions are currently awaited. Summary of the Invention

[0004] The purpose of this application is to provide an internet leasing risk control method, system, and medium based on a knowledge graph. This method can obtain information about leased items, lease models, and basic information about leased objects through an internet leasing system platform and construct a knowledge graph for identifying leasing behavior. It can then extract repayment capacity information and credit behavior information, and obtain repayment capacity stability data and behavior reliability data through corresponding preset database queries. It then obtains market behavior change information and processes it through a preset market risk assessment model to obtain market behavior anomaly data. Finally, it performs risk assessment processing to obtain an internet leasing risk index and determine the internet leasing risk control situation. This application achieves rapid and accurate calculation of real-time indicators for internet leasing risk control business data, and can complete indicator updates at the moment business data is generated or within a very short period of time, providing strong support for real-time risk control decisions.

[0005] This application provides an Internet leasing risk control method based on a knowledge graph, comprising the following steps: Obtain the leased property information, lease model information and basic information of the leased object within a preset time period through the Internet leasing system platform, build a knowledge graph for leasing behavior identification, and extract repayment ability information and credit behavior information; According to the repayment ability information, query the preset debt capacity database to obtain the debt repayment ability stability data of the lease object; According to the credit behavior information, a query is performed through a preset credit behavior database to obtain the behavior reliability data of the lease object; Obtaining market behavior change information within the preset time period and processing it through a preset market risk assessment model to obtain market behavior anomaly data; The internet leasing risk index is obtained by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data through a preset leasing risk assessment model and comparing it with the preset risk index to judge the risk control situation of internet leasing.

[0006] Among them, in the Internet leasing risk control method based on knowledge graph described in this application, the construction of the leasing behavior identification knowledge graph is specifically: Obtaining rental information, rental model information and basic information of the rental object within a preset time period through the Internet rental system platform; The leased property information includes leased property type information, leased property quantity information and leased property status information; The lease mode information includes lease term information, rent payment method information and lease terms information; The basic information of the leased object includes the identity information, communication information and basic credit record information of the leased object; A knowledge graph for identifying leasing behavior is constructed based on the leased item information, leasing model information, and basic information of the leased object, and repayment ability information and credit behavior information are extracted.

[0007] Among them, in the Internet leasing risk control method based on knowledge graph described in this application, the data on the stability of the debt repayment ability of the leased object is obtained as follows: extracting asset and liability information, cash transaction record information, and profit information based on the solvency information; According to the asset and liability information, cash transaction record information and profit information, a query is performed through a preset debt capacity database to obtain the debt repayment ability stability data of the lease object.

[0008] Among them, in the Internet leasing risk control method based on knowledge graph described in this application, the obtaining of the reliability data of the leasing object behavior is specifically: Extracting historical loan record information, consumption habit information, public affairs payment record information and social behavior information based on the credit behavior information; According to the historical loan record information, consumption habit information, public affairs payment record information and social behavior information, a query is performed through a preset credit behavior database to obtain the reliability data of the rental object's behavior.

[0009] Among them, in the Internet leasing risk control method based on knowledge graph described in this application, the acquisition of market behavior anomaly data is specifically: Obtaining market behavior change information within the preset time period; Extracting value volatility data, demand mutation data, and market share data based on the market behavior change information; The value volatility data, demand mutation data and market share data are processed through a preset market risk assessment model to obtain market behavior abnormality data.

[0010] Among them, in the Internet leasing risk control method based on knowledge graph described in this application, the determination of Internet leasing risk control situation is specifically as follows: Obtaining an internet leasing risk index by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data using a preset leasing risk assessment model; Comparing the Internet rental risk index with a preset risk index to obtain a risk deviation rate; comparing the risk deviation rate with a preset risk deviation rate threshold; If the risk deviation rate is greater than or equal to the risk deviation rate threshold, a high-risk message is sent; If the risk deviation rate is less than the risk deviation rate threshold, a risk controllable information is sent.

[0011] In a second aspect, the present application provides an internet leasing risk control system based on a knowledge graph, the system comprising: a memory and a processor, the memory comprising a program for an internet leasing risk control method based on a knowledge graph, and the program for an internet leasing risk control method based on a knowledge graph, when executed by the processor, implements the following steps: Obtain the leased property information, lease model information and basic information of the leased object within a preset time period through the Internet leasing system platform, build a knowledge graph for leasing behavior identification, and extract repayment ability information and credit behavior information; According to the repayment ability information, query the preset debt capacity database to obtain the debt repayment ability stability data of the lease object; According to the credit behavior information, a query is performed through a preset credit behavior database to obtain the behavior reliability data of the lease object; Obtaining market behavior change information within the preset time period and processing it through a preset market risk assessment model to obtain market behavior anomaly data; The internet leasing risk index is obtained by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data through a preset leasing risk assessment model and comparing it with the preset risk index to judge the risk control situation of internet leasing.

[0012] Among them, in the Internet leasing risk control system based on knowledge graph described in this application, the construction of the leasing behavior identification knowledge graph is specifically: Obtaining rental information, rental model information and basic information of the rental object within a preset time period through the Internet rental system platform; The leased property information includes leased property type information, leased property quantity information and leased property status information; The lease mode information includes lease term information, rent payment method information and lease terms information; The basic information of the leased object includes the identity information, communication information and basic credit record information of the leased object; A knowledge graph for identifying leasing behavior is constructed based on the leased item information, leasing model information, and basic information of the leased object, and repayment ability information and credit behavior information are extracted.

[0013] In the Internet leasing risk control system based on knowledge graph described in this application, the data on the stability of the debt repayment ability of the leased object is obtained as follows: extracting asset and liability information, cash transaction record information, and profit information based on the solvency information; According to the asset and liability information, cash transaction record information and profit information, a query is performed through a preset debt capacity database to obtain the debt repayment ability stability data of the lease object.

[0014] In a third aspect, the present application also provides a computer-readable storage medium, which includes an Internet leasing risk control method program based on a knowledge graph. When the Internet leasing risk control method program based on a knowledge graph is executed by a processor, the steps of the Internet leasing risk control method based on a knowledge graph as described in any one of the above items are implemented.

[0015] As can be seen from the above, the Internet leasing risk control method, system and medium based on the knowledge graph provided in the embodiment of the present application obtains the leased property information, leasing model information and basic information of the leased object within a preset time period through the Internet leasing system platform and constructs a leasing behavior identification knowledge graph, and then extracts the repayment ability information and credit behavior information. According to the repayment ability information, a query is made through the preset debt capacity database to obtain the repayment ability stability data of the leased object; according to the credit behavior information, a query is made through the preset credit behavior database to obtain the behavior reliability data of the leased object. The market behavior change information within the preset time period is obtained and processed through the preset market risk assessment model to obtain market behavior anomaly data. Finally, according to the repayment ability stability data of the leased object and the reliability data of the leased object behavior, combined with the market behavior anomaly data, the preset leasing risk assessment model is used to process the data to obtain the Internet leasing risk index and compare it with the preset risk index to judge the Internet leasing risk control situation. This application can obtain the debt repayment ability and behavioral reliability of the leased object through the pre-established debt capacity database and credit behavior database. The repayment capacity information and credit behavior information provide a solid foundation for risk assessment, and then the market behavior anomalies are obtained according to the changes in market behavior. The three aspects of information are combined to finally obtain the leasing risk index, which realizes the rapid and accurate calculation of real-time indicators of Internet leasing risk control business data. It can complete the indicator update at the moment the business data is generated or in a very short time, providing strong support for real-time risk control decision-making, improving resource utilization and reducing operating costs.

[0016] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A flowchart of the knowledge graph-based Internet leasing risk control method provided in an embodiment of the present application; Figure 2 A flowchart of the knowledge graph-based internet rental risk control method for constructing a rental behavior identification knowledge graph provided in an embodiment of the present application; Figure 3A flowchart of obtaining data on the stability of the debt repayment ability of a leased entity in a knowledge graph-based internet leasing risk control method provided in an embodiment of the present application; Figure 4 A flowchart of obtaining the reliability data of the behavior of the leased object in the Internet lease risk control method based on the knowledge graph provided in an embodiment of the present application; Figure 5 A flowchart of obtaining market behavior anomaly data for the knowledge graph-based Internet leasing risk control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0020] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0021] Please refer to Figure 1 , Figure 1 This is a flow chart of a knowledge graph-based internet rental risk control method in some embodiments of the present application. This knowledge graph-based internet rental risk control method is used in terminal devices, such as computers, mobile phones, etc. This knowledge graph-based internet rental risk control method includes the following steps: S101. Obtaining, through the Internet leasing system platform, information on leased items, leasing model information, and basic information on leased objects within a preset time period, constructing a knowledge graph for leasing behavior identification, and extracting repayment ability information and credit behavior information; S102: Querying a preset debt capacity database based on the repayment capacity information to obtain data on the stability of the repayment capacity of the leased object; S103: querying a preset credit behavior database based on the credit behavior information to obtain the behavior reliability data of the leased object; S104: Obtain market behavior change information within the preset time period and process it using a preset market risk assessment model to obtain market behavior anomaly data; S105. Process the data on the stability of the debt repayment ability of the leased object and the reliability data on the behavior of the leased object in combination with the market behavior anomaly data through a preset lease risk assessment model to obtain an internet lease risk index, and compare the index with the preset risk index to determine the risk control status of internet leases.

[0022] Among them, this application obtains the leased property information, lease model information and basic information of the leased object within a preset time period through the Internet leasing system platform and constructs a knowledge graph for leasing behavior identification, and then extracts repayment ability information and credit behavior information, such as income status, debt situation, historical credit record, default situation, etc. According to the repayment ability information, a query is made through the preset debt capacity database to obtain the repayment ability stability data of the leased object; according to the credit behavior information, a query is made through the preset credit behavior database to obtain the behavior reliability data of the leased object. The market behavior change information within the preset time period is obtained and processed through the preset market risk assessment model to obtain market behavior anomaly data. Finally, according to the repayment ability stability data of the leased object and the reliability data of the leased object behavior combined with the market behavior anomaly data, the preset leasing risk assessment model is used to process and obtain the Internet leasing risk index and compare it with the preset risk index to judge the risk control situation of Internet leasing. This application can obtain the debt repayment ability and behavioral reliability of the leased object through the pre-established debt capacity database and credit behavior database. The repayment capacity information and credit behavior information provide a solid foundation for risk assessment, and then the market behavior anomalies are obtained according to the changes in market behavior. The three aspects of information are combined to finally obtain the leasing risk index, which realizes the rapid and accurate calculation of real-time indicators of Internet leasing risk control business data. It can complete the indicator update at the moment the business data is generated or in a very short time, providing strong support for real-time risk control decision-making, improving resource utilization and reducing operating costs.

[0023] Please refer to Figure 2 , Figure 2 This is a flowchart of the construction of a knowledge graph for identifying rental behavior in an Internet rental risk control method based on a knowledge graph in some embodiments of the present application. According to an embodiment of the present invention, the construction of a knowledge graph for identifying rental behavior is specifically as follows: S201. Obtaining rental information, rental model information, and basic information of the rental object within a preset time period through the Internet rental system platform; S202: The leased property information includes leased property type information, leased property quantity information, and leased property status information; S203, the lease model information includes lease term information, rent payment method information and lease terms information; S204: The basic information of the leased object includes the leased object's identity information, communication information, and basic credit record information; S205: Construct a lease behavior identification knowledge graph based on the leased property information, lease model information, and leased object basic information, and extract repayment ability information and credit behavior information.

[0024] To construct a knowledge graph for identifying leasing behavior, information on leased items, leasing models, and basic information about leased entities within a preset time period is collected through the internet leasing system platform. Leased item information includes the type, quantity, and status of the leased items (e.g., intact, damaged, or under repair). Leased model information includes the lease term, payment method, and lease terms. Basic information about leased entities includes their identity, communication methods, and basic credit history. A knowledge graph for identifying leasing behavior is constructed based on this information, including information on repayment capacity and credit behavior. This graph visually displays the relationships between leased items, leasing models, and leased entities through nodes and edges. Nodes represent entities such as leased items, leasing models, and leased entities, while edges represent interactions or relationships between these entities, such as the type of leased item or leasing model employed by the leased entity.

[0025] Please refer to Figure 3 , Figure 3 This is a flow chart of obtaining the debt repayment stability data of the leased object in the knowledge graph-based internet leasing risk control method in some embodiments of the present application. According to an embodiment of the present invention, obtaining the debt repayment stability data of the leased object is specifically as follows: S301, extracting asset and liability information, cash transaction record information, and profit information based on the solvency information; S302: Query a preset debt capacity database based on the asset and liability information, cash transaction record information, and profit information to obtain debt repayment stability data of the leased object.

[0026] To assess the leasing entity's solvency, asset and liability information, cash transaction records, and profit information are extracted from the solvency information. Asset and liability information includes all valuable assets or equity held by the leasing entity, including cash, deposits, real estate, vehicles, and investments, as well as debts owed, such as loans, credit card balances, and other unpaid bills. Cash transaction records reflect all sources of income, such as wages, bonuses, and investment returns, and all expenditures, such as living expenses, rent, and loan repayments. Profit information represents operating revenue, costs, and net profit, reflecting the leasing entity's profitability. Data on the leasing entity's solvency stability is then retrieved through a pre-defined solvency database. This database, which is maintained on a third-party platform and contains a series of financial indicators based on historical data and industry standards, is used to assess solvency under different financial conditions.

[0027] Please refer to Figure 4 , Figure 4 This is a flow chart of obtaining the reliability data of the behavior of the leased object in the knowledge graph-based Internet lease risk control method in some embodiments of the present application. According to an embodiment of the present invention, obtaining the reliability data of the behavior of the leased object is specifically as follows: S401, extracting historical loan record information, consumption habit information, public affairs payment record information, and social behavior information based on the credit behavior information; S402: Query a preset credit behavior database based on the historical loan record information, consumption habit information, public affairs payment record information, and social behavior information to obtain the behavior reliability data of the lease object.

[0028] To assess the creditworthiness and related behavior of the lessee, historical loan records, consumption habits, public utility payment records, and social behavior information are extracted based on credit behavior information. Historical loan records include the number of loans, amount, and repayment status; consumption habits include consumption frequency, amount, and type of consumption; public utility payment records include utility bills, property management fees, and water charges; and social behavior information includes social activity, social evaluations, and relationships. A query is then performed through a pre-set credit behavior database to obtain data on the lessee's behavioral reliability, which indicates the lessee's reliability in complying with credit rules and fulfilling their obligations. This database contains a series of credit behavior assessments based on historical data and industry standards, used to assess behavioral reliability under different credit behavior indicators. The database relies on a third-party platform.

[0029] Please refer to Figure 5 , Figure 5This is a flow chart of obtaining market behavior anomaly data for the knowledge graph-based internet rental risk control method in some embodiments of the present application. According to an embodiment of the present invention, obtaining market behavior anomaly data is specifically as follows: S501, obtaining market behavior change information within the preset time period; S502: extracting value volatility data, demand mutation data, and market share data based on the market behavior change information; S503: Process the value volatility data, demand mutation data, and market share data using a preset market risk assessment model to obtain market behavior anomaly data.

[0030] Among them, in order to analyze the leasing risks brought about by market changes, information on market behavior changes within a preset time period is obtained and value volatility data, demand mutation data and market share data are extracted. Value volatility data measures the degree of change in market value within a certain period of time; demand mutation data refers to significant changes in market demand in a short period of time, which may be due to various factors such as changes in consumer preferences, policy adjustments, and new product launches; market share data reflects the relative position of specific participants or products in the entire market. Finally, through the preset market risk assessment model, market behavior variation data is obtained, which provides market participants with important information about market risks and helps them make informed decisions. The model aims to assess market risks by analyzing these key data; The calculation formula of the market risk assessment model is: ; in, For market behavior abnormality data, They are value volatility data, demand mutation data and market share data, It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset market behavior monitoring database).

[0031] According to an embodiment of the present invention, the determination of the risk control status of Internet leasing is specifically as follows: Obtaining an internet leasing risk index by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data using a preset leasing risk assessment model; Comparing the Internet rental risk index with a preset risk index to obtain a risk deviation rate; comparing the risk deviation rate with a preset risk deviation rate threshold; If the risk deviation rate is greater than or equal to the risk deviation rate threshold, a high-risk message is sent; If the risk deviation rate is less than the risk deviation rate threshold, a risk controllable information is sent.

[0032] Among them, in order to assess the degree of leasing risk and determine whether it is controllable, the data on the stability of the debt repayment ability of the leasing object and the reliability data on the behavior of the leasing object are combined with the market behavior variation data and processed through a preset leasing risk assessment model to obtain an Internet leasing risk index, which reflects the overall risk level of the leasing business in the current market environment. The Internet leasing risk index is compared with the preset risk index to obtain a risk deviation rate, which is then compared with the preset risk deviation rate threshold. If the risk deviation rate is greater than or equal to the risk deviation rate threshold, a high-risk message is sent, indicating that the risk level of the current leasing business is high and corresponding measures need to be taken to reduce the risk; if the risk deviation rate is less than the risk deviation rate threshold, a controllable risk message is sent, indicating that the risk level of the current leasing business is within a controllable range and business operations can continue; The calculation formula of the lease risk assessment model is: ; in, is the Internet rental risk index, They are the data on the stability of the leasing object's debt repayment ability, the data on the reliability of the leasing object's behavior and the data on market behavior anomalies. It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset market behavior monitoring database).

[0033] According to an embodiment of the present invention, the further embodiment includes: Obtaining usage record information of the leased item within the preset time period; Extracting usage frequency data and failure rate data based on the usage record information of the leased item; Querying a preset value list based on the usage frequency data and the failure rate data to obtain a depreciation ratio of the leased property; Comparing the depreciation ratio of the leased property with a preset depreciation threshold; If the depreciation ratio of the leased property is less than or equal to the depreciation threshold, the leased property will be assigned a low value rating and appropriate countermeasures will be taken; If the depreciation ratio of the leased property is greater than the depreciation threshold, the leased property will be given a high value level.

[0034] To assess the value of the leased property and implement appropriate management measures, the system collects usage records for a preset time period, extracts usage frequency data and failure rate data, and then searches through a preset value list to obtain the leased property's depreciation ratio. This ratio is compared with a preset depreciation threshold. If the depreciation ratio is less than or equal to the threshold, the property is assigned a low value rating and appropriate measures are taken, such as shortening the lease period, increasing rent, or increasing the deposit, to reduce potential losses. If the depreciation ratio is greater than the threshold, the property is assigned a high value rating, requiring better maintenance and service to improve tenant satisfaction and loyalty.

[0035] According to an embodiment of the present invention, the further embodiment includes: Inputting the data on the stability of the debt repayment ability of the leased object, the data on the reliability of the behavior of the leased object, the data on the abnormal market behavior, and the Internet lease risk index into the lease behavior identification knowledge graph; Update the rental behavior recognition knowledge graph according to a preset frequency and obtain an update result; Obtaining parameter change rate data according to the update result; Comparing the parameter change rate data with a preset change rate threshold; If the parameter change rate data is greater than or equal to the change rate threshold, an update verification message is sent; If the parameter change rate data is less than the change rate threshold, an update success message is sent.

[0036] Among them, in order to realize the automatic completion of ring networking, the debt repayment ability stability data of the leasing object, the behavior reliability data of the leasing object, the market behavior abnormality data and the Internet leasing risk index are input into the leasing behavior identification knowledge graph, and the leasing behavior identification knowledge graph is updated according to the preset frequency and the update result is obtained. The parameter change rate data is obtained according to the update result, and then compared with the preset change rate threshold. If the parameter change rate data is greater than or equal to the change rate threshold, an update verification information is sent, indicating that the parameters in the graph have changed significantly and may need further verification; if the parameter change rate data is less than the change rate threshold, an update success information is sent, indicating that the parameter changes in the graph are within the normal range and the update is successful.

[0037] The present invention also discloses a knowledge graph-based internet rental risk control system, comprising a memory and a processor. The memory includes a knowledge graph-based internet rental risk control method program. When the knowledge graph-based internet rental risk control method program is executed by the processor, the following steps are implemented: Obtain the leased property information, lease model information and basic information of the leased object within a preset time period through the Internet leasing system platform, build a knowledge graph for leasing behavior identification, and extract repayment ability information and credit behavior information; According to the repayment ability information, query the preset debt capacity database to obtain the debt repayment ability stability data of the lease object; According to the credit behavior information, a query is performed through a preset credit behavior database to obtain the behavior reliability data of the lease object; Obtaining market behavior change information within the preset time period and processing it through a preset market risk assessment model to obtain market behavior anomaly data; The internet leasing risk index is obtained by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data through a preset leasing risk assessment model and comparing it with the preset risk index to judge the risk control situation of internet leasing.

[0038] Among them, this application obtains the leased property information, lease model information and basic information of the leased object within a preset time period through the Internet leasing system platform and constructs a knowledge graph for leasing behavior identification, and then extracts repayment ability information and credit behavior information, such as income status, debt situation, historical credit record, default situation, etc. According to the repayment ability information, a query is made through the preset debt capacity database to obtain the repayment ability stability data of the leased object; according to the credit behavior information, a query is made through the preset credit behavior database to obtain the behavior reliability data of the leased object. The market behavior change information within the preset time period is obtained and processed through the preset market risk assessment model to obtain market behavior anomaly data. Finally, according to the repayment ability stability data of the leased object and the reliability data of the leased object behavior combined with the market behavior anomaly data, the preset leasing risk assessment model is used to process and obtain the Internet leasing risk index and compare it with the preset risk index to judge the risk control situation of Internet leasing. This application can obtain the debt repayment ability and behavioral reliability of the leased object through the pre-established debt capacity database and credit behavior database. The repayment capacity information and credit behavior information provide a solid foundation for risk assessment, and then the market behavior anomalies are obtained according to the changes in market behavior. The three aspects of information are combined to finally obtain the leasing risk index, which realizes the rapid and accurate calculation of real-time indicators of Internet leasing risk control business data. It can complete the indicator update at the moment the business data is generated or in a very short time, providing strong support for real-time risk control decision-making, improving resource utilization and reducing operating costs.

[0039] According to an embodiment of the present invention, the construction of a rental behavior identification knowledge graph specifically includes: Obtaining rental information, rental model information and basic information of the rental object within a preset time period through the Internet rental system platform; The leased property information includes leased property type information, leased property quantity information and leased property status information; The lease mode information includes lease term information, rent payment method information and lease terms information; The basic information of the leased object includes the identity information, communication information and basic credit record information of the leased object; A knowledge graph for identifying leasing behavior is constructed based on the leased item information, leasing model information, and basic information of the leased object, and repayment ability information and credit behavior information are extracted.

[0040] To construct a knowledge graph for identifying leasing behavior, information on leased items, leasing models, and basic information about leased entities within a preset time period is collected through the internet leasing system platform. Leased item information includes the type, quantity, and status of the leased items (e.g., intact, damaged, or under repair). Leased model information includes the lease term, payment method, and lease terms. Basic information about leased entities includes their identity, communication methods, and basic credit history. A knowledge graph for identifying leasing behavior is constructed based on this information, including information on repayment capacity and credit behavior. This graph visually displays the relationships between leased items, leasing models, and leased entities through nodes and edges. Nodes represent entities such as leased items, leasing models, and leased entities, while edges represent interactions or relationships between these entities, such as the type of leased item or leasing model employed by the leased entity.

[0041] According to an embodiment of the present invention, obtaining the debt repayment stability data of the leased object is specifically as follows: extracting asset and liability information, cash transaction record information, and profit information based on the solvency information; According to the asset and liability information, cash transaction record information and profit information, a query is performed through a preset debt capacity database to obtain the debt repayment ability stability data of the lease object.

[0042] To assess the leasing entity's solvency, asset and liability information, cash transaction records, and profit information are extracted from the solvency information. Asset and liability information includes all valuable assets or equity held by the leasing entity, including cash, deposits, real estate, vehicles, and investments, as well as debts owed, such as loans, credit card balances, and other unpaid bills. Cash transaction records reflect all sources of income, such as wages, bonuses, and investment returns, and all expenditures, such as living expenses, rent, and loan repayments. Profit information represents operating revenue, costs, and net profit, reflecting the leasing entity's profitability. Data on the leasing entity's solvency stability is then retrieved through a pre-defined solvency database. This database, which is maintained on a third-party platform and contains a series of financial indicators based on historical data and industry standards, is used to assess solvency under different financial conditions.

[0043] According to an embodiment of the present invention, obtaining the rental object behavior reliability data specifically includes: Extracting historical loan record information, consumption habit information, public affairs payment record information and social behavior information based on the credit behavior information; According to the historical loan record information, consumption habit information, public affairs payment record information and social behavior information, a query is performed through a preset credit behavior database to obtain the reliability data of the rental object's behavior.

[0044] To assess the creditworthiness and related behavior of the lessee, historical loan records, consumption habits, public utility payment records, and social behavior information are extracted based on credit behavior information. Historical loan records include the number of loans, amount, and repayment status; consumption habits include consumption frequency, amount, and type of consumption; public utility payment records include utility bills, property management fees, and water charges; and social behavior information includes social activity, social evaluations, and relationships. A query is then performed through a pre-set credit behavior database to obtain data on the lessee's behavioral reliability, which indicates the lessee's reliability in complying with credit rules and fulfilling their obligations. This database contains a series of credit behavior assessments based on historical data and industry standards, used to assess behavioral reliability under different credit behavior indicators. The database relies on a third-party platform.

[0045] According to an embodiment of the present invention, obtaining market behavior abnormality data specifically includes: Obtaining market behavior change information within the preset time period; Extracting value volatility data, demand mutation data, and market share data based on the market behavior change information; The value volatility data, demand mutation data and market share data are processed through a preset market risk assessment model to obtain market behavior abnormality data.

[0046] Among them, in order to analyze the leasing risks brought about by market changes, information on market behavior changes within a preset time period is obtained and value volatility data, demand mutation data and market share data are extracted. Value volatility data measures the degree of change in market value within a certain period of time; demand mutation data refers to significant changes in market demand in a short period of time, which may be due to various factors such as changes in consumer preferences, policy adjustments, and new product launches; market share data reflects the relative position of specific participants or products in the entire market. Finally, through the preset market risk assessment model, market behavior variation data is obtained, which provides market participants with important information about market risks and helps them make informed decisions. The model aims to assess market risks by analyzing these key data; The calculation formula of the market risk assessment model is: ; in, For market behavior abnormality data, They are value volatility data, demand mutation data and market share data, It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset market behavior monitoring database).

[0047] According to an embodiment of the present invention, the determination of the risk control status of Internet leasing is specifically as follows: Obtaining an internet leasing risk index by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data using a preset leasing risk assessment model; Comparing the Internet rental risk index with a preset risk index to obtain a risk deviation rate; comparing the risk deviation rate with a preset risk deviation rate threshold; If the risk deviation rate is greater than or equal to the risk deviation rate threshold, a high-risk message is sent; If the risk deviation rate is less than the risk deviation rate threshold, a risk controllable information is sent.

[0048] Among them, in order to assess the degree of leasing risk and determine whether it is controllable, the data on the stability of the debt repayment ability of the leasing object and the reliability data on the behavior of the leasing object are combined with the market behavior variation data and processed through a preset leasing risk assessment model to obtain an Internet leasing risk index, which reflects the overall risk level of the leasing business in the current market environment. The Internet leasing risk index is compared with the preset risk index to obtain a risk deviation rate, which is then compared with the preset risk deviation rate threshold. If the risk deviation rate is greater than or equal to the risk deviation rate threshold, a high-risk message is sent, indicating that the risk level of the current leasing business is high and corresponding measures need to be taken to reduce the risk; if the risk deviation rate is less than the risk deviation rate threshold, a controllable risk message is sent, indicating that the risk level of the current leasing business is within a controllable range and business operations can continue; The calculation formula of the lease risk assessment model is: ; in, is the Internet rental risk index, They are the data on the stability of the leasing object's debt repayment ability, the data on the reliability of the leasing object's behavior and the data on market behavior anomalies. It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset market behavior monitoring database).

[0049] According to an embodiment of the present invention, the further embodiment includes: Obtaining usage record information of the leased item within the preset time period; Extracting usage frequency data and failure rate data based on the usage record information of the leased item; Querying a preset value list based on the usage frequency data and the failure rate data to obtain a depreciation ratio of the leased property; Comparing the depreciation ratio of the leased property with a preset depreciation threshold; If the depreciation ratio of the leased property is less than or equal to the depreciation threshold, the leased property will be assigned a low value rating and appropriate countermeasures will be taken; If the depreciation ratio of the leased property is greater than the depreciation threshold, the leased property will be given a high value level.

[0050] To assess the value of the leased property and implement appropriate management measures, the system collects usage records for a preset time period, extracts usage frequency data and failure rate data, and then searches through a preset value list to obtain the leased property's depreciation ratio. This ratio is compared with a preset depreciation threshold. If the depreciation ratio is less than or equal to the threshold, the property is assigned a low value rating and appropriate measures are taken, such as shortening the lease period, increasing rent, or increasing the deposit, to reduce potential losses. If the depreciation ratio is greater than the threshold, the property is assigned a high value rating, requiring better maintenance and service to improve tenant satisfaction and loyalty.

[0051] According to an embodiment of the present invention, the further embodiment includes: Inputting the data on the stability of the debt repayment ability of the leased object, the data on the reliability of the behavior of the leased object, the data on the abnormal market behavior, and the Internet lease risk index into the lease behavior identification knowledge graph; Update the rental behavior recognition knowledge graph according to a preset frequency and obtain an update result; Obtaining parameter change rate data according to the update result; Comparing the parameter change rate data with a preset change rate threshold; If the parameter change rate data is greater than or equal to the change rate threshold, an update verification message is sent; If the parameter change rate data is less than the change rate threshold, an update success message is sent.

[0052] Among them, in order to realize the automatic completion of ring networking, the debt repayment ability stability data of the leasing object, the behavior reliability data of the leasing object, the market behavior abnormality data and the Internet leasing risk index are input into the leasing behavior identification knowledge graph, and the leasing behavior identification knowledge graph is updated according to the preset frequency and the update result is obtained. The parameter change rate data is obtained according to the update result, and then compared with the preset change rate threshold. If the parameter change rate data is greater than or equal to the change rate threshold, an update verification information is sent, indicating that the parameters in the graph have changed significantly and may need further verification; if the parameter change rate data is less than the change rate threshold, an update success information is sent, indicating that the parameter changes in the graph are within the normal range and the update is successful.

[0053] The third aspect of the present invention provides a computer-readable storage medium, which includes an Internet leasing risk control method program based on a knowledge graph. When the Internet leasing risk control method program based on a knowledge graph is executed by a processor, the steps of the Internet leasing risk control method based on a knowledge graph as described in any one of the above items are implemented.

[0054] The present invention discloses a knowledge graph-based internet leasing risk control method, system, and medium. The method, system, and medium utilize an internet leasing system platform to obtain information about leased items, lease models, and basic information about leased entities within a preset time period, construct a knowledge graph for identifying leasing behavior, and then extract information about repayment capacity and credit behavior. Based on the repayment capacity information, a pre-set debt capacity database is queried to obtain data on the leasing entity's debt repayment stability. Based on the credit behavior information, a pre-set credit behavior database is queried to obtain data on the leasing entity's behavior reliability. Market behavior change information within the preset time period is obtained and processed using a pre-set market risk assessment model to obtain market behavior anomaly data. Finally, the pre-set leasing risk assessment model processes the data on the leasing entity's debt repayment stability and reliability, combined with the market behavior anomaly data, to obtain an internet leasing risk index. This index is then compared with the pre-set risk index to assess the internet leasing risk control situation. By utilizing pre-established debt capacity and credit behavior databases, the present application can determine the leasing entity's debt repayment capacity and behavioral reliability. The repayment capacity and credit behavior information provide a solid foundation for risk assessment. Market behavior anomalies are then determined based on market behavior changes. Combining these three pieces of information, the leasing risk index is ultimately obtained. In addition, the data on the stability of the debt repayment ability of the lease object, the reliability data on the behavior of the lease object, the market behavior change data and the Internet leasing risk index will be reversely input into the leasing behavior identification knowledge graph, and the data will be updated at a preset frequency, thereby realizing the rapid and accurate calculation of real-time indicators of Internet leasing risk control business data. The indicator update can be completed at the moment the business data is generated or in a very short time, providing strong support for real-time risk control decision-making, improving resource utilization and reducing operating costs.

[0055] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0056] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0057] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0058] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories, random access memories, magnetic disks or optical disks, and other media that can store program codes.

[0059] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as standalone products, they can also be stored on a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. The Internet leasing risk control method based on knowledge graph is characterized by: The following steps are involved: Obtain the leased property information, lease model information and basic information of the leased object within a preset time period through the Internet leasing system platform, build a knowledge graph for leasing behavior identification, and extract repayment ability information and credit behavior information; According to the repayment ability information, query the preset debt capacity database to obtain the debt repayment ability stability data of the lease object; According to the credit behavior information, a query is performed through a preset credit behavior database to obtain the behavior reliability data of the lease object; Obtaining market behavior change information within the preset time period and processing it through a preset market risk assessment model to obtain market behavior anomaly data; The internet leasing risk index is obtained by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data through a preset leasing risk assessment model and comparing it with the preset risk index to judge the risk control situation of internet leasing.

2. The Internet leasing risk control method based on knowledge graph according to claim 1 is characterized in that: The construction of the rental behavior identification knowledge graph is specifically as follows: Obtaining rental information, rental model information and basic information of the rental object within a preset time period through the Internet rental system platform; The leased property information includes leased property type information, leased property quantity information and leased property status information; The lease mode information includes lease term information, rent payment method information and lease terms information; The basic information of the leased object includes the identity information, communication information and basic credit record information of the leased object; A knowledge graph for identifying leasing behavior is constructed based on the leased item information, leasing model information, and basic information of the leased object, and repayment ability information and credit behavior information are extracted.

3. The Internet leasing risk control method based on knowledge graph according to claim 2 is characterized in that: The data on the stability of the debt repayment ability of the leased object is obtained as follows: extracting asset and liability information, cash transaction record information, and profit information based on the solvency information; According to the asset and liability information, cash transaction record information and profit information, a query is performed through a preset debt capacity database to obtain the debt repayment ability stability data of the lease object.

4. The Internet leasing risk control method based on knowledge graph according to claim 3 is characterized in that: The obtaining of the rental object behavior reliability data is specifically as follows: Extracting historical loan record information, consumption habit information, public affairs payment record information and social behavior information based on the credit behavior information; According to the historical loan record information, consumption habit information, public affairs payment record information and social behavior information, a query is performed through a preset credit behavior database to obtain the reliability data of the rental object's behavior.

5. The Internet leasing risk control method based on knowledge graph according to claim 4 is characterized in that: The obtaining of market behavior abnormality data is specifically as follows: Obtaining market behavior change information within the preset time period; Extracting value volatility data, demand mutation data, and market share data based on the market behavior change information; The value volatility data, demand mutation data and market share data are processed through a preset market risk assessment model to obtain market behavior abnormality data.

6. The Internet leasing risk control method based on knowledge graph according to claim 5 is characterized in that: The judgment of the risk control situation of Internet leasing is specifically as follows: Obtaining an internet leasing risk index by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data using a preset leasing risk assessment model; Comparing the Internet rental risk index with a preset risk index to obtain a risk deviation rate; comparing the risk deviation rate with a preset risk deviation rate threshold; If the risk deviation rate is greater than or equal to the risk deviation rate threshold, a high-risk message is sent; If the risk deviation rate is less than the risk deviation rate threshold, a risk controllable information is sent.

7. The Internet leasing risk control system based on knowledge graph is characterized by: The system comprises a memory and a processor, wherein the memory comprises a knowledge graph-based internet leasing risk control method program, and when the knowledge graph-based internet leasing risk control method program is executed by the processor, the following steps are implemented: Obtain the leased property information, lease model information and basic information of the leased object within a preset time period through the Internet leasing system platform, build a knowledge graph for leasing behavior identification, and extract repayment ability information and credit behavior information; According to the repayment ability information, query the preset debt capacity database to obtain the debt repayment ability stability data of the lease object; According to the credit behavior information, a query is performed through a preset credit behavior database to obtain the behavior reliability data of the lease object; Obtaining market behavior change information within the preset time period and processing it through a preset market risk assessment model to obtain market behavior anomaly data; The internet leasing risk index is obtained by processing the data on the stability of the leasing object's debt repayment ability and the reliability of the leasing object's behavior in combination with the market behavior anomaly data through a preset leasing risk assessment model and comparing it with the preset risk index to judge the risk control situation of internet leasing.

8. The Internet leasing risk control system based on knowledge graph according to claim 7 is characterized in that: The construction of the rental behavior identification knowledge graph is specifically as follows: Obtaining rental information, rental model information and basic information of the rental object within a preset time period through the Internet rental system platform; The leased property information includes leased property type information, leased property quantity information and leased property status information; The lease mode information includes lease term information, rent payment method information and lease terms information; The basic information of the leased object includes the identity information, communication information and basic credit record information of the leased object; A knowledge graph for identifying leasing behavior is constructed based on the leased item information, leasing model information, and basic information of the leased object, and repayment ability information and credit behavior information are extracted.

9. The Internet leasing risk control system based on knowledge graph according to claim 8 is characterized in that: The data on the stability of the debt repayment ability of the leased object is obtained as follows: extracting asset and liability information, cash transaction record information, and profit information based on the solvency information; According to the asset and liability information, cash transaction record information and profit information, a query is performed through a preset debt capacity database to obtain the debt repayment ability stability data of the lease object.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a knowledge graph-based Internet leasing risk control method program. When the knowledge graph-based Internet leasing risk control method program is executed by a processor, the steps of the knowledge graph-based Internet leasing risk control method as described in any one of claims 1 to 6 are implemented.

Images