Search

CN-122022962-A - Credit evaluation-based deposit money-free service management method and system

CN122022962ACN 122022962 ACN122022962 ACN 122022962ACN-122022962-A

Abstract

The invention discloses a credit evaluation-based deposit money-free service management method and system, and relates to the technical field of service management. The method comprises the steps of traversing a user set in a deposit money-free service, constructing a no-leasing multi-source behavior data set, constructing a deposit money-free service relation diagram, constructing a credit homogamete diagram and a risk heterogamete diagram, carrying out feature analysis on the credit homogamete diagram and the risk heterogamete diagram to obtain user stability credit features and user risk abnormality features, carrying out feature fusion based on the user stability credit features and the user risk abnormality features to obtain a user comprehensive credit evaluation result, and carrying out deposit money-free service management decision analysis on a target user to obtain a deposit money-free management strategy. The technical problem of insufficient reliability of service management decisions caused by inaccurate credit assessment of a user in deposit money-free service in the prior art is solved, and the technical effects of improving credit assessment accuracy and enhancing reliability of service management decisions through multisource behavior data association analysis are achieved.

Inventors

  • Wu Feineng

Assignees

  • 赞童(厦门)科技有限公司

Dates

Publication Date
20260512
Application Date
20260213

Claims (10)

  1. 1. A credit-assessment-based deposit money-free service management method, the method comprising: Traversing a user set in the deposit money-free service, collecting user information, lease order information, equipment information, address information and payment account information corresponding to each user, and constructing a deposit money-free multisource behavior data set; constructing a deposit money-free business relationship graph based on the free-leasing multi-source behavioral data set, wherein the deposit money-free business relationship graph comprises business relationship edges and multi-type nodes; Performing relationship heteroleptic identification based on characteristic differences of nodes at two ends of a service relationship edge in the deposit money-free service relationship graph by taking a target user as an index, and constructing a credit homogamete graph and a risk heteroleptic graph; respectively carrying out feature analysis on the credit homogamete graph and the risk heterogamete graph to obtain user stability credit features and user risk abnormality features; performing feature fusion based on the user stability credit feature and the user risk abnormality feature to obtain a user comprehensive credit assessment result; And executing deposit money-free service management decision analysis on the target user based on the comprehensive credit evaluation result of the user to obtain deposit money-free management strategy.
  2. 2. A credit assessment based deposit money-free service management method as recited in claim 1, wherein said deposit money-free service relationship graph includes multiple types of nodes including user nodes, device nodes, address nodes, and payment account nodes; the service relationship edges in the deposit money-free service relationship graph are used to describe the service relationships between user nodes, device nodes, address nodes, and payment account nodes.
  3. 3. The credit-evaluation-based exempt deposit money land management method as claimed in claim 1, wherein the constructing a credit homogamete graph and a risk heterogamete graph based on the feature differences of the two end nodes of the business relationship edge in the exempt deposit money land graph with the target user as an index comprises: Performing K-order association extraction on the deposit money-free service relation diagram by taking a target user as an index to obtain an association deposit money-free service relation diagram, wherein K is a positive integer greater than or equal to 2; Traversing nodes in the association-free deposit money-land service relation graph according to a preset credit index to extract node credit characteristics and obtain a node credit characteristic set; And taking a corresponding target node of the target user in the association free deposit money service relation diagram as a starting point, and executing relation heteroleptic identification by combining the node credit feature set to construct the credit homogamete diagram and the risk heteroleptic diagram.
  4. 4. The credit-evaluation-based deposit money-game-play-free management method of claim 3, wherein said predetermined credit criteria include a normal performance rate of historical rental orders, a overdue order rate, a number of default orders, a pre-return order rate, and a frequency of order cancellation per unit time.
  5. 5. The credit-evaluation-based deposit money-free business management method of claim 3, wherein performing relational heteroleptic identification in combination with said node credit feature set with a corresponding target node of said target user in said associated deposit money-free business relationship graph as a starting point, constructing said credit homogamete graph and risk heteroleptic graph, comprising: traversing the service relation edge in the association-free deposit money-step service relation diagram, and executing feature difference analysis on nodes at two ends of the service relation edge by combining the node credit feature set to obtain a corresponding service relation edge feature difference result; And based on the characteristic difference result of the service relationship side, carrying out relationship heteroleptic identification on the service relationship side, and respectively mapping the service relationship side to a credit homogametic graph and a risk heteroleptic graph according to the relationship heteroleptic identification result.
  6. 6. The credit-evaluation-based deposit money-game-based service management method as set forth in claim 5, wherein traversing the service relationship edges in the association-game deposit money-game-graph, in combination with the node credit feature set, performing feature difference analysis on nodes at both ends of the service relationship edges to obtain corresponding service relationship edge feature difference results, includes: Node credit features of two end nodes of each service relation side are extracted from the node credit feature sets respectively, and a matched node credit feature set is constructed; respectively carrying out dimension alignment and difference calculation on the matched node credit feature set to obtain a multidimensional matched node credit feature set difference set; and taking the multi-dimensional matching node credit feature group difference degree set as a business relation edge feature difference result.
  7. 7. The credit-evaluation-based deposit money-free transaction management method as claimed in claim 1, wherein the feature analysis is performed on the credit homogamete graph and the risk heterogamete graph, respectively, to obtain a user-stable credit feature and a user risk anomaly feature, comprising: traversing the credit homogamete graph to analyze performance behavior, identity consistency and relationship stability, and obtaining user stability credit characteristics representing long-term credit performance of a target user; and traversing the risk heterogamete graph to analyze behavior differences and relationship conflicts, and obtaining user risk anomaly characteristics representing an anomaly behavior mode of the target user.
  8. 8. A credit-evaluation-based, deposit money-free transaction management method as recited in claim 7 wherein traversing the credit homogamete graph for performing performance, identity consistency, and relationship stability analysis obtains user-stable credit characteristics characterizing long-term credit performance of the target user, comprising: traversing the credit homogamete graph, extracting performance data in a plurality of lease periods, and executing stability analysis to obtain performance characteristics; extracting identity information data, equipment use data and address use data in the credit identical-match graph, and executing joint consistency analysis to obtain identity consistency characteristics; Counting the number of continuous association relations in the credit homoscore graph, and comparing the counted result with a preset number threshold value to obtain a relation stability characteristic; and summarizing the performance characteristics, the identity consistency characteristics and the relationship stability characteristics to obtain the user stability credit characteristics.
  9. 9. A credit-evaluation-based, deposit money-free transaction management method as defined in claim 7 wherein traversing said risk heterogamete graph for behavioral difference and relationship conflict analysis obtains user risk anomaly characteristics that characterize a target user anomaly behavior pattern, comprising: performing statistics on abnormal frequency of performance by traversing the credit gametock map to obtain abnormal frequency of performance; Traversing the credit homogamete graph to analyze the equipment sharing conflict degree and the address multiplexing abnormality degree to obtain the relation conflict strength; And summarizing the abnormal frequency of the performance and the relation conflict strength to obtain the abnormal risk characteristics of the user.
  10. 10. A credit-based, deposit money-free transaction management system for implementing a credit-based, deposit money-free transaction management method as claimed in any one of claims 1 to 9, said system comprising: The data acquisition module is used for traversing the user set in the deposit money-free service, acquiring user information, lease order information, equipment information, address information and payment account information corresponding to each user, and constructing a deposit money-free multisource behavior data set; The relation diagram construction module is used for constructing a deposit money-free business relation diagram based on the free-push lease multisource behavior data set, wherein the free-push deposit money-free business relation diagram comprises business relation edges and multi-type nodes; The subgraph construction module takes a target user as an index, carries out relationship heteroleptic recognition based on the characteristic difference of the nodes at the two ends of the service relationship side in the deposit money-free service relationship graph, and constructs a credit homogamete graph and a risk heterogamete graph; The feature analysis module is used for respectively carrying out feature analysis on the credit homogamete graph and the risk heterogamete graph to obtain user stability credit features and user risk abnormality features; the feature fusion module is used for executing feature fusion based on the user stable credit feature and the user risk abnormal feature to obtain a user comprehensive credit evaluation result; And the decision analysis module is used for executing deposit money-free service management decision analysis on the target user based on the comprehensive credit evaluation result of the user to obtain deposit money-free management strategy.

Description

Credit evaluation-based deposit money-free service management method and system Technical Field The invention relates to the technical field of service management, in particular to a deposit money-free service management method and system based on credit evaluation. Background Along with the rapid development of the operation modes of shared economy and light assets, deposit money-free businesses are widely applied to the fields of digital equipment leasing, traveling tool leasing, office equipment leasing and the like. The deposit money-free mode improves business conversion and market coverage by lowering user admission thresholds, but also places higher demands on risk control and credit assessment. The existing deposit money-free service generally performs credit judgment based on historical credit scores, payment records or simple behavior rules of users, and part of the system introduces third-party credit data for auxiliary evaluation. However, the above-described evaluation method focuses on single-dimension or static feature analysis, lacks structural modeling of association relationships between multisource behavior data, and has difficulty in identifying implicit associations, abnormal group behaviors, or risk propagation paths between users. When complex associated risks such as address sharing and frequent abnormal equipment circulation exist, the traditional credit evaluation model often cannot be effectively identified, so that a credit evaluation result is inaccurate, and the reliability of deposit money-unit-free service management decision is further affected. Disclosure of Invention The application provides a deposit money-free credit service management method and a deposit money-free credit service management system based on credit evaluation, which solve the technical problem of insufficient reliability of service management decision caused by inaccurate credit evaluation of a user in deposit money-free credit service in the prior art. In a first aspect of the present application, there is provided a credit-evaluation-based method of claim deposit money for exemption of a service, the method comprising: Traversing a user set in a service of no-deposit money, collecting user information, lease order information, equipment information, address information and payment account information corresponding to each user, constructing a data set of no-deposit money-multi-source behavior, constructing a service relation diagram of no-deposit money-level based on the data set of no-push lease multi-source behavior, wherein the service relation diagram of no-deposit money-level comprises a service relation side and multi-type nodes, carrying out relation heteroleptic identification based on characteristic differences of two end nodes of the service relation side in the service relation diagram of no-deposit money-level with a target user as an index, constructing a credit homogamete diagram and a risk heterogamete diagram, carrying out characteristic analysis on the credit homogamete diagram and the risk heterogamete diagram respectively to obtain user stable credit characteristics and user risk abnormal characteristics, carrying out characteristic fusion based on the user stable credit characteristics and the user risk abnormal characteristics to obtain a user comprehensive credit evaluation result, and carrying out service management decision analysis of no-deposit money-level service on the target user based on the user comprehensive credit evaluation result to obtain a no-deposit money-level policy management. In a second aspect of the application, there is provided a credit-based, credit-evaluation-based, deposit money-game-exemption service management system, said system comprising: The system comprises a data acquisition module, a relation graph construction module, a sub-graph construction module, a characteristic analysis module and a characteristic fusion module, wherein the data acquisition module traverses a user set in deposit money-free service, acquires user information, lease order information, equipment information, address information and payment account information corresponding to each user, constructs deposit money-free multisource behavior data set, the relation graph construction module constructs deposit money-free service relation graph based on the 3784-free lease multisource behavior data set, the deposit money-free service relation graph comprises a service relation edge and multiple types of nodes, the sub-graph construction module takes a target user as an index, carries out relation heteroleptic recognition based on characteristic differences of two end nodes of the service relation edge in the deposit money-free service relation graph, constructs a credit homogamer graph and a risk heteroleptic sub-graph, carries out characteristic analysis on the credit homogamer graph and the risk heterogamer graph respectively, obtains user stability credit characteristics and user