CN-122019633-A - Service object query method and device and electronic equipment

CN122019633ACN 122019633 ACN122019633 ACN 122019633ACN-122019633-A

Abstract

The application discloses a service object query method and device and electronic equipment. The method comprises the steps of determining target service objects from P preset service objects according to target service types in a query request in a target relation map, determining service objects with connection relation with the target service objects in the target relation map to obtain H first service objects, determining strength values of connection relation between each first service object and the target service objects to obtain H target strength values, selecting Q third service objects according to the H target strength values and the target service types, and determining the Q third service objects as query results of the service object query request. The application solves the problems of lower accuracy rate of inquiring the service object, smaller inquiring range and lower service popularization efficiency in the related technology.

Inventors

HUANG WENCHEN
NI XIAOPING
ZHANG PEIYU

Assignees

中国工商银行股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260113

Claims (10)

1. A method for querying a business object, comprising: Receiving a query request sent by a financial institution, and determining a target service object from P preset service objects in a target relation map according to a target service type in the query request, wherein the target relation map comprises N initial service objects, the N initial service objects comprise the P preset service objects, and P, N is a positive integer; Determining a service object with a connection relation with the target service object in the target relation map to obtain H first service objects, wherein each first service object has a direct connection relation or an indirect connection relation with the target service, and H is a positive integer; Determining the strength value of the connection relation between each first service object and the target service object to obtain H target strength values, selecting T second service objects from the H first service objects according to the H target strength values, and selecting Q third service objects from the T second service objects according to the target service type, wherein T, Q is a positive integer; And determining the Q third business objects as query results of the business object query requests.
2. The method of claim 1, wherein the target relationship map is constructed by: Acquiring first public attribute information of M internal business objects in the financial institution, and determining external associated objects of all the internal business objects according to the first public attribute information to obtain M groups of external business objects, wherein M is a positive integer; determining each external service object in the M internal service objects and the M groups of external service objects as an initial service object, obtaining N initial service objects, and determining the association relationship between the N initial service objects according to the first public attribute information and the second public attribute information, wherein the second public attribute information is the attribute information of each external service object in the M groups of external service objects; Generating initial relation graphs of the N initial business objects according to the association relation, carrying out group division on the N initial business objects in the initial relation graphs to obtain P groups, and determining preset business objects in each group to obtain P preset business objects; And determining an initial relation map for completing the determination operation of the P groups and the P preset business objects as the target relation map.
3. The method of claim 2, wherein grouping the N initial business objects in the initial relationship graph to obtain P groups comprises: determining a correlation strength value between each initial business object and adjacent initial business objects, and determining a dividing mode for primarily dividing the N initial business objects according to the correlation strength values to obtain an initial dividing mode; Calculating the modularity of the target relation graph under the initial division mode to obtain initial modularity, and carrying out iterative updating on the initial division mode to obtain the initial modularity of the initial division mode obtained after each iteration; And calculating the difference value of the initial modularity obtained by two adjacent iterative operations, stopping iterative updating operation under the condition that the difference value is smaller than a difference value threshold value, determining an initial dividing mode obtained after the last iterative updating as a target dividing mode, and carrying out group division on the N initial business objects in the target relation graph by using the target dividing mode to obtain P groups.
4. The method of claim 2, wherein determining the preset business objects in each group to obtain P preset business objects comprises: for any one target group, configuring an initial weight value for each service object in the target group, and obtaining the sum of node index values of upstream nodes of each service object to obtain a total node index value of each service object, wherein the node index value is a value obtained by dividing the upstream weight value of any upstream node by the total edge number of the upstream node, and the upstream weight value is obtained by multiplying the initial weight value and the edge weight of the upstream node; updating the initial weight value of each business object according to the total node index value and the damping factor of each business object to obtain an updated initial weight value, and repeatedly executing the updating operation of the initial weight value; And under the condition that the weight change rate between two adjacent weight updating operations is smaller than a preset threshold value, determining an initial weight value obtained after the last time of executing the updating operation of the initial weight value as a target weight value, and determining a service object with the maximum target weight value as a preset service object in the target group.
5. The method of claim 1, wherein determining the strength value of the connection relationship between each first business object and the target business object, obtaining H target strength values comprises: for any one first business object, acquiring the number of edges between the first business object and the target business object to obtain a first numerical value; calculating the total weight value of the edge between the first service object and the target service object to obtain a second value; and dividing the second numerical value by the first numerical value to obtain a target intensity value of the first business object.
6. The method of claim 1, wherein selecting T second business objects from the H first business objects based on the H target intensity values comprises: and determining the first business object with the target intensity value larger than an intensity value threshold value in the H first business objects as the second business object, and obtaining the T second business objects.
7. The method of claim 1, wherein selecting Q third business objects from the T second business objects according to the target business type comprises: acquiring service contents of each second service object, and determining an initial service type of each second service object according to the service contents; And determining the second service object with the same initial service type as the target service type as the third service object to obtain the Q third service objects.
8. A business object querying device, comprising: The first determining unit is used for receiving a query request sent by a financial institution, and determining a target service object from P preset service objects in a target relation map according to a target service type in the query request, wherein the target relation map comprises N initial service objects, the N initial service objects comprise the P preset service objects, and P, N is a positive integer; the second determining unit is used for determining the service object with the connection relation with the target service object in the target relation map to obtain H first service objects, wherein each first service object has a direct connection relation or an indirect connection relation with the target service, and H is a positive integer; A third determining unit, configured to determine an intensity value of a connection relationship between each first service object and the target service object, obtain H target intensity values, select T second service objects from the H first service objects according to the H target intensity values, and select Q third service objects from the T second service objects according to the target service type, where T, Q is a positive integer; and the fourth determining unit is used for determining the Q third business objects as the query results of the business object query requests.
9. A computer program product comprising computer instructions which, when executed by a processor, implement the steps of the business object querying method of any of claims 1 to 7.
10. An electronic device, comprising: A memory storing an executable program; a processor for running the program, wherein the program runs to perform the method of querying a business object according to any of claims 1 to 7.

Description

Service object query method and device and electronic equipment Technical Field The present application relates to the field of big data, and in particular, to a method and an apparatus for querying a service object, and an electronic device. Background When the financial institutions expand the service, the success rate can be improved when the service is expanded by determining which service objects have higher matching degree with the service to be expanded. However, when the business objects are inquired, the business objects can be inquired only for the business objects reserved in the financial institutions, and the matching degree between the inquired business objects and the business to be expanded cannot be determined, so that the inquired business objects are incomplete and inaccurate, and further the efficiency of the follow-up business popularization is lower. Aiming at the problems that in the related technology, the accuracy rate of inquiring the service object is low, the inquiring range is small, and the service popularization efficiency is low, no effective solution is proposed at present. Disclosure of Invention The application mainly aims to provide a query method, a query device and electronic equipment for service objects, which are used for solving the problems that the accuracy of querying the service objects is low, the query range is small, and the service popularization efficiency is low in the related technology. In order to achieve the above object, according to one aspect of the present application, there is provided a query method of a business object. The method comprises the steps of receiving a query request sent by a financial institution, determining target business objects from P preset business objects according to target business types in the query request in a target relation graph, wherein the target relation graph comprises N initial business objects, the N initial business objects comprise P preset business objects, P, N are positive integers, determining business objects with connection relation with the target business objects in the target relation graph to obtain H first business objects, wherein each first business object has direct connection relation or indirect connection relation with the target business, H is a positive integer, determining the strength value of the connection relation between each first business object and the target business object to obtain H target strength values, selecting T second business objects from the H first business objects according to the H target strength values, selecting Q third business objects from the T second business objects according to the target business types, wherein T, Q is a positive integer, and determining the Q third business objects as query results of the business object query request. Optionally, the target relation graph is constructed by acquiring first public attribute information of M internal business objects in a financial institution, determining external association objects of all internal business objects according to the first public attribute information to obtain M groups of external business objects, wherein M is a positive integer, determining all external business objects in the M internal business objects and the M groups of external business objects as initial business objects to obtain N initial business objects, determining association relations among the N initial business objects according to the first public attribute information and second public attribute information, wherein the second public attribute information is attribute information of all external business objects in the M groups of external business objects, generating initial relation graphs of the N initial business objects according to the association relations, performing group division on the N initial business objects in the initial relation graph to obtain P groups, determining preset business objects in all groups to obtain P preset business objects, and determining the initial relation of the P groups and the P preset business objects as the target relation. Optionally, grouping N initial business objects in the initial relation map to obtain P groups, wherein the P groups comprise determining the association strength value between each initial business object and the adjacent initial business object, determining the preliminary division mode of the N initial business objects according to the association strength value to obtain an initial division mode, calculating the modularity of the target relation map in the initial division mode to obtain initial modularity, carrying out iterative updating on the initial division mode to obtain the initial modularity of the initial division mode obtained after each iteration, calculating the difference value of the initial modularity obtained by the two adjacent iterative operations, stopping iterative updating operation when the difference value is smaller than a differe