CN-120765389-B - Intelligent verification method, device, equipment and medium based on knowledge graph deduction

CN120765389BCN 120765389 BCN120765389 BCN 120765389BCN-120765389-B

Abstract

The disclosure provides an intelligent underwriting method, device, equipment and medium based on knowledge graph deduction, which comprise the steps of obtaining health representation data of a target entity object, performing medical deduction analysis on the health representation data through a medical knowledge graph to obtain a medical evolution factor sequence, determining a medical deduction factor from the medical evolution factor sequence according to application time information and the health representation data of the target entity object, performing intelligent underwriting analysis on the health representation data to obtain intelligent underwriting information, determining dynamic evolution probability of the target entity object corresponding to the medical deduction factor according to historical evolution data between the health representation data and the medical deduction factor, and performing information optimization on intelligent underwriting information corresponding to the target entity object based on the dynamic evolution probability of the target entity object corresponding to the medical deduction factor to obtain the objective underwriting information corresponding to the target entity object. Thereby effectively improving the accuracy of intelligent underwriting.

Inventors

Request for anonymity
Request for anonymity

Assignees

浙江华方睿保科技有限公司

Dates

Publication Date: 20260505
Application Date: 20250606

Claims (9)

1. The intelligent verification method based on knowledge graph deduction is characterized by comprising the following steps of: obtaining health characterization data of a target entity object, wherein the health characterization data of the target entity object are screened from historical visit information of the target entity object; the medical analysis method comprises the steps of matching a plurality of corresponding associated evolution factors from a medical knowledge graph based on health characterization data of a target entity object, calculating an evolution fusion value between the health characterization data of the target entity object and each associated evolution factor, determining a plurality of node evolution factors related to the health characterization data of the target entity object based on the evolution fusion value between the health characterization data of the target entity object and each associated evolution factor, and generating a medical evolution factor sequence related to the health characterization data of the target entity object based on the plurality of node evolution factors related to the health characterization data of the target entity object; acquiring the insuring time information of the target entity object, and determining a medical deduction factor mapped by the target entity object corresponding to the insuring time information from the medical evolution factor sequence according to the insuring time information of the target entity object and the health characterization data of the target entity object; performing intelligent underwriting analysis on the health characterization data of the target entity object to obtain intelligent underwriting information corresponding to the target entity object; Acquiring historical evolution data between the health characterization data of the target entity object and the medical deduction factor, and determining the dynamic evolution probability of the target entity object corresponding to the medical deduction factor according to the historical evolution data between the health characterization data of the target entity object and the medical deduction factor; And based on the dynamic evolution probability of the target entity object corresponding to the medical deduction factor, carrying out information optimization on the intelligent underwriting information corresponding to the target entity object to obtain the target underwriting information corresponding to the target entity object.
2. The method of claim 1, wherein determining, from the sequence of medical evolution factors, the medical deduction factor mapped by the target entity object corresponding to the time of application information based on the time of application information of the target entity object and the health characterization data of the target entity object, comprises: Estimating the evolution time of a plurality of node evolution factors contained in the medical evolution factor sequence based on the health representation data of the target entity object to obtain the corresponding estimated evolution time when the node evolution factors are evolved to each node evolution factor; And matching the estimated evolution time length corresponding to each node evolution factor and the insuring time information of the target entity object to obtain the medical deduction factor mapped by the target entity object corresponding to the insuring time information.
3. The method of claim 1, wherein the performing intelligent underwriting analysis on the health characterization data of the target entity object to obtain intelligent underwriting information corresponding to the target entity object comprises: determining a corresponding intelligent nuclear care analysis model from a disease model library based on the medical nuclear care type of the target entity object, and determining health characterization features related to the medical nuclear care type from health characterization data of the target entity object; Inputting health characterization features related to the medical insurance type into the intelligent insurance analysis model, and determining the underwriting risk probability of the target entity object corresponding to the medical insurance type based on the output of the intelligent insurance analysis model; and determining intelligent underwriting information corresponding to the target entity object based on the underwriting risk probability of the target entity object corresponding to the medical underwriting type.
4. The method of claim 1, wherein the obtaining historical evolution data between the health characterization data of the target entity object and the medical deduction factor comprises: acquiring a first entity object set, wherein the first entity object set comprises a plurality of other entity objects, and each other entity object has an association relation with the medical deduction factor; acquiring health characterization data of each other entity object in the first entity object set; performing time matching from the health characterization data of a plurality of other entity objects based on the insuring time information of the target entity object to obtain a second entity object set; based on the number of other entity objects in the second set of entity objects and the number of other entity objects in the first set of entity objects, historical evolution data between the health characterization data of the target entity object and the medical deduction factor is determined.
5. The method according to claim 1, wherein the performing information optimization on the intelligent underwriting information corresponding to the target entity object based on the dynamic evolution probability of the target entity object corresponding to the medical deduction factor to obtain the target underwriting information corresponding to the target entity object includes: Determining corresponding underwriting optimization parameters and parameter optimization data from an evolution rule set based on the dynamic evolution probability of the target entity object corresponding to the medical deduction factor; And carrying out parameter adjustment on the underwriting optimization parameters included in the intelligent underwriting information corresponding to the target entity object based on the parameter optimization data to obtain target underwriting information corresponding to the target entity object.
6. A method according to claim 3, further comprising: Medical characteristic query is carried out on the target entity object, and medical response characteristics are obtained; Feature screening is carried out on the medical response features based on the medical insurance type to obtain insurance related features related to the medical insurance type; And performing feature adjustment on the health characterization features related to the medical insurance type based on the insurance related features related to the medical insurance type.
7. An intelligent underwriting device based on knowledge graph deduction is characterized by comprising: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring health representation data of a target entity object, and the health representation data of the target entity object is screened from historical visit information of the target entity object; The first analysis module is used for carrying out medical deduction analysis on the health representation data of the target entity object through a medical knowledge graph to obtain a medical evolution factor sequence associated with the health representation data of the target entity object; the first analysis module is specifically configured to match a plurality of corresponding associated evolution factors from a medical knowledge graph based on the health characterization data of the target entity object, and calculate an evolution fusion value between the health characterization data of the target entity object and each associated evolution factor; determining a plurality of node evolution factors related to the health characterization data of the target entity object based on the evolution fusion value between the health characterization data of the target entity object and each associated evolution factor; The first determining module is used for acquiring the application time information of the target entity object, and determining a medical deduction factor mapped by the target entity object corresponding to the application time information from the medical evolution factor sequence according to the application time information of the target entity object and the health characterization data of the target entity object; The second analysis module is used for performing intelligent underwriting analysis on the health characterization data of the target entity object to obtain intelligent underwriting information corresponding to the target entity object; a second determining module, configured to obtain historical evolution data between the health characterization data of the target entity object and the medical deduction factor, and determine a dynamic evolution probability of the target entity object corresponding to the medical deduction factor according to the historical evolution data between the health characterization data of the target entity object and the medical deduction factor; And the optimization module is used for carrying out information optimization on the intelligent underwriting information corresponding to the target entity object based on the dynamic evolution probability of the target entity object corresponding to the medical deduction factor to obtain the target underwriting information corresponding to the target entity object.
8. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the knowledge-graph-based deduction intelligent underwriting method according to any one of claims 1 to 6 when executing the computer program.
9. A computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the knowledge-graph-deduction-based intelligent underwriting method according to any one of claims 1 to 6.

Description

Intelligent verification method, device, equipment and medium based on knowledge graph deduction Technical Field The embodiment of the disclosure relates to the technical field of intelligent nuclear protection, in particular to an intelligent nuclear protection method, device, equipment and medium suitable for deduction based on a knowledge graph. Background The insurance can ensure the fairness and legality of insurance transactions while protecting the interests of insurance companies and insurance applicant, and simultaneously help the insurance companies accurately evaluate the risk level to prevent the accumulation of bad risks. Therefore, when purchasing insurance, the applicant should understand and cooperate with the verification process to provide real and accurate personal information so as to obtain proper insurance. In the related art, most of the existing kernel protection systems adopt a layering mode of database, platform layer and application layer. The data layer integrates multi-source data such as historical data of an applicant, medical records, financial information and the like, the platform layer comprises a rule engine and an AI (ARTIFICIAL INTELLIGENCE ) model and supports automatic decision making, and the application layer realizes an interactive nuclear protection flow through technologies such as OCR (Optical Character Recognition ) and the like. However, in the existing method, the verification accuracy is not high. Disclosure of Invention Embodiments described herein provide an intelligent underwriting method, apparatus, device, and medium based on knowledge-graph deduction, which overcome the above-described problems. According to a first aspect of the present disclosure, there is provided an intelligent underwriting method based on knowledge-graph deduction, including: obtaining health characterization data of a target entity object, wherein the health characterization data of the target entity object are screened from historical visit information of the target entity object; medical deduction analysis is carried out on the health representation data of the target entity object through a medical knowledge graph, and a medical evolution factor sequence associated with the health representation data of the target entity object is obtained; acquiring the insuring time information of the target entity object, and determining a medical deduction factor mapped by the target entity object corresponding to the insuring time information from the medical evolution factor sequence according to the insuring time information of the target entity object and the health characterization data of the target entity object; performing intelligent underwriting analysis on the health characterization data of the target entity object to obtain intelligent underwriting information corresponding to the target entity object; Acquiring historical evolution data between the health characterization data of the target entity object and the medical deduction factor, and determining the dynamic evolution probability of the target entity object corresponding to the medical deduction factor according to the historical evolution data between the health characterization data of the target entity object and the medical deduction factor; And based on the dynamic evolution probability of the target entity object corresponding to the medical deduction factor, carrying out information optimization on the intelligent underwriting information corresponding to the target entity object to obtain the target underwriting information corresponding to the target entity object. According to a second aspect of the present disclosure, there is provided an intelligent underwriting apparatus based on knowledge-graph deduction, including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring health representation data of a target entity object, and the health representation data of the target entity object is screened from historical visit information of the target entity object; the first analysis module is used for carrying out medical deduction analysis on the health representation data of the target entity object through a medical knowledge graph to obtain a medical evolution factor sequence associated with the health representation data of the target entity object; The first determining module is used for acquiring the application time information of the target entity object, and determining a medical deduction factor mapped by the target entity object corresponding to the application time information from the medical evolution factor sequence according to the application time information of the target entity object and the health characterization data of the target entity object; The second analysis module is used for performing intelligent underwriting analysis on the health characterization data of the target entity object to obtain