Insurance policy classification method and device, computer device and storage medium
By clustering the policy set and calculating factor risk values, the risk of the policies to be classified is automatically assessed, which solves the problem of large errors in manual classification and improves the accuracy of policy classification.
CN117113209BActive Publication Date: 2026-05-29CHINA PING AN PROPERTY INSURANCE CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA PING AN PROPERTY INSURANCE CO LTD
- Filing Date
- 2023-08-25
- Publication Date
- 2026-05-29
AI Technical Summary
Technical Problem
In the current technology, policy classification and risk identification mainly rely on manual methods, which are prone to errors and inaccuracies.
Method used
By acquiring a set of risky insurance policies, performing cluster analysis, calculating the factor risk values of policy factors, and determining the target cluster of policies to be classified based on similarity, the policy classification results are generated.
Benefits of technology
It enables automatic assessment of policy risks, improving the accuracy and efficiency of policy classification.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN117113209B_ABST
Abstract
The embodiment of the application belongs to the field of artificial intelligence and financial technology, and relates to a policy classification method and device, a computer device and a storage medium. The method comprises the following steps: acquiring a risk policy set; clustering all risk policies in the risk policy set to obtain a plurality of risk policy clusters; calculating a factor risk value of each policy factor in each risk policy cluster based on policy data of each risk policy in each risk policy cluster; acquiring a to-be-classified policy and determining a target policy cluster to which the to-be-classified policy belongs, the target policy cluster being one of the plurality of risk policy clusters; calculating a risk assessment value of the to-be-classified policy according to the factor risk value of each policy factor in the target policy cluster, and generating a policy classification result of the to-be-classified policy according to the risk assessment value. In addition, the application also relates to blockchain technology, and the risk policy set can be stored in a blockchain. The application improves the accuracy of policy classification.
Need to check novelty before this filing date? Find Prior Art