Insurance policy claim settlement risk assessment method and device, electronic equipment and storage medium

Abstract

The invention relates to the field of artificial intelligence, and discloses an insurance policy claim risk assessment method, which comprises the steps of obtaining a claim insurance policy which comprises an insurance policy picture and an insurance policy text; inputting the insurance policy picture into a picture detection model so as to detect a target region of the insurance policy picture through a region detection network in the picture detection model, identifying a region category of the target region by using a region classification network in the picture detection model, extracting structured information of the target region, taking the region category and the structured information as picture features of the insurance policy picture; extracting text features of the insurance policy text by using a text semantic recognition model; and respectively calculating index scores of the picture features and the text features by using an insurance policy risk score table so as to calculate a risk score of the claim insurance policy, and determining a risk level of the claim insurance policy according to the risk score. In addition, the invention also relates to a block chain technology, and the claim settlement insurance policy can be stored in a block chain. The risk control accuracy of insurance policy claim settlement can be improved.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a risk assessment method, device, electronic equipment and computer-readable storage medium for policy claims. Background technique [0002] Insurance fraud has always been an important part of insurance risk control and claim settlement, such as auto insurance fraud. Due to the weak legal concept of some customers, the fraud risk prevention of insurance companies is not in place, resulting in a large number of fraud cases in the normal insurance claim settlement process. Therefore, the anti-fraud of insurance claims is becoming more and more important. The anti-fraud of insurance claims refers to the settlement of claims by insurance companies for the insured targets of their companies and the occurrence of responsible accidents within the validity period of the policy. The act of analyzing the situation. [0003] At present, the risk control of insurance claims i...

AI Technical Summary

Problems solved by technology

[0003] At present, the risk control of insurance claims is usually implemented by using a rule engine and a statistical model. The rule engine refers to the use of business experience by claim experts to write specific claim settlement rules for risk control of claim settlement policies. However, each claim expert has different business experience. As a result, there will be differences in the written claim settlement rules, which will affect the accuracy of the risk control of the claim settlement policy. The statistical model refers to the construction of an anti-fraud model based on the characteristics of historical claim settlement cases to control the risk of the claim settlement policy. However, this method uses traditional mathematical statistics method, resulting in limited data processing capacity, which will also affect the accuracy of risk control of claims policy

Images