Data clustering identification method and device, computer system and readable storage medium

Abstract

The invention discloses a data clustering identification method and device, a computer system and a readable storage medium, and the method is based on artificial intelligence, and comprises the following steps: setting one case in a case library as a reference case, and setting other cases, except the reference case, in the case library as contrast cases; sequentially judging whether an association relationship exists between the reference case and each contrast case or not, and making a one-dimensional vector; sequentially obtaining one-dimensional vectors of all cases in the case library, and combining the one-dimensional vectors of all cases to obtain an adjacent matrix; calculating an adjacency matrix to obtain a dense vector; calculating a dense vector so as to cluster all cases in the case library and output a clustering result; and calculating a risk value of the case according to the insurance policy information, the automobile features and the case reporter features of the case in the clustering result. According to the method, the high-risk cases are obtained by analyzing the cases in the cluster below the clustering threshold, so that practitioners can perform key analysis on the high-risk cases to identify suspected fraudulent cases which are not compensated or reported in the high-risk cases.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a data clustering identification method, device, computer system and readable storage medium. Background technique [0002] The current insurance anti-fraud scheme mainly uses black and white list rules to screen cases. However, the existing black and white list rule engines can only rely on human experience. Increased fatigue strength, resulting in increased personnel costs; [0003] If the method of supervised learning modeling is adopted according to the rules of the black and white list, and a mature neural network is made to screen cases, a large amount of labeled data, that is, cases suspected of fraud, are required for the neural network to learn; In , it is difficult to obtain a large amount of labeled data, so this method is often difficult to implement in practice, and it is difficult to make an effective and reliable mature neural network. Contents of the inv...

AI Technical Summary

Problems solved by technology

[0002] The current insurance anti-fraud scheme mainly uses black and white list rules to screen cases. However, the existing black and white list rule engines can only rely on human experience. Increased fatigue strength, resulting in increased personnel costs;

[0003] If the method of supervised learning modeling is adopted according to the rules of the black and white list, and a mature neural network is made to screen cases, a large amount of labeled data, that is, cases suspected of fraud, are required for the neural network to learn; In , it is difficult to obtain a large amount of labeled data, so this method is often difficult to implement in practice, and it is difficult to make an effective and reliable mature neural network

Images