Fraud monitoring method, system and storage medium for medical insurance groups

Abstract

The present invention provides a method for monitoring medical insurance group fraud, the method comprising the following steps: step S1, generating patient analysis data sets; step S2, calculating the similarity between patients; step S3, mining extremely similar groups that are highly similar to each other ; Step S4, manually reviewing and judging suspicious groups according to the medical treatment details of the group members. The present invention also proposes a fraud monitoring system for medical insurance groups, including: a memory, storing a computer program; a processor, used to run the computer program, and the computer program executes the above method except step S4 when running step. The present invention is convenient for accurate and efficient identification of abnormal groups with medical insurance fund fraud and violations of laws and regulations.

Description

technical field [0001] The invention relates to the field of anti-fraud of medical insurance funds, in particular to a method and system for monitoring fraud of medical insurance groups. Background technique [0002] At present, the application system in the field of medical insurance anti-fraud in my country is mainly to establish a rule base by summarizing the fraud cases that have occurred in the actual business. As time goes by, the patterns of fraudulent behavior become more and more complex and diverse, and it is difficult to remove the solidified rule base. Identify new fraudulent behavior. In addition, fraud detection rules defined by experts are used to delineate suspected fraudulent behaviors. It is very difficult to choose thresholds and weights in the rules. In addition, the diagnosis and treatment in the treatment are highly professional and fraudulent behaviors are relatively hidden. Rationality makes the accuracy rate extremely low. [0003] In reality, due t...

AI Technical Summary

Problems solved by technology

[0002] At present, the application system in the field of medical insurance anti-fraud in my country is mainly to establish a rule base by summarizing the fraud cases that have occurred in the actual business. As time goes by, the patterns of fraudulent behavior become more and more complex and diverse, and it is difficult to remove the solidified rule base. Identify new fraudulent behavior

In addition, fraud detection rules defined by experts are used to delineate suspected fraudulent behaviors. It is very difficult to choose thresholds and weights in the rules. In addition, the diagnosis and treatment in the treatment are highly professional and fraudulent behaviors are relatively hidden. Rationality makes the accuracy rate extremely low

[0003] In reality, due to the concealment of fraudulent behavior, the complexity of the actors, the high incidence and diversity of fraudulent cases, and the limitations of the anti-fraud capabilities of the medical insurance department, it is very difficult to intuitively judge fraudulent behavior. Direct screening Fraud cases are even more difficult

Images