Package type medicine purchasing anomaly detection method based on FP-growth and graph network

Abstract

The invention belongs to the technical field of medical data mining, and particularly relates to a package type medicine purchasing anomaly detection method based on an FP-growth and graph network. The invention discloses a package type medicine purchasing anomaly detection method based on an FP-growth and graph network. The method comprises the following steps: S1, data preprocessing; S2, establishing a drug relation graph; S3, training the network; S4, drug combination mining; S5, establishing a drug relation graph of a single mechanism; s6, predicting a result; and S7, obtaining a final result, and repeatedly iterating the steps S4 to S6 to obtain all abnormal detail results of the specific region. The invention provides an FP-growth and graph network-based package type medicine purchasing anomaly detection method for solving the problem of institution package type medicine purchasing for extracting medical insurance funds. The FP-growth and graph network-based package type medicine purchasing anomaly detection method provided by the invention is used for solving the problem of institution package type medicine purchasing.

Description

technical field [0001] The invention belongs to the technical field of medical data mining, and in particular relates to an abnormal detection method for package medicine purchase based on FP-growth and graph network. Background technique [0002] The current situation of defrauding medical insurance funds by fraud is relatively severe. [0003] The use of automated technology to detect fraudulent insurance institutions / crowds is the main method other than manual spot checks. At the same time, the use of rule-based detection methods is the mainstream method. Its advantages lie in simple logic and a high degree of compliance with the detected objects, but it also has the ability to migrate algorithms. Poor, high space-time overhead, complex data preprocessing and weak ability to detect masquerade behavior. [0004] In order to solve the shortcomings of the above rule-based algorithms, a package-based drug purchase anomaly detection method based on FP-growth and graph network...

AI Technical Summary

Problems solved by technology

[0011] The technical problem to be solved by the present invention is to provide an abnormal detection method based on FP-growth and graph network to solve the problem of institutional package drug purchase and medical insurance fund

Images