Bill Abnormality Detection Model Generation Method and Bill Abnormality Detection Method

Abstract

The present application relates to a method for generating a bill anomaly detection model and a method for detecting bill anomaly, wherein the model generating method includes: acquiring historical bill data; identifying a type field in the historical bill data; Perform numerical transformation and standardization processing on the type field, and perform field derivation based on different time granularities on the time type field to obtain sample data; according to the sample data, an improved isolated forest model is obtained by training. In the whole process, on the one hand, the classification fields in the bill data are digitized and standardized, and the fields of different time granularities are derived for the time type fields, which are more suitable for the training of the subsequent improved isolated forest model. On the other hand, The improved isolated forest model is used as the basic model, which supports local point detection. Therefore, the whole scheme can support comprehensive and accurate bill anomaly detection.

Description

technical field [0001] The present application relates to the technical field of intelligent detection, in particular to a method, device, computer equipment, storage medium and computer program product for generating a bill anomaly detection model; and a method, device, computer equipment, storage medium and computer program for bill anomaly detection product. Background technique [0002] With the further development of electronic bills, the number of electronic bills issued by enterprises across the country is increasing at a very high rate every year. Although electronic flat bills have brought great convenience to enterprises, the management of bills has also brought a lot to the invoice management department. New challenges, especially in the prevention of various false and abnormal invoices, have brought challenges. [0003] At present, most of the bill anomaly detection adopts the method of rule engine for risk control, and some methods such as the isolated forest a...

AI Technical Summary

Problems solved by technology

Although the above-mentioned methods can realize basic outlier detection, the rule engine method needs to be based on manual setting of rules, so it is difficult to achieve all-round coverage detection of outliers; and although the isolated forest algorithm has the ability to detect global outliers, it is not suitable for multiple outliers. The data shape gathered by the central point is not effective in detecting abnormalities, especially some local abnormal points cannot be detected

[0004] It can be seen that the traditional bill anomaly detection scheme cannot achieve comprehensive and accurate bill anomaly detection

Images