Multi-modal information abnormity monitoring method and device, computer equipment and storage medium

Abstract

The invention discloses a multi-modal information exception monitoring method, which is applied to the field of data processing and is used for improving the exception monitoring accuracy. The method provided by the invention comprises the following steps: acquiring node information, recording information and screen recording information at the same time based on an information abnormity monitoring strategy; performing feature extraction on the recording information and the screen recording information to obtain recording features corresponding to the recording information and screen recording features corresponding to the screen recording information; performing multi-mode feature fusion on the recording features and the screen recording features to obtain multi-mode features; based on the node information, performing theme matching degree calculation processing on the multimode features to obtain a matching value; the matching value is compared with a preset matching value to obtain a comparison result, when the matching value is not smaller than the preset matching value, it is determined that the node corresponding to the node information is normal, and when the matching value is smaller than the preset matching value, it is determined that the node corresponding to the node information is abnormal.

Description

technical field [0001] The present invention relates to the field of data processing, in particular to a multimodal information abnormality monitoring method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of the economy, insurance has been paid more and more attention by the public, and the sales of insurance have also been paid more and more attention. At present, the process of insurance sales business is mainly carried out by insurance personnel to sell to customers. In this business process, in order to ensure the interests of consumers, it is necessary to monitor abnormalities in the business guidance and signing process to ensure that there are no false propaganda, one-sided introduction, exaggerated functions, confusing products, and tampering with customer information during the sales process. user experience. [0003] At present, double recording is mainly used, that is, audio recording and screen recording...

AI Technical Summary

Problems solved by technology

However, since the recording and screen recording only record the current situation of business personnel, business misleading problems may occur in every link of the entire guidance and signing process, which makes the amount of information obtained by the current double recording method limited, resulting in abnormal information The problem of insufficient monitoring accuracy

[0004] Therefore, there is a problem of low accuracy of information abnormality monitoring in the existing business guidance process

Images