Customer confirmation detection method and device in double-record data quality inspection

Abstract

The invention provides a customer confirmation detection method and device in double-record data quality inspection, which can be used in the financial field or other fields. The method comprises the following steps: acquiring double-recording data, and decomposing the double-recording data into video data and audio data; performing confirmation action detection on the video data to obtain a confirmation action detection result; performing voice recognition on the audio data to obtain voice text data, and performing text rule matching on the voice text data to obtain a text matching result; and generating a customer confirmation detection result according to the confirmation action detection result and the text matching result. The video data and the audio data are identified and detected, so that the detection accuracy of a customer confirmation link during double-recording quality inspection is improved, meanwhile, the confirmation action of the customer is identified and detected, the problem of low detection accuracy caused by detection simply relying on voice-to-text is solved, and thus, the double-recording quality inspection success rate is improved.

Description

technical field [0001] The invention relates to the technical field of audio and video processing, in particular to a method and device for customer confirmation detection in double-record data quality inspection. Background technique [0002] In order to protect the rights and interests of consumers, regulatory agencies require commercial banking and financial institutions to regulate the sales behavior of financial institutions through audio and video recording (double recording) when selling financial products such as wealth management and consignment insurance policies. At present, commercial banks usually cache video files locally, and upload them to the cloud asynchronously after the entire double-recording video is recorded, for subsequent compliance review by regulatory authorities. [0003] In order to ensure the compliance of double-recorded videos, financial institutions generally use artificial intelligence technology to check offline audio and video data, but th...

AI Technical Summary

Problems solved by technology

[0003] In order to ensure the compliance of double-recorded videos, financial institutions generally use artificial intelligence technology to check offline audio and video data, but there is a problem that the customer confirmation process cannot be accurately detected, resulting in a low success rate of quality inspection

The customer confirmation process relies on the rule matching after voice-to-text conversion, but when the customer’s voice is low or the environment is noisy, the customer confirmation process can easily lead to quality inspection failure

Images