Online dialogue log violation detection method and system based on BERT model

Abstract

The invention provides an online dialog violation detection method and system based on a BERT model, and the method comprises the following steps: determining violation keywords, and constructing a violation word bank; extracting statements related to the violation keywords in a dialog by utilizing the violation keywords, and constructing a violation sentence library; determining a to-be-comparedonline dialog, and detecting violation statements of the online dialog based on a BERT model in combination with a preset similarity algorithm. The system comprises a violation word bank generation module, a violation sentence bank generation module and a violation sentence detection module. According to the invention, the violation word bank and the violation sentence bank are automatically constructed, and the BERT model and the similarity algorithm are combined, so that the problem that an online customer service platform in the current market cannot find out suspected violation customers in the platform in time through customer service log analysis can be accurately solved, timely and targeted processing is performed, the network security is guaranteed, and thus boosting network healthdevelopment.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a BERT model-based online dialogue log violation detection method and system. Background technique [0002] With the development of the Internet, more and more people use the Internet to communicate with institutions, businesses, hospitals, etc., and online customer service platforms have emerged as the times require. As a bridge for direct communication between merchants and customers, the online customer service platform is also easily used by criminals to conduct illegal business activities such as fraud, gambling, and swiping orders on the online customer service platform. As a provider of an online customer service platform, it is necessary to analyze the customer service logs in a timely manner to find out the suspected violators in the platform, and to block and report them. [0003] However, the online customer service platforms on the market ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the online customer service platforms in the current market cannot timely analyze the customer service logs to find out the suspected violation customers in the platform and deal with them in a timely and targeted manner, this invention proposes a method for detecting violations of online dialogue logs based on the BERT model and systems to solve this problem and help ensure network security

Images