Man-machine interaction method of customer service system

Abstract

The invention relates to a man-machine interaction method of a customer service system. The method enables the effect to be continuously optimized by virtue of user feedbacks, and comprises the following steps that a user raises a question and waits the customer service system to answer the question; buttons representing satisfactory and dissatisfactory feedbacks of the user are added on a question answering interface of the customer service system, and the user is invited to give feedback to whether an answer is satisfactory or not; satisfaction and dissatisfaction clicking behaviors of the user are fed back to logs of the customer service system and associated with the question of the user and the answer of a customer service staff at that time; a positive sample and a negative sample of the answer of the customer service staff are generated based on the logs; offline learning is carried out by utilizing the positive sample and the negative sample; and frequently asked question (FAQ) knowledge after the offline learning of the customer service system is updated. According to the method, the user experience is improved and the user does not feel unfriendly; sufficient positive and negative samples are provided for question and answer effects of customer service staffs; and continuously innovated fresh question-asking ways of users can be quickly adapted.

Description

technical field [0001] The invention relates to a human-computer interaction method, in particular to a human-computer interaction method for a customer service system. Background technique [0002] Enterprise customer service is an important means for enterprises to carry out network marketing, technical support and after-sales service. Divided by channel, including telephone customer service, video customer service, IM customer service. According to the carrier of customer service, it can be divided into human customer service and robot customer service. Among them, manual customer service requires a large number of customer service seats and a complicated call system, which is costly. Robot customer service has developed rapidly in recent years. It has obvious advantages in answering FAQ (Frequently Asked Questions) types. It can completely or partially replace the work of manual customer service and greatly reduce the cost of manual customer service. [0003] Robot cu...

AI Technical Summary

Problems solved by technology

However, due to the limited training samples (because human language is difficult to exhaustively), it is still not 100% accurate for unknown user questions.

[0014] Since Query comprehension and similarity matching cannot be perfect, when robot customer service faces unknown user questions, situations (2) and (3) will always exist, and wrong answers will be answered next time.

Even if advanced methods such as LDA, LSA, Word2Vec, and deep learning are used, they will be limited by the amount of training corpus that can be obtained, and continuous learning cannot be achieved

Images