Method and apparatus for switching from machine dialogue to human dialogue

Abstract

The invention discloses a method and device for switching machine conversation to artificial conversation. The method specifically includes the steps of obtaining the number of conversation statements sent by a user; extracting keywords of conversation and matching the keywords with a preset keyword set when the number of conversation statements is larger than a preset first threshold value, wherein the keywords are used for representing the emotional characteristics of the user; extracting the conversation characteristics of conversation and inputting the conversation characteristics to a preset train classifying model when the keyword set is not matched with the keywords to obtain the satisfaction degree of the user, wherein the classifying model is used for predicting the satisfaction degree of the user through the conversation characteristics; switching machine conversation to artificial conversation when the satisfaction degree of the user is smaller than a preset second threshold value. By means of the implementation mode, the accuracy of judging the moment of switching machine conversation to artificial conversation is improved, and the conversation efficiency is improved.

Description

technical field [0001] The present application relates to the field of computer technology, specifically to the field of Internet technology, and in particular to a method and device for switching from machine dialogue to manual dialogue. Background technique [0002] With the development of artificial intelligence technology, more and more question answering systems adopt artificial intelligence technology. The existing artificial intelligence question answering system can only answer the questions raised by the user according to the pre-designed process, for example, match the set questions with the user session characteristics (such as keywords), and then feed back the corresponding generated answers to the user . However, this method of machine dialogue cannot detect in time whether the user is emotional, angry, or dissatisfied with the machine's answer. Although the above-mentioned problems can be solved by adopting the mode of manual dialogue, it will cause a great w...

AI Technical Summary

Problems solved by technology

The existing artificial intelligence question answering system can only answer the questions raised by the user according to the pre-designed process, for example, match the set questions with the user session characteristics (such as keywords), and then feed back the corresponding generated answers to the user

However, this method of machine dialogue cannot detect whether the user is emotional, angry, or dissatisfied with the machine's answer in a timely manner.

Although the above-mentioned problems can be solved by using manual dialogue, it will cause a great waste of labor costs.

Further, although there are currently some question answering systems that combine machine dialogue with human dialogue to form an artificial intelligence question answering system, because such question answering systems cannot accurately determine the best time to switch from machine dialogue to human dialogue, they still cannot Effectively improve user experience

Images