Automatic answering system

Abstract

The invention discloses an automatic answering system which can provide answers for community customers on line in real time, reduce distribution processing pressure during an answering process and improve answering efficiency. Moreover, the system provided by the invention can continuously update and adjust knowledge databases and key words according to questions put forth by users and feedback information, thus improving the accuracy of answering and the satisfaction of the customers. Distributed decision of answering questions is realized by a communication conversion and pressure balancing module, a distributed decision module and a guide module; classification of knowledge points, extraction of key words and searching and matching for answering questions are realized by a searching and matching module of answering results; recording of knowledge data, user operation and feedback is carried out by a knowledge database module; updating and adjusting of knowledge point data are carried out respectively from the aspects of manual management and automatic learning by a learning analyzing module and a management and data maintenance module.

Description

technical field [0001] The invention relates to an automatic question answering system, in particular to an automatic question answering system for customer service used in network communities. Background technique [0002] With the rapid expansion of content in various online communities (such as online game entertainment communities, electronic bulletin boards), the number of users is increasing day by day, and the number of online people is constantly increasing, the existing way of providing customer service manually is facing difficulties. With the increasing pressure, it not only consumes more manpower and material resources, but also does not have real-time performance and low efficiency, and it is easy to leave a bad impression on customers. Although there are various automatic question answering systems that can answer questions of users in the online community online and in real time through the network, such systems generally classify user questions, extract keywo...

AI Technical Summary

Problems solved by technology

Since these question answering systems in the prior art have no pressure distribution mechanism, and do not regularly monitor and maintain the knowledge database, and adjust and update the knowledge data and keywords according to user operations and feedback, it is easy to cause pressure Problems such as too much concentration (especially in the case of many answering users), which affect the efficiency of answering questions, and the accuracy of answering questions is difficult to be effectively guaranteed for a long time, and user satisfaction is difficult to guarantee

Images