Intelligent question-answer (Q&A) method and device

Abstract

The invention concerns to an intelligent question-answer (Q&A) method and device, and belongs to the processing field of natural languages. The method comprises the following steps: establishing an initial business guiding model for each business scene; performing skip node complementarity optimization on the initial business guiding model to obtain a complete business guiding model; acquiring the specified user answer content matched with the machine output content stored at the current state node; performing text similarity matching on the specified user answer content and the user answer content stored at a specified skip node according to the compete business guiding model; determining the next state node of state migration according to an obtained matching result, and outputting the machine output content stored at the next state node. The business scene is modelled by intelligently analyzing the question suggested by a user, and relatively high matching accuracy rate is guaranteed according to strict text similarity matching, the free migration among various state nodes in the business scene is realized, and the intelligence is excellent.

Description

[0001] This application claims the priority of the Chinese patent application with the application number 201610355154.1 and the title of the invention "Intelligent Question Answering Technology and Device Based on Directed Graph-Based Free-Walking Business Guidance" submitted to the China Patent Office on May 26, 2016. The entire contents of which are incorporated by reference in this application. technical field [0002] The present disclosure relates to the field of natural language processing, in particular to an intelligent question answering method and device. Background technique [0003] In this era of rapid development, the more human resources can be saved, the greater the liberation of productivity. In order to better meet the needs of users and save human resources, more and more service industries have sorted out common questions and their answers raised by users, that is, sorting out common questions and their answers into a standardized question-and-answer dat...

AI Technical Summary

Problems solved by technology

[0004] At present, the intelligent question answering system only answers the questions raised by users, and cannot be applied to scenarios that require the intelligent question answering system to actively ask questions. Customers who need to perform dunning business

At the same time, the question-and-answer database organized by the intelligent question-and-answer system is a fixed question-and-answer database. For the questions continuously raised by users, it cannot be flexibly modified according to user needs, and the business guidance can only follow the pre-set steps, and cannot skip steps or take multiple steps. waiting for free walk

On the other hand, the word recognition technology of the intelligent question answering system only recognizes keywords and cannot explore the deep semantics of the keywords, which is not intelligent enough and the effect is poor

Images