Automatic question-answering system and method

Abstract

A system and method for automatic question answering is provided. Wherein the system includes: a user inputting module configured to receive question information; a question analyzing module configured to analyze the question information, and determine a set of keywords, a question type and a user intention type corresponding to the question information; a syntax retrieving and ranking module configured to retrieve, in a question and answer library and a category tree, answer candidates based on the question information, the set of keywords, the question type and the user intention type, determine a retrieval relevance between each of the answer candidates and the question information and rank the answer candidates according to the retrieval relevance, each of the answer candidates having a sequence number; and an outputting module configured to output an answer candidate ranked a specified sequence number. By using the application, lower costs for collection and improve successful rate of answers are provided by the system for automatic question answering.

Description

Technical field [0001] This application relates to the field of human-computer intelligent interaction technology, and in particular to an automatic question answering system and method. Background technique [0002] The automatic question answering system refers to the natural language understanding technology as the core, so that the computer can understand the content of the user's conversation, and realize the effective communication between people and the computer. Among them, the chat robot system commonly used in computer customer service systems is an automatic question answering system, which is an artificial intelligence system that can automatically talk to users through natural language technology. [0003] The automatic question answering system in the prior art is generally a text dialogue system based on a chat question and answer library, that is, a user enters a text, and the system finds the optimal matching text as answer information and returns it to the user th...

AI Technical Summary

Problems solved by technology

[0009] At present, the chat robot system usually needs a large amount of chat question and answer database, that is to say, the content of chat question and answer pairs in the chat question and answer database must cover all the questions that users may ask, which will cause operators to need to go through long-term operation and collection. Obtaining a chat question-and-answer library that completely covers all possible questions that users may ask will cause operators to consume a large amount of operational collection costs, and the chat question-and-answer library needs to store a large number of chat question-answer pairs, which will occupy a large amount of storage resources

Moreover, if the user input has no matching question-answer pair in the chat question-answer library, the system will be unable to answer, resulting in question-and-answer failure, or the general remedy is to change the subject, or give an answer at random, so that the answer result given is the same as The matching degree of the question entered by the user is very low, which is equivalent to a failure to answer

Images