Intelligent question answering method, device and system

Abstract

The invention discloses an intelligent questioning and answering method, an intelligent questioning and answering device and an intelligent questioning and answering system.The method includes: receiving user input information; subjecting the user input information to abstract semantic recommendation according to an abstract semantic database to obtain an abstract semantic category and an abstract semantic expression corresponding to the user input information, wherein the abstract semantic database comprises a plurality of categories of abstract semantics, each category of abstract semantics includes one or more abstract semantic expressions, and each abstract semantic expression includes absence semantic components; when the obtained category is in accordance with a preset category, extracting first subject information and first attribute information from the user input information according to the absence semantic components in the abstract semantic expression; when an external data source matched with the first subject information and the first attribute information exists, extracting a corresponding attribute content from the external data as an answer.By the intelligent questioning and answering method, the intelligent questioning and answering device and the intelligent questioning and answering system, maintenance of a knowledge base can be simplified, and answering accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to an intelligent question answering method, device and system. Background technique [0002] Knowledge base, also known as intelligent database or artificial intelligence database, in knowledge base, information is effectively organized for retrieval and utilization. Knowledge bases are widely used in the field of artificial intelligence, and one of the typical applications is intelligent question answering system, also known as automatic question system. [0003] Multiple knowledge points are stored in the knowledge base applied to the intelligent question answering system, and each knowledge point includes one or more preset questions and corresponding answer information. When the user asks a question by inputting request information, calculate the semantic similarity between the request information and the preset question, and if there is a preset question with a semant...

AI Technical Summary

Problems solved by technology

[0005] However, in such questions about subjects and attributes, the specific content of subjects is ever-changing. According to existing methods, when subjects change, questions also change accordingly. In order to provide corresponding answers, it is necessary to Establishing corresponding knowledge points will undoubtedly increase the storage capacity of the knowledge base of the intelligent question answering system, and it is time-consuming and labor-intensive to preset different questions, and the maintenance of the knowledge base will also be very complicated

[0006] In the existing technology, there is also a method of directly using user input questions to crawl the closest answer from an external data source, but the answer obtained by this method is not accurate enough

Images