Method and device for determining answers of question data

Abstract

The invention discloses a method and device for determining the answers of the question data, which relates to the field of computers, and is used for accurately determining the answers of the question data. The method comprises the steps of obtaining the first question data inputted by a user, wherein the first question data comprises at least one word; determining a word relationship between the words in the at least one word; determining a service type corresponding to the first problem data according to the at least one word, the word relationship and the intention map, wherein the intention map at least comprises a service type associated with the at least one word; and determining the answer of the first question data from at least one preset answer according to the service type corresponding to the first question data.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular to a method and device for determining answers to question data. Background technique [0002] The realization of the question answering system requires a powerful and comprehensive knowledge resource base as the foundation. Most of the early knowledge resource databases were constructed by experts in various fields in their respective professional fields. However, the disadvantage of building a knowledge resource library for experts is that it takes time and effort to build a large-scale knowledge resource library, and when switching fields, it is necessary to build a knowledge resource library in another field, and the construction methods and construction of knowledge resource libraries in various fields are completed. The structure of the knowledge resource base is generally inconsistent. The construction method is not universal and the struct...

AI Technical Summary

Problems solved by technology

However, most of the vocabulary that plays an important role in the CCG method is artificially generated, thus limiting the transformation and expansion of the domain

If the domain is switched, a batch of new domain-specific vocabulary must be regenerated, and it will take a lot of manpower and time when large-scale vocabulary needs to be generated

[0005] The method based on information retrieval is relatively mature, simple and practical, and does not need to manually generate vocabulary like CCG, but the disadvantage is that the method based on information retrieval requires that the answer must contain at least one word or word in the question sentence, so it is not as accurate as the semantic analysis method

Images