Generation system and method for structured query sentence used for precise retrieval of natural language

Abstract

The invention discloses a generation method for a structured query sentence used for the precise retrieval of a natural language. The generation method comprises the following steps: obtaining a natural language query sentence; carrying out word segmentation on the natural language query sentence by a preset dictionary and a first rule to obtain a word segmentation scheme; generating an analytic tree on the word segmentation scheme by a preset second rule; according to the root node of the analytic tree, generating a local query parameter, and substituting the global query parameter of a first layer of subnodes of the analytic tree, and obtaining the global query parameter of the root node of the analytic tree; according to the global query parameter of the root node of the analytic tree, generating the structured query sentence. The invention also provides a generation system for the structured query sentence used for the precise retrieval of the natural language. According to the generation method and the generation system, the natural language query sentence can be automatically converted into the structured query sentence.

Description

technical field [0001] The invention relates to retrieval technology, in particular to a system and method for generating structured query sentences for accurate natural language retrieval. Background technique [0002] With the development of Internet technology, users have higher and higher requirements for precise query. Traditional search engines can only mechanically segment the query sentences entered by users, and cannot truly understand the user's intentions and requirements. The returned query results are very biased, which especially affects the user experience when applied to mobile phones. Moreover, whether it is an enterprise or a website, a large amount of data is stored in a relational database. These data are usually not published directly on the webpage, so they cannot be accessed by search engines. Therefore, these data will not be included in the query results at all. Appear. [0003] In addition, in the era of big data, human-computer interaction proble...

AI Technical Summary

Problems solved by technology

[0007] However, the method for generating structured query statements as described above needs to manually configure query templates in advance, and write structured query statements for each query template, so there are at least the following problems: 1) manually configure query templates, write structured query Query statements are very expensive and inefficient; 2) Different users may use different expressions to express natural language query statements, which will prevent the query template from being matched correctly and affect the accuracy of matching; 3) When natural language When the language query statement is a nested question sentence, the query template cannot be matched, resulting in semantic loss, which cannot meet the requirements of large-scale industrial applications

Images