Short text understanding method and device based on knowledgegraph

Abstract

The invention discloses a short text understanding method and device based on a knowledgegraph. The short text understanding method comprises the following steps that S1, feature words in short texts are extracted according tofeature word data; S2, the feature words are judged, the step S3 is executedif the feature words are entity feature words, and the step S4 is executedif the feature words are other feature words; S3, knowledgegraph searching is conducted on the entity feature words; S4, the entity feature words corresponding to attributefeature words or relation feature words or concept feature words are searched out, and then knowledgegraph searching is conducted on the entity feature words; S5, result trees are generated according to feature word group and are relations of the feature words. The short text understanding method makes short text understanding method product searching and query more convenient, does not need to accurately edit and search statements or edit the statements according to a certain text rule and greatly improves the knowledgegraph based query efficiency.

Description

technical field [0001] The invention belongs to the field of information search, and in particular relates to a short text understanding method and device based on a knowledge map. Background technique [0002] Knowledge graphs aim to describe various entities or concepts that exist in the real world. Among them, each entity or concept is identified by a globally unique ID, which is called their identifier. Each attribute-value pair (also known as AVP) is used to describe the intrinsic characteristics of the entity, and the relationship (relation) is used to connect two entities and describe the relationship between them. The knowledge graph can also be regarded as a huge graph, the nodes in the graph represent entities or concepts, and the edges in the graph are composed of attributes or relationships, such as figure 1 As shown, it is a schematic diagram of the knowledge map. Now the knowledge map is mainly used in answer reasoning, document importance ranking and precise...

AI Technical Summary

Problems solved by technology

[0003] The current search of knowledge graph products requires precise editing of search sentences or query and search based on a text rule, which cannot realize query search based on daily sentences. Therefore, the query search of knowledge graph based on daily sentences has become a technology in the field problems that people need to solve,

Images