Method and device for generation of Chinese general knowledge atlas with entity relation attributes

Abstract

The invention provides a method and device for generation of a Chinese general knowledge atlas with entity relation attributes. The method includes the steps that entities in multiple external data sources and databases are subjected to named entity identification, and the multiple named entities obtained through identification are connected, so that multiple entity relations are obtained; attribute identifiers are added into the multiple entity relations, and the multiple entity relation attributes are obtained; according to the multiple entities, the multiple entity relations and the multiple entity relation attributes, the Chinese general knowledge atlas with the entity relation attributes is generated. According to the method and device, through addition of the identifiers into the entity relations, the entity relation attributes are built, and when answers are extracted through the knowledge atlas, the efficiency and the integrity of answer extraction are improved due to increase of the entity relation attributes, so that a user is provided with service by the knowledge atlas more efficiently.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to the field of a method and a device for generating a Chinese general knowledge graph carrying entity relationship attributes. Background technique [0002] Knowledge graph technology was proposed by Google in 2012. Its goal is to describe various entities and concepts that exist in the real world, as well as the relationship between entities and concepts, so as to improve search results. Subsequently, knowledge graph technology has been valued by researchers and enterprises, and has been applied in retrieval, risk control and other aspects. In the process of replying to the input, the knowledge graph can perform one-level, two-level or even multi-level retrieval in order to organize comprehensive answers that best meet the user's intentions. [0003] Most of the existing technical solutions are developed by search engine companies (google baidu sougou), which are used in sp...

AI Technical Summary

Problems solved by technology

In addition, because the same semantics has many different expressions in natural language ("Lu Xun was born in Shaoxing, Zhejiang" and "Shaoxing, Zhejiang is Lu Xun's hometown"), it is impossible to extract complete answers when performing structured queries (SPARQL)

[0005] Therefore, the defects in the existing technology are: the existing knowledge map, due to the increasing scale of the knowledge map, only relies on entities, entity attributes and entity relationships to extract answers from the knowledge map, resulting in slow efficiency and poor reliability, and due to the same Semantics can be expressed in many different ways in natural language, so that the extracted answers cannot guarantee the integrity

Images