Knowledge graph construction method and device, equipment and medium

A knowledge graph and construction method technology, which is applied in the creation of semantic tools, unstructured text data retrieval, special data processing applications, etc. The effect of accuracy

Active Publication Date: 2019-12-06
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF17 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, when the knowledge map is used to identify information beyond text, such as pictures, audio, and video, it is difficult to meet the information identification requirements because the above information covers the complexity of entities.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Knowledge graph construction method and device, equipment and medium
  • Knowledge graph construction method and device, equipment and medium
  • Knowledge graph construction method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] Figure 1A It is a flow chart of a method for constructing a knowledge graph provided in Embodiment 1 of the present application. This embodiment is applicable to the situation of constructing a cognitive graph of knowledge data. This method can be implemented by the device for constructing a knowledge graph in the embodiment of the present application. Execution, the device can be implemented in the form of software and / or hardware, and can generally be integrated on a knowledge map construction server. The method specifically includes the following operations:

[0069] S110. Acquire text corpus of at least one information object.

[0070] Corpus, that is, language materials; text corpus of information objects, that is, textual language materials related to information objects; text corpora of information objects can be obtained from open data in the Internet, for example, KG (KnowledgeGraph, knowledge map ) database; such as Figure 1B As shown, the KG database conta...

Embodiment 2

[0090] figure 2 It is a flowchart of a method for constructing a knowledge map in Embodiment 2 of the present application. This embodiment is embodied on the basis of the above-mentioned embodiments. In this embodiment, the smallest unit phrase and compound After the phrase, it also includes: according to the text corpus, adjusting the vocabulary in the compound phrase to expand and generate other compound phrases. Correspondingly, the method in this embodiment specifically includes the following operations:

[0091] S210. Acquire text corpus of at least one information object.

[0092] S220. Extract phrases from the text corpus; phrases include minimum unit phrases and compound phrases, the minimum unit phrases include one vocabulary, and the compound phrases include at least two vocabulary.

[0093] S230. According to the syntactic dependency tree relationship of the vocabulary in the text corpus, combine at least two vocabulary to generate a new compound phrase; and / or f...

Embodiment 3

[0106] Figure 3AIt is a flowchart of a method for constructing a knowledge graph in Embodiment 3 of the present application. This embodiment is embodied on the basis of the above-mentioned embodiments. In this embodiment, according to the vocabulary structure in the phrase, and the The sentence structure in the text corpus where the phrase is located, and the identification of the relationship between the phrases as the topic of interest includes: clustering and identification based on the text corpus of the information object, and matching with the preset parent topic in the knowledge map according to the clustering result, And determine the association relationship between the information object and the parent topic. Correspondingly, the method in this embodiment specifically includes the following operations:

[0107] S310. Acquire text corpus of at least one information object.

[0108] S320. Extract phrases from the text corpus, the phrases include a minimum unit phras...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the invention discloses a knowledge graph construction method and device, equipment and a medium. The method comprises the steps of obtaining a text corpus of at least one information object; extracting phrases from the text corpus; from the extracted phrases, identifying content phrases of an attention theme, an object entity, an object side surface and an action event, and identifying an association relationship between the phrases; and updating the content phrases to point elements of the knowledge graph, and updating the association relationship to edge elements of the knowledge graph. According to the technical scheme of the embodiment of the invention, the information object text corpus is extracted, the knowledge graph of the information object is constructed, a plurality of point elements and corresponding side elements such as attention topics, action events and object side surfaces are added, information extension of existing object entities in the knowledgegraph is realized, and new object entities are continuously mined from the information object to continuously expand and supplement the composition of the knowledge graph.

Description

technical field [0001] The embodiments of the present application relate to data processing technology, in particular to natural language processing technology, and in particular to a method, device, device and medium for constructing a knowledge graph. Background technique [0002] In the existing natural language processing (NLP) technology, in order to facilitate the identification of semantic knowledge, a database of knowledge graphs is gradually constructed. The knowledge graph includes point elements and edge elements. Point elements are used to record entities, and edge elements are used to record the relationship between entities. Entities are usually specific things in the real world. [0003] However, when the knowledge graph is used to identify information beyond text, such as pictures, audio, and video, it is difficult to meet the information identification requirements because the above information covers the complexity of entities. Contents of the invention ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/36
CPCG06F16/367
Inventor 方舟冯知凡汪琦秦华鹏张扬陆超
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap