Knowledge graph construction method and system and query method and system

A knowledge map and construction method technology, applied in the field of query methods and systems, knowledge map construction methods and systems, can solve problems such as weak inheritance, achieve accurate query results, and facilitate management and maintenance

Pending Publication Date: 2020-12-01
新华智云科技有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When using this method, an ontology model needs to be built in advance, but the existing ontology-based model is relatively weak when dealing with inheritance between types

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 system and query method and system
  • Knowledge graph construction method and system and query method and system
  • Knowledge graph construction method and system and query method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Example 1 A method of mapping knowledge construction, increase the derived label constructed based on the existing entry step methods, such as figure 2 As shown in, in particular the steps of:

[0067] SlOO, constructed based on the relationship information inheritance tree, each node of the tree for the inheritance relationship between an entity class, the node is inheritance relationship between the corresponding entity class;

[0068] S200, when the entity entering, based on said inheritance tree to extract all of the entity class corresponding to an entity, and to generate the derived tag entry.

[0069] The present embodiment indicates inheritance-related entity involved by the derived tag, open Query inheritance tree of any level suitable for the multilayer to inherit the scene.

[0070] For example: entity classes for disaster, natural disasters, typhoons, earthquakes, then you can use any inheritance tree a query, such as query-based natural disaster, you can extrac...

Embodiment 2

[0123] Example 2, a construction system of a knowledge map, such as Image 6 As shown, including the body model build module 110, the data extraction module 120, the knowledge map generation module 130, the derived tag entry module 140, and the inheritance tree change module 150;

[0124] The body model build module 110 is configured to construct a body model including the relationship information between the entity class and each of the entities;

[0125] The data extraction module 120 is used to perform data extraction of the collected industry data based on the body model, obtain entity data;

[0126] The knowledge map generation module 130 is configured to enter the entity data to generate a corresponding knowledge map.

[0127] The derived label is entered into module 140 for constructing inheritance trees based on the relationship information, the inherited tree, each of which is a physical class, and the relationship between the node is the inheritance relationship between t...

Embodiment 4

[0169] Example 4, a query system of a knowledge map comprising a knowledge map and a query module, the knowledge map being a knowledge map constructed in Example 1. The query module is used to obtain the query request data, and the query is performed in the knowledge map based on the query request data to generate a query result and output.

[0170] Further, it also includes a query expansion module that is configured to:

[0171] Based on whether the query request data determines whether or not to perform type screening, when it is determined that the required type screening is required, the query type is acquired based on the query request data;

[0172] The new time point of the query type is extracted as the first point of time, and the entity class corresponding to the node corresponding to the node is used as a supplemental type based on the node, which is less than the node of the first time point, based on the inherited tree. ;

[0173] Type filtering is performed based on...

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 invention discloses a knowledge graph construction method and system, and a query method and system, and the construction method comprises a derived label input step, and the specific steps are asfollows: constructing an inheritance tree based on the relation information, each node of the inheritance tree being an entity class, and the relation between the nodes being the inheritance relationbetween the corresponding entity classes; when the entity is input, extracting all entity classes corresponding to the entity based on the inheritance tree, generating a derived label and inputting the derived label; the query method comprises the specific steps of obtaining query request data, performing query in the constructed knowledge graph based on the query request data, generating a queryresult and outputting the query result. According to the method, the inheritance relationship related to the related entity is indicated through the derived label, query of any level on the inheritance tree is broken through, and the method is suitable for multi-layer inheritance scenes and particularly suitable for the news industry which is large in data size, wide in inheritance tree and deepin inheritance tree.

Description

Technical field [0001] The present invention relates to information processing, and in particular relates to a method and system for constructing knowledge map is also directed to a method and system of the query pattern corresponding knowledge. Background technique [0002] Knowledge maps are structured semantic knowledge can be used to describe the concepts and their relationships in the physical world, fill the machine for less than the world of human cognition, construct knowledge map is divided into a bottom-up approach to build and construct a top-down approach , bottom-up approach to build data-driven, there is no data for a complete knowledge system; to build a top-down approach to expert drivers, we need to pre-defined ontology model. [0003] For a clear business structure scenarios when building the body of knowledge map is usually used to build a top-down fashion. When required pre-built model ontology using this mode, but the existing ontology model based upon the re...

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): G06F16/36G06F16/35G06F16/33
CPCG06F16/3331G06F16/35G06F16/367
Inventor 杨丛聿仇应俊郝凯
Owner 新华智云科技有限公司
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