Visual knowledge graph query template construction method, device and system and storage medium

A knowledge map and construction method technology, applied in the system and storage media, the visual knowledge map query template construction method, and the device field, can solve the problems of high learning cost, hindering the application of knowledge map question answering, and low efficiency, and achieve the goal of improving construction efficiency Effect

Active Publication Date: 2021-03-16
深圳市一号互联科技有限公司
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Query and retrieval are important ways of using knowledge graphs, and they are also one of the core capabilities of knowledge graph data management systems. However, the current query and retrieval requires users to use complex graph query statements, and the learning cost is very high.
[0003] At present, the query template techno

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
  • Visual knowledge graph query template construction method, device and system and storage medium
  • Visual knowledge graph query template construction method, device and system and storage medium
  • Visual knowledge graph query template construction method, device and system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0048] Example 1

[0049] See figure 1 , A flow chart of a visualized knowledge map query template for the first embodiment of the present invention. In this embodiment, according to different needs. figure 1 The execution order of the steps shown in the flowchart shown can be changed, and some steps can be omitted.

[0050] Several basic terms of knowledge maps are first briefly described before describing the specific steps of the present invention.

[0051] Concept: That is, the entity type, does not specifically refers to a entity, but a class of entities, such as "people"; entity (entity): Also known as object (object) or instance, such as "Zhang San" ; Relation: The relationship between the entity and the entity, for example: Zhang San and Li Si's relationship is "friend"; attribute value: the attribute included in the entity itself, such as "Zhang San's height"; path: more Subgraphs in a knowledge map formed by the entity node and the relationship (see figure 2 Indicate...

Example Embodiment

[0089] Example 2

[0090] See Figure 6 A schematic structural diagram of the apparatus provided in Example 2 of the present invention.

[0091] In some embodiments, the device 2 can include, but is not limited to, a memory 21 coupled to the memory 21, the memory 21 and processor 22 can communicate with each other through a system bus. It should be pointed out that Figure 6 Only means 2 having components 21 and 22, but it is understood that the second embodiment does not show all components of the device 2, and the device 2 has more or fewer components that can be replaced. The device 2 can be a rack server, a blade server, a tower server, or a cabinet server, etc., which can be a stand-alone server, or a server cluster composed of multiple servers.

[0092] The memory 21 stores program instructions for implementing the visual knowledge map query template build method. The memory 21 includes at least one type of readable storage medium including flash memory, hard disk, multime...

Example Embodiment

[0095] Example 3

[0096] See Figure 7 Schematic structural diagram of the visual knowledge map query template construction system provided in Example 3 of the present invention.

[0097] In this embodiment, the visualized knowledge map query template build system 3 can be divided into one or more program modules, the one or more program modules being stored in the memory 21, and by one or more The processor (such as processor 22) is performed to complete the present invention. For example, Figure 7 In, the visual knowledge map query template build system 3 can be divided into query template build module 31, extracting module 32, matching module 33, query statement build module 34, and query module 35. The program module referred to herein refers to a series of computer program instruction segments capable of completing a particular function, more suitable for describing the visual knowledge map query template build system 3 in the device 2 execution process. Hereinafter, the ...

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 provides a visual knowledge graph query template construction method, which comprises the following steps: pre-constructing query templates corresponding to different intentions througha visual query mode; receiving a user question, and extracting an intention and an entity contained in the user question; matching a query template corresponding to the user question from pre-constructed query templates according to the extracted intention and entity; constructing a corresponding query statement according to the query template matched with the user question; and querying knowledgegraph data according to the constructed query statement, and returning a query result. In addition, the invention also provides a device and system for constructing the visual knowledge graph query template, and a storage medium. According to the invention, the construction efficiency of the knowledge graph query template can be improved.

Description

technical field [0001] The present invention relates to the technical field of knowledge graph question answering, in particular to a method, device, system and storage medium for constructing a visualized knowledge graph query template. Background technique [0002] As a structured representation of knowledge, a knowledge graph is a large-scale semantic network that includes entities, concepts and various semantic relationships among them. Query and retrieval are important ways of using knowledge graphs, and they are also one of the core capabilities of the knowledge graph data management system. However, the current query and retrieval requires users to use complex graph query statements, and the learning cost is very high. [0003] At present, the query template technology involved in question answering based on knowledge graph structured data needs to be implemented by manually constructing query templates in a non-visual manner, which is inefficient and requires users t...

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
IPC IPC(8): G06F16/36G06F16/332G06F16/33G06F16/34G06F40/186G06F40/279G06K9/62
CPCG06F16/367G06F16/3329G06F16/3344G06F16/34G06F40/186G06F40/279G06F18/24155
Inventor 周柳阳吴杰积蒋林林
Owner 深圳市一号互联科技有限公司
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