Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

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 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 to have a deep foundation for complex graph query languages, which hinders knowledge. Application of Graph Question Answering

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

Embodiment 1

[0049] see figure 1 , is a flow chart of the method for constructing a visual knowledge graph query template provided in Embodiment 1 of the present invention. In this embodiment, according to different requirements, figure 1 The order of execution of the steps in the flowcharts shown may be changed, and certain steps may be omitted.

[0050] Before describing the specific steps of the present invention, first briefly introduce several basic terms of the knowledge map.

[0051] Concept: the type of entity, not specifically referring to a certain entity, but a class of entities, such as "person"; entity: also known as object or instance, such as "Zhang San" ;relation: the relationship between entities, for example: the relationship between Zhang San and Li Si is "friend"; attribute value: the attribute attached to the entity itself, such as "Zhang San's height"; path: multiple A sub-graph in a knowledge graph formed by entity nodes and relationships (see figure 2 shown).

...

Embodiment 2

[0090] see Figure 6 , is a schematic structural diagram of the device provided by Embodiment 2 of the present invention.

[0091] In some of these embodiments, the device 2 may include, but not limited to, a memory 21 and a processor 22 coupled to the memory 21, and the memory 21 and the processor 22 may be communicatively connected to each other through a system bus. It should be pointed out that, Figure 6 Only device 2 is shown with components 21 and 22, but it is to be understood that embodiment 2 does not show all components of device 2 and that device 2 has more or fewer components that may alternatively be implemented. Wherein, the device 2 may be a computing device such as a rack server, a blade server, a tower server, or a cabinet server, and the device 2 may be an independent server or a server cluster composed of multiple servers.

[0092] The memory 21 stores program instructions for realizing the above-mentioned method for constructing a visual knowledge map qu...

Embodiment 3

[0096] see Figure 7 , is a schematic structural diagram of a system for constructing a visual knowledge graph query template provided in Embodiment 3 of the present invention.

[0097] In this embodiment, the visual knowledge map query template construction system 3 can be divided into one or more program modules, the one or more program modules are stored in the memory 21, and are composed of one or more executed by a processor (such as the processor 22) to implement the present invention. For example, in Figure 7 Among them, the visual knowledge map query template construction system 3 can be divided into a query template construction module 31 , an extraction module 32 , a matching module 33 , a query sentence construction module 34 , and a query module 35 . The program module referred to in the present invention refers to a series of computer program instruction segments capable of completing specific functions, which are more suitable than programs for describing 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
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com