Semantic search method and device based on knowledge map

A technology of knowledge graph and semantic search, which is applied in the field of semantic search method and device based on knowledge graph, which can solve problems such as inability to identify ambiguous product names and inability to analyze user semantics, and achieve the effect of improving search experience, efficiency and accuracy

Inactive Publication Date: 2019-03-26
STATE GRID CORP OF CHINA +1
View PDF3 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing search technologies have the disadvantages of being unable to analyze user semantics and identifying ambiguous product names, etc.

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
  • Semantic search method and device based on knowledge map
  • Semantic search method and device based on knowledge map
  • Semantic search method and device based on knowledge map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] An embodiment of the present application provides a semantic search method based on a knowledge graph, the knowledge graph may include the first entity set and the association relationship of multiple entities in the first entity set, refer to figure 2 As shown in, the method includes S101-S104:

[0041] S101. Obtain search information.

[0042] When a user enters information through the interface layer of the knowledge graph-based search system, the information can be an entity name or a user question.

[0043] optional, see image 3 As shown in , S101 can include S201-S202:

[0044]S201. If the search information is pinyin, convert the search information into Chinese characters according to the pinyin library.

[0045] Among them, the pinyin database includes pinyin notation of industry thesaurus.

[0046] When the information entered by the user is mistyped as pinyin, the search system can automatically convert it into Chinese characters and can identify polypho...

Embodiment 2

[0077] The embodiment of this application provides a semantic search device based on knowledge graph, refer to Figure 6 As shown in , the semantic search device 100 may include:

[0078] An acquisition unit 110, configured to acquire search information;

[0079] The identification unit 120 is configured to perform semantic identification on the search information according to the association relationship of multiple entities in the first entity set in the knowledge graph, so as to obtain user intentions;

[0080] The search unit 130 is configured to reason and query the first entity set of the knowledge map according to the user's intention to obtain a second entity set, wherein the second entity set is one of the first entity set that is highly correlated with the user's intention collection of entities;

[0081] The notification unit 140 is configured to notify the user of the second entity set as the search result.

[0082] Optionally, the identification unit 120 is spe...

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 semantic search method and device based on a knowledge map, relating to the search engine field, which is used for satisfying the search requirements of a user at the semantic level, thereby providing an accurate and efficient search experience for the user. The method comprises the following steps of: obtaining search information; Carrying out semantic identification onthe search information according to the knowledge map to obtain the user intention; Reasoning and querying the first set of entities according to the user intention to obtain a second set of entities,wherein the second set of entities is a set of entities of high relevance to the user intention in the first set of entities; notifying The user of the second set of entities as a search result. Embodiments of the present application are applied to a semantic search based on a knowledge map.

Description

technical field [0001] The present invention relates to the field of search engines, in particular to a semantic search method and device based on knowledge graphs Background technique [0002] With the accumulation of Internet data, people are no longer satisfied with only obtaining a collection of search web pages, that is, only obtaining a few document links related to user queries, but hope to obtain more specific answer-style search results. Especially in the e-commerce industry, the accuracy of user search is directly related to business experience. [0003] Although the existing search technology has achieved great success, when users search for information, the existing search technology cannot accurately understand the user's search intent, especially in the e-commerce industry, where the accuracy of user search is directly related to business experience. [0004] In the operation process of the e-commerce platform, the most critical part is to understand the user...

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): G06F16/951G06F16/36
Inventor 周晶罗鹏张宾孙喜民
Owner STATE GRID CORP OF CHINA
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