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

A search intent expression method and system based on ontology

A technology of search intent and expression method, applied in the field of knowledge graph, it can solve problems such as affecting the search effect and failing to meet user search requirements, and achieve the effect of accurate search results and improved accuracy.

Active Publication Date: 2022-06-07
广州极天信息技术股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, only using keywords, natural language sentences or texts to express search intentions obviously cannot meet the user's search requirements, because the keywords, natural language sentences or texts entered by users are only an expression of their search intentions
For the same intention, different people will use different words or word combinations to express it. If the content in the data source is the result of multiple expressions, using an expression of intention to match the search will obviously seriously affect the search results. full effect

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
  • A search intent expression method and system based on ontology
  • A search intent expression method and system based on ontology
  • A search intent expression method and system based on ontology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] The present embodiment proposes an ontology-based search intent expression method, such as Figure 1 Shown, a flowchart of the search intent expression method for the present embodiment.

[0029] The present embodiment proposes a search intent expression method, comprising the following steps:

[0030] S1. Obtain the search content entered by the user and segment the search content.

[0031] S2. Use the preset knowledge graph based on the domain ontology to conceptually identify the word segmentation results, and obtain the concept label corresponding to the word segmentation results.

[0032] S3, according to the concept label corresponding to the word segmentation results, from the knowledge graph based on the domain ontology, search for synonyms, epitaxial words and / or associative words and display.

[0033] S4, the user selects the target search term from the displayed synonyms, epitaxial terms and / or associative terms, combines the selected target search terms, and gen...

Embodiment 2

[0040] The present embodiment proposes an ontology-based search intent expression method, such as Figure 3 Shown, a flowchart of the search intent expression method for the present embodiment. These include the following steps:

[0041] S1. Obtain the search content entered by the user and segment the search content.

[0042] In this step, the search content such as keywords entered by the user, logical combinations of keywords, sentences, and text is divided, and the word segmentation results are obtained, which are used for further concept recognition and search intent generation.

[0043] S2. Use the preset knowledge graph based on the domain ontology to conceptually identify the word segmentation results, and obtain the concept label corresponding to the word segmentation results.

[0044] In the present embodiment, the domain ontology based on the domain ontology in the knowledge graph comprises a set of concepts, a set of attributes, a set of individuals, and a set of facts;...

Embodiment 3

[0065] The present embodiment proposes an ontology-based search intent expression system, applying the search intent expression method proposed in Example 1 or Embodiment 2. as Figure 4 As shown, the search intent expresses the architecture diagram of the present embodiment of the system.

[0066] The search intent expression system proposed in the present embodiment includes a human-computer interaction module, a word segmentation module, a knowledge graph module, a concept recognition module, a recommendation word generation module and a search intent expression generation module.

[0067] Wherein, the word segmentation module is used to segment the search content obtained by the human-computer interaction module.

[0068] The Knowledge Graph module stores a preset knowledge graph based on domain ontologies. The domain ontology in the knowledge graph includes a set of concepts, a set of attributes, a set of individuals, and a set of facts. Wherein, the property collection includ...

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 present invention relates to the technical field of knowledge graphs, and proposes an ontology-based search intent expression method and system, which includes the following steps: obtaining search content input by a user, and performing word segmentation on the search content; using a preset domain ontology-based knowledge graph to Perform concept recognition on the word segmentation result to obtain the concept label corresponding to the word segmentation result; according to the concept label corresponding to the word segmentation result, search for synonyms, extension words and / or associated words from the domain ontology-based knowledge map and display them; The target search words are selected from the extension words and / or associated words, and the selected target search words are combined to generate a search intent expression result. The present invention divides the search content input by the user and converts it into a concept, and further combines the domain ontology-based knowledge graph to search for recommended words, which helps to fully list the word chain expression of the user's intention and generate more accurate search intention expression results .

Description

Technical field [0001] The present invention relates to the field of knowledge graph technology, more particularly, to an ontology-based search intent expression method and system. Background [0002] Ontology is an explicit formal specification of a shared conceptual model (Rudi Studer, 1998). Ontology defines concepts and the relationships between concepts and concepts. Words are the denotations of concepts, concepts are units of thought, and people's thoughts are communicated through language (vocabulary strings). Ontology establishes a human-like conceptual system for computers, enabling people to communicate with each other and between people and computers based on shared concepts. As a knowledge organization method for machines to understand human language, ontology application scenarios include information search, analysis, knowledge automation, knowledge management, etc., to improve the intelligence level of these scenarios. Among them, ontology can be divided into genera...

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 Patents(China)
IPC IPC(8): G06F16/33G06F16/35G06F16/36G06F40/295
CPCG06F16/3344G06F16/367G06F16/35G06F40/295
Inventor 胡炜梅陈丽莎陈锦毅
Owner 广州极天信息技术股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com