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

A method and device for sorting entity semantics and word frequency based on comprehensive knowledge

A sorting method and entity technology, which is applied in the field of entity search, can solve problems such as inaccurate correlation between predicted queries and entities, and achieve the effects of improving retrieval performance, accurate results, and improving satisfaction

Inactive Publication Date: 2020-04-10
HENAN UNIVERSITY OF TECHNOLOGY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method and device for sorting entity semantics and word frequency based on comprehensive knowledge, so as to solve the problem of inaccurate correlation between predicted queries and entities in the prior art

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 method and device for sorting entity semantics and word frequency based on comprehensive knowledge
  • A method and device for sorting entity semantics and word frequency based on comprehensive knowledge
  • A method and device for sorting entity semantics and word frequency based on comprehensive knowledge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and examples, but the embodiments of the present invention are not limited thereto.

[0031] Embodiment of the sorting method of the entity semantics and word frequency based on comprehensive knowledge of the present invention:

[0032] A query is a set of keywords or key phrases that describe a user's needs. An entity is an individual with independent characteristics, such as a person, restaurant, movie or TV series, and so on. The goal is to query for entities that fit a certain description, such as a review for a certain movie, or a certain feeling in a restaurant environment, etc. The present invention is used to train a ranking model and predict the order of candidate entities based on it.

[0033] First, collect entity description information and user comment...

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 relates to a sorting method and apparatus based on entity semantics and word frequencies of comprehensive knowledge. After a domain knowledge expansion entity object is crawled, various different effective characteristics including word frequency characteristics and semantic characteristics are designed; and the correlation between query and entities is predicted by applying a sorting learning method. The word frequency characteristics of a bottom layer and the entity semantic characteristics of a top layer are fully utilized, so that the correlation between the query and the entities can be better reflected, the retrieval performance is improved, namely, an entity search result is more accurate, and the satisfaction of user retrieval is improved.

Description

technical field [0001] The invention belongs to the technical field of entity search, in particular to a method and device for sorting entity semantics and word frequency based on comprehensive knowledge. Background technique [0002] The mainstream search technology "keyword search" adopted by current search engines is a kind of "existence search" technology, which returns a list of webpages containing keywords to users. Users often need to further browse these webpages and filter out a lot of useless information to find the real The desired result is that the cost of information consumption in this process is high, which significantly reduces the user experience, and users hope to "get the answer directly". For example, if you query "Who is Barack Obama's wife", the search result that the user expects is a concise information item "Michelle Obama" instead of a large number of web pages. This kind of search is an entity search (EntitySearch). The salient feature of entity ...

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): G06F16/33G06F16/36G06F16/951
CPCG06F16/3344G06F16/367G06F16/951
Inventor 靳小波王胜曹鹤玲肖乐费选
Owner HENAN UNIVERSITY OF TECHNOLOGY
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