Knowledge-based entity detection and disambiguation

An entity and knowledge technology, applied in the direction of network data retrieval, other database retrieval, instruments, etc., can solve problems such as hindering the organization of search results, unclear users, etc.

Active Publication Date: 2013-06-26
MICROSOFT TECH LICENSING LLC
View PDF4 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is not actually clear from the user's query which of these people the user is trying to find, but it is likely that the user is only interested in one of them, and a large subset of the results are therefore irrelevant
The inability of search engines to resolve the underlying identities of entity instances in web pages hampers their ability to effectively organize search results

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
  • Knowledge-based entity detection and disambiguation
  • Knowledge-based entity detection and disambiguation
  • Knowledge-based entity detection and disambiguation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0010] Described herein is an entity-based search system that detects and identifies entities in Internet-based content and uses this identification to organize search results. One goal of entity detection and disambiguation is to label named entities in web pages (or other types of text data) with distinguishable identifiers that unambiguously identify the entities. The system associates one or more entity identifiers with a web page and stores this information as metadata for the page in a search engine index. This metadata will enable entity-based queries and rich data presentation in search engine results pages (SERPs), including: grouping results by entity; filtering results by one or more specific entities; or User preferences for reranking search results.

[0011] In some embodiments, an entity-based search system includes four high-level components: 1) a knowledge repository, which stores a large collection of known entities; 2) a named entity detector, which detects ...

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

An entity-based search system is described herein that detects and recognizes entities in Internet-based content and uses this recognition to organize search results. The system associates one or more entity identifiers with a web page and stores this information as metadata of the page in a search engine index. This metadata will enable entity-based queries as well as rich data presentations in a search engine result page (SERP), including grouping results by entities, filtering results by one or more particular entities, or re-ranking search results based on user preference of entities. Thus, the entity-based search system allows users to identify a particular entity the user is interested in finding, and to receive search results directly related to that entity.

Description

Background technique [0001] The Internet provides access to a vast amount of information. A major challenge given the amount of information is how to find and discover information to provide users with the most relevant information for a particular context. The most common tool used to accomplish this today is a keyword-based search query provided to a search engine. The search engine matches the received keywords to one or more words or phrases in the search index in order to identify documents, web pages or other content potentially relevant to the user's query. For example, if a user searches for "dinosaurs," the search engine provides the user with a list of search results that are links to web pages that contain the term. [0002] User queries typically contain one or more entities identified by names or attributes associated with the entities (for example, person, location, or organization names). For example, one query might search for "Barack Obama," while another m...

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): G06F17/30G06F40/00
CPCG06F16/9535G06F16/951G06F16/3346G06F16/9538
Inventor 李康李鹢周一萍吕正东曹涌
Owner MICROSOFT TECH LICENSING LLC
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