Unlock instant, AI-driven research and patent intelligence for your innovation.

Natural language search results for intent queries

A technology of intent and title, applied in the field of natural language search results for intent queries, can solve the problems of not being able to provide non-factual questions, reduce user experience, etc., and achieve the effect of quick and easy comparison and reduction of search results

Active Publication Date: 2019-09-17
GOOGLE LLC
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such excerpts are not natural language results and typically do not provide complete understandable answers to non-factual questions for which there is no single correct answer
While a user can select a link associated with an excerpt to view the context of the excerpt in the original document to determine whether the identified information is sufficient, this degrades the user experience and requires additional s hard work

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
  • Natural language search results for intent queries
  • Natural language search results for intent queries
  • Natural language search results for intent queries

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] figure 1 is a block diagram of system 100 according to an exemplary implementation. System 100 can be used to implement a search engine that provides natural language answers to queries that include questions with identifiable intent. right figure 1 The description of system 100 in is described as a system capable of searching authoritative sources available through the Internet to generate a question and answer (Q&A) data store that provides natural language answers. The system can provide intent templates for identifying queries with explicit intent and for identifying natural language answers from authoritative source content. Other configurations and applications of the described techniques may be used. For example, the system may include other methods of categorizing text from authoritative sources or identifying issues of explicit intent. As another example, natural language answers may be provided for other corpora such as intranets, libraries, or other docum...

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

A system and method provides natural language search results for clearly intended queries. To provide natural language search results, the system may parse documents from authoritative sources to generate at least one headline text pair that appears in the document under the headline. The system can assign a subject and a question category to the title text pair and store the title text pair in a data store keyed by the subject and question category. The system determines that the query corresponds to a topic and question category, and provides the title-text pair as a natural language search result for the query. In some implementations, the text portion of the headline-text pair can be a paragraph or a list of items and natural language search results can be provided along with conventional snippet-based search results in response to the query.

Description

[0001] Cross References to Related Applications [0002] This application claims priority to and is a continuation of U.S. Nonprovisional Patent Application No. 13 / 910,031, filed June 4, 2013, entitled "NATURAL LANGUAGE SEARCH RESULTSFOR INTENT QUERIES," the disclosure of which is incorporated by reference in its entirety at this. Background technique [0003] Search engines are a popular method of discovering information. Conventionally, search engines crawl documents in a corpus, build an inverted index of the documents, and use the index to determine which documents are responses to search queries. Search results typically include titles from the responsive document and text excerpts from the document that include one or more search terms in the query. Such excerpts are not natural language results and typically do not provide complete understandable answers to non-factual questions for which there is not a single correct answer. While a user can select a link associated...

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): G06F17/27G06F16/332
CPCG06F16/3329G06F40/258G06F16/35G06F16/93G06F16/334G06F40/186G06F40/205
Inventor 托默·什米尔德维尔·凯沙尔扬纳坦·埃雷兹
Owner GOOGLE LLC