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

Query string paraphrasing method and equipment

A technology for transforming equipment and query strings, which is applied in the search field and can solve problems such as query strings not meeting language habits and grammatical requirements, semantic shifts, etc., and achieve the effect of reducing semantic shifts and accurate synonymous strings

Inactive Publication Date: 2016-05-11
ALIBABA (CHINA) CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] In the existing technology, the query string is synonymously transformed only by replacing the synonym of the participle segment, which may easily cause the query string obtained by the synonymous transformation to not meet the language habits and grammatical requirements, and may easily cause semantic deviation.

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
  • Query string paraphrasing method and equipment
  • Query string paraphrasing method and equipment
  • Query string paraphrasing method and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] see figure 2 , which is a flow chart of Embodiment 1 of the query string synonym transformation method provided by the present invention.

[0080] The synonym transformation method of the query string in the search engine provided by this embodiment includes:

[0081] S201: Perform word segmentation processing on the query string to obtain word segmentation fragments;

[0082] It should be noted that S201 can use the word segmentation processing method in the prior art. For example, if the query string is "Fangheng International Center, Futong East Street, Chaoyang District, Beijing", the word segmentation segment obtained after the word segmentation processing is: "Beijing / Word segmentation results of multiple granularities such as Chaoyang District / Futong East Street / Fangheng International Center", "Beijing / City / Chaoyang / District / Futong / East / Ave / Fangheng / International / Center".

[0083] It is understandable that a query string can have multiple word segmentation re...

Embodiment 2

[0106] see image 3 , which is a flow chart of Embodiment 2 of the query string synonym transformation method provided by the present invention.

[0107] In the first embodiment, it is introduced that if the synonymous string after the synonymous string A ranked nth is the same as the demand satisfaction value of A, any one of these synonymous strings with the same demand satisfaction value can be randomly selected as the first n synonymous strings are fed back. The following describes that the embodiments of the present invention do not provide random feedback for this situation, but perform selective feedback according to the probability of the language model.

[0108] For example, if two synonymous strings need to be fed back, and the demand satisfaction values ​​of the two synonymous strings ranked 2nd and 3rd are equal, the two synonymous strings are represented by b and c respectively , at this time, it is necessary to judge the probability of the language model corres...

Embodiment 3

[0165] see Figure 4 , which is a flow chart of Embodiment 3 of the query string synonym transformation method provided by the present invention.

[0166] In the second embodiment of the method, it is introduced that if the synonymous string after the nth synonymous string A is the same as the demand satisfaction value of A, then the synonymous string is selected by calculating the probability of the language model. In this embodiment This paper introduces the situation that if the synonym strings before and after the synonym strings ranked nth are the same as A's demand satisfaction, the synonym strings are selected by calculating the language model probability.

[0167] S401-S405 in this embodiment are respectively the same as S301-S305 in the second method embodiment, and will not be repeated here.

[0168] S406: Judging that the synonym string before and after the synonym string A ranked nth is the same as the demand satisfaction of A, if yes, execute S408; otherwise, exe...

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 provides a query string paraphrasing method and equipment. The method comprises the following steps: carrying out word segmentation processing on a query string to obtain a segmentation segment; with the segmentation segment as a unit, carrying out synonym query on the query string in a preset word stock by a positive forward maximum matching algorithm; replacing the corresponding segmentation segment in the query string with the queried synonym to obtain a plurality of synonym strings; carrying out need satisfaction statistics on each synonym string and obtaining a need satisfaction value of each synonym string; ranking the synonym strings according to the need satisfaction values from large to small; and regarding front n synonym strings as paraphrased query strings, wherein n is a preset number of to-be-fed synonym strings. The positive forward maximum matching algorithm is matching the longest synonym in priority, so that the obtained synonym strings can conform to the expressing habit of a user; and a semantic shift can be reduced to the maximal extent. The synonym strings with relatively high need satisfaction values relatively conform to the query intention of the user, so that the fed synonym strings are relatively accurate.

Description

technical field [0001] The invention relates to the field of search technology, in particular to a method and device for synonymous transformation of query strings. Background technique [0002] At present, address search is already a search method frequently used in people's lives, for example, searching for hotels, restaurants, and shopping centers. In this way, people can realize route planning to the destination before or during the trip. [0003] However, different users have different names for the same thing. For example, the query string entered by the user is "Fangheng International Building", but in the database corresponding to the search engine, there is only POI data named "Fangheng International Center". It can be seen that although the query string entered by the user is "Fangheng International Building", what it actually expects to query is "Fangheng International Center". [0004] Therefore, it is necessary for the search engine to perform synonym transfor...

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): G06F17/30G06F17/27
Inventor 王思聪
Owner ALIBABA (CHINA) CO LTD
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