Semantic similarity computing method, search result processing method and search result processing device

A technology of semantic similarity and search results, applied in computing, semantic analysis, digital data processing and other directions, can solve the problems of low similarity accuracy and inability to take into account the degree of matching, and achieve the effect of improving accuracy

Active Publication Date: 2015-03-25
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF8 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For example, for two text strings "acupuncture for baby's fever" and "diagram of acupoint massage for child with fever", since "fever" appears in both text strings, "baby" and "child" are not considered complete Therefore, the degree of matching between words such as "baby has a fever" and "child has a fever" and "acupuncture" and "acupoint massage" cannot be considered. The accuracy of the similarity calculated by the above method is low

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
  • Semantic similarity computing method, search result processing method and search result processing device
  • Semantic similarity computing method, search result processing method and search result processing device
  • Semantic similarity computing method, search result processing method and search result processing device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] figure 2 It is a flow chart of the semantic similarity calculation method in Embodiment 1 of the present invention. The method may be performed, for example, on a search engine server. Described semantic similarity computing method comprises the steps:

[0024] Step 11: Obtain the first text string and the second text string. For example, the first text string and the second text string may be the user's search term and the content title of any search result item obtained according to the search term.

[0025] Step 12: Segment the first text string and the second text string respectively to generate word segmentation results.

[0026] The search engine server can use the existing text string word segmentation technology to perform word segmentation on the two text strings respectively, and obtain the respective word segmentation results of the two text strings.

[0027] Step 13: According to the word segmentation results, the word segmentation of the fir...

Embodiment 2

[0068] image 3 It is a flow chart of the search result processing method according to Embodiment 2 of the present invention. The method may be performed, for example, on a search engine server. The method comprises the steps of:

[0069] Step 21: Receive the user's search term.

[0070] The search term may be a search term sent from a client. For example, the user enters "baby has a fever according to acupuncture points" on the browser search engine interface to search, and the browser application sends the search term to the search engine server.

[0071] Step 22: Obtain multiple search result items according to the search term.

[0072] After receiving the user's search term in step 21, multiple search result items can be obtained according to the search term. Specifically, the search engine server can use the search term to obtain multiple search result entries.

[0073] Step 23: Calculate the semantic similarity values ​​between the search term and the c...

Embodiment 3

[0080] Figure 4 It is a logical block diagram of the semantic similarity calculation device according to Embodiment 3 of the present invention. refer to Figure 4 , the semantic similarity computing device includes:

[0081] A text string obtaining module 31, configured to obtain a first text string and a second text string.

[0082] The text string word segmentation module 32 is configured to perform word segmentation on the first text string and the second text string respectively, and generate word segmentation results.

[0083] The semantic layer generating module 33 is configured to generate a plurality of predetermined semantic layers from the word segmentation of the first text string and the second text string according to the word segmentation results.

[0084] Preferably, the semantic layer generation module 33 is used for any text string in the first text string and the second text string, by each single word in the word segmentation result of the te...

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 embodiment of the invention provides a semantic similarity computing method, a search result processing method and a search result processing device. The semantic similarity computing method comprises the following steps: obtaining a first text string and a second text string; carrying out word segmentation on the first text string and the second text string respectively to generate word segmentation results; generating and reserving a plurality of semantic layers from the word segmentation obtained by the first text string and the second text string according to the word segmentation results; carrying out dependency similarity computing on each semantic layer of the first text string with all semantic layers of the second text string respectively to obtain N*N dependency similarity values; computing the semantic similarity values of the first text string and the second text string according to the computed N*N dependency similarity values. Through the semantic similarity computing method, the search result processing method and the search result processing device provided by the embodiment of the invention, the accuracy of semantic similarity computing between the text strings can be improved.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a semantic similarity calculation method, a search result processing method and a device. Background technique [0002] In search engine technology, providing search result pages that match users' search terms is a problem that R&D designers continue to research and explore. The degree of matching between the search result web page and the user's search term can be judged by calculating the similarity between the search term and the title of the search result web page, which involves calculating the time similarity of text strings. [0003] In the prior art, the similarity between the two text strings is usually calculated by considering the number of completely matched words in the two text strings, without considering the matching of semantically identical or similar words, thus The calculated similarity is less accurate. [0004] For example, for two text...

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
CPCG06F16/951G06F40/30
Inventor 张军吴先超刘占一
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
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