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

A Modular User Retrieval Intent Modeling Method for Small and Medium-sized Websites

A modeling method and user intent technology, applied in the computer field, can solve the problems of time-consuming, inaccurate and inaccurate retrieval results, and less consideration of user retrieval intent, saving time and energy and improving efficiency.

Active Publication Date: 2020-03-24
CENT SOUTH UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the retrieval mode adopted for text retrieval of small and medium-sized websites only uses the keywords submitted by users as the query basis, and seldom considers the user's retrieval intention.
Generally, users only enter short words as query conditions, which leads to inaccurate search results in this search mode, and users need to spend more time and energy to find the target by viewing the detailed information of the link result

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 Modular User Retrieval Intent Modeling Method for Small and Medium-sized Websites
  • A Modular User Retrieval Intent Modeling Method for Small and Medium-sized Websites
  • A Modular User Retrieval Intent Modeling Method for Small and Medium-sized Websites

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Based on the characteristics of simple webpage structure of small and medium-sized websites, the present invention digs out a user intention model by fully analyzing the access behavior during the interaction process between the user and the server. The model uses a keyword extraction method that combines interaction information entropy and word feature information, and a text ranking method that combines cosine similarity and weighted Hamming distance. It first extracts keyword sets from web pages browsed by users and establishes intent models. Then re-retrieve the new keyword set as a query condition, and finally re-rank the retrieval results, so as to provide users with results that are more in line with the user's retrieval intention. This scheme does not require users to perform additional feedback operations, and can realize the instant modeling process of user intentions during normal retrieval. Its specific process is shown in the accompanying drawing figure 1...

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 discloses a small and medium-sized website-oriented modularized user retrieval intention modeling method, and a user intention retrieval model on the basis of a cross information entropy and word feature information combined keyword extraction method and a cosine similarity and weighted Hamming distance combined text sorting method. According to the method, a progress of not requiring the users to carry out extra feedback operations and realizing the instant modeling process of user intentions during the normal retrieval of the users is made, so that an effect of recommending more satisfied retrieval effects to the users without requiring any feedback of the users is achieved, the time and vigor for searching target results by the users is saved, the query efficiency of the users is improved, and the target results more accord with the user retrieval intentions.

Description

technical field [0001] The invention relates to the field of computers, in particular to a modular user retrieval intention modeling method for small and medium-sized websites. Background technique [0002] In recent years, major search engine companies have been devoting themselves to the optimization of search engine algorithms to predict users' search intentions. Compared with large search engine companies, the investment cost of small and medium-sized websites is generally lower, and the optimization of search algorithms is often ignored in the construction and maintenance of websites. the result of. Therefore, it is necessary to provide a search optimization method for small and medium-sized websites, so that it can provide users with better search services. [0003] At present, mature commercial search engines have achieved considerable results in the research of user search intentions. The technical solutions that have been proposed mainly include the following: cla...

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): G06F16/951G06F16/33
CPCG06F16/3334G06F16/951
Inventor 郭克华李婷
Owner CENT SOUTH UNIV