Method and device for determining suggest word

A technology of recommended words and candidate words, which is applied in the computer field, can solve the problems of large amount of calculations for recommended words and the inability to generate personalized recommended words for users, and achieve the effect of reducing workload and improving efficiency

Active Publication Date: 2012-09-19
ALIBABA GRP HLDG LTD
View PDF3 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of this application is to provide a method and device for determining recommended words to solve the problem in th

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
  • Method and device for determining suggest word
  • Method and device for determining suggest word
  • Method and device for determining suggest word

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Embodiment 1 of the present application provides a method for determining recommended words, such as figure 1 As shown, the method includes the following steps:

[0032] Step 101: Receive a search request including query words sent by a user.

[0033] In this step, when a user wishes to perform an information search process, a search request including query words is actively initiated. The query words involved in this step may be the query words obtained by the user converting the item to be searched for, or the user actively selects the previously displayed recommended words as the new query words.

[0034] If the device for determining the recommended words (hereinafter referred to as the device for determining the recommended words) is a logical component integrated in the search engine, then in this step, after receiving the search request sent by the user, the device for determining the recommended words will search according to the search request. The included q...

Embodiment 2

[0058] Embodiment 2 of the present application describes the scheme of Embodiment 1 of the present application in detail through specific examples.

[0059] In the solution of the second embodiment, it is necessary to analyze the user's behavior within a set time period, and generate a category feature model of the user behavior and a word feature model of the user behavior. The modeling process of the category feature model and the word feature model will be described in detail below.

[0060] 1. The modeling process of the category feature model:

[0061] The query words and documents browsed by the user in the set time period of history can reflect the user's interest field, and the categories of the query words and the subject terms of the browsed documents can reflect the user's interest in various categories. The degree of interest, the degree of interest of users in various categories can be described through the model based on vector space, as shown in formula (1):

...

Embodiment 3

[0155] Embodiment 3 of the present application also provides a device for determining recommended words, such as image 3As shown, it includes: a receiving module 11, a candidate set determining module 12, a correlation determining module 13 and a recommendation module 14, wherein: the receiving module 11 is used to receive a search request containing query words sent by a user; the candidate set determining module 12 is used to According to the pre-stored word sets used by a plurality of users, the word set that contains the query word is used as the candidate word set; the correlation determination module 13 is used to determine the correlation between the candidate word and the query word for a plurality of candidate words in the candidate word set degree, and determine the degree of relevance of each word in the word set used by the user who sends the search request to the candidate word; the recommendation module 14 is used to combine the degree of relevance with the query...

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 application discloses a method and a device for determining a suggest word. In the method and the device, the relevance between a candidate word and an inquired word and the relevance between the candidate word and an interested field of a user are considered comprehensively according to the relevance of word characteristics and category characteristic, and further the candidate word with relatively high relevance with the inquired word and the interested field of the user is selected as the suggest word, so that the finally obtained suggest word is highly relevant to the inquired word and the interesting of the user in the meaning of the word and the category of the word; when the suggest word is determined according to the same inquired word of different users, the interesting points of the users can be distinguished effectively, so that the suggest word capable of reflecting the demands of the user can be determined finally; and meanwhile, the relevance of word category is considered when the suggest word is determined, so that even if the inquired word has various meanings in different fields, the suggest word can be determined accurately according to the interested fields of the user. According to the method and the device, the workload in the suggest word determining process can be reduced effectively, and the suggest word determining efficiency is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a method and device for determining recommended words. Background technique [0002] The information search process refers to the process that the search engine searches out the search information related to the query word from a specific search information base according to the query word input by the user, and displays the obtained search information to the user. During the information search process, the user needs to convert the item to be searched into a query word for searching. If the query word used by the user is inaccurate, the final search information may not be the search information the user actually wants to obtain. In order to improve the accuracy of search results, a relevant search scheme is introduced in the process of information search. [0003] Relevant search means that the search engine pushes recommended words that are highly relevant to the q...

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
IPC IPC(8): G06F17/30
Inventor 廖剑林锋黎耀炳冯炯
Owner ALIBABA GRP HLDG 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