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

Method and equipment for determining word information entropy and searching by using word information entropy

A technology of information entropy and information entropy value, which is applied in the field of computer networks, can solve the problem of deviation in the determination of word information entropy, and achieve the effect of improving accuracy and accurate word information entropy value

Active Publication Date: 2011-09-21
ALIBABA GRP HLDG LTD
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] On the one hand, the present application provides a method and device for determining word information entropy to solve the problem existing in the prior art that there is a deviation in the determination of word information entropy of words in a search request
[0008] On the other hand, the present application also provides a search method to solve the problem of how to improve the accuracy of the search results when the search request does not fully match the search results

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 equipment for determining word information entropy and searching by using word information entropy
  • Method and equipment for determining word information entropy and searching by using word information entropy
  • Method and equipment for determining word information entropy and searching by using word information entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Embodiment 1 of the present application provides a method for determining word information entropy, the schematic diagram of which is as follows figure 1 shown, including the following steps:

[0041] Step 101: Receive multiple search requests input by the user, and determine the category to which each search request belongs.

[0042] In this embodiment, the search request input by the user is a short text containing only about 2-3 words on average.

[0043] This embodiment does not limit the solution for determining the category of the search request. Two available solutions are given below:

[0044] The first solution: use user behavior data to automatically mine the category of the search request.

[0045] In the web log (web log), the direct click behavior from the search request to the category is often disturbed by the page layout, and the data is relatively sparse. Therefore, an indirect method is needed to obtain the category to which the search request belon...

Embodiment 2

[0081] Embodiment 2 of the present application is based on Embodiment 1, using the determined word information entropy value of each word to search, such as figure 2 shown, including the following steps:

[0082] Step 201: According to a search request input by a user, determine whether there is a search result matching the search request.

[0083] In this step, if there is a search result that directly matches a search request input by the user, the corresponding search result is directly returned to the user; otherwise, step 202 is executed.

[0084] Step 202: According to the saved words and word information entropy values ​​corresponding to each word, select at least one word whose word information entropy value is smaller than a set threshold value among the words obtained after word segmentation of the search request.

[0085] In this step, the previously received search requests can be grouped according to the category they belong to according to the method in Embodim...

Embodiment 3

[0094] The schemes of Embodiment 1 and Embodiment 2 of the present application will be described in detail below in conjunction with specific examples.

[0095] The specific implementation process of the third embodiment is as follows:

[0096] Step 1: Determine the category to which the input search request_1, search request_2...search request_n belongs.

[0097] Assuming that the number of input search requests is 2, which are "new mobile phone" and "new dress", it is determined that the category of "new mobile phone" is "mobile phone", and the category of "new dress" is "skirt".

[0098] Step 2: Group search request 1 to search request n by category.

[0099] Classify "new phone" into group 1 and "new dress" into group 2.

[0100] Step 3: Determine the frequency information of the search request in each group, that is, determine D={, ...}, where: D represents a group, and Q1 represents a search request, QC1 indicates the number of search requests identical to Q1 in group...

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 method and equipment for determining word information entropy and searching by using the word information entropy. The method comprises the following steps of: grouping search requests according to subordinate categories so as to form a data group similar to a large text; calculating the word information entropy of a word on the basis of the data group so as to accurately measure an important degree of the word, wherein the calculated word information entropy is accurate; and determining an important word in the search request by using the calculated word informationentropy so as to display a matching result of the word having a higher important level to a user at first when the search request cannot be matched with a search result totally and enhance the accuracy of the search result.

Description

technical field [0001] The present application relates to the field of computer networks, in particular to a method and device for determining word information entropy, and a method and device for searching using the determined word information entropy. Background technique [0002] A search request (Query) is a unique short text in the search engine scenario. The user describes the information to be retrieved through the search request, and the search engine retrieves the database through the information described in the search request and returns the result that the user wants. A search request initiated by a user consists of an average of 2.4 words (for example: silk dress, candy bar mobile phone). Generally, users use natural text as a search request instead of using statements such as and, or, and not, so search engines based on When retrieving the received search request, it is necessary to determine the user's intention to search according to the amount of information...

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
CPCG06F17/30979G06F17/30684G06F16/319G06F16/355G06F16/353G06F16/3331G06F16/951G06F16/35G06F16/3325G06F16/3344G06F16/90335
Inventor 金凯民
Owner ALIBABA GRP HLDG LTD