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

Method, device and equipment for determining search result and computer storage medium

A technology of search results and search history, applied in the field of intelligent search and computer application, it can solve problems such as inability to accurately reflect user needs, inaccurate related entities of search keywords, and inability to know whether users refer to cities, movies or operas, etc.

Active Publication Date: 2020-05-19
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF11 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, traditional related entity recommendation only considers the user's current search keywords. For the same search keyword, the same related entity recommendation is performed for all users.
But this situation cannot solve the problem of inaccurate related entities with ambiguous search keywords
For example, if the user's current search keyword is "Chicago", it is impossible to know whether the user is referring to a city, a movie, or an opera, so it is inevitable that the user's needs cannot be accurately reflected when recommending related entities

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, device and equipment for determining search result and computer storage medium
  • Method, device and equipment for determining search result and computer storage medium
  • Method, device and equipment for determining search result and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] figure 2 The flow chart of the method recommended by the relevant entity provided in Embodiment 1 of this application, such as figure 2 As shown in , the method may include the following steps:

[0073] In 201, obtain the user's current query (search keyword), the user's search history information within the first time length, the user's search history information within the second time length, and the candidate related entities of the current query, wherein the second time length is longer than the first time length for a while.

[0074] The traditional entity recommendation system is only based on the recommendation of the current query. The current query refers to the query currently input by the user, and cannot understand the user's real search needs, resulting in inaccurate recommendations for related entities that do not meet the user's needs.

[0075] After research, it is found that search history can provide very valuable clues, and these clues can better ...

Embodiment 2

[0122] Figure 4 The flow chart of the method for training the entity ranking model provided in Embodiment 2 of the present application, such as Figure 4 As shown in , the method may include the following steps:

[0123] In 401, a training sample is acquired by using a search log.

[0124] The acquired training samples include the sample query, the user's search history information within the first period of time before entering the sample query, the user's search history information within the second period of time before entering the sample query, the search results corresponding to the sample query, and the clicks of the search results situation, the second duration is greater than the first duration.

[0125] In this application, the search logs for a continuous period of time are obtained, and the above-mentioned training samples are extracted from them.

[0126] Similar to that in Embodiment 1, the search history information of the user within the first period of tim...

Embodiment 3

[0144] For entity ranking, there is a problem of sparse entity click data to a certain extent. Because of the limitation of display space, the entity ranking model of the entity ranking model tends to recommend entities based on the most frequently mentioned meaning of the query. For ambiguous queries, except for the most frequently mentioned meaning, the entity click data corresponding to less and rarely mentioned meanings are very sparse. In order to better meet the diverse information needs of users, most search engines will provide users with diverse search results. Therefore, when users search, it is easier to find results that match their own information needs in web search results than entity recommendation results. In this embodiment, the overall model may include a shared vector sub-model, a first ranking sub-model and a second ranking sub-model. The first sorting sub-model adopts the sorting sub-model described in Embodiment 2 above as the main task for sorting rela...

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, device and equipment for determining a search result and a computer storage medium, and relates to the field of intelligent search. According to the specific implementation scheme, the method comprises the steps that 1, obtaining the current query of the user, the search history information of the user in the first duration, the search history information of the user in the second duration and the candidate search result of the current query; a search result ranking model is input, a search result corresponding to the current query is determined according to scores of the candidate search results, and the second duration is longer than the first duration; wherein the score of the candidate results by the search result sorting model is determined accordingto the similarity between the integration of the vector representation of the current query and the vector representation of the search history information of the user within the first duration and the vector representation of the candidate search results; and determining the similarity between the integration of the vector representation of the current query and the vector representation of the search history information of the user within the second duration and the vector representation of the candidate search result.

Description

technical field [0001] The present application relates to the field of computer application technology, in particular to a method, device, device and computer storage medium for determining search results in the field of intelligent search. Background technique [0002] In recent years, in order to provide users with richer search results and better search experience, mainstream search engines have provided relevant entity recommendations for users' searches. For example, when a user uses a search engine to search for the keyword "Chicago", the search results page provides information such as figure 1 Related entity recommendations shown in . figure 1 The left part of the center displays the document search results of "Chicago", and the right part displays the entity recommendation results of "Chicago" (the entity recommendation result can also be regarded as a search result, which is an entity related to the input search keyword). Suggests related entities such as "San Fr...

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): G06F16/9535G06F16/9538
CPCG06F16/9535G06F16/9538G06F16/9035
Inventor 黄际洲王海峰张伟
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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