Supercharge Your Innovation With Domain-Expert AI Agents!

Method for generating ranking model, method for ranking search results, device and equipment

A search result and sorting model technology, applied in the search field, can solve the problems of high manual fitting costs and difficulty in ensuring accuracy, and achieve the effect of reducing time and labor costs and improving accuracy

Active Publication Date: 2020-12-29
CHENGDU OPPO TELECOMM TECH CORP LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] When the number of ranking factors is large or the ranking factors change, the cost of manual fitting is high, and the accuracy is difficult to guarantee

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 for generating ranking model, method for ranking search results, device and equipment
  • Method for generating ranking model, method for ranking search results, device and equipment
  • Method for generating ranking model, method for ranking search results, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0034] In the technical solution provided by the embodiment of the present application, by constructing multiple sets of training samples, using a machine learning algorithm to study the training samples, a machine learning sorting model is obtained, and the machine learning sorting model is used to output the sorting results of the search results. The ranking factors involved in the combined ranking formula are converted into the feature factors of the machine learning ranking model. Even when the number of feature factors is large or the feature factors change, the machine learning ranking model can be automatically trained to reduce time and labor costs. , and helps to improve the accuracy of sorting search results.

[0035] I...

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

Embodiments of the present application provide a method for generating a ranking model, a method for ranking search results, an apparatus, and an apparatus. The method comprises the following steps: acquiring a plurality of groups of training samples; Wherein each set of training samples comprises a sample search term corresponding to a search operation and at least one search result thereof, anda ranking priority of each search result label; For each group of training samples, the feature vectors of n dimensions corresponding to the respective search results of the sample search terms are obtained. The machine learning ranking model is trained by using multiple groups of training samples, and the machine learning ranking model is obtained. In an embodiment of that present application, Bytransforming the sorting factors involved in the artificial fitting sorting formula into the characteristic factors of the machine learning sorting model, Even when the number of feature factors is large or the feature factors are changed, the machine learning ranking model can be trained automatically, which reduces the time and labor cost, and helps to improve the accuracy of ranking search results.

Description

technical field [0001] The embodiments of the present application relate to the field of search technology, and in particular to a method for generating a ranking model, a method, device and equipment for sorting search results. Background technique [0002] The performance of a search engine is not only reflected in the accuracy of search results, but also in the accuracy of sorting search results. [0003] In related technologies, a sorting algorithm presets multiple sorting factors, and then artificially fits a sorting formula based on the sorting factors. After obtaining multiple search results for a certain search term, the score corresponding to each search result is calculated through the above sorting formula, and the above multiple search results are sorted in descending order of scores. [0004] When the number of ranking factors is large or the ranking factors change, the cost of manual fitting is high, and the accuracy is difficult to guarantee. Contents of th...

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): G06F16/9038G06F16/953
Inventor 罗月
Owner CHENGDU OPPO TELECOMM TECH CORP LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com