Information recall sorting method, device and equipment based on label grading

A sorting method and information technology, applied in the computer field, can solve problems such as low sorting accuracy, high false recall rate, and weak correlation of user interests, and achieve the effect of improving accuracy, raising standards, and reducing false recall rate

Pending Publication Date: 2022-03-18
宁波深擎信息科技有限公司 +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, all information related to user interest tags is usually pushed to users based on user interest tags, and the false recall rate is relatively high; in addition, the sorting of information is usually based on factors such as the reading volume of the information itself. The relevance of user interests is weak, and there is a problem of low sorting accuracy

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
  • Information recall sorting method, device and equipment based on label grading
  • Information recall sorting method, device and equipment based on label grading
  • Information recall sorting method, device and equipment based on label grading

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0042] In one embodiment, such as figure 1 As shown, a label-based information recall sorting method is provided, including the following steps:

[0043] Step 102: Acquire user behavior log data within a preset time period, obtain user portrait labels according to the user behavior log data, and input user portrait labels into a pre-trained logistic regression model to obtain user portrait classification labels.

[0044] User portraits are user interest portraits, also known as user interest models, which are generally calculated based on user behavior. Give interest poi...

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 relates to an information recall sorting method and device based on label grading and computer equipment. The method comprises the steps that user portrait labels are classified into main body labels and auxiliary labels, then information is processed, information portrait labels with weight information are extracted, and in the information recall stage, a candidate information set is obtained from original information according to the user portrait main body labels and the information portrait labels; and in an information sorting stage, according to the user portrait main body label, the user portrait auxiliary label and the information portrait label, obtaining a relevancy value between the user and each piece of information in the candidate information set, and sorting the information in the candidate information set according to the relevancy value. According to the method, only the information related to the main body label is recalled in the recall stage, the recall standard is improved, the false recall rate is reduced, the main body label and the auxiliary label of the user portrait are taken into consideration in the sorting stage, the information hitting the joint label can be sorted preferentially, and the sorting accuracy is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a label-based information recall sorting method, device and computer equipment. Background technique [0002] The information recommendation system can recommend information collections that users are interested in, and it is divided into two parts: recall and sorting. Recall is to obtain candidate information sets according to user interests, and sorting is to sort the information in candidate information sets according to the degree of possible interest of users. In the prior art, all information related to user interest tags is usually pushed to users based on user interest tags, and the false recall rate is relatively high; in addition, the sorting of information is usually based on factors such as the reading volume of the information itself. The relevance of user interests is weak, and there is a problem of low ranking accuracy. Contents of the invention [...

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): G06F16/9038
CPCG06F16/9038
Inventor 吴晨
Owner 宁波深擎信息科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap