Information recommendation method and device

A technology for information recommendation and information recommendation, applied in the computer field, can solve problems such as reducing the effect of information recommendation and inaccurate target users

Pending Publication Date: 2019-11-01
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide an information recommendation method and device to solve the problems in the p

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 recommendation method and device
  • Information recommendation method and device
  • Information recommendation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0103] 1) Obtain the click data of each target user based on the parameter identification added in the short message; wherein, the click data includes at least the interconnection protocol (Internet Protocol, IP) between user networks and the type of terminal equipment.

[0104] 2) Filter the obtained click data according to the preset black IP database and the preset server IP.

[0105] That is, the user IP is the IP in the black IP library or the server IP, and the corresponding click data is filtered out. This is because there may be some illegal or abnormal black IPs, and the click data of the black IP is usually abnormal click data, and the server IP Usually it is the IP owned by the server, and generally not the user IP. The click data of the server IP may be automatically clicked by the machine, not manually operated by the user. It is abnormal click data. Therefore, the click data can be processed according to the black IP and server IP. filter.

[0106] 3) Determine ...

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 the technical field of computers, in particular to an information recommendation method and device, and the method comprises the steps: obtaining a corresponding recall strategy and a short message model according to an information recommendation demand; obtaining a recalled user according to the recall strategy; according to the short message model, predicting recalled users respectively, and determining a candidate user set in which a short message click score of the user for the recommendation demand is greater than a threshold value, wherein the short message modelis trained by adopting a positive sample set and a negative sample set which are obtained according to the recommendation demand, so as to determine a click score of a user to a short message; filtering users in the candidate user set according to a preset filtering strategy to obtain a target user set; and sending a short message containing the to-be-recommended information to each target user in the target user set. The target user set is determined through recalling, short message model prediction, filtering and other operations, and the accuracy of the target users is improved, so that the information recommendation effect can be improved, and the cost is reduced.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an information recommendation method and device. Background technique [0002] At present, because SMS has the advantages of wide coverage, high reach rate, flexible time, and high reading rate, it is possible to recommend information based on SMS, and carry advertisements, application software and other recommended information in the content of SMS to recommend to users , However, blindly based on SMS delivery, will increase costs. [0003] In the prior art, the SMS-based information recommendation method adopts a relatively simple and fixed method, which is mainly to randomly select or use user tags to manually select numbers to determine the target user. Target users perform large-scale distribution. [0004] However, in the prior art, the selection of target users has strong human factors and low accuracy, thereby reducing the click-through rate of recommended inf...

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): G06F16/9535H04W4/14
CPCH04W4/14Y02D30/70
Inventor 曹路洋
Owner TENCENT TECH (SHENZHEN) CO 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

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