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

Method and device for generating recommendation information

A technology of recommending information and recommending parties, applied in the multimedia field, can solve the problems of slow improvement of transaction ability and limited range of recommended products, and achieve the effect of promoting promotion, promoting transaction volume and transaction efficiency, and improving product selection efficiency.

Pending Publication Date: 2022-04-12
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since such a product selection method is only based on the historical behavior of the talent itself, it is easy to form an information cocoon, resulting in the dilemma of limited recommended product range and slow improvement in transaction ability

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 device for generating recommendation information
  • Method and device for generating recommendation information
  • Method and device for generating recommendation information

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0117] Example 1: In the case that the scenario information indicates that alternative recommended items are recommended to the purchaser based on the key recommender, the recommender identifier in step S240 is the recommender identifier corresponding to the key recommender. Next, based on the recommendation direction quantity corresponding to the key recommender identifier, the first recommendation information to be delivered may be generated, the first recommendation information including the information of multiple candidate recommenders associated with the key recommender . Since the recommendation direction vector and the recommendation item vector are obtained based on the same conversion relationship graph, the recommended items that the key recommender may like can be obtained directly according to the recommendation direction vector corresponding to the key recommender identifier. After obtaining such recommended item information, the recommended information can be di...

example 2

[0118] Example 2: In the case that the scenario information indicates that a candidate recommender is recommended to a key recommender, the recommender identifier in step S240 is the recommender identifier corresponding to the key recommender. Next, based on the recommendation direction quantity corresponding to the key recommender identifier, second recommendation information to be delivered is generated, where the second recommendation information includes information about a plurality of candidate recommenders similar to the key recommender. In such a scenario, you can recommend Talent B to Talent A who is similar in product selection style and transaction results. Therefore, talent A may pay attention to talent B, and assist in product selection based on the recommended items corresponding to talent B.

example 3

[0119] Example 3: In the case where the scenario information indicates that a candidate recommender is recommended to a key recommender, the recommender identifier in step S240 is the recommender identifier corresponding to the key recommender. Next, based on the recommendation direction quantity corresponding to the key recommender, third recommendation information to be delivered is generated, where the third recommendation information includes information of a plurality of candidate recommenders associated with the key recommender. In such a scenario, you can directly recommend to Talent A the recommended items that Talent B has recommended in terms of product selection style and transaction results. In this way, expert A can directly assist in product selection based on the recommended items corresponding to expert B.

[0120] Example 4: In the case where the scenario information indicates that alternative recommended items are recommended to the buyer based on the recomme...

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 provides a method and a corresponding device for generating recommendation information. The method comprises the steps that a conversion relation graph is determined based on conversion data corresponding to recommended objects recommended by a recommendation party, the conversion relation graph comprises a plurality of recommendation party nodes and a plurality of recommended object nodes, and edges connecting the recommendation party nodes and the recommended object nodes indicate that the recommendation party recommends the recommended objects; based on the conversion relation graph, a recommendation relation sequence set comprising a plurality of recommendation relation sequences is determined, and each recommendation relation sequence comprises a plurality of alternative recommender identifiers and recommendation object identifiers; generating at least one of a recommendation vector and a recommendation object vector based on the recommendation relationship sequence set; and generating to-be-released recommendation information based on the similarity between at least one of the recommendation vector and the recommendation object vector. The product recommendation range can be expanded, the product selection efficiency is improved, and improvement of the trading volume and the trading efficiency is promoted.

Description

technical field [0001] The present disclosure relates to the field of multimedia, and more particularly, to a method, device, device, computer-readable storage medium, and computer program product for generating recommendation information. Background technique [0002] At present, a CPS (Cost per Sales, pay per sale) alliance type advertising promotion model has appeared. The CPS Alliance calculates the advertising fee based on the actual sales of products, which can most directly reflect the effect of advertising promotion. In the CPS scenario, Key Opinion Consumers (Key Opinion Consumers, KOCs) earn commissions by promoting products and earning commissions according to the actual sales of products. Key Opinion Consumers, also known as experts, generally refer to influential consumers on the Internet, who are often followed by a large number of ordinary consumers. After the expert promotes the product, ordinary consumers can purchase the product through the link shared by...

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): G06Q30/02G06Q30/06G06F16/9535G06F40/242G06N3/04G06N3/08
Inventor 董喆
Owner TENCENT TECH (SHENZHEN) 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