Power point commodity recommendation method and system based on logistic regression

A product recommendation and logistic regression technology, which is applied in the direction of business, equipment, sales/lease transactions, etc., can solve the problems of weak recommendation targets, increased system burden, and no consideration of user behavior habits, etc., to meet the real-time requirements of the system Effect

Inactive Publication Date: 2019-08-20
DAREWAY SOFTWARE
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Different users have different behavior habits, and the same is true in the field of e-commerce. The traditional recommendation system does not consider the behavior habits of users, but calculates and recommends them all. This increases the burden of the system invisibly and makes the recommendation target Sex is not strong

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
  • Power point commodity recommendation method and system based on logistic regression
  • Power point commodity recommendation method and system based on logistic regression
  • Power point commodity recommendation method and system based on logistic regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Embodiment 1, this embodiment provides a method for recommending power points commodities based on logistic regression;

[0039] A method for recommending power points products based on logistic regression, including:

[0040] S0: Cluster users to obtain different user groups;

[0041] S1: For each type of user, obtain the most relevant feature data of positive sample users who have points and have redeemed products with points, and also obtain the most relevant feature data of negative sample users who have points and have not redeemed products with points;

[0042] S2: Using the logistic regression algorithm, the most relevant feature data of positive sample users, the most relevant feature data of negative sample users, and the label of points redemption or not are used as training set data to establish a potential customer prediction model;

[0043] S3: Based on the potential customer prediction model, predict the probability of the user's points exchange according...

Embodiment 2

[0098] Embodiment 2: This embodiment provides a power point commodity recommendation system based on logistic regression;

[0099] A power point commodity recommendation system based on logistic regression, including:

[0100] User classification module, which clusters users to obtain different user groups;

[0101] The most relevant feature acquisition module, which is configured to obtain the most relevant feature data of positive sample users who have points and have redeemed commodities with points for each type of user, and also obtain negative samples that have points and have never redeemed commodities with points User's most relevant characteristic data;

[0102] A potential customer prediction model building module, which is configured to adopt a logistic regression algorithm, using the most relevant feature data of positive sample users, the most relevant feature data of negative sample users, and the label of points redemption or not as training set data to establi...

Embodiment 3

[0105] Embodiment 3: This embodiment also provides an electronic device, including a memory, a processor, and computer instructions stored in the memory and run on the processor. When the computer instructions are executed by the processor, each step in the method is completed. For the sake of brevity, the operation will not be repeated here.

[0106] Described electronic device can be mobile terminal and non-mobile terminal, and non-mobile terminal comprises desktop computer, and mobile terminal comprises smart phone (Smart Phone, such as Android mobile phone, IOS mobile phone etc.), smart glasses, smart watch, smart bracelet, tablet computer , laptops, personal digital assistants and other mobile Internet devices that can communicate wirelessly.

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 power point commodity recommendation method and system based on logistic regression, and the method comprises the steps: obtaining the most relevant feature data of a positive sample user who has points and exchange commodities with points for each type of users, and obtaining the most relevant feature data of a negative sample user who has points and does not exchange commodities with points; establishing a potential customer prediction model by adopting a logistic regression algorithm and taking the most relevant characteristic data of the positive sample user, themost relevant characteristic data of the negative sample user and a score exchange label as training set data; based on the potential customer prediction model, predicting the probability of credit exchange of the user according to the historical credit exchange record of the to-be-predicted user; and regarding the users whose probabilities are greater than a set threshold value as potential pointexchange users, and recommending commodities for the potential point exchange users by adopting a collaborative filtering algorithm.

Description

technical field [0001] The present disclosure relates to the field of personalized recommendation, and in particular to a method and system for recommending power points commodities based on logistic regression. Background technique [0002] The statements in this section merely mention background art related to the present disclosure and do not necessarily constitute prior art. [0003] In the process of realizing the present disclosure, the inventors found that the following technical problems existed in the prior art: [0004] In recent years, the rapid development of information technology has led to the continuous increase of the number of Internet users, and the exponential growth of data volume. People have entered an era of information overload. How to obtain the information that users want from the massive amount of information under the background of big data It has become an important research topic. As an important technology to overcome information overload, 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 Applications(China)
IPC IPC(8): G06Q30/02G06Q30/06G06Q50/06
CPCG06Q30/0202G06Q30/0222G06Q30/0224G06Q30/0226G06Q30/0631G06Q50/06
Inventor 史玉良张晖管永明吕梁张洪涛吕贺
Owner DAREWAY SOFTWARE
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