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

A user preference prediction method and device, electronic equipment

A prediction method and user technology, which is applied in the computer field, can solve problems such as limited scope of use, inaccurate prediction results, and inability to predict preferences for unknown objects, so as to achieve accurate prediction results

Active Publication Date: 2021-09-03
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present application provides a user preference prediction method, which solves at least one of the problems in the prior art that the user preference prediction method has a limited range of use, cannot predict the preference of unknown objects, and has inaccurate prediction results.

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
  • A user preference prediction method and device, electronic equipment
  • A user preference prediction method and device, electronic equipment
  • A user preference prediction method and device, electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] A method for predicting user preferences disclosed in this embodiment, such as figure 1 As shown, the method includes: Step 110 to Step 130.

[0026] Step 110, acquiring the characteristics of the target user's interaction behavior with the target object.

[0027] During specific implementation, the target user's interactive behavior characteristics on the target object may include any one or more items of the number of times the target user purchases, clicks, browses, and favorites the target object. Taking the prediction of user u's preference for product I as an example, first, according to the user's historical behavior data stored on the platform or the entire network, determine the number of purchases, clicks, browsing times, and favorites of user u for product I within a period of time, as Interaction behavior characteristics of different dimensions.

[0028] Step 120, using a pre-trained preference prediction model to make predictions based on the interaction ...

Embodiment 2

[0034] Such as figure 2 As shown, a user preference prediction method disclosed in another embodiment of the present application includes: Step 210 to Step 240 .

[0035] Step 210: Determine a preference prediction model constituting the purchase prediction model by training the purchase prediction model.

[0036] Wherein, the purchase prediction model is obtained by superimposing the preference prediction model, the user factor model and the object factor model, and performing a sigmoid operation; the preference prediction model is used to fit the user's preference for the object; the user factor model is used to simulate The potential non-intuitive factors of the user's own shopping; the object factor model is used to fit the popularity of the object. Wherein, the training data used for training the purchase prediction model at least includes: basic user characteristics, basic object characteristics, and user interaction behavior characteristics for objects.

[0037] Befo...

Embodiment 3

[0061] A user preference prediction device disclosed in this embodiment, such as image 3 As shown, the device includes:

[0062] The feature acquisition module 310 to be predicted is used to acquire the interaction behavior characteristics of the target user to the target object;

[0063] A preference prediction module 320, configured to use a pre-trained preference prediction model to make predictions based on the characteristics of the interaction behavior, and determine the prediction result of the target user's preference for the target object;

[0064] A preference determination module 330, configured to determine the target user's preference for the target object according to the preference prediction result.

[0065] Optionally, the preference determination module 330 is further configured to determine that the target user does not prefer the target object if the score corresponding to the preference prediction result is negative; if the score corresponding...

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 present application provides a user preference prediction method, which belongs to the field of computer technology, and solves the problem of inaccurate prediction results existing in the user preference prediction method in the prior art. The prediction method of user preference includes: obtaining the interaction behavior characteristics of the target user to the target object, and predicting based on the interaction behavior characteristics through a pre-trained preference prediction model, and determining the preference of the target user to the target object A prediction result, determining the target user's preference for the target object according to the preference prediction result. In the method for predicting user preferences disclosed in this application, since the model training is realized based on a large amount of common data, the trained model is predicted based on common features rather than based on a single user ID or object ID, so the preference prediction result is more accurate. precise.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a user preference prediction method and device, and electronic equipment. Background technique [0002] In order to improve the click rate or purchase rate of network objects, such as goods and services, or to improve the user experience of the platform, many network platforms will recommend objects for users according to user preferences, or in search applications, combine user preferences to recall search results. At present, most of the methods for determining user preferences are obtained by counting the number of times users browse, click or purchase objects on the platform. When a user browses or clicks on an object (such as a product, POI), he usually has a tendency to choose according to the current environment. These factors ultimately determine whether the user places an order to buy. The number of behaviors of an object to get user preferences is inaccurat...

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): G06Q30/02
CPCG06Q30/0202
Inventor 吕兵左元付晴川朱日兵吴金蔚
Owner BEIJING SANKUAI ONLINE TECH CO LTD
Features
  • Generate Ideas
  • 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