Group demand prediction method based on long-term and short-term interests and social influence

An influential, long-term and short-term technology, applied in the field of group demand prediction based on long-term and short-term interests and social influence, to reduce data sparsity, improve satisfaction and group prediction effect, and improve accuracy

Pending Publication Date: 2022-01-21
NORTHWEST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, in most existing group demand forecasting methods, user preference is mainly considered, and some other factors that aff

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
  • Group demand prediction method based on long-term and short-term interests and social influence
  • Group demand prediction method based on long-term and short-term interests and social influence
  • Group demand prediction method based on long-term and short-term interests and social influence

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0068] The present invention will be further described below in conjunction with the embodiments and the accompanying drawings.

[0069] like figure 1 As shown in the figure, a group demand prediction method based on long-term and short-term interests and social influence includes the following steps:

[0070] Step 1, group division: divide groups according to user IP addresses;

[0071] Step 2, user access data processing: build a user's interest-rating association table at different times according to the user's historical access data to resources, and mine the changes of user needs over time, including:

[0072] 1) Numbering and marking the resource categories, constructing a resource category label dictionary, and attributing resources to different categories according to the resource attribute values, and then constructing a resource-category table;

[0073] 2) Construct two matrices with q rows and M columns, respectively, to store the access times and scores of q user...

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 group demand prediction method based on long-term and short-term interests and social influence. The method comprises the following steps: firstly, dividing groups based on IP addresses when users access resources; secondly, establishing an interest-score association table for each user in combination with historical access records of the users, training an individual LSTM network model, performing score prediction on a specified item under the condition of comprehensively considering historical behaviors and interest migration of the users, and further constructing a group user-item score table; then, on the basis of analyzing the personality and the professional degree of the users, investigating the sensitive degree of the users to the opinions of other users in the group, and analyzing the mutual relation between the users by mining the intimacy degree between the users in the group, so that a group user model based on social influence is formed; and finally, predicting the group demand according to the model. Long-term and short-term interests of the users and social influence among the users are applied to the demand prediction method, and demands of group members are met to the greatest extent.

Description

technical field [0001] The invention belongs to the technical field of group recommendation, and specifically relates to a group demand prediction method based on long-term and short-term interests and social influence. Background technique [0002] There are still many bottlenecks in public digital cultural services, such as: the lack of unified standards and specifications for resource collection and exchange, the widespread phenomenon of "islanding" of digital resources, the single participation of social subjects in resource construction, and the lack of personalized services. A research breakthrough has been made to address the above-mentioned problems. This invention is a group demand prediction method based on long-term and short-term interests and social influence. Focusing on the improvement of the level of public digital cultural services in our country by focusing on the intelligentization of public digital cultural services for the benefit of the people, it is 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
IPC IPC(8): G06F16/9536G06F16/9537G06N3/04G06N3/08G06Q10/04G06Q10/06
CPCG06F16/9536G06F16/9537G06N3/084G06Q10/06393G06Q10/04G06N3/044
Inventor 高岭李妍向东许佶鹏朱海蓉孙秦豫郭子正杨旭东郭红波杨琰
Owner NORTHWEST UNIV
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