Information microcosmic diffusion prediction model fusing cascade frequency domain features

By using Fourier transform and attention fusion strategies in the information diffusion prediction model, fusing frequency domain features and user features, the existing models are solved in capturing the complexity and dynamics of information dissemination, and achieving higher prediction accuracy and efficiency.

CN119761568APending Publication Date: 2025-04-04CHONGQING UNIV OF TECH
0 Cites 2 Cited by

Patent Information

Application Number
CN202411815457.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-11
Publication Date
2025-04-04

AI Technical Summary

Technical Problem

Existing information diffusion prediction models have limitations in capturing the complexity and dynamicity of the information dissemination process, resulting in the loss of social impact of relevant nodes and dynamic information between sub-graphs, unable to accurately describe the user's impact, and may retain redundant information or lose important information.

Method used

The time domain signal is converted to the frequency domain through Fourier transform, fusing low-frequency signals and high-frequency signals, designing an additional fusion layer to gather user characteristics, and introducing an attention fusion strategy to calculate the correlation scores of the two vectors to retain valid information.

Benefits of technology

Effectively identify the frequency characteristics during the propagation process, improve the accuracy and efficiency of information diffusion prediction, and significantly improve the performance of Hits@K and Map@K indicators.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of information propagation prediction, and discloses an information microcosmic diffusion prediction model fusing cascade frequency domain characteristics, which comprises the following steps: firstly, constructing a social graph and an information diffusion hypergraph, and capturing the influence of social homogeneity and social influence factors on information propagation by using the powerful capability of a graph convolutional neural network; then, Fourier transform is ingeniously applied, time domain information of the cascade is mapped to a frequency domain, and the deep matching degree between the user and the cascade is learned by combining high-frequency and low-frequency components. Finally, the model performance is further optimized through an attention fusion layer, and the purpose is to generate more expressive user representation, so that the problems of feature redundancy and information loss are effectively avoided. Experiments on four public datasets, such as Douban and Meteracker, show that compared with the existing most advanced baseline model, the method provided by the invention has the advantages that the two key evaluation indexes, namely Hits (at) K and Map (at) K, are obviously improved, and the highest values are up to 10.94% and 23.03%.
Need to check novelty before this filing date? Find Prior Art