Check patentability & draft patents in minutes with Patsnap Eureka AI!

A Topic Popularity Trend Prediction Method Based on Markov Chain and Dynamic Backtracking

A Markov chain and trend prediction technology, applied in the field of social network information analysis, can solve the problems of greatly reduced value of prediction, low probability of obtaining high-accuracy results, and high difficulty of absolute prediction, so as to achieve the goal of improving accuracy Effect

Active Publication Date: 2021-12-31
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The strictness of the absolute prediction makes the prediction too difficult, the probability of obtaining high-accuracy results is very small, and the value of the prediction is greatly reduced

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 Topic Popularity Trend Prediction Method Based on Markov Chain and Dynamic Backtracking
  • A Topic Popularity Trend Prediction Method Based on Markov Chain and Dynamic Backtracking
  • A Topic Popularity Trend Prediction Method Based on Markov Chain and Dynamic Backtracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] In the present invention, a topic heat trend prediction method based on Markov chain and dynamic backtracking selects T=3 as the time window parameter for prediction. Specific steps are as follows:

[0047] Step 1: Utilize the known historical data of microblog topics for self-learning, and complete the parameter correction of the rising factor and the falling factor; in order to ensure the accuracy of the parameters in the prediction algorithm, the present invention optimizes the parameters up_factor and attenuation_factor by using simulated annealing algorithm. up_factor represents the rising factor, which is mainly used to adjust the speed of Weibo popularity rising during the prediction process, and attenuation_factor represents the attenuation factor, which is mainly used to adjust the speed of Weibo popularity decline during the prediction process.

[0048] The simulated annealing algorithm is a general optimization algorithm with asymptotic convergence, and it ha...

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 topic heat trend prediction method based on Markov chain and dynamic backtracking. The present invention integrates four influencing factors of microblogs (the number of microblogs, the total number of reposts, the total number of comments and the total number of likes), and utilizes a relative ranking method to define the popularity value of microblogs. The Markov chain algorithm is improved during prediction, and the relevant parameters are optimized based on the historical backtracking optimization simulated annealing algorithm. The method proposed by the present invention can improve the accuracy of topic popularity trend prediction.

Description

technical field [0001] The present invention relates to social network information analysis, in particular to a topic popularity trend prediction method based on Markov chain and dynamic backtracking. Background technique [0002] Aiming at the problem of social network prediction, researches have been increasing in recent years. Globally, it mainly studies Twitter, Facebook and other platforms, while in China, Sina Weibo and WeChat are the main platforms. The content of prediction includes user influence prediction based on user, user preference prediction and theme popularity prediction based on theme. [0003] Research on the development trend of microblog topics has become one of the focuses of social network forecasting research. Research from time series includes Tong, H. et al. proposed the use of adaptive AR model to predict the number of page views of network topics. Han, Y. et al. proposed to use the existing user published text to generate time series with infl...

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): G06K9/62
CPCG06F18/2113G06F18/2415
Inventor 许峰何颖苏明明尉凯博
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Features
  • R&D
  • 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