Information popularity prediction method and device, and storage medium

A prediction method and popularity technology, applied in the computer field, can solve the problems of poor stability and accuracy of prediction results, and achieve the effect of improving prediction performance, accurate prediction results, and stable popularity prediction

Active Publication Date: 2019-10-15
北京中科闻歌科技股份有限公司
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide a method, device and storage medium for predicting information popularity, so as to solve the problem of poor stability and accuracy of prediction results when using a single model to predict information popularity

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
  • Information popularity prediction method and device, and storage medium
  • Information popularity prediction method and device, and storage medium
  • Information popularity prediction method and device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] According to an embodiment of the present invention, a method for predicting information popularity is provided. Such as figure 1 Shown is a flow chart of the method for predicting information popularity according to the first embodiment of the present invention.

[0026] Step S110, acquiring information to be predicted.

[0027] In this embodiment, the information to be predicted is information released by the network platform.

[0028] In this embodiment, the information to be predicted may be long text information.

[0029] The long text information refers to text information whose content is normalized (prescribed format). For example: news information including title, text, picture, publication time, release time and other standardized content.

[0030] Step S120, extracting the popularity-influencing features of the information to be predicted according to the predetermined popularity-influencing feature categories.

[0031] In this embodiment, not only the f...

Embodiment 2

[0060] Before inputting the popularity-influencing features into a pre-trained multi-model predictor that integrates multiple prediction models, the present invention also requires training to obtain the multi-model predictor.

[0061] This embodiment builds a multi-model predictor based on the Stacking integration strategy.

[0062] The idea of ​​Stacking is a hierarchical fusion model. For example, when merging base learners trained with different data, the base learner will be used as the base model, and then a meta-learner will be trained. This meta-learner is used to organize Use the output of the base learner, that is, use the output of the base layer model as the input of the meta-learner, and let the meta-learner assign weights to the output of the base-level model in order to select the most credible one from the output of the base learner. , as the final output.

[0063] This embodiment will describe in detail the steps of obtaining the multi-model predictor. Such ...

Embodiment 3

[0099] This embodiment provides an information popularity prediction device. Such as Figure 6 Shown is a structural diagram of an information popularity prediction device according to a third embodiment of the present invention.

[0100] In this embodiment, the device for predicting information popularity includes, but is not limited to: a processor 610 and a memory 620 .

[0101] The processor 610 is configured to execute the information popularity prediction program stored in the memory 620, so as to realize the information popularity prediction method described in Embodiment 1 to Embodiment 2.

[0102] Specifically, the processor 610 is configured to execute the information popularity prediction program stored in the memory 620, so as to realize the following steps: obtain the information to be predicted; Popularity influence features: input the popularity influence features into a pre-trained multi-model predictor integrating multiple prediction models, and obtain the p...

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 an information popularity prediction method and device and a storage medium. The information popularity prediction method comprises the steps: obtaining to-be-predicted information; according to a predetermined popularity influence characteristic category, extracting popularity influence characteristics of the to-be-predicted information; and inputting the popularity influence characteristics into a pre-trained multi-model predictor integrated with a plurality of prediction models to obtain the popularity of the to-be-predicted information output by the multi-model predictor. According to the invention, the multi-model predictor integrated with a plurality of prediction models is used to predict the information popularity of the to-be-predicted information; and by adopting the multi-model predictor to predict the information popularity, the stability of a prediction result of the prediction model can be improved, and the prediction performance of the predictionmodel can be remarkably improved, so that the popularity prediction is more stable, and the prediction result is more accurate.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an information popularity prediction method, device and storage medium. Background technique [0002] With the continuous development of the Internet, all kinds of information are flooded in the network. In order to find valuable information in the massive information, information popularity prediction has attracted a lot of attention from academia and industry, and has produced A large number of research results. [0003] Information popularity prediction is to predict the degree of attention of information in the future, for example: hot news prediction for news information on the Internet, aiming at researching and exploring future hot news, predicting the degree of attention of the news information in the future, so that you can Identify potential future hot news from massive published news information. Hot news prediction has important significance and broad appl...

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): G06F16/9535G06F16/958
CPCG06F16/9535G06F16/958
Inventor 郭建彬孔庆超罗引郝艳妮赵菲菲皇秋曼王磊曹家张西娜
Owner 北京中科闻歌科技股份有限公司
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