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

News heat pre-estimating method and system

A news and popularity technology, applied in forecasting, instrumentation, electrical digital data processing, etc., can solve the problems of timeliness and low accuracy, and achieve the effect of improving accuracy, increasing probability, and improving real-time performance

Active Publication Date: 2017-11-07
BEIJING SOHU NEW MEDIA INFORMATION TECH
View PDF5 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the object of the present invention is to provide a news popularity estimation method and system, which aims to overcome the problems of low timeliness and accuracy in the hot article scoring technology in the prior art when scoring news popularity, and improve The Timeliness and Confidence of News Recommendation

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
  • News heat pre-estimating method and system
  • News heat pre-estimating method and system
  • News heat pre-estimating method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] For the sake of reference and clarity, the technical terms, abbreviations or abbreviations used in the following text are summarized as follows:

[0044] Cold start news: Newly entered news that does not display historical clicks and exposure information.

[0045] word embedding: Words are converted into vectors, such as 'apple', which is represented as a 200-dimensional semantic vector. The traditional one-hot encoding method is highly sparse, and this encoding method does not have any similarity between 'apple' and 'apple', but the vector generated by the word embedding using the deep learning of the present invention carries semantic layer information, would consider 'apple' to be highly similar to 'apple'.

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only ...

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 news heat pre-estimating method and system. Compared with a traditional news heat marking system based on statistics, such as a Bayes smoothness method, the scheme that a heat pre-estimating model of cold-start news (namely news without historical click display and new storage of exposure information) is built based on deep and wide learning, and the model is utilized to conduct heat pre-estimating on the cold-start news is put forward; through the conception of a training model based on deep and wide learning, the accuracy rate of the model is improved, due to the fact that the news heat pre-estimating method can achieve heat pre-estimating on the cold-start news, news exposure is not needed to be used as the premise, the probability of high-quality cold-start news exposure can be increased, and the real-time performance of high-quality cold-start news exposure is improved.

Description

technical field [0001] The invention belongs to the field of personalized recommendation of news, and in particular relates to a method and system for predicting news popularity. Background technique [0002] In the field of news personalized recommendation, it is often necessary to calculate and score news popularity to realize the recommendation of high-hot news. [0003] Traditional news popularity calculation methods mostly use hot article scoring technology based on historical click statistics, such as news popularity calculation using Bayesian smoothing. Specifically, the trending article scoring technology generally calculates the clicks of users on the article, and then scores the popularity of the article. That is to say, in this trending article scoring technology, the news must have exposure to calculate the score. [0004] As we all know, in the field of news recommendation, the accuracy and timeliness of news recommendation are one of the most important factors...

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): G06F17/30G06F17/27G06Q10/04G06Q50/00
CPCG06F16/35G06F16/9535G06F40/289G06Q10/04G06Q50/01
Inventor 安鸣佳
Owner BEIJING SOHU NEW MEDIA INFORMATION TECH
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