Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Intelligent news recommendation system based on emotion protection

A recommendation system and news technology, applied in the direction of specific mathematical models, probabilistic networks, and other database searches, can solve the problem that the emotional dictionary is difficult to cover completely, so as to facilitate personalized recommendations, suppress bad emotions, and avoid harm. Effect

Pending Publication Date: 2021-09-03
HARBIN UNIV OF SCI & TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The research method based on the emotional dictionary is mainly to construct the emotional dictionary, compare the emotional words in the text with the words in the emotional dictionary, and find out the corresponding emotional tendency. Such a method needs to manually construct the emotional dictionary, and the emotional dictionary is difficult to cover completely

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
  • Intelligent news recommendation system based on emotion protection
  • Intelligent news recommendation system based on emotion protection
  • Intelligent news recommendation system based on emotion protection

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0098] Example 1: Construct news feature matrix.

[0099] Step1_1, load the news content, news headlines, and user comments in the system as corpus data, clean the corpus data, and initialize the parameters of the BERT pre-training model;

[0100] Step1_2, convert the text into a vector form through the BERT model and compare the text content with the prepared non-characteristic vocabulary, remove the non-characteristic words in the text content, and segment the text with the non-characteristic words as the boundary;

[0101] Step1_3, calculate the Euclidean distance between the vector corresponding to each word after word segmentation and all other words in turn and accumulate them, and take the top 2 items with the highest results as the feature words corresponding to the news;

[0102] Set the vector after word segmentation as:

[0103] word1=[0.25,0.32,0.18,...,0.67];

[0104] word2=[0.35,0.64,0.37,...,0.82];

[0105] word3=[0.25,0.32,0.15,...,0.66];

[0106] Euclidean...

example 2

[0111] Example 2: Sentiment Grading.

[0112] Step2_1, randomly select the emotional feature vectors as positive emotions, compare positive emotions, neutral emotions, and compare negative emotions and the category center sum of negative emotions, divide the samples into five categories, and set the feature vectors as follows:

[0113] NEW_e_c1=[0.52,0.35,...,0.68];

[0114]NEW_e_c2=[0.62,0.38,...,0.82];

[0115] NEW_e_c3=[0.18,0.97,...,0.98];

[0116] NEW_e_c4=[0.27,0.48,...,0.64];

[0117] NEW_e_c5=[0.72,0.16,...,0.23];

[0118] Set the sample NEW_e1=[0.93,0.28,…,0.45], the vector dimension is 10, then the distance from the category center NEW_e_c1

[0119] in where n is the sample size;

[0120] Step2_2, the fuzzy classification matrix U is obtained through the fuzzy C-means clustering algorithm, and the solution formula of U is as follows:

[0121] Among them, u_ij represents the membership degree of sample i to category j, m is the fuzzy coefficient, and c is ...

example 3

[0134] Example 3: Construct user feature matrix.

[0135] Step3_1, r=2, take the randomly selected news label vector NEW_L1 as a circle with a center vector radius of 2 as a sliding window, and calculate the Euclidean distance L between all news label vectors and the center point NEW_L1 in turn, and calculate the distance between the news label vector and NEW_L1 that is less than or equal to r The news tag vectors are marked to the set M, that is, these points belong to cluster c1;

[0136] Step3_2, secondly calculate the offset vector N from the center vector NEW_L1 to all elements in the set i , get the offset vector N=N 1 +N 2 +…+N N ;

[0137] Set offset vector N1=[1.0,2.0,…,1.0], N2=[2.0,2.0,…,3.0],…,Nn=[3.0,4.0,…,3.0], then N=[6.0,8.0 ,...,7.0];

[0138] Step3_3, the center vector NEW_Li moves along the density rising direction (6.0 2 +8.0 2 +…+7.0 2 ) 1 / 2 distance;

[0139] Step3_4, the above operations until the offset is less than the threshold 5, mark the ...

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 provides an intelligent news recommendation system based on emotion protection. A method comprises the following steps: 1, extracting news features and text feature words by utilizing a BERT pre-training model, and constructing a news feature matrix through news feature vectors; 2, performing emotion filtering on the text information to establish an emotion grading model, and performing emotion grading on user comments, news titles and contents to distinguish negative and positive degrees; 3, clustering news labels through a clustering algorithm, distributing weights to news browsed by users according to user comment emotion levels and user behavior time, and constructing a user matrix according to user feature information; 4, predicting the emotion level of the user in the next time period according to the time sequence of the user emotion; and 5, generating a recommendation table by calculating the similarity between the user and the news vector, predicting the emotional state of the user, and recommending the news in proportion by using a Bayesian method to realize dynamic pushing. According to the invention, negative energy and negative public opinions are prevented from hurting the psychology of the user and harming the public safety of the society.

Description

technical field [0001] The invention belongs to the fields of computer software, artificial intelligence and recommendation systems, and in particular relates to a news intelligence recommendation system based on emotion protection. Background technique [0002] At the beginning of the rise of the Internet, there were few data and information on the Internet, and there were not many interactions between people and the Internet. Therefore, websites generally only need to display their own information to users to meet the requirements. With more and more interactions between people and the Internet, resulting in exponential growth of information, it is too slow for users to obtain the data they need by sequentially viewing information, so search engines have become a common way for people to retrieve information. In addition, with the development of the mobile Internet and the Internet of Things, the content and form of the Internet have been enriched, leading to a continuous ...

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): G06F16/9536G06F16/906G06F40/284G06N7/00G06Q50/00
CPCG06F16/9536G06F16/906G06F40/284G06Q50/01G06N7/01
Inventor 刘嘉辉杜金仇化平
Owner HARBIN UNIV OF SCI & TECH
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
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com