Supercharge Your Innovation With Domain-Expert AI Agents!

Establishment and tendency classifying methods of CNN-SVM model

A construction method and propensity technology, applied in the field of CNN-SVM model construction and propensity classification, can solve problems such as wrong propensity classification, and achieve the effect of improving the accuracy rate

Active Publication Date: 2018-02-13
INST OF ACOUSTICS CHINESE ACAD OF SCI +1
View PDF18 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, if forwarding behavior is not considered, it will lead to wrong propensity classification

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
  • Establishment and tendency classifying methods of CNN-SVM model
  • Establishment and tendency classifying methods of CNN-SVM model
  • Establishment and tendency classifying methods of CNN-SVM model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0039] Such as figure 1 Shown, a kind of construction method of CNN-SVM model, described method comprises:

[0040] Step 1) Grab all comments and forwarding information based on a certain event from social media, preprocess the information, and obtain several sentences; extract the word2vec features of the sentence; combine all sentences containing equal positive and negative tendencies Form a training sample set;

[0041] The preprocessing includes: removing too short sentences, word segmentation and stop words.

[0042] Step 2) set up CNN (convolutional neural network) model; Described CNN model comprises: convolutional layer, sampling layer and classification layer; Wherein, the number of layers of convolutional layer and sampling layer is 1; Classification layer is a soft-max The fully connected layer;

[0043] Step 3) Utilize...

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 establishment and tendency classifying methods of a CNN-SVM model. The establishment method comprises the steps that all comment and forward information based on a certain event is captured from social media to establish a training sample set; a CNN model including a convolution layer, a sampling layer and a classifying layer is established, and the training sample set is utilized to train each layer of parameters of the CNN model; the convolution layer and the sampling layer in the CNN model with trained parameters are combined with an SVM classifier together to form the CNN-SVM model; the training sample set is input into the CNN-SVM model, and parameters of the SVM classifier are trained; establishment of the CNN-SVM model is completed. Based on the CNN-SVM model, the invention also provides a tendency classifying method. A forward tree is established, to-be-classified comments including forwarded texts can be accurately classified. The classifying accuracy can be improved by adopting the tendency classifying method.

Description

technical field [0001] The invention relates to the field of social media information processing, in particular to a method for constructing a CNN-SVM model and a tendency classification method. Background technique [0002] In daily life, social media (such as facebook, twitter, Weibo, etc.) has gradually replaced paper media as a new media for people to understand news, and it also provides a relatively free public platform for expressing personal opinions and expressing emotions. Due to the convenience of using social media and the timely update of information, more and more people have become loyal users of social media, and their freedom of speech is very high. The huge flow of information covers many topics, which seem trivial and irregular , but in fact it contains huge potential value. Therefore, how to obtain user tendencies from social media and serve life is a very valuable job. In real life, people hope to predict movie box office, stock market conditions, etc....

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): G06F17/30G06K9/62G06N3/04G06N3/08
CPCG06F16/35G06N3/08G06N3/045G06F18/2411G06F18/2414
Inventor 张艳涂曼姝颜永红
Owner INST OF ACOUSTICS CHINESE ACAD OF SCI
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