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

Text semantic analysis method and system

A semantic analysis and text technology, applied in the field of computer artificial intelligence, can solve the problems of low efficiency in pushing effective content information, affecting user experience, etc., and achieve the effect of enhancing feature extraction capabilities

Pending Publication Date: 2020-06-05
CHONGQING UNIV OF TECH
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, some users may not be interested in the pushed content, and being forced to accept uninteresting news content for a long time may affect the user experience. Therefore, it is necessary to filter the pushed content through artificial intelligence methods, but generally The efficiency of pushing effective content information is not high

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
  • Text semantic analysis method and system
  • Text semantic analysis method and system
  • Text semantic analysis method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Such as figure 1 As shown, a text semantic analysis method, the specific steps include:

[0027] Step S1, extracting a text vector representing the semantics of the text;

[0028] Step S2, inputting the text vector into a network structure, wherein the network structure includes a TextCNN network structure and a FastCNN network structure, and extracts features from the text vector based on a convolutional neural network;

[0029] Step S3, obtaining the text feature vector output by the network structure.

[0030] In this embodiment, the text vectors of the text semantics refer to some vocabulary contained in text data or other news media, and the importance of each text vector is calculated according to a certain theory, and important features are retained accordingly, while discarding Less important text vectors. That is, first do a basic screening of the text semantics to improve the training efficiency, but in order to make the obtained output vectors have stronge...

Embodiment 2

[0040] Such as Figure 4 As shown, a text semantic analysis system, the system includes: an extraction unit 301, an input unit 302 and an acquisition unit 303, wherein the extraction unit 301 is used to extract a text vector representing the text semantics; the input unit 302 is used to The text vector is input into the network structure, wherein the network structure includes a TextCNN network structure and a FastCNN network structure, and a feature extraction is performed on the text vector based on a convolutional neural network; an acquisition unit 303 is used to obtain the output of the TextCNN network structure The text feature vector of .

[0041] When the text vector is input into the TextCNN network structure, the network structure includes: a convolution processing module 3021, a pooling processing module 3022 and a flattening module 3023, wherein the convolution processing module 3021 is used to express the extracted The text vectors of the text semantics are input...

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 a text semantic analysis method and system, wherein the method comprises the steps: extracting a text vector representing text semantics, and inputting the text vector into a network structure which is based on a convolutional neural network and comprises a TextCNN and a FastCNN, and carrying out feature extraction. According to the method, the types or the number of convolution kernels are increased in the TextCNN; the width of the network structure is increased; the feature extraction capability of a convolution layer is greatly enhanced; a connection mode similar to a'residual neural network structure' is adopted, so that a first vector output by the convolution layer is connected with a text vector compressed by the FastCNN network structure to form a second vector, the second vector is transmitted to an output layer through a full connection layer, and the probability that the text vector classifies various categories is obtained. The initial text vector extracted from text semantics is mapped into a series of hidden text vectors through TextCNN convolution pooling nonlinear processing, FastCNN linear processing and other screening modes, and the classification result of the text vectors is obtained more efficiently and accurately.

Description

technical field [0001] The invention relates to the technical field of computer artificial intelligence, in particular to a text semantic analysis method and system. Background technique [0002] Artificial Intelligence (Artificial Intelligence), the English abbreviation is AI. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. It is also a branch of computer science. It attempts to understand the essence of intelligent thinking patterns and produce A new kind of intelligent machine that can be similar to human thinking mode and can respond accordingly. Research directions in this field include robotics, language recognition, image recognition, and natural language processing, among which natural language processing is an important direction in the field of computer science and artificial intelligence. It studies various theories and methods that can rea...

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): G06F40/30G06F16/35G06N3/04
CPCG06F16/35G06N3/045
Inventor 胡顺仁马宇航
Owner CHONGQING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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