A text classification method, computer readable storage medium and system
A technology of text classification and computer programs, which is applied in text database clustering/classification, text database query, unstructured text data retrieval, etc. It can solve the problems of low analysis accuracy and low efficiency of information selection methods
Active Publication Date: 2021-10-22
SOUTH CHINA NORMAL UNIVERSITY
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Among them, in the process of making the invention, the inventor found that the method of obtaining selection information was inefficient and the accuracy of analysis was low
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] see figure 1 , which is a flow chart of the text classification method in the embodiment of the present invention. Described text classification method, comprises the steps:
[0032] Step S1: Obtain the text to be classified.
[0033] In one embodiment, the text to be classified is a text with a tendency to select, such as positive emotions such as liking and approving of a character, event or product means selecting the text of this character, event or product; Negative emotions such as disgust and opposition to an event or product mean not choosing the text of this character, event or product.
[0034] Step S2: Carry out character segmentation and word segmentation on the text to be classified, and obtain multiple characters and multiple words representing the text to be classified.
[0035] Step S3: Vectorize the multiple characters and the multiple words respectively to obtain multiple character vectors and multiple word vectors.
[0036] In one embodiment, 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
Login to View More Abstract
The present invention relates to a text classification method, a computer-readable storage medium and a system, comprising: obtaining a text to be classified; obtaining a plurality of characters and a plurality of words representing the text to be classified; obtaining a plurality of word vectors and a plurality of word vectors A plurality of said word vectors are input to the stacked bidirectional cyclic neural network based on word vectors, and a classification result based on word vectors is obtained, and a plurality of said word vectors are input to a stacked bidirectional cyclic neural network based on word vectors, and obtained based on word vectors. The classification result of the vector; the number of words and the number of words that represent the text to be classified statistically, if the relationship between the number of words and the number of words meets the set threshold, the classification result based on the word vector is selected; otherwise, the classification result based on the word vector is selected. classification results. By using the stacked bidirectional cyclic neural network, high-level features representing the semantics of the text are obtained; by fusing word information and word information of the text to be classified, the accuracy and efficiency are improved.
Description
technical field [0001] The invention relates to the field of natural language processing, in particular to a text classification method, a computer-readable storage medium and a system. Background technique [0002] With the development of Internet technology, people use the Internet to express all kinds of speeches, which also produces a large amount of text information. These text messages express people's preference and provide a platform for information display and communication. How to obtain selection tendency information from these text information has become a research topic. Among them, during the process of making the present invention, the inventor found that the method of obtaining selection information was inefficient and the accuracy of analysis was low. Contents of the invention [0003] Based on this, the object of the present invention is to provide a text classification method, which has the advantages of improving accuracy and efficiency. [0004] A t...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/35G06F16/33
Inventor 曾碧卿杨健豪黄泳锐
Owner SOUTH CHINA NORMAL UNIVERSITY