Data classification method and system based on machine learning

A data classification and machine learning technology, applied in the field of data processing, can solve problems such as loss of user groups, large amount of comments, and lack of energy for merchants to browse and reply one by one, achieving high efficiency, accurate identification, and realizing learning and updating identification mechanism. Effect

Inactive Publication Date: 2019-11-19
HEZE UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the large number of comments, merchants do not have the energy to browse and reply one by one, so they miss some negative comments, resulting in the loss of user groups

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
  • Data classification method and system based on machine learning
  • Data classification method and system based on machine learning
  • Data classification method and system based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] See Figure 1~2 In the embodiment of the present invention, a data classification method based on machine learning includes the following steps:

[0025] S1. Collect the raw data to be classified, and save all the collected raw data in the database. Of course, in actual application, the database can be established locally or the raw data can be obtained from the cloud database through the network. This is not correct. It makes specific restrictions;

[0026] S2: Analyze the data in the database, extract the keywords, and import the keywords into the pre-trained SVM model to obtain the classification and recognition results. For example, in practical applications, for the buyer’s comment "This isolation cream It works well", then its "good effect" is the keyword that it recognizes. When it is imported into the trained SVM model, the output result is the corresponding "good comment". Here, as the preferred one, SVM model uses linear kernel function;

[0027] S3: The result an...

Embodiment 2

[0031] See image 3 In the embodiment of the present invention, a data classification system based on machine learning includes a central processing unit 1, a database 2, an SVM model 3, a result analysis module 4, a sub-database 5 and a data analysis module 6,

[0032] The database 2 is used to store the raw data to be classified, and is called by the data analysis module 6 after receiving an instruction from the central processing unit 1;

[0033] The data analysis module 6 is used to analyze the original data and extract one or several keywords;

[0034] The SVM model 3 trains the extracted keywords. When the number of keywords is greater than one, weight is assigned to each keyword to obtain the classification and recognition results;

[0035] The result analysis module 4 performs recognition analysis on the classification and recognition results obtained by the SVM model 3, obtains the effective classification and recognition results therein, and imports the original data in the c...

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 data classification method based on machine learning, and relates to the technical field of data processing, and the method comprises the following steps: S1, collecting to-be-classified original data, and storing all collected original data in a database; S2, analyzing the data in the database, extracting keywords in the data, and importing the keywords into a pre-trained SVM model to obtain a classification and recognition result; S3, a result analysis module identifying the classification identification result; extracting effective classification and identificationresults, namely effective results; importing the original data in the database corresponding to the effective result into the corresponding sub-database. The beneficial effects of the data classification method are that the method can achieve the effective classification and recognition of data through the SVM model, is higher in efficiency, can effectively judge the correctness of a result through the data analysis module, achieves the learning and updating of a recognition mechanism, and is more precise in later recognition.

Description

Technical field [0001] The invention relates to the technical field of data processing, in particular to a data classification method and system based on machine learning. Background technique [0002] Big data refers to a collection of data that cannot be captured, managed, and processed with conventional software tools within a certain time frame. It is a massive and high growth rate that requires a new processing model to have stronger decision-making power, insight discovery and process optimization capabilities. And diverse information assets. With the development of Internet technology, big data is the main source for the majority of enterprises to obtain information on users' living habits and purchasing power. [0003] In an e-commerce platform, comments after users purchase products are very important to sellers, and can even determine the survival of the merchant. Therefore, timely browsing and replying to comments is an important daily work of e-commerce. However, due ...

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): G06Q30/02G06K9/62
CPCG06Q30/0201G06F18/2411
Inventor 刘春英
Owner HEZE UNIV
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
Try Eureka
PatSnap group products