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

A Classification Method of Network Academic Reports Based on Multi-feature Fusion

A multi-feature fusion, academic report technology, applied in the field of academic report forecast classification based on multi-feature fusion, can solve the problems of inability to meet the classification accuracy requirements, high accuracy, poor practicability, etc., to solve the problem of insufficient data utilization and improve accuracy. efficiency, and the effect of improving utilization efficiency

Active Publication Date: 2019-06-18
HEFEI UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The method of manual classification is very simple, but it is only suitable when the amount of data is extremely small. Manual classification requires a lot of manpower and energy, and requires the participation of professional personnel, otherwise the accuracy rate will not be very high, and the method is not practical.
Classification using machine learning methods is suitable for those situations where the text does not contain helpful information for classification. Currently, there are many methods for text classification using machine learning, but they still cannot achieve high accuracy.
Integrating various methods of machine learning and adding other useful features contained in the text for fusion classification, but still unable to meet the actual classification accuracy requirements

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
  • A Classification Method of Network Academic Reports Based on Multi-feature Fusion
  • A Classification Method of Network Academic Reports Based on Multi-feature Fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In this embodiment, a network academic report classification method based on multi-feature fusion is to classify academic reports through a multi-factor method. The overall flow chart is as follows figure 1 shown, and proceed as follows:

[0043] Step 1. Collect and establish academic report database;

[0044] Step 1.1. Use the crawler tool to collect the information of the academic report on the Internet and use it as a corresponding entry. The information on the academic report on the Internet includes: report title, report time, report location, reporter, reporter profile, report profile and report organizer;

[0045] Step 1.2, add the entry of the subject classification information to which the academic report belongs, so as to establish the academic report database;

[0046] Step 2, obtaining the first matching result set;

[0047] Step 2.1, collecting and establishing a collection of college names and the collection of subject names contained therein;

[0048] ...

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 present invention disclosed a method of multi -characteristic integration of online academic report classification methods; its characteristics include: 1. Collect and establish an academic report database, according to the information of the organizer in the databaseAmong some disciplines; 2. Establish a database of researchers across the country, match the information of the reporter in the academic report, and determine the classification; 3. Extract the keywords in the title of the data of the academic report; 4.Expansion of synonymous words; 5. Expansion of synonymous words to classify the characteristics obtained after expansion; 6. The classification results of the synthesis obtained the final classification result of the academic report.The present invention classifies academic reports through multiple factors to ensure the speed and accuracy of classification.

Description

technical field [0001] The invention belongs to the technical field of text classification based on machine learning, and mainly relates to a method for classifying academic report forecasts based on multi-feature fusion. Background technique [0002] Academic reports help to broaden horizons and knowledge and obtain cutting-edge research information. The content of academic reports is usually the latest research results of the reporter, which helps scientific and technological workers understand the latest research progress of the discipline, and can also obtain cross-disciplinary knowledge through this way. Subject knowledge, through face-to-face listening, can also acquire the knowledge and thinking of experts, which helps scientific and technological workers to unlock their inherent intuitive ability, and can also use the environment to unlock their inherent intuitive ability. [0003] In addition, as the number of scientific and technological workers continues to increa...

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 Patents(China)
IPC IPC(8): G06F16/35G06F17/27G06K9/62
CPCG06F16/358G06F40/284G06F18/22G06F18/24155G06F18/2411G06F18/253
Inventor 薛峰夏帅王健伟许剑东王东
Owner HEFEI 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