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

Knowledge recommendation method for academic literature

A recommendation method, an academic technology, applied in the field of knowledge recommendation for academic literature

Inactive Publication Date: 2016-09-21
PEKING UNIV
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can be seen that there is a certain possibility of realizing the recommendation of academic methods

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
  • Knowledge recommendation method for academic literature
  • Knowledge recommendation method for academic literature
  • Knowledge recommendation method for academic literature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071]Further illustrate technical scheme of the present invention below in conjunction with accompanying drawing:

[0072] Such as figure 1 As shown, a knowledge recommendation method for academic literature includes the following steps:

[0073] (1) Text preprocessing. Read in a certain amount of literature text, and only extract the title, abstract, introduction and related work parts of the literature. Preprocess the text, filter out some obvious noise, and apply the noun phrase extraction tool (StanfordNLP toolkit) to extract all noun phrases from the original text and mark them in the original text.

[0074] (2) Academic concepts and relationship extraction between concepts. Apply the model based on conditional random field (CRF) and use sequence labeling to extract academic concepts. The features used in the extraction model include features of the current word, features of the words before and after the current word, features of Part-of-Speech, features of noun phr...

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 relates to a knowledge recommendation method for academic literature, and belongs to the technology of language word processing. In order to search an effective research solution to a problem in the research, a researcher needs to read a large number of literatures, deeply understands the academic knowledge and related technologies in the field, proposes and verifies the ideas through thinking, analysis and a large amount of testing and try. For an inexperienced researcher, the above work is more difficult. According to the invention, the method builds a matrix decomposition model based on the conventionalization of the relation among academic concepts, recommends an academic method for an academic task or problem, and serves as the reference for the research. On the basis of a conventional matrix decomposition model, the method combines the relation between the same type of academic concepts as a conventionalized condition, and builds matrix decomposition models MF-TRR and MF-MRR based on the academic task or the conventionalization of the relation among academic concepts. The knowledge recommendation for academic literatures aims at bringing inspiration to the work of the researcher, alleviates the workload of research, and improves the output of scientific payoffs.

Description

technical field [0001] The invention belongs to the technical field of language and word processing and information extraction, and in particular relates to a knowledge recommendation method for academic documents. Background technique [0002] An important task for researchers is to seek effective research methods (such as "graph-based ranking algorithms") to solve academic tasks (such as "document summarization"). This requires researchers to read a large amount of literature, gain an in-depth understanding of academic knowledge and related technologies in the field, and then through thinking, analysis, and a large number of experiments and attempts, finally propose and verify their own ideas. For inexperienced researchers, the job is even more difficult. If the computer can automatically recommend several research methods for academic issues as a reference for research work, it will help reduce the workload of researchers and improve research efficiency to a certain exte...

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): G06F17/30G06K9/62
CPCG06F16/313G06F16/35G06F18/2411
Inventor 黄珊珊万小军唐学伟
Owner PEKING UNIV
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