Method and system for calculating relevant knowledge points of domain knowledge points

A technology of domain knowledge and knowledge points, applied in the field of electrical data processing, can solve the problems of insufficient utilization of digital resources and semantic vector processing methods, and achieve the effect of simple and convenient calculation and good accuracy

Inactive Publication Date: 2016-03-30
PEKING UNIV FOUNDER GRP CO LTD +2
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] For this reason, the technical problem to be solved by the present invention is that information recommendation in the prior art has limitations, and the existing digital resources and semantic ve

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
  • Method and system for calculating relevant knowledge points of domain knowledge points
  • Method and system for calculating relevant knowledge points of domain knowledge points
  • Method and system for calculating relevant knowledge points of domain knowledge points

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0029] Example 1:

[0030] The semantic vector of knowledge points is a way to describe knowledge points in the vector space. By obtaining the semantic vectors of knowledge points, knowledge points can be made highly computable, and can be used in text retrieval, automatic summarization, automatic keyword extraction, Fields such as text classification have potential applications.

[0031] This embodiment provides a method for calculating related knowledge points of domain knowledge points by means of semantic vectors, including the following steps:

[0032] S1. First, acquire domain knowledge points, which are basic units representing a certain type of information. General knowledge points are classified based on fields, such as historical fields and military fields. If you need to obtain knowledge points in the historical field, you can obtain the entries in the historical encyclopedia as knowledge points in this field.

[0033] S2. Then, select a reference text, perform...

Example Embodiment

[0054] Example 2:

[0055] This embodiment provides a method for calculating related knowledge points of domain knowledge points, and using the related knowledge points to recommend knowledge points. The specific steps are as follows.

[0056] The first step is to extract the name set O={o of domain knowledge points from the domain encyclopedia 1 , o 2 , …, o n}, the number of domain knowledge point names is n. Add the name of the domain knowledge point to the tokenizer dictionary.

[0057] The second step is to select a certain number of e-books from domain digital publishing resources, and extract text from the selected e-books.

[0058] The third step is to use a word segmenter to segment the extracted text, and use all words obtained after word segmentation as knowledge points. Since there are enough digital resources in the selected field, the knowledge points include domain knowledge points and other some other knowledge points. All these knowledge points are st...

Example Embodiment

[0071] Example 3:

[0072] In this embodiment, a system for calculating related knowledge points of domain knowledge points is provided, and the structural block diagram is as follows: image 3 shown, including

[0073] Extraction unit: obtain domain knowledge points;

[0074] Word segmentation unit: determine the reference text, perform word segmentation on the reference text according to the domain knowledge point, obtain a word segmentation result, and use the word in the word segmentation result as a knowledge point, and the knowledge point includes the domain knowledge point and other knowledge point;

[0075]Indexing unit: build an index for each knowledge point in the word segmentation result in turn;

[0076] Training unit: determine the semantic vector of each domain knowledge point according to the index of the knowledge point and the sequence of the knowledge point;

[0077] Similarity calculation unit: for each domain knowledge point, determine the similarity...

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 method for calculating relevant knowledge points of domain knowledge points. The domain knowledge points are obtained at first; all knowledge points are obtained from a reference text through word separation; the knowledge points include the domain knowledge points and other knowledge points; then, an index is established for each knowledge point in a word separation result; semantic vectors of the domain knowledge points are obtained in a neural network model training manner according to the index and the sequence of each knowledge point; therefore, semantic information of the knowledge points is quantified; semantic features of the semantic information are embodied in a digital manner; therefore, the knowledge points are more convenient to analyze subsequently; then, the similarity among the domain knowledge points is determined according to the semantic vectors of various domain knowledge points; relevant knowledge points can be easily distinguished according to the degree of the similarity; the number of the relevant knowledge points can be selected according to requirements; and the method is simple and convenient to calculate and high in accuracy and is applied to the aspects, such as recommendation and retrieval.

Description

technical field [0001] The invention relates to the field of electrical data processing, in particular to a method for calculating related knowledge points of knowledge points in the field. Background technique [0002] Digital publishing resources have become one of the main ways of information provision. People have shifted from paper reading to electronic reading in large numbers. Digital publishing resources include e-books, digital encyclopedias, digital periodicals, digital newspapers, etc. The information provided by digital publishing resources is usually more authoritative and accurate than that of the Internet. Therefore, how to improve people's learning or reading experience according to the characteristics of digital publishing resources has become particularly important. [0003] In Technology Enhanced Learning (TechnologyEnhancedLearning), the development of recommender systems is getting more and more attention. However, most recommendation systems use use...

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): G06F17/30G06F17/27
Inventor 叶茂汤帜徐剑波马佳乐杨亮
Owner PEKING UNIV FOUNDER GRP CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap