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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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