Related knowledge point acquisition method and system
A technology of knowledge points and domain knowledge, which is applied in the field of electronic digital data processing, can solve problems such as poor objectivity, heavy workload, and artificial screening, so as to reduce workload, improve efficiency and accuracy, and save time and labor costs. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0032] Example 1:
[0033] In this embodiment, a method for acquiring related knowledge points is provided, by which related knowledge points of all the knowledge points in the field are obtained, and then based on the obtained relevant knowledge points, for the entries in the established domain encyclopedia It has very good guiding value to conduct further improvement by checking for leaks. Knowledge points refer to the basic unit of information transmission. Research on the representation and association of knowledge points plays an important role in improving learning navigation, information recommendation, retrieval, and building thesaurus.
[0034] The method of obtaining the relevant knowledge points, the flowchart is as follows figure 1 As shown, the specific process is as follows:
[0035] First, obtain domain knowledge points and obtain all knowledge points in the field. For example, when building an encyclopedia, you can obtain all the entries in the field that have been ...
Example Embodiment
[0047] Example 2:
[0048] This embodiment provides a method for acquiring related knowledge points. The steps are the same as those in Embodiment 1. In this embodiment, a specific method for calculating the semantic vector of each candidate knowledge point in the above process is provided. The specific process is as follows :
[0049] The first step is to determine the number of occurrences of each candidate knowledge point in the candidate file, so that the text of each candidate knowledge point and its occurrence number is obtained. The candidate text is the text obtained after word segmentation from the selected digital resource, and the candidate knowledge points are the words obtained by subtracting common words from the words obtained after word segmentation in the candidate text. This part is the same as in Embodiment 1, and will not be repeated here.
[0050] The second step is to calculate the binary tree with the smallest weighted path length according to each candidate ...
Example Embodiment
[0065] Example 3:
[0066] The domain encyclopedia is an important digital publishing resource. Domain encyclopedias usually organize domain information in terms of entries. The domain encyclopedia needs to contain important entries in the domain. However, building an encyclopedia in the field requires a lot of manpower investment. In this embodiment, a method for obtaining related knowledge points is provided. Domain knowledge points are also entries in the domain encyclopedia. In this embodiment, the domain e-book text and newspaper text are used to calculate the semantic vector of the candidate term through the skip-gram model. The semantic similarity between the constructed domain entry and the obtained candidate entry is calculated through the semantic vector. Using the semantic similarity of the entries, discover the semantically related and missed entries in other fields to reduce the possibility of missing entries in certain fields. Specific steps are as follows.
[...
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