Classification method and system for link resources in scientific and technical literature, and equipment
A technology of linking resources and classification methods, which is applied to the classification field of linking resources in scientific and technological literature, can solve problems such as fine-grained scientific and technological literature linking resource model framework, and achieve the effect of improving recognition
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0038] Such as figure 1 As shown, Embodiment 1 of the present invention provides a method for establishing a classification model applicable to link resource citations in scientific and technological documents, the method comprising:
[0039] Step S1) Constructing a resource reference data set by using an existing document data set; the data set includes resource hyperlinks and related resource description texts;
[0040] Resource citation: the hyperlink mentioned by the author in the text, which directly points to a specific online resource; resource description text: the continuous text that the author appears near the resource citation, especially the text that appears before and after the hyperlink. Extract the hyperlinks of the resources from the text and footnotes of the literature, and extract the five sentences before and after the hyperlinks as the description text of the resources;
[0041] Step S2) labeling the training data set based on the knowledge repr...
Embodiment 2
[0083] Based on the knowledge representation framework and classification model established by the above method, the present invention also provides a method for classifying link resources in scientific and technological documents, the method comprising:
[0084] Step T1) extracting the description text of the resources to be classified;
[0085] Extract the hyperlinks of the resources from the text and footnotes of the literature of the resources to be classified, and extract the five sentences before and after the hyperlinks as the description text of the resources. After extracting the description text of the resource to be classified, it also includes: adding a reference position identifier in the description text, that is, inserting at the position where the reference appears in the text Marker, added to the text as an independent word, is used to indicate that a resource reference occurs at the current position.
[0086] Step T2) Input the description text into ...
Embodiment 3
[0089] A computer device includes a memory, a processor, and a computer program stored on the memory and operable on the processor, and the method of Embodiment 2 is implemented when the processor executes the computer program.
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com