Entry synonymy discrimination evidence searching method, apparatus and device, and storage medium
A technology of entries and evidence, applied in the field of knowledge graphs, can solve problems such as insufficient authority, insufficient basis for synonymous judgments, and difficulty in evaluating the accuracy of synonymous judgments, so as to improve authority and accuracy, improve accuracy and authority Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0084] figure 1 It is a flow chart of a proof-seeking method for synonymous discrimination of terms in Embodiment 1 of the present application. This embodiment of the present application is suitable for finding evidence for synonymous discrimination of a pair of terms, so as to perform synonymous judgment based on the evidence for synonymous discrimination. In this case, the method is executed by a device for identifying synonyms of terms, which is implemented by software and / or hardware, and is specifically configured in an electronic device with a certain data computing capability.
[0085] Such as figure 1 A proof-seeking method for synonymous discrimination of an entry is shown, including:
[0086] S110. Obtain the entry pairs to be synonymously determined and the data source of the field to which the entry pairs belong.
[0087] The entry pair to be synonymously determined includes two entries, and this embodiment does not limit the length, language, field, and type of ...
Embodiment 2
[0101] figure 2 It is a flow chart of a proof-seeking method for synonymous entry discrimination in Embodiment 2 of the present application. This embodiment of the present application is optimized on the basis of the technical solutions of the foregoing embodiments.
[0102] Optionally, refine the operation "according to whether the term pair appears in each text of the multi-paragraph text, calculate the correlation degree of the term pair" to "according to whether the term pair appears in each text of the multi-paragraph text, calculate The co-occurrence probability of the entry pair and the occurrence probability of each entry in the entry pair; according to the co-occurrence probability of the entry pair and the occurrence probability of each entry, calculate the correlation degree of the entry pair", providing a Calculation method of correlation.
[0103] Such as figure 2 A proof-seeking method for synonymous discrimination of an entry is shown, including:
[0104] S...
Embodiment 3
[0123] image 3 It is a flow chart of a proof-seeking method for synonymous entry discrimination in Embodiment 3 of the present application. This embodiment of the present application is optimized on the basis of the technical solutions of the above-mentioned embodiments, and provides another calculation method of correlation .
[0124] Optionally, after the operation "if the correlation degree of the entry pair satisfies the set condition, use the co-occurring text segment of the entry pair as the synonymous discrimination evidence of the entry pair", add "according to each of the synonymous discrimination evidence The authoritative degree of the source works, determine the weight of each source work; according to the relevance of the entry pair in each source work and the weight of each source work, calculate the entry pair in each source work According to the weighted correlation degree in each source work, sort the synonymous discrimination evidence of multiple source wor...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More - R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com



