Intelligent detection method for semantic mutual exclusion of multi-source management terms
A technology of intelligent detection and terms, applied in semantic analysis, digital data processing, special data processing applications, etc., can solve problems such as conflict between superiors and subordinates, imbalance of powers and responsibilities, and hindering the implementation of actual tasks.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0063] The present invention will be further described below through specific embodiments.
[0064] Model Training Phase
[0065] Step S1: Obtain the dependent resources in the model training phase, that is, obtain the texts of each management clause, sort out the clause text pairs of the upper and lower levels, split and match the text pairs according to each item, and obtain a set of NS policy item text pairs S={S (i)} is the training corpus, and each text pair is marked as S(i), where the upper-level policy item is T(i), and the lower-level policy item is H(i), where 1≤i≤NS, requiring NS≥10000;
[0066] Step S2: For NS policy item text pairs, modify the corresponding content to construct NS pairs containing contradictions, label the text pairs containing contradictions as 1, and label the text pairs without contradictions as 0, a total of 2NS Text pairs are used as training corpus;
[0067] Step S3: In order to facilitate feature extraction, perform text preprocessing on ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


