Decision-support expert system and methods for real-time exploitation of documents in non-english languages
AssigneeIntuview Ltd.
InventorShmuel Bar
Life of this patent
Estimating the term…
Abstract
A method for real-time exploitation of documents in non-English languages includes processing an input document in into a processed input document, extracting ontology elements from the processed input document to obtain a document digest (DD), statistically scoring each DD to obtain a DD with category scores, refining the DD and the category scores to obtain a summary of each document in the form of a refined DD with refined category scores. The summary allows a user to estimate in real-time if the input document warrants added attention.
Claims20
A method for real-time exploitation of documents in non-English languages comprising steps of:
- a. processing an input document into a processed input document;
- b. extracting ontology elements from the processed input document to obtain a document digest (DD);
- c. based on predefined categories, statistically scoring each DD to obtain a DD with associated category scores;
- d. using predefined rules, refining the DD and associated category scores to obtain a refined DD with associated category scores;
- and
- e. outputting a summary of the refined DD with associated category scores.
A method for real-time exploitation of documents in non-English languages comprising steps of:
- a. inputting a non-English text document;
- b. analyzing the non-English text;
- and
- c. based on the analysis, providing a summary of the text along with respective categorization.
A system for real-time exploitation of documents in non-English languages comprising:
- a. a natural language (NL) engine for receiving an input non-English text document and for outputting a document digest (DD);
- b. a Statistical Engine for processing the DD into a DD with associated category scores;
- c. a Rules Engine for refining the DD with associated category scores and for outputting a refined DD with associated category scores;
- d. a Summary Engine for generating an appropriate output in English or other requested natural language based on the refined DD with associated category scores;
- and
- e. a knowledge base for providing appropriate inputs to the processes carried out by the various engines.
Dependencies are inferred from the claim text.