Systems and methods for classifying electronic documents

• US 10,579,646 B2
• Filed: 06/21/2017
• Issued: 03/03/2020
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Tsg Technologies, LLC
• Original Assignee: Tsg Technologies, LLC
• Inventors: Lu, Caimei, Prosser, Ricky John, Bryars, Michael Wayne
• Primary Examiner(s): Nguyen, Cam Linh T
• Application Number:
  US15/629,332
• Publication Number:
  US 20170286524A1
• Time in Patent Office: 986 Days
• Field of Search: 707738
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A method of classifying an electronic document from an electronic media source includes generating statistical data from one or more training documents and creating a plurality of classification rules, including creating at least one topic model-based classification rule using the statistical data and creating at least one query-based classification rule using one or more user defined categories and the statistical data. The method further includes classifying the electronic document using the at least one topic model-based classification rule. Example systems for classifying an electronic document from an electronic media source are also disclosed.

Claims

1. A non-transitory computer readable medium having instructions stored thereon that, when executed by at least one processor, cause the at least one processor to perform operations for creating a plurality of classification rules to classify an electronic document from an electronic media source, the operations comprising:

generating statistical data from one or more training documents, and creating a plurality of classification rules, including creating at least one topic model-based classification rule using the statistical data, the at least one topic model-based classification rule formatted as an XML file; and

creating at least one query-based classification rule using one or more user defined categories and the statistical data, the at least one query based classification rule formatted as an XML file.

2. The non-transitory computer readable medium of claim 1, the operations further comprising using a Lucene engine to create the at least one query-based classification rule.

3. The non-transitory computer readable medium of claim 2, wherein the at least one query-based classification rule is a Boolean Lucene query defined by Lucene query grammar.

4. The non-transitory computer-readable medium of claim 1, the operations further comprising using one of a Sphinx search engine, a DataparkSearch search engine, a Terrier search engine, and an OpenSearchServer search engine to create the at least one query-based classification rule.

5. The non-transitory computer readable medium of claim 1, the operations further comprising formatting the at least one topic model-based classification rule to include a probability threshold.

6. The non-transitory computer readable medium of claim 1, the operations further comprising receiving the electronic document as streaming data and processing the streaming data to obtain clean textual content.

7. The non-transitory computer readable medium of claim 6, the operations further comprising translating words in the textual content to a desired language.

8. The non-transitory computer readable medium of claim 1, the operations further comprising using one of a probabilistic latent semantic indexing (PLSI) model and a latent Direchlet allocation (LDA) model to classify the electronic document into a topical category using a topic predictor.

9. A system comprising:

a memory; and

at least one processor to;

generate statistical data from one or more training documents, and create a plurality of classification rules, including creating at least one topic model-based classification rule using the statistical data, the at least one topic model-based classification rule formatted as an XML file; and

create at least one query-based classification rule using one or more user defined categories and the statistical data, the at least one query-based classification rule formatted as an XML file.

10. The system of claim 9, the at least one processor further to use a Lucene engine to create the at least one query-based classification rule.

11. The system of claim 10, wherein the at least one query-based classification rule is a Boolean Lucene query defined by Lucene query grammar.

12. The system of claim 9, the at least one processor further to use one of a Sphinx search engine, a DataparkSearch search engine, a Terrier search engine, and an OpenSearchServer search engine to create the at least one query-based classification rule.

13. The system of claim 9, the at least one processor further to format the at least one topic model-based classification rule to include a probability threshold.

14. The system of claim 9, the at least one processor further to receive the electronic document as streaming data and process the streaming data to obtain clean textual content.

15. The system of claim 14, the at least one processor further to translate words in the textual content to a desired language.

16. The system of claim 9, the at least one processor further to use one of a probabilistic latent semantic indexing (PLSI) model and a latent Direchlet allocation (LDA) model to classify the electronic document into a topical category using a topic predictor.

17. A method comprising:

generating, by at least one processor, statistical data from one or more training documents, and creating a plurality of classification rules, including creating at least one topic model-based classification rule using the statistical data, the at least one topic model-based classification rule formatted as an XML file; and

creating, by the at least one processor, at least one query-based classification rule using one or more user defined categories and the statistical data, the at least one query based classification rule formatted as an XML file.

18. The method of claim 17, further comprising using a Lucene engine to create the at least one query-based classification rule.

19. The method of claim 18, wherein the at least one query-based classification rule is a Boolean Lucene query defined by Lucene query grammar.

20. The method of claim 17, further comprising using one of a Sphinx search engine, a DataparkSearch search engine, a Terrier search engine, and an OpenSearchServer search engine to create the at least one query-based classification rule.