Method and system for personal information extraction and modeling with fully generalized extraction contexts

• US 9,177,051 B2
• Filed: 04/18/2011
• Issued: 11/03/2015
• Est. Priority Date: 10/30/2006
• Status: Expired due to Fees

• Current Assignee: Noblis, Inc.
• Original Assignee: Noblis, Inc.
• Inventors: Pollara, Victor J.
• Primary Examiner(s): Ruiz, Angelica
• Application Number:
  US13/088,570
• Publication Number:
  US 20110258213A1
• Time in Patent Office: 1,660 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/36 Creation of semantic tools, e.g. ontology or thesauri

Abstract

Systems and methods for modeling information from a set of documents are disclosed. A tool allows a user to model concepts of interest and extract information from a set of documents in an editable format. The extracted information includes a list of instances of a document from the set of documents that contains the selected concept. The user may modify the extracted information to create subsets of information, add new concepts to the model, and share the model with others.

Claims

1. A method for extracting information from a set of documents, the method comprising:

receiving a set of documents;

receiving a first concept, the first concept representing first information for extraction from the set of documents, wherein the first concept comprises a plurality of trigger phrases related to the first concept;

updating the first concept into a first subset and a second subset, the first subset comprising one or more of the plurality of trigger phrases of the first concept, the second subset comprising remaining trigger phrases of the plurality of trigger phrases of the first concept;

creating a second concept based on the first concept, the second concept having a definitional dependency from the first concept, the definitional dependency providing a contextual relationship to the second concept such that the second concept represents second information within a context of the first information;

updating the second concept into a third concept and a fourth concept, the third concept depending on the first subset of the first concept, the fourth concept depending on the second subset of the first concept;

selecting the second concept; and

based on the selection of the second concept, extracting from the set of documents, the second information within the context of the first information.

2. The method of claim 1, wherein the second information within a context of the first information comprises the second information in a contiguous block of text in proximity of the first information.

3. The method of claim 1, wherein the second information within a context of the first information comprises the second information in a subset of the set of documents containing the first information.

4. The method of claim 1, wherein the second information within a context of the first information comprises the second information in a section of a document in the set of documents, the section containing the first information.

5. The method of claim 1, further comprising:

receiving a change to the first concept; and

updating the second concept to reflect the change to the first concept using the definitional dependency.

6. The method of claim 1, further comprising:

based on a selection of the third concept, extracting from the set of documents, the second information within a context of the first subset of the first concept.

7. The method of claim 1, further comprising:

based on a selection of the fourth concept, extracting from the set of documents, the second information within a context of the second subset of the first concept.

8. The method of claim 1, further comprising:

creating a fifth concept based on the second concept, the fifth concept representing third information within a context of the second information within the context of the first information; and

based on a selection of the fifth concept, extracting from the set of documents, the third information within the context of the second information within the context of the first information.

9. A system for extracting information from a set of documents, comprising:

a memory; and

a processor configured to;

receive a set of documents;

receive a first concept, the first concept representing first information for extraction from the set of documents, wherein the first concept comprises a plurality of trigger phases related to the first concept;

update the first concept into a first subset and a second subset, the first subset comprising one or more of the plurality of trigger phrases of the first concept, the second subset comprising remaining trigger phrases of the plurality of trigger phrases of the first concept;

create a second concept based on the first concept, the second concept having a definitional dependency from the first concept, the definitional dependency providing a contextual relationship to the second concept such that the second concept represents second information within a context of the first information;

update the second concept into a third concept and a fourth concept, the third concept depending on the first subset of the first concept, the fourth concept depending on the second subset of the first concept;

select the second concept; and

based on the selection of the second concept, extract from the set of documents, the second information within the context of the first information.

10. The system of claim 9, wherein the second information within a context of the first information comprises the second information in a contiguous block of text in proximity of the first information.

11. The system of claim 9, wherein the second information within a context of the first information comprises the second information in a subset of the set of documents containing the first information.

12. The system of claim 9, wherein the second information within a context of the first information comprises the second information in a section of a document in the set of documents, the section containing the first information.

13. The system of claim 9, wherein the processor is further configured to:

receive a change to the first concept; and

update the second concept to reflect the change to the first concept using the definitional dependency.

14. The system of claim 9, wherein the processor is further configured to:

based on a selection of the third concept, extract from the set of documents, the second information within a context of the first subset of the first concept; and

based on a selection of the fourth concept, extract from the set of documents, the second information within a context of the second subset of the first concept.

15. The system of claim 9, wherein the processor is further configured to:

create a fifth concept, the fifth concept defining the third information within a context of the second information within the context of the first information; and

based on a selection of the fifth concept, extract from the set of documents, the third information within a context of the second information within the context of the first information.

16. A non-transitory computer-readable medium encoded with instructions which, when executed by a computer, perform a method for extracting information from a set of documents, the method comprising:

receiving a set of documents;

receiving a first concept, the first concept representing first information for extraction from the set of documents, wherein the first concept comprises a plurality of trigger phrases related to the first concept;

updating the first concept into a first subset and a second subset, the first subset comprising one or more of the plurality of trigger phrases of the first concept, the second subset comprising remaining trigger phrases of the plurality of trigger phrases of the first concept;

creating a second concept based on the first concept, the second concept having a definitional dependency from the first concept, the definitional dependency providing a contextual relationship to the second concept such that the second concept represents second information within a context of the first information;

updating the second concept into a third concept a fourth concept, the third concept depending on the first subset of the first concept, the fourth concept depending on the second subset of the first concept;

selecting the second concept; and

based on the selection of the second concept, extracting from the set of documents, the second information within the context of the first information.

17. The non-transitory computer-readable medium of claim 16, the method further comprising:

based on a selection of the third concept, extracting from the set of documents, the second information within a context of the first subset of the first concept; and

based on a selection of the fourth concept, extracting from the set of documents, the second information within a context of the second subset of the first concept.