Computer-Implemented System And Method For Assigning Document Classifications

• US 20170083564A1
• Filed: 12/05/2016
• Published: 03/23/2017
• Est. Priority Date: 02/05/2010
• Status: Abandoned Application

• Current Assignee: Nuix North America Inc. (Nuix Ltd.)
• Original Assignee: FTI Consulting Incorporated
• Inventors: Robinson, Eric Michael, Gabriel, Manfred J.
• Application Number:
  US15/369,632
• Publication Number:
  US 20170083564A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 50/18 Legal services

Abstract

A computer-implemented system and method for assigning document classifications is provided. A set of documents to be classified is provided to the user. The documents in the set are selected from a corpus. The user provides identification of a common classification for one or more of the documents in the set and at least one highlighted portion of text in each of the identified documents. The identified documents are compared to further documents in the corpus. Those further documents that satisfy a similarity threshold with the identified documents are identified and provided to the user for review.

Claims

1. A computer-implemented system for assigning document classifications, comprising:

a set of documents provided to a user to be classified, wherein the document set is selected from a corpus;

a receipt module to receive from the user, identification of a common classification for one or more of the documents in the set and at least one highlighted portion of text in each of the identified documents;

a comparison module to compare the identified documents to further documents in the corpus and to identify those further documents that satisfy a similarity threshold with the identified documents; and

a result module to provide to the user for review only those further documents in the corpus that are identified.

2. A system according to claim 1, further comprising:

a selection module to randomly select the documents in the set.

3. A system according to claim 1, further comprising:

a determination module to determine a number of the documents in the set for providing to the user.

4. A system according to claim 3, further comprising:

a probability module to determine, upon review of the determined number of documents in the set by the user, a probability that one such document includes text consistent with the common classification

5. A system according to claim 4, further comprising:

a document selection module to select further documents from the corpus for providing to the user until an expected number of documents associated with the common classification is reached.

6. A system according to claim 5, further comprising:

a determination module to determine the expected number of documents associated with the common classification based on a total number of documents in the corpus and the probability that one such document includes text consistent with the common classification.

7. A system according to claim 3, further comprising:

a calculation module to calculate the number of documents in the set based one or more of on a level of precision, a probability that one such document is associated with the common classification, a probability that the one such document fails to include text associated with the common classification, and a global setting for review of the documents in the corpus.

8. A system according to claim 1, further comprising:

an identification module to identify one or more of the further documents that are the same as at least one of the identified documents; and

an assignment module to automatically assign the common classification of identified documents to the further documents that are the same as the identified documents.

9. A system according to claim 1, further comprising:

a performance module to perform quality control of the further documents identified as satisfying a similarity threshold with the identified documents.

10. A system according to claim 1, further comprising:

a validation module to ensure that all the documents associated with the common classification in the corpus are identified by performing validation when the further documents that satisfy the similarity threshold reach an expected number of documents associated with the common classification.

11. A computer-implemented method for assigning document classifications, comprising:

providing to a user a set of documents to be classified, wherein the document set is selected from a corpus;

receiving from the user, identification of a common classification for one or more of the documents in the set and at least one highlighted portion of text in each of the identified documents;

comparing the identified documents to further documents in the corpus and identifying those further documents that satisfy a similarity threshold with the identified documents; and

providing to the user for review only those further documents in the corpus that are identified.

12. A method according to claim 11, further comprising:

randomly selecting the documents in the set.

13. A method according to claim 11, further comprising:

determining a number of the documents in the set for providing to the user.

14. A method according to claim 13, further comprising:

upon review of the determined number of documents in the set by the user, determining a probability that one such document includes text consistent with the common classification

15. A method according to claim 14, further comprising:

selecting further documents from the corpus for providing to the user until an expected number of documents associated with the common classification is reached.

16. A method according to claim 15, further comprising:

determining the expected number of documents associated with the common classification based on a total number of documents in the corpus and the probability that one such document includes text consistent with the common classification.

17. A method according to claim 13, further comprising:

calculating the number of documents in the set based one or more of on a level of precision, a probability that one such document is associated with the common classification, a probability that the one such document fails to include text associated with the common classification, and a global setting for review of the documents in the corpus.

18. A method according to claim 11, further comprising:

identifying one or more of the further documents that are the same as at least one of the identified documents; and

automatically assigning the common classification of identified documents to the further documents that are the same as the identified documents.

19. A method according to claim 11, further comprising:

performing quality control of the further documents identified as satisfying a similarity threshold with the identified documents.

20. A method according to claim 11, further comprising:

ensuring that all the documents associated with the common classification in the corpus are identified by performing validation when the further documents that satisfy the similarity threshold reach an expected number of documents associated with the common classification.