IP Library Granted Patent US 10,318,556
Granted Patent B2
US 10,318,556 · App. 15/431,335 · Granted Jun 11, 2019

Computer readable electronic records automated classification system

Inventors: Thomas A. Summerlin (Lutherville, MD); Timothy Shinkle (Alexandria, VA); Russell E. Stalters (Bethesda, MD)
Assignee: Open Text Corporation
G06F16/285G06F16/23G06F16/353G06F16/93G06F16/951G06F17/2785G06N20/00Y10S707/99932Y10S707/99935Y10S707/99936Y10S707/99942Y10S707/99943Y10S707/99945
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,318,556
App. No.
15/431,335
Granted
Jun 11, 2019
Kind
B2
Abstract

Classifying an electronic document in a computer-based system is disclosed. For each classification instance in a plurality of classification instances, a confidence data indicating a degree of confidence that the electronic document is associated with that classification instance is determined. A classification, based on a first classification instance in the plurality of classification instances, is assigned without human intervention to the electronic document if the confidence data associated with the first classification instance exceeds a first threshold.

Claims (64)

1. A method for classifying an electronic document in a computer-based system, comprising:

receiving, by a processor, an indication to classify the electronic document;

accessing a computer memory configured with associations between document contents and a plurality of classification instances, the associations based on document contents of training documents and pre-assigned classifications;

generating, by the processor, a set of confidence data using the associations, the set of confidence data comprising for each of one or more classification instances from the plurality of classification instances, a corresponding determined confidence data, wherein each corresponding determined confidence data indicates a degree of confidence that the electronic document is associated with a corresponding classification instance;

selecting, by the processor, a processing action to assign a classification to the electronic document, the selected processing action selected from a set of processing actions based on the set of confidence data, wherein the set of processing actions comprise:

a first processing action comprising, in the event at least one of the corresponding determined confidence data in the set of confidence data exceeds a first predetermined threshold, automatically assigning the classification to the electronic document without user input; and

a second processing action comprising, in the event none of the corresponding determined confidence data in the set of confidence data exceeds the first predetermined threshold and that at least one of the corresponding determined confidence data in the set of confidence data exceeds a second predetermined threshold that is lower than the first predetermined threshold, providing a user interface to a user, the user interface comprising controls to receive, via user interaction with the user interface, a user input indicating a selection of the classification

implementing, by the processor, the selected processing action to classify the electronic document.

2. The method of claim 1 , wherein the set of processing actions further comprises:

a third processing action comprising assigning a review classification to the electronic document to indicate that the electronic document is required to be reviewed by the user.

3. The method of claim 2 , wherein the set of processing actions further comprises a fourth processing action comprising assigning a null classification to the electronic document.

4. The method of claim 1 , wherein selecting the processing action comprises:

accessing decision control data comprising a plurality of confidence factor ranges, the decision control data associating each of the set of processing actions with a corresponding confidence factor range;

determining a confidence factor range from the plurality of confidence factor ranges into which the at least one corresponding determined confidence data falls; and

selecting, as the selected processing action, the processing action associated with the determined confidence factor range.

5. The method of claim 1 , wherein the associations between document contents and the plurality of classification instances is stored as a file plan taxonomy.

6. The method of claim 1 , further comprising:

maintaining a file plan comprising a hierarchical tree structure that includes a plurality of classification folders, the plurality of classification folders corresponding to the plurality of classification instances; and

updating a first folder of the file plan to point to the electronic document, wherein the first folder corresponds to the classification assigned to the electronic document.

7. A computer program product comprising a non-transitory computer readable medium storing a set of computer executable instructions executable by a processor to:

receive an indication to classify an electronic document;

access a computer memory configured with associations between document contents and a plurality of classification instances, the associations based on document contents of training documents and pre-assigned classifications;

generate a set of confidence data using the associations, the set of confidence data comprising for each of one or more classification instances from the plurality of classification instances, a corresponding determined confidence data, wherein each corresponding determined confidence data indicates a degree of confidence that the electronic document is associated with a corresponding classification instance;

select a processing action to assign a classification to the electronic document, the selected processing action selected from a set of processing actions based on the set of confidence data, wherein the set of processing actions comprise:

a first processing action to automatically assign the classification to the electronic document without user input, wherein the set of computer executable instructions are executable to select the first processing action as the selected processing action based on a determination that at least one of the corresponding determined confidence data in the set of confidence data exceeds a first predetermined threshold; and

a second processing action to provide a user interface to a user, the user interface comprising controls to receive, via user interaction with the user interface, a user input indicating a selection of the classification, wherein the set of computer executable instructions are executable to select the second processing action as the selected processing action based on a determination that none of the corresponding determined confidence data in the set of confidence data exceeds the first predetermined threshold and that at least one of the corresponding determined confidence data in the set of confidence data exceeds a second predetermined threshold that is lower than the first predetermined threshold;

implement the selected processing action to classify the electronic document.

8. The computer program product of claim 7 , wherein the set of processing actions further comprises:

a third processing action to assign a review classification to the electronic document to indicate that the electronic document is required to be reviewed by the user, wherein the set of computer executable instructions are executable to select the third processing action as the selected processing action based on a determination that fewer than a prescribed number of classification instances has corresponding determined confidence data that exceeds the second predetermined threshold.

9. The computer program product of claim 8 , wherein the set of processing actions further comprises a fourth processing action comprising assigning a null classification to the electronic document, wherein the set of computer executable instructions are executable to select the fourth processing action as the selected processing action based on a determination that none of the corresponding determined confidence data in the set of confidence data exceeds a third predetermined threshold.

10. The computer program product of claim 7 , wherein the set of computer executable instructions are further executable to:

access decision control data comprising a plurality of confidence factor ranges, the decision control data associating each of the set of processing actions with a corresponding confidence factor range;

determine a confidence factor range from the plurality of confidence factor ranges into which the at least one corresponding determined confidence data falls; and

select, as the selected processing action, the processing action associated with the determined confidence factor range.

11. The computer program product of claim 7 , wherein the associations between document contents and the plurality of classification instances is stored as a file plan taxonomy.

12. The computer program product of claim 7 , wherein the set of computer executable instructions are further executable to:

maintain a file plan comprising a hierarchical tree structure that includes a plurality of classification folders, the plurality of classification folders corresponding to the plurality of classification instances;

update a first folder of the file plan to point to the electronic document based on the classification assigned to the electronic document, wherein the first folder corresponds to the classification assigned to the electronic document.

13. The computer program product of claim 7 , wherein the user interface comprises controls to allow the user to select the classification for the electronic document from the one or more classification instances.

14. A system comprising:

a computer memory configured with associations between document contents and a plurality of classification instances, the associations based on document contents of training documents and pre-assigned classifications;

a processor coupled to the computer memory;

a non-transitory computer readable medium storing a set of computer executable instructions executable by the processor to:

receive an indication to classify an electronic document;

access the associations;

generate a set of confidence data using the associations, the set of confidence data comprising for each of one or more classification instances from the plurality of classification instances, a corresponding determined confidence data, wherein each corresponding determined confidence data indicates a degree of confidence that the electronic document is associated with a corresponding classification instance;

select a processing action to assign a classification to the electronic document, the selected processing action selected from a set of processing actions based on the set of confidence data, wherein the set of processing actions comprise:

a first processing action to automatically assign the classification to the electronic document without user input, wherein the set of computer executable instructions are executable to select the first processing action as the selected processing action based on a determination that at least one of the corresponding determined confidence data in the set of confidence data exceeds a first predetermined threshold; and

a second processing action to provide a user interface to a user, the user interface comprising controls to receive, via user interaction with the user interface, a user input indicating a selection of the classification, wherein the set of computer executable instructions are executable to select the second processing action as the selected processing action based on a determination that none of the corresponding determined confidence data in the set of confidence data exceeds the first predetermined threshold and that at least one of the corresponding determined confidence data in the set of confidence data exceeds a second predetermined threshold that is lower than the first predetermined threshold; and

implement the selected processing action to classify the electronic document.

15. The system of claim 14 , wherein the set of processing actions further comprises:

a third processing action to assign a review classification to the electronic document to indicate that the electronic document is required to be reviewed by the user, wherein the set of computer executable instructions are executable to select the third processing action as the selected processing action based on a determination that fewer than a prescribed number of classification instances has corresponding determined confidence data that exceeds the second predetermined threshold.

16. The system of claim 15 , wherein the set of processing actions further comprises a fourth processing action comprising assigning a null classification to the electronic document, wherein the set of computer executable instructions are executable to select the fourth processing action as the selected processing action based on a determination that none of the corresponding determined confidence data in the set of confidence data exceeds a third predetermined threshold.

17. The system of claim 14 , wherein:

the computer memory is further configured with decision control data comprising a plurality of confidence factor ranges, the decision control data associating each of the set of processing actions with a corresponding confidence factor range; and

the set of computer executable instructions are further executable to:

access the decision control data;

determine a confidence factor range from the plurality of confidence factor ranges into which the at least one corresponding determined confidence data falls; and

select, as the selected processing action, the processing action associated with the determined confidence factor range.

18. The system of claim 14 , wherein the associations between document contents and the plurality of classification instances is stored as a file plan taxonomy.

19. The system of claim 14 , wherein the set of computer executable instructions are further executable to:

maintain a file plan comprising a hierarchical tree structure that includes a plurality of classification folders, the plurality of classification folders corresponding to the plurality of classification instances;

update a first folder of the file plan to point to the electronic document based on the classification assigned to the electronic document, wherein the first folder corresponds to the classification.

20. The system of claim 14 , wherein the user interface comprises controls to allow the user to select the classification for the electronic document from the one or more classification instances.

Assignments (7)
MERGER Recorded Feb 6, 2018
From: TRUEARC CORPORATION
To: DOCUMENTUM RECORDS MANAGEMENT INC.
Reel/Frame 045261/0631 →
CHANGE OF NAME Recorded Nov 17, 2017
From: PROVENANCE SYSTEMS INC.
To: TRUEARC CORPORATION
Reel/Frame 044483/0310 →
ARTICLES OF AMALGAMATION Recorded Nov 17, 2017
From: DOCUMENTUM CANADA COMPANY
To: EMC CORPORATION OF CANADA
Reel/Frame 044784/0181 →
CERTIFICATE OF AMALGAMATION Recorded Nov 17, 2017
From: DOCUMENTUM RECORDS MANAGEMENT INC.
To: DOCUMENTUM CANADA COMPANY
Reel/Frame 044481/0516 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 17, 2017
From: SUMMERLIN, THOMAS A.; SHINKLE, TIMOTHY; STALTERS, RUSSELL E.
To: PROVENANCE SYSTEMS INC.
Reel/Frame 044164/0439 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 17, 2017
From: EMC CORPORATION OF CANADA
To: EMC CORPORATION
Reel/Frame 044164/0576 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 17, 2017
From: EMC CORPORATION
To: OPEN TEXT CORPORATION
Reel/Frame 044164/0620 →
Continuity (7)
Continuation 14819341 · Aug 5, 2015
Continuation 14173186 · Feb 5, 2014
Continuation 13369006 · Feb 8, 2012
Continuation 12315610 · Dec 4, 2008
Continuation 10378025 · Feb 28, 2003
Continuation 09592778 · Jun 13, 2000
Related Publication 20170220666A1 · Aug 3, 2017