Computer-implemented system and method for displaying visual classification suggestions for concepts

• US 9,064,008 B2
• Filed: 08/19/2013
• Issued: 06/23/2015
• Est. Priority Date: 07/28/2009
• Status: Active Grant

• Current Assignee: Nuix North America Inc. (Nuix Ltd.)
• Original Assignee: FTI Consulting Incorporated
• Inventors: Knight, William C.
• Primary Examiner(s): Choi, Yuk Ting
• Application Number:
  US13/970,545
• Publication Number:
  US 20130339275A1
• Time in Patent Office: 673 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/287 Visualization; Browsing
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/358 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/047 Pattern matching networks; Rete networks
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A computer-implemented system and method for displaying visual classification suggestions for concepts is provided. At least one cluster is provided, the cluster including one or more uncoded concepts, each associated with a visual representation that includes a geometric shape, and one or more reference concepts, each associated with a visual representation of an assigned classification code. For at least one of the uncoded concepts, a neighborhood that includes at least one of the reference concepts is determined. A classification code for the neighborhood is determined based on the at least one of the reference concepts. The classification code of the neighborhood is suggested as a classification code for the uncoded concept, which includes displaying the visual representation of the suggested classification code placed on a portion of the geometric shape associated with the uncoded concept.

Claims

1. A computer-implemented system for displaying visual classification suggestions for concepts, comprising:

a processor to execute modules, comprising;

a clustering module to provide at least one cluster comprising one or more uncoded concepts, each associated with a visual representation comprising a geometric shape, and one or more reference concepts, each associated with a visual representation of an assigned classification code;

a neighborhood module to determine for at least one of the uncoded concepts a neighborhood comprising at least one of the reference concepts;

a classification module to determine a classification code for the neighborhood based on the at least one of the reference concepts;

a suggestion module to suggest the classification code of the neighborhood as a classification code for the uncoded concept, comprising a display module to display the visual representation of the suggested classification code placed on a portion of the geometric shape associated with the uncoded concept;

a confidence module to determine a confidence level for the suggested classification code;

a difference module to receive from a user a classification code different from the suggested classification code and associated with a visual representation;

a comparison module to compare the confidence level to a threshold; and

a discordance module to display a discordance between the suggested classification code and the received classification code when the confidence level exceeds the threshold, comprising a discordance display module to display the visual representation of the received classification code on a different portion of the geometric shape.

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

a receipt module to receive acceptance of the suggested classification code from a user; and

an acceptance module to place the visual representation of the suggested classification code on one of a larger portion of the geometric shape and an entirety of the geometric shape upon receiving the acceptance.

3. The system according to claim 2, wherein the visual representation of the suggested classification code comprises at least one of a color, a pattern, a different shape, and a symbol.

4. The system according to claim 1, further comprising:

a confidence module to determine a confidence level for a further suggested classification code;

a difference module to receive from a user a classification code different from the further suggested classification code and associated with a visual representation;

a determination module to determine a confidence level for the received classification code;

a calculation module to calculate a difference between the confidence level for the further suggested classification code and the confidence level for the received classification code and comparing the difference to a threshold; and

a discordance module to display a discordance between the further suggested classification code and the received classification code when the confidence level exceeds the threshold, comprising a discordance display module to display the visual representation of the received classification code on a different portion of the geometric shape.

5. The system according to claim 1, further comprising:

a representation module to display the visual representations associated with all of the concepts in the cluster;

a selection module to receive a user selection of one of the visual representations; and

a presentation module to present to the user one or more documents associated with the concept whose visual representation was selected.

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

a shape module to display a shape around the displayed visual representations associated with the concepts;

a cluster classification module to suggest the classification code of the neighborhood as the classification code for the cluster, comprising a placement module to place the visual representation of the suggested classification code on the displayed shape,

wherein a center of the cluster comprises the uncoded concept.

7. The system according to claim 1, further comprising:

a similarity module to determine a similarity between the clusters; and

an organization module to organize the clusters along one or more spines, each spine comprising a vector, based on the similarity.

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

a conversion module to convert a document into one or more of the uncoded concepts;

an identification module to identify all of the classified uncoded concepts associated with the document upon classification of multiple uncoded concepts; and

a document classification module to determine a classification code of the document based on the classification codes of all of the associated classified uncoded concepts.

9. The system according to claim 8, further comprising at least one of:

a count module to count the associated classified uncoded concepts for each of the classification codes and to assign the classification code with the most associated concepts as the classification code of the document; and

an assignment module to assign a weight to each of the associated classified uncoded concepts, determine the classification code associated with a highest weight of the classified uncoded concepts, and to assign the classification code associated with the highest weight as the classification code of the document.

10. A computer-implemented method for displaying visual classification suggestions for concepts, comprising the steps of:

providing at least one cluster comprising one or more uncoded concepts, each associated with a visual representation comprising a geometric shape, and one or more reference concepts, each associated with a visual representation of an assigned classification code;

determining for at least one of the uncoded concepts a neighborhood comprising at least one of the reference concepts;

determining a classification code for the neighborhood based on the at least one of the reference concepts;

suggesting the classification code of the neighborhood as a classification code for the uncoded concept, comprising displaying the visual representation of the suggested classification code placed on a portion of the geometric shape associated with the uncoded concept;

determining a confidence level for the suggested classification code;

receiving from a user a classification code different from the suggested classification code and associated with a visual representation;

comparing the confidence level to a threshold; and

displaying a discordance between the suggested classification code and the received classification code when the confidence level exceeds the threshold, comprising displaying the visual representation of the received classification code on a different portion of the geometric shape,

wherein the steps are performed by a suitably programmed computer.

11. The method according to claim 10, further comprising:

receiving acceptance of the suggested classification code from a user; and

upon receiving the acceptance, placing the visual representation of the suggested classification code on one of a larger portion of the geometric shape and an entirety of the geometric shape.

12. The method according to claim 11, wherein the visual representation of the suggested classification code comprises at least one of a color, a pattern, a different shape, and a symbol.

13. The method according to claim 10, further comprising:

determining a similarity between the clusters; and

organizing the clusters along one or more spines, each spine comprising a vector, based on the similarity.

14. The method according to claim 10, further comprising:

converting a document into one or more of the uncoded concepts;

upon classification of multiple uncoded concepts, identifying all of the classified uncoded concepts associated with the document; and

determining a classification code of the document based on the classification codes of all of the associated classified uncoded concepts.

15. The method according to claim 14, further comprising at least one of:

counting the associated classified uncoded concepts for each of the classification codes, and assigning the classification code with the most associated concepts as the classification code of the document; and

assigning a weight to each of the associated classified uncoded concepts, determining the classification code associated with a highest weight of the classified uncoded concepts, and assigning the classification code associated with the highest weight as the classification code of the document.

16. The method according to claim 10, further comprising:

displaying the visual representations associated with all of the concepts in the cluster;

receiving a user selection of one of the visual representations; and

presenting to the user one or more documents associated with the concept whose visual representation was selected.

17. The method according to claim 16, further comprising:

displaying a shape around the displayed visual representations associated with the concepts;

suggesting the classification code of the neighborhood as the classification code for the cluster, comprising placing the visual representation of the suggested classification code on the displayed shape,

wherein a center of the cluster comprises the uncoded concept.

18. A computer-implemented method for displaying visual classification suggestions for concepts, comprising the steps of:

providing at least one cluster comprising one or more uncoded concepts, each associated with a visual representation comprising a geometric shape, and one or more reference concepts, each associated with a visual representation of an assigned classification code;

determining for at least one of the uncoded concepts a neighborhood comprising at least one of the reference concepts;

determining a classification code for the neighborhood based on the at least one of the reference concepts;

suggesting the classification code of the neighborhood as a classification code for the uncoded concept, comprising displaying the visual representation of the suggested classification code placed on a portion of the geometric shape associated with the uncoded concept;

determining a confidence level for the suggested classification code;

receiving from a user a classification code different from the suggested classification code and associated with a visual representation;

determining a confidence level for the received classification code;

calculating a difference between the confidence level for the suggested classification code and the confidence level for the received classification code and comparing the difference to a threshold; and

displaying a discordance between the suggested classification code and the received classification code when the confidence level exceeds the threshold, comprising displaying the visual representation of the received classification code on a different portion of the geometric shape,

wherein the steps are performed by a suitably programmed computer.