Computer-implemented system and method for inclusion-based electronically stored information item cluster visual representation

• US 9,898,526 B2
• Filed: 01/09/2017
• Issued: 02/20/2018
• 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., Nussbaum, Nicholas I.
• Primary Examiner(s): Choi, Carol
• Application Number:
  US15/401,450
• Publication Number:
  US 20170116325A1
• Time in Patent Office: 407 Days
• Field of Search: None
• 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 inclusion-based electronically stored information item cluster visual representation is provided. A set of reference electronically stored information items is maintained. A subset of the electronically stored information items is selected from the set, each associated with a classification code, each of the classification codes associated with a visual representation different from the visual representations of the remaining classification codes. The subset is combined with a set of uncoded electronically stored information items, each associated with a visual representation different from the visual representations of the classification codes. The combined electronically stored information items are grouped into clusters. Each of the clusters is visually represented, including displaying the visual representation associated with the code of each of the reference electronically stored information items in that cluster and the visual representation associated with each of the uncoded electronically stored information item in that cluster.

Claims

1. A computer-implemented system for inclusion-based electronically stored information item cluster visual representation, comprising:

a non-transitory computer readable storage medium comprising program code; and

a computer processor configured coupled to the storage medium, wherein the processor is configured to execute the program code to perform steps to;

maintain a set of reference electronically stored information items;

select from the set a subset of the electronically stored information items, each of the reference electronically stored information items in the subset associated with a classification code, each of the classification codes associated with a visual representation different from the visual representations of the remaining classification codes;

combine the subset with a set of uncoded electronically stored information items, each of the uncoded electronically stored information items associated with a visual representation different from the visual representations of the classification codes;

group the combined electronically stored information items into clusters, further comprising;

convert each of the combined electronically stored information items into one or more tokens;

generate a score vector for each of the electronically stored information items based on the tokens associated with that electronically stored information item, further comprising;

score each of the tokens;

generate paired values for each of the combined electronically stored information items comprising paring the token with the score associated with that token; and

for each of the combined electronically stored information items, order the paired values along a vector for that combined electronically stored information item to create the score vector for that electronically stored information item, wherein the tokens are ordered along the vector based on a frequency of the tokens within that combined electronically stored information item; and

compare the score vector for each of the combined electronically stored information items, wherein the clustering is performed based on the comparison; and

visually represent each of the clusters comprising displaying the visual representation associated with the code of each of the reference electronically stored information items in that cluster and the visual representation associated with each of the uncoded electronically stored information item in that cluster.

2. The system according to claim 1, wherein the reference electronically stored information items in the subset are randomly selected from the set.

3. The system according to claim 1, the steps further comprising:

obtain item selection criteria comprising one or more of reviewer preference, classification category, electronically stored information item source, electronically stored information item content, and an electronically stored information item review project for which the subset is selected;

wherein the subset of the reference electronically stored information items is selected using the item selection criteria.

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

determine a number of the reference electronically stored information items selected into the subset based one or more reference factors, the reference factors comprising a size of a review project for which the subset is selected, an average size of the reference electronically stored information items, types of the classification codes, and a number of the reference electronically stored information items associated with each of the classification codes.

5. The system according to claim 1, wherein the subset comprises more than one occurrence of at least one of the reference electronically stored information items.

6. The system according to claim 1, wherein the visual representation of one of the reference documents associated with one of the classification codes comprises at least one of a symbol, shape, and color.

7. The system according to claim 6, wherein visually representing each of the clusters further comprises displaying a shape within which the visual representations for the reference electronically stored information items and uncoded electronically stored information items are displayed.

8. A computer-implemented method for inclusion-based electronically stored information item cluster visual representation, comprising the steps of:

maintaining a set of reference electronically stored information items;

selecting from the set a subset of the electronically stored information items, each of the reference electronically stored information items in the subset associated with a classification code, each of the classification codes associated with a visual representation different from the visual representations of the remaining classification codes;

combining the subset with a set of uncoded electronically stored information items, each of the uncoded electronically stored information items associated with a visual representation different from the visual representations of the classification codes;

grouping the combined electronically stored information items into clusters, further comprising;

converting each of the combined electronically stored information items into one or more tokens;

generating a score vector for each of the electronically stored information items based on the tokens associated with that electronically stored information item, further comprising;

scoring each of the tokens;

generating paired values for each of the combined electronically stored information items comprising paring the token with the score associated with that token; and

for each of the combined electronically stored information items, ordering the paired values along a vector for that combined electronically stored information item to create the score vector for that electronically stored information item, wherein the tokens are ordered along the vector based on a frequency of the tokens within that combined electronically stored information item; and

comparing the score vector for each of the combined electronically stored information items, wherein the clustering is performed based on the comparison; and

visually representing each of the clusters comprising displaying the visual representation associated with the code of each of the reference electronically stored information items in that cluster and the visual representation associated with each of the uncoded electronically stored information item in that cluster,

wherein the steps are performed on a suitably-programmed computer.

9. The method according to claim 8, wherein the reference electronically stored information items in the subset are randomly selected from the set.

10. The method according to claim 8, further comprising the steps of:

obtaining item selection criteria comprising one or more of reviewer preference, classification category, electronically stored information item source, electronically stored information item content, and an electronically stored information item review project for which the subset is selected;

wherein the subset of the reference electronically stored information items is selected using the item selection criteria.

11. The method according to claim 8, further comprising:

determining a number of the reference electronically stored information items selected into the subset based one or more reference factors, the reference factors comprising a size of a review project for which the subset is selected, an average size of the reference electronically stored information items, types of the classification codes, and a number of the reference electronically stored information items associated with each of the classification codes.

12. The method according to claim 8, wherein the subset comprises more than one occurrence of at least one of the reference electronically stored information items.

13. The method according to claim 8, wherein the visual representation of one of the reference documents associated with one of the classification codes comprises at least one of a symbol, shape, and color.

14. The method according to claim 13, wherein visually representing each of the clusters further comprises displaying a shape within which the visual representations for the reference electronically stored information items and uncoded electronically stored information items are displayed.