System and method for displaying relationships between electronically stored information to provide classification suggestions via inclusion

• US 8,713,018 B2
• Filed: 07/09/2010
• Issued: 04/29/2014
• 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, Yuk Ting
• Application Number:
  US12/833,860
• Publication Number:
  US 20110029526A1
• Time in Patent Office: 1,390 Days
• Field of Search: None
• US Class Current: 707/737
• 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 system and for providing reference documents as a suggestion for classifying uncoded documents is provided. A set of reference electronically stored information items, each associated with a classification code, is designated. One or more of the reference electronically stored information items is combined with a set of uncoded electronically stored information items. Clusters of the uncoded electronically stored information items and the one or more reference electronically stored information items are generated. Relationships between the uncoded electronically stored information items and the one or more reference electronically stored information items in at least one cluster are visually depicted as suggestions for classifying the uncoded electronically stored information items in that cluster.

Claims

1. A system for providing reference items as a suggestion for classifying uncoded electronically stored information items, comprising:

a set of reference electronically stored information items each associated with one of a plurality of classification codes and a visual representation of that classification code comprising at least one of a shape and a symbol, wherein the visual representation of each of the classification codes is different from the visual representations of the remaining classification codes;

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

a processor to execute modules, comprising;

a clustering module to combine one or more of the coded reference electronically stored information items with the set of the uncoded electronically stored information items and to group the combined uncoded electronically stored information items and one or more coded reference electronically stored information items into clusters; and

a display to visually depict relationships between the uncoded electronically stored information items and the one or more coded reference electronically stored information items in at least one of the clusters as suggestions for classifying the uncoded electronically stored information items in that cluster by displaying the visual representation associated with each of the coded reference electronically stored information items in that cluster and the visual representation associated with each of the uncoded electronically stored information items in that cluster.

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

a reference module to generate the set of reference electronically stored information items, comprising at least one of;

a similarity module to identify dissimilar electronically stored information items for a document review project and to assign a classification code to each of the dissimilar electronically stored information items; and

a reference clustering module to cluster electronically stored information items for a document review project, to select one or more of the electronically stored information items in at least one cluster, and to assign a classification code to each of the selected electronically stored information items.

3. A system according to claim 1, wherein the clusters are generated based on a similarity metric comprising forming a score vector for each uncoded electronically stored information item in the portion and each coded electronically stored information item in the reference set and calculating the similarity metric by comparing the score vectors for one of the uncoded electronically stored information items and one of the coded electronically stored information items in the reference set as an inner product.

4. A system according to claim 3, wherein the inner product is determined according to the following equation:

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

a classification module to assign a classification code to one or more of the uncoded electronically stored information items in the at least one cluster.

6. A system according to claim 1, wherein each uncoded electronically stored information item in the at least one cluster is represented by a symbol in the display and each of the one or more coded reference electronically stored information items is represented by an additional symbol in the display, and further wherein the coded reference electronically stored information items associated with different classification codes are distinguished by assigning a different color to the different symbols.

7. A method for providing reference items as a suggestion for classifying uncoded electronically stored information items, comprising the steps of:

designating a set of reference electronically stored information items each associated with one of a plurality of classification codes and a visual representation of that classification code comprising at least one of a shape and a symbol, wherein the visual representation of each of the classification codes is different from the visual representations of the remaining classification codes;

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

combining one or more of the coded reference electronically stored information items with the set of the uncoded electronically stored information items;

grouping the combined uncoded electronically stored information items and one or more coded reference electronically stored information items into clusters; and

visually depicting relationships between the uncoded electronically stored information items and one or more coded reference electronically stored information items in at least one of the clusters as suggestions for classifying the uncoded electronically stored information items in that cluster, comprising displaying the visual representation associated with each of the coded reference electronically stored information items in that cluster and the visual representation associated with each of the uncoded electronically stored information items in that cluster,

wherein the steps are performed by a suitably programmed computer.

8. A method according to claim 7, further comprising:

generating the set of reference electronically stored information items, comprising at least one of;

identifying dissimilar electronically stored information items for a document review project and assigning a classification code to each of the dissimilar electronically stored information items; and

clustering electronically stored information items for a document review project, selecting one or more of the electronically stored information items in at least one cluster and assigning a classification code to each of the selected electronically stored information items.

9. A method according to claim 7, wherein the clusters are generated based on a similarity metric, comprising:

forming a score vector for each uncoded electronically stored information item in the portion and each coded electronically stored information item in the reference set; and

calculating the similarity metric by comparing the score vectors for one of the uncoded electronically stored information items and one of the electronically stored information items in the reference set as an inner product.

10. A method according to claim 9, wherein the inner product is determined according to the following equation:

11. A method according to claim 7, further comprising:

assigning a classification code to one or more of the uncoded electronically stored information items in the at least one cluster.

12. A method according to claim 7, further comprising:

representing each uncoded electronically stored information item in the at least one cluster with a symbol; and

representing each of the one or more coded reference electronically stored information items with a different symbol; and

distinguishing the coded reference electronically stored information items associated with different classification codes by assigning a different color to the different symbols.

13. A system for clustering reference documents to generate suggestions for classification of uncoded documents, comprising:

a set of reference documents each associated with one of a plurality of classification codes and a visual representation of that classification code comprising at least one of a shape and a symbol, wherein the visual representation of each of the classification codes is different from the visual representations of the remaining classification codes;

a set of uncoded documents each associated with a visual representation different from the visual representations of the classification codes;

a processor to execute modules, comprising;

a clustering module to select one or more of the coded reference documents, to combine the one or more coded reference documents selected with the uncoded documents as a set of combined documents, and to group the combined set of documents into clusters, further comprising;

a cluster similarity module to determine a similarity between each document; and

a grouping module to group the documents into the clusters based on the similarity;

an identification module to identify at least one of the clusters with the coded reference documents; and

a display to visually depict relationships between the uncoded documents and the one or more coded reference documents in the at least one cluster as suggestions for classifying the uncoded documents in that cluster by displaying the visual representation associated with each of the coded reference documents in that cluster and the visual representation associated with each of the uncoded documents in that cluster.

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

a reference module to generate the set of reference documents, comprising at least one of;

a reference similarity module to identify dissimilar documents for a document review project and assign a classification code to each of the dissimilar documents; and

a reference cluster module to generate clusters of documents for a document review project, selecting one or more of the documents in at least one of the clusters and assigning a classification code to each of the documents.

15. A system according to claim 13, wherein the one or more coded reference documents are selected from at least one of a predefined, customized, or arbitrary reference document set.

16. A system according to claim 13, wherein the similarity is determined by forming a score vector for each uncoded document and each coded reference document and calculating a similarity metric between the score vectors for the uncoded documents and coded reference documents as an inner product.

17. A system according to claim 16, wherein the inner product is determined according to the following equation:

18. A system according to claim 13, wherein each uncoded document in the at least one cluster is represented by a symbol and each coded reference document is represented by a different symbol, and further wherein the coded reference electronically stored information items associated with different classification codes are distinguished by different color assigned to the different symbols.

19. A method for clustering reference documents to generate suggestions for classification of uncoded documents, comprising the steps of:

designating a set of reference documents each associated with one of a plurality of classification codes and a visual representation of that classification code comprising at least one of a shape and a symbol, wherein the visual representation of each of the classification codes is different from the visual representations of the remaining classification codes;

obtaining a set of uncoded documents each associated with a visual representation different from the visual representations of the classification codes;

selecting one or more of the coded reference documents and combining the one or more coded reference documents selected with the uncoded documents as a set of combined documents;

grouping the combined set of documents into clusters, comprising;

determining a similarity between each document; and

grouping the documents into the clusters based on the similarity;

identifying at least one cluster of the clusters with the coded reference documents; and

visually depicting relationships between the uncoded documents and the one or more coded reference documents in the at least one cluster as suggestions for classifying the uncoded documents in that cluster, comprising displaying the visual representation associated with each of the coded reference documents in that cluster and the visual representation associated with each of the uncoded documents in that cluster,

wherein the steps are performed by a suitably programmed computer.

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

generating the set of reference documents, comprising at least one of;

identifying dissimilar documents for a document review project and assigning a classification code to each of the dissimilar documents; and

generating clusters of documents for a document review project, selecting one or more of the documents in at least one of the clusters and assigning a classification code to each of the documents.

21. A method according to claim 19, wherein the one or more coded reference documents are selected from at least one of a predefined, customized, or arbitrary reference document set.

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

determining the similarity, comprising;

forming a score vector for each uncoded document and each coded reference document; and

calculating a similarity metric between the score vectors for the uncoded documents and coded reference documents as an inner product.

23. A method according to claim 22, wherein the inner product is determined according to the following equation:

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

representing each uncoded document in the at least one cluster with a symbol; and

representing each coded reference document with a different symbol; and

distinguishing the coded reference documents with different classification codes with different colors of the different symbols.