System And Method For Displaying Relationships Between Electronically Stored Information To Provide Classification Suggestions Via Injection

• US 20110029536A1
• Filed: 07/09/2010
• Published: 02/03/2011
• Est. Priority Date: 07/28/2009
• Status: Active Grant

• Current Assignee: Nuix North America Inc. (Nuix Ltd.)
• Original Assignee: FTI Consulting Incorporated
• Inventors: Nussbaum, Nicholas I., Knight, William C.
• Granted Patent: US 8,515,957 B2
• Time in Patent Office: Days
• US Class Current: 707/740
• 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 reference set of electronically stored information items, each associated with a classification code, is designated. Clusters of uncoded electronically stored information items are designated. One or more of the uncoded electronically stored information items from at least one cluster is compared to the reference set. At least one of the electronically stored information items in the reference set is identified as similar to the one or more uncoded electronically stored information items. The similar electronically stored information items are injected into the at least one cluster. Relationships are visually depicted between the uncoded electronically stored information items and the similar electronically stored information items in the at least one cluster as suggestions for classifying the uncoded electronically stored information items.

Claims

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

a database to store a reference set comprising electronically stored information items each associated with a classification code;

a cluster module to designate clusters of uncoded electronically stored information items;

a similarity module to compare one or more of the uncoded electronically stored information items from at least one cluster to the reference set and to identify at least one of the electronically stored information items in the reference set that is similar to the one or more uncoded electronically stored information items;

an injection module to inject the similar electronically stored information items into the at least one cluster; and

a display to visually depict relationships between the uncoded electronically stored information items and the similar electronically stored information items in the at least one cluster as suggestions for classifying the uncoded electronically stored information items.

2. A system according to claim 1, wherein the comparison of the one or more uncoded documents and the reference document set comprises identifying a cluster center for the at least one cluster based on the one or more uncoded electronically stored information items and comparing the cluster center to the reference set.

3. A system according to claim 1, wherein the comparison of the one or more uncoded documents and the reference document set comprises identifying a sample comprising the one or more uncoded electronically stored information items in the at least one cluster and comparing the sample to the reference set.

4. A system according to claim 1, wherein the comparison of the one or more uncoded documents and the reference document set comprises identifying a cluster center for the at least one cluster, identifying a sample comprising the one or more uncoded electronically stored information items in the at least one cluster, and comparing the cluster center and the sample to the reference set.

5. A system according to claim 1, wherein the comparison of the one or more uncoded documents and the reference document set comprises identifying a vector upon which the at least one cluster is located, wherein the vector comprises one or more other clusters, identifying a cluster center for each of the at least one cluster and the other clusters along the vector, summing the cluster centers, and applying the summed cluster centers to the reference set.

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

a scoring module to form a score vector for the one or more uncoded electronically stored information items and each electronically stored information item in the reference set; and

a metric module to calculate a similarity metric by comparing the score vector for the one or more uncoded electronically stored information items with the score vectors for each of the electronically stored information items in the reference set to determine the similar electronically stored information items.

7. A method for providing reference documents as a suggestion for classifying uncoded electronically stored information, comprising:

designating a reference set comprising electronically stored information items each associated with a classification code;

designating clusters of uncoded electronically stored information items;

comparing one or more of the uncoded electronically stored information items from at least one cluster to the reference set;

identifying at least one of the electronically stored information items in the reference set that is similar to the one or more uncoded electronically stored information items;

injecting the similar electronically stored information items into the at least one cluster; and

visually depicting relationships between the uncoded electronically stored information items and the similar electronically stored information items in the at least one cluster as suggestions for classifying the uncoded electronically stored information items.

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

performing the comparison of the one or more uncoded electronically stored information items and the reference set, comprising;

calculating a cluster center for the at least one cluster based on the one or more uncoded electronically stored information items; and

comparing the cluster center to the reference set.

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

performing the comparison of the one or more uncoded electronically stored information items and the reference set, comprising;

identifying a sample comprising the one or more uncoded electronically stored information items in the at least one cluster; and

comparing the sample to the reference set.

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

performing the comparison of the one or more uncoded electronically stored information items and the reference set, comprising;

calculating a cluster center for the at least one cluster;

identifying a sample comprising the one or more uncoded electronically stored information items in the at least one cluster; and

comparing the cluster center and the sample to the reference set.

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

performing the comparison of the one or more uncoded electronically stored information items and the reference set, comprising;

identifying a vector upon which the at least one cluster is located, wherein the vector comprises one or more other clusters;

determining a cluster center for each of the at least one cluster and the other clusters along the vector; and

summing the cluster centers and applying the summed cluster centers to the reference set.

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

determining the similar electronically stored information items based on a similarity metric, comprising;

forming a score vector for the one or more uncoded electronically stored information items and each electronically stored information items in the reference set; and

calculating the similarity metric by comparing the score vector for the one or more uncoded electronically stored information items with the score vectors for each of the electronically stored information items in the reference set.

13. A system for injecting reference documents into a cluster set as suggestions for classifying uncoded documents, comprising:

a database to store a set of reference documents each associated with a classification code;

a cluster module to designate clusters of uncoded reference documents;

a comparison module to compare one or more of the uncoded documents in at least one of the clusters to the reference document set and selecting the reference documents that satisfy a similarity threshold with the at least one cluster;

an injection module to inject the selected reference documents into the at least one cluster; and

a display to display relationships between the uncoded documents and the selected reference documents in the at least one cluster as suggestions for classifying the uncoded documents.

14. A system according to claim 13, wherein the comparison of the one or more uncoded documents and the reference document set comprises calculating a cluster center for the at least one cluster based on the one or more uncoded documents and comparing the cluster center to the reference document set to identify the similar reference documents.

15. A system according to claim 13, wherein the comparison of the one or more uncoded documents and the reference document set comprises identifying a sample comprising at least one uncoded document in the at least one cluster and comparing the sample to the reference document set.

16. A system according to claim 13, wherein the comparison of the one or more uncoded documents and the reference document set comprises calculating a cluster center for the at least one cluster based on the uncoded documents in that cluster, identifying a sample comprising one or more of the uncoded documents in the at least one cluster, and comparing the cluster center and the sample to the reference document set.

17. A system according to claim 13, wherein the comparison of the one or more uncoded documents and the reference document set comprises identifying a vector upon which the at least one cluster is located, wherein the vector comprises one or more other clusters, determining a cluster center for each of the at least one cluster and the other clusters along the vector, summing the cluster centers, and applying the summed cluster centers to the reference document set.

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

a score module to form a score vector for the one or more uncoded documents in the at least one cluster and each reference document in the reference document set; and

a similarity metric module to calculate a similarity metric by comparing the score vector for the one or more uncoded documents with the score vector for one of the reference documents as an inner product.

19. A method for injecting reference documents into a cluster set as suggestions for classifying uncoded documents, comprising:

designating a set of reference documents each associated with a classification code;

designating clusters of uncoded reference documents;

comparing one or more of the uncoded documents in at least one of the clusters to the reference document set and selecting the reference documents that satisfy a similarity threshold with the one or more uncoded documents;

injecting the selected reference documents into the at least one cluster; and

displaying relationships between the uncoded documents and the selected reference documents in the at least one cluster as suggestions for classifying the uncoded documents.

20. A method according to claim 19, wherein the comparison of the one or more uncoded documents and the reference document set comprises:

calculating a cluster center for the at least one cluster based on the one or more uncoded documents and comparing the cluster center to the reference document set.

21. A method according to claim 19, wherein the comparison of the one or more uncoded documents and the reference document set comprises:

identifying a sample comprising at least one uncoded document in the at least one cluster and comparing the sample to the reference document set.

22. A method according to claim 19, wherein the comparison of the one or more uncoded documents and the reference document set comprises:

calculating a cluster center for the at least one cluster based on the uncoded documents in that cluster;

identifying a sample comprising one or more uncoded documents in the at least one cluster; and

comparing the cluster center and the sample to the reference document set.

23. A method according to claim 19, wherein the comparison of the one or more uncoded documents and the reference document set comprises:

identifying a vector upon which the at least one cluster is located, wherein the vector comprises one or more other clusters;

determining a cluster center for each of the at least one cluster and the other clusters along the vector; and

summing the cluster centers and applying the summed cluster centers to the reference document set.

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

determining the selected reference documents based on a similarity metric, comprising;

forming a score vector for the one or more uncoded documents in the at least one cluster and each reference document in the reference document set; and

calculating the similarity metric by comparing the score vector for the one or more uncoded documents with the score vector for one of the reference documents as an inner product.