Computer-implemented system and method for analyzing clusters of coded documents
A computer-implemented system and method for analyzing clusters of coded documents is provided. Clusters of documents are displayed and at least a portion of the documents are each associated with a classification code. A representation of each document is provided based on the associated classification code or an absence of the associated classification code. A search query with search terms is received. Each search term is associated with one of the classification codes. Those documents that satisfy the search query are identified and the representations of the identified documents are changed based on the classification codes associated with the search terms. The change in representation provides an indication of agreement between the classification code of such document and the classification codes of the search terms, or an indication of disagreement between the classification code of the document and the classification codes of the search terms.
1. A computer-implemented system for displaying multi-dimensional clusters of documents on a two-dimensional screen, the system including one or more a programmed digital computing devices configured to execute computer code to implement a plurality of components, comprising:
a clustering component to form, in a three-dimensional cluster space, a plurality of clusters comprising one or more documents,
each cluster of the plurality of clusters having an associated cluster concept,
each document having an associated concept score, and
each document assigned to a cluster based on the concept score;
a cluster spine placement component to map each cluster to a corresponding cluster spine from a plurality of spines, such that each spine comprises a group of clusters sharing a concept; and
a display generator component to generate a visualization of the clusters and spines in two-dimensional space for projection onto a two-dimensional display, and to generate a heads-up display for projection onto a two-dimensional display, the heads-up display including:
a compass logically framing the cluster spines, the compass including a plurality of slots positioned circumferentially around the compass, and
a plurality of labels, each label of the plurality of labels indicating the associated cluster concept for a corresponding spine; and
a concept pointer from each label to its corresponding spine from among of the plurality of spines.
2. The computer-implemented system of claim 1 , wherein the compass further comprises plurality of slots positioned circumferentially around the compass, each cluster spine displayed within a corresponding slot, and each label disposed within a slot corresponding to its associated spine.
3. The computer-implemented system as described in claim 1 , wherein at least one spine comprises a plurality of clusters arranged linearly.
4. The computer-implemented system as described in claim 1 , wherein the clusters and spines are displayed in three-dimensional space.
5. The computer-implemented system as described in claim 1 , wherein the concept score is generated from one or both of concepts and terms extracted from the documents.
6. The computer-implemented system as described in claim 1 , wherein the compass logically separates cluster spines into a focused area displaying some of the cluster spines, and an unfocused area displaying remaining cluster spines, and wherein each concept pointer extends from a label to a corresponding cluster spine in the focused area.
7. The computer-implemented system as described in claim 1 , wherein the heads-up display provides controls for one or more of navigating, exploring, and searching the visualization.
8. The computer-implemented system as described in claim 1 , further comprising:
a division module to divide the display of clusters, comprising:
a priority module to prioritize documents;
an order module to order the documents based on the prioritization;
a bin classification module to divide the ordered documents into bins; and
a bin display module to separately display the documents associated with each bin.
9. A computer-implemented method for displaying multi-dimensional clusters of documents, the method comprising:
forming a plurality of clusters of one or more documents,
associating with each cluster a cluster concept,
associating with each document a cluster concept score;
assigning each document to a cluster based on the document's concept score;
mapping each cluster to a corresponding cluster spine from a plurality of spines, such that each spine comprises a group of clusters sharing a concept;
displaying a heads-up display, the heads-up display comprising:
a visualization showing the clusters and spines and
a compass logically framing the cluster spines, the compass including a plurality of slots positioned circumferentially around the compass, and
a plurality of labels, each label of the plurality of labels indicating the associated cluster concept for a corresponding spine; and
a concept pointer from each label to its corresponding spine from among of the plurality of spines.
10. The computer-implemented method as described in claim 9 , wherein the clusters and spines are displayed in two-dimensional space for projection onto a two-dimensional display.
11. The computer-implemented method as described in claim 9 , wherein the clusters and spines are displayed in three-dimensional space.
12. The computer-implemented method as described in claim 9 , wherein the concept score is generated from one or both of concepts and terms extracted from the documents.
13. The computer-implemented method as described in claim 9 , wherein the compass logically separates cluster spines into a focused area displaying some of the cluster spines, and an unfocused area displaying remaining cluster spines, and wherein each concept pointer extends from a label to a corresponding cluster spine in the focused area.
14. The method as described in claim 9 , wherein the heads-up display provides controls for one or more of navigating, exploring, and searching the visualization.
15. The computer-implemented method as described in claim 9 , further comprising:
dividing the display of clusters via a division module, the division module comprising:
a priority module to prioritize documents;
ordering the documents based on the prioritization via an ordering module;
dividing the ordered documents into bins; and
separately displaying the documents associated with each bin.
16. A non-volatile computer-readable storage medium having computer-executable code thereon, the computer code, when executed by a computer processor, causing a computer to perform a method for displaying multi-dimensional clusters of documents on a two-dimensional screen, the code comprising:
code for forming, in a three-dimensional cluster space, a plurality of clusters comprising one or more documents,
each cluster of the plurality of clusters having an associated cluster concept,
each document having an associated concept score, and
each document assigned to a cluster based on the concept score;
code for mapping each cluster to a corresponding cluster spine from a plurality of spines, such that each spine comprises a group of clusters sharing a concept; and
code for generating a visualization of the clusters and spines in two-dimensional space for projection onto a two-dimensional display, and for generating a heads-up display for projection onto a two-dimensional display, the heads-up display including:
a compass logically framing the cluster spines, the compass including a plurality of slots positioned circumferentially around the compass, and
a plurality of labels, each label of the plurality of labels indicating the associated cluster concept for a corresponding spine; and
a concept pointer from each label to its corresponding spine from among of the plurality of spines.
17. The non-volatile computer-readable storage medium of claim 16 , wherein the compass further comprises plurality of slots positioned circumferentially around the compass, each cluster spine displayed within a corresponding slot, and each label disposed within a slot corresponding to its associated spine.
18. The non-volatile computer-readable storage medium of claim 16 , wherein the concept score is generated from one or both of concepts and terms extracted from the documents.
19. The non-volatile computer-readable storage medium of claim 16 , wherein the compass logically separates cluster spines into a focused area displaying some of the cluster spines, and an unfocused area displaying remaining cluster spines, and wherein each concept pointer extends from a label to a corresponding cluster spine in the focused area.
20. The non-volatile computer-readable storage medium of claim 16 , wherein the heads-up display provides controls for one or more of navigating, exploring, and searching the visualization.