COMPUTER-AIDED METHODS AND SYSTEMS FOR PATTERN-BASED COGNITION FROM FRAGMENTED MATERIAL

• US 20120036131A1
• Filed: 09/30/2011
• Published: 02/09/2012
• Est. Priority Date: 02/13/2009
• Status: Active Grant

• Current Assignee: Cognitive Edge Pte., Ltd.
• Original Assignee: Cognitive Edge Pte., Ltd.
• Inventors: Bealing, Steven Anthony, Snowden, David John, Cheveldave, Michael Alexander, Stanbridge, Peter Richard, McHugh, Kenneth John-Paul
• Granted Patent: US 8,339,410 B2
• Time in Patent Office: Days
• US Class Current: 707/736
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures

Abstract

A method for obtaining and analyzing information objects including generating, collecting or discovering information objects. The information objects are signified at least in part using deliberately ambiguated signifier prompts, for example, linear scale opposing negatives or positives, and/or multi-dimensional signifier prompts. The information objects may comprise text or non-text fragments, and may be generated or selected. The responses to the signifier prompts are stored with the fragments to provide a dataset of signified fragments. The signified fragments may be analyzed based on the signifiers and can be utilized as part of an explorable knowledge repository, or objective measures can be created to aid in mass opinion capture or human attitude auditing. The fragments may be represented on a graphical template. In one embodiment, fragment exemplars are identified that exemplify significant locations on the template, and the exemplar signifiers are used to automatically locate other signified fragments on the template.

Claims

1. A method for selectively analyzing a large set of signified information objects comprising:

collecting a large set of information objects;

signifying the information objects, wherein at least a portion of the signification is produced by responding to deliberately ambiguated signifier prompts;

selecting suitable axes based on the signification of the information objects for generating a landscape of the signification data;

generating the landscape with links to the information objects; and

using the landscape to identify potentially relevant information objects, and reviewing only the identified potentially relevant information objects.

2. The method of 1, wherein one axis represents stability.

3. A method for seeking greater understanding of an issue from mass opinion capture comprising the steps:

creating a set of information objects and signifier prompts related to an issue;

providing this set of information objects and signifier prompts to a plurality of individuals, wherein at least a portion of the signification is produced by responding to deliberately ambiguated signifier prompts;

collecting the responses to the deliberately ambiguated signifier prompts from the plurality of individuals; and

analyzing the responses to the deliberately ambiguated signifier prompts and their associated patterns to develop further understanding of the issue.

5. The method of claim 3, wherein the first set of information objects are signified by a first group and the subsequent sets of information objects are signified by subsequent groups.

6. The method of claim 5, further comprising the step of determining set points that indicate a change in opinion requiring further investigation, and creating a notification when the step of comparing the analysis indicates the set point has been met.

4. The method of 3, further comprising the steps:

developing a baseline measure to function as an indicator of the mass opinion related to the issue;

periodically generating subsequent sets of information objects;

signifying the subsequent sets of information objects;

analyzing the signifiers of the second set of information objects consistently with the step of analyzing the signifiers of the first set of information objects; and

comparing the analysis of the signifiers of the second set of information objects with the baseline measure to identify changes in opinion.