Method and apparatus for iterative computer-mediated collaborative synthesis and analysis

• US 9,704,128 B2
• Filed: 02/08/2007
• Issued: 07/11/2017
• Est. Priority Date: 09/12/2000
• Status: Expired due to Fees

• Current Assignee: SRI International, Inc.
• Original Assignee: SRI International, Inc.
• Inventors: Lowrance, John D., Boyce, Thomas A.
• Primary Examiner(s): Koneru, Sujay
• Application Number:
  US11/672,930
• Publication Number:
  US 20070226296A1
• Time in Patent Office: 3,806 Days
• Field of Search: 715751
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

A method and apparatus for iterative computer-mediated collaborative synthesis and analysis synthesizes a first focus topic in accordance with ideas collected from a plurality of cooperating users. The first focus topic triggers an analysis of that focus topic. The conclusions of this analysis indicate shortcomings in the first focus topic and trigger a further synthesis of the first focus topic. The further synthesis results trigger further analysis, and so on, on an iterative basis. The cooperating users follow a process template comprises of a scripted series of synthesis and analysis activities. Facilitation support is provided to the cooperating users to assist the cooperating users in accomplishing each activity in sequence. In further embodiments, a second focus topic is synthesized in response to the conclusion implied by the analysis of the first focus topic, and an analysis of the second focus topic is triggered.

Claims

1. A computer-implemented method for synthesizing and analyzing user input in a collaborative work session, the method comprising:

monitoring a plurality of inputs submitted by a group of users in the collaborative work session, wherein at least some of the plurality of inputs include natural language content;

algorithmically analyzing the natural language content in real time in order to parse a plurality of ideas from the plurality of inputs;

algorithmically identifying similarities among the plurality of ideas;

clustering the plurality of ideas into a set of clusters based on the similarities; and

presenting the clusters to the group of users during the collaborative work session,

wherein the algorithmically analyzing, the algorithmically identifying, and the clustering are each performed at least in part using a processor, and

wherein at least one user of the group of users is a synthetic participant that is independent from a moderator for the collaborative work session.

2. The computer-implemented method of claim 1, wherein the synthetic participant simulates an expert in a given field.

3. The computer-implemented method of claim 1, wherein the algorithmically analyzing and the algorithmically identifying are performed by the moderator who is a synthetic, non-human moderator.

4. The computer-implemented method of claim 1, wherein the algorithmically analyzing is performed using natural language processing techniques.

5. The computer-implemented method of claim 4, wherein the natural language processing techniques include generating canonical representations of the plurality of ideas.

6. The computer-implemented method of claim 5, wherein canonical representations comprise trees of words mapped to a lexical system.

7. The computer-implemented method of claim 1, wherein the algorithmically identifying is performed using pattern recognition techniques.

8. The computer-implemented method of claim 7, wherein the pattern recognition techniques identify similarities between a current collaborative work session and a previous, stored collaborative work session.

9. The computer-implemented method of claim 8, wherein the similarities are quantified using a graph edit distance.

10. The computer-implemented method of claim 1, wherein the clustering comprises:

filtering those of the plurality of ideas that are duplicative.

11. The computer-implemented method of claim 1, wherein the algorithmically identifying comprises:

assessing a thematic closeness of a subset of the plurality of ideas.

12. The computer-implemented method of claim 1, wherein the clustering is performed in part with assistance from the group of users.

13. The computer-implemented method of claim 12, further comprising:

forwarding the plurality of inputs to the group of users;

receiving initial clusters of the plurality of inputs from the group of users; and

incorporating at least a portion of at least one of the initial clusters of the plurality of inputs into the set of clusters.

14. The computer-implemented method of claim 1, wherein the algorithmically analyzing comprises:

algorithmically identifying a known bias in the natural language content.

15. The computer-implemented method of claim 1, further comprising:

automatically formulating a question that is relevant to the natural language content; and

posing the question to the group of users.

16. A computer readable storage device containing an executable program for synthesizing and analyzing user input in a collaborative work session, where the program performs steps of:

monitoring a plurality of inputs submitted by a group of users in the collaborative work session, wherein at least some of the plurality of inputs include natural language content;

algorithmically analyzing the natural language content in real time in order to parse a plurality of ideas from the plurality of inputs;

algorithmically identifying similarities among the plurality of ideas;

clustering the plurality of ideas into a set of clusters based on the similarities; and

presenting the set of clusters to the group of users during the collaborative work session,

wherein at least one user of the group of users is a synthetic participant that is independent from a moderator for the collaborative work session.

17. The computer readable storage device of claim 16, wherein the synthetic participant simulates an expert in a given field.

18. An apparatus for synthesizing and analyzing user input in a collaborative work session, the apparatus comprising:

means for monitoring a plurality of inputs submitted by a group of users in the collaborative work session, wherein at least some of the plurality of inputs include natural language content;

means for algorithmically analyzing the natural language content in real time in order to parse a plurality of ideas from the plurality of inputs;

means for algorithmically identifying similarities among the plurality of ideas;

means for clustering the plurality of ideas into a set of clusters based on the similarities; and

means for presenting the set of clusters to the group of users during the collaborative work session,

wherein at least one user of the group of users is a synthetic participant that is independent from a collaborative work session moderator.