Context-Aware, Adaptive Approach to Information Selection for Interactive Information Analysis

• US 20080221846A1
• Filed: 05/22/2008
• Published: 09/11/2008
• Est. Priority Date: 06/27/2006
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: International Business Machines Corporation
• Inventors: Zhou, Michelle X., Aggarwal, Vikram, Wen, Zhen
• Granted Patent: US 8,001,119 B2
• Time in Patent Office: Days
• US Class Current: 703/2
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

Improved information analysis techniques are disclosed. For example, a computer-implemented method of automatically assisting an analyst in a current information analysis task includes the following steps. An analytic context is modeled in a user-system cooperative manner, wherein the analytic context is a structure representative of user analytic actions and relationships associated therewith. At least a portion of the user-system cooperatively-modeled analytic context structure is utilized to adaptively gather information relevant to a current information analysis task.

Claims

1. A computer-implemented method of automatically assisting an analyst in a current information analysis task, comprising the steps of:

modeling an analytic context, in a user-system cooperative manner, wherein the analytic context is a structure representative of user analytic actions and relationships associated therewith; and

utilizing at least a portion of the user-system cooperatively-modeled analytic context structure to adaptively gather information relevant to a current information analysis task.

2. The method of claim 1, wherein the step of user-system cooperative modeling of an analytic context further comprises modeling the analytic context as a graph of user analytic actions.

3. The method of claim 2, wherein the step of modeling the analytic context as a graph of user analytic actions further comprises the step of modeling a user analytic action for a particular investigative target as a node of the analytic action graph.

4. The method of claim 3, wherein the step of modeling a user analytic action for a particular investigative target as a node of the analytic action graph further comprises the step of persisting user queries on investigative targets, gathered information and interactions with the results related to information gathering.

5. The method of claim 2, wherein the step of modeling the analytic context as a graph of user analytic actions further comprises the step of cooperatively modeling the relationships of user analytic actions in accordance with the graph.

6. The method of claim 5, wherein the step of cooperatively modeling the relationships of user analytic actions further comprises the step of modeling logical relationships between user analytic actions in accordance with the graph.

7. The method of claim 5, wherein the step of cooperatively modeling the relationships of user analytic actions further comprises the step of modeling relationships between user analytic actions beyond logical relationships via user annotations in accordance with the graph.

8. The method of claim 2, wherein the step of modeling the analytic context as a graph of user analytic actions further comprises generating a user interface that allows the analyst to one of view and modify the analytic action graph during analysis.

9. The method of claim 2, wherein the step of adaptively gathering information relevant to a current information analysis task further comprises the step of adaptive information selection based on evolving analytic context persisted in the analytic action graph.

10. The method of claim 9, wherein the step of adaptive information selection based on evolving analytic context persisted in the analytic action graph further comprises the step of evaluating information relevance using a context vector that is extracted from the analytic action graph to represent contextual information of interests for each analytic action.

11. The method of claim 9, wherein the step of adaptive information selection based on evolving analytic context persisted in the analytic action graph further comprises the step of re-ranking previously persisted information in the analytic action graph when the analytic context evolves so as to identify previous information relevant to current analysis in non-linear investigations.

12. The method of claim 11, wherein the step of re-ranking previously persisted information further comprises the step of assessing the re-ranking quality and sending appropriate notifications based on the re-ranking quality.

13. The method of claim 9, wherein the step of adaptive information selection based on evolving analytic context persisted in the analytic action graph further comprises permitting an observer to assess the analytic context for information gathering based on the analytic action graph.

14. The method of claim 13, wherein the step of adaptive information selection based on evolving analytic context persisted in the analytic action graph further comprises permitting the observer to recommend one or more changes to the analytic action graph to improve information gathering.

15. The method of claim 13, wherein the observer comprises the analyst or a computer program.

16. Apparatus for automatically assisting an analyst in a current information analysis task, comprising:

a memory; and

at least one processor coupled to the memory and operative to;

(i) model an analytic context, in a user-system cooperative manner, wherein the analytic context is a structure representative of user analytic actions and relationships associated therewith; and

(ii) utilize at least a portion of the user-system cooperatively-modeled analytic context structure to adaptively gather information relevant to a current information analysis task.

17. An article of manufacture for automatically assisting an analyst in a current information analysis task, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

modeling an analytic context, in a user-system cooperative manner, wherein the analytic context is a structure representative of user analytic actions and relationships associated therewith; and

utilizing at least a portion of the user-system cooperatively-modeled analytic context structure to adaptively gather information relevant to a current information analysis task.