Selection of graphical user interface agents by cluster analysis

• US 8,019,698 B1
• Filed: 12/17/1996
• Issued: 09/13/2011
• Est. Priority Date: 12/17/1996
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Wilson, Leslie Robert, Dryer, David Christopher
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US08/767,928
• Time in Patent Office: 5,383 Days
• Field of Search: 379/265, 379/266, 379/265.06, 706/11, 706/45, 705/42, 709/202
• US Class Current: 706/11
• CPC Class Codes: G06F 9/451 Execution arrangements for user interfaces
• CPC Class Codes: G06F 9/453 Help systems

Abstract

Intelligent computer implemented agents are associated with computer user interface tasks by dividing the tasks into statistically distinct clusters based on sampled user assessments. The assessments collect data on multiple user variables. Multivariate statistical analysis is used to divide the tasks into distinct clusters. The clusters are validated using univariate analysis on each of the measured variables. Intelligent agents are associated based on the measured variables to ensure that agents are effective. The objective assessment and association avoids costly creation and overhead of agents applied where not effective.

Claims

1. A computer implemented method of providing a graphical user interface agent to a user performing a task in a computer system comprising a processor, an operating system, memory, and a plurality of intelligent agents, comprising the steps of:

receiving data assessing at least two user assessment variables for each of a plurality of tasks;

performing multivariate analysis on said data to derive from said plurality of tasks at least as many mutually exclusive clusters of tasks as there are intelligent agents to assign;

storing an association linking each of said intelligent agents with one of said mutually exclusive clusters; and

upon user selection of a task, displaying an intelligent agent associated with a cluster containing the task selected by the user.

2. The method of claim 1, further comprising the step of:

transforming said multivariate data to eliminate individual respondent differences.

3. The method of claim 2 further comprising the step of:

performing univariate analysis on each of said assessment variables to validate cluster derivation.

4. The method of claim 1, wherein said intelligent agents include a first “

wizard”

agent applicable to infrequent, difficult tasks and a second “

guide”

applicable to frequent tasks, and wherein the multivariate analysis step comprises the steps of;

separating said tasks into two groups based on a frequency variable;

performing multivariate statistical analysis on said two groups to determine whether the groupings are statistically distinct;

if not distinct, creating an additional group and performing said multivariate analysis again until a statistically distinct set of groups is found.

5. A system for providing a graphical user interface agent to a user performing a task on a computer system comprising a processor means, storage means and input/output means, and a plurality of intelligent agents, the system comprising:

means for receiving data assessing at least two user assessment variables for each of a plurality of tasks;

means for performing multivariate statistical analysis on said data to determine at least as many statistically distinct groups of tasks as there are intelligent agents to assign;

means for storing in said storage means an association linking each of said intelligent agents with one of said statistically distinct groups; and

means, operable upon user selection of a task, for displaying an intelligent agent associated with a group of tasks containing the task selected by the user.

6. The system of claim 5, further comprising:

means for transforming said multivariate data to eliminate individual respondent differences; and

means for performing univariate analyses on each of said assessment variables to validate cluster groupings.

7. The system of claim 5, wherein said intelligent agents include a first “

wizard”

agent applicable to infrequent, difficult tasks and a second “

guide”

agent applicable to frequent tasks, and wherein the means for performing multivariate analysis comprises;

means for separating said tasks into two groups based on a frequency variable;

means for performing multivariate statistical analysis on said two groups top determine whether the groupings are statistically distinct; and

if not distinct, means for creating an additional group and means for performing said multivariate analysis again until a statistically distinct set of groups is found.

8. A computer program product including a computer readable medium having computer program logic recorded thereon for use in a data processing system for providing a graphical user interface agent to a user performing a task comprising:

means for receiving data assessing at least two user assessment variables for each of said tasks;

means for performing multivariate statistical analysis on said data to determine at least as many statistically distinct clusters of tasks as there are intelligent agents to assign;

means for storing in said storage means an association linking each of said intelligent agents with one of said statistically distinct clusters; and

means for displaying an intelligent agent using a stored association when a user of said data processing system executes a task from one of said statistically distinct clusters.

9. The computer program product of claim 8, further comprising:

means for transforming said multivariate data to eliminate individual respondent differences; and

means for performing univariate analyses on each of said assessment variables to validate cluster groupings.