User interaction management using an ongoing estimate of user interaction skills

• US 7,539,654 B2
• Filed: 01/21/2005
• Issued: 05/26/2009
• Est. Priority Date: 01/21/2005
• Status: Active Grant

• Current Assignee: Maplebear Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Ramaswamy, Ganesh N., Zilca, Ran D.
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US11/041,134
• Publication Number:
  US 20060167837A1
• Time in Patent Office: 1,586 Days
• Field of Search: 706/20, 706/45
• US Class Current: 706/20
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance

Abstract

User interaction management techniques are disclosed. In a first aspect of the invention, an automated technique for managing interaction between a user and a system includes the following steps/operations. One or more behaviors associated with a user are observed as the user interacts with the system. A skill level of a user accessing the system is determined. Then, a user interaction profile is modified based on the determined skill level of the user. In a second aspect of the invention, an automated technique for generating a skill level classifier for use in classifying users interacting with a system includes the following steps/operations. Input from multiple users having various skill levels is obtained. Then, a classifier is trained using the obtained input from the multiple users such that the classifier automatically detects in which category of interaction skills a subsequent user belongs.

Claims

1. An automated method of managing a user interface between a user and a system, wherein the user interface and the system are implemented via a computer, the method comprising the computer performing the steps of:

observing one or more behaviors associated with a user as the user interacts with the system;

automatically determining a skill level of the user accessing the system in real time based on the observed one or more behaviors;

modifying a user interaction profile based on the determined skill level of the user;

switching the user interface as the user interacts with the system to one of a plurality of pre-trained interaction models for a pre-defined skill level in accordance with the user interaction profile; and

presenting the switched user interface to the user.

2. The method of claim 1, wherein the skill level determination step further comprises classifying input obtained from the user based on pre-trained skill level models.

3. The method of claim 2, wherein the skill level models are previously trained from input obtained from multiple users having various skill levels.

4. The method of claim 2, wherein the classifying step further comprises extracting one or more features from the obtained user input.

5. The method of claim 1, wherein the interaction profile modifying step further comprises selecting a human-computer interface to be presented to the user from among a plurality of human-computer interfaces.

6. The method of claim 5, wherein a human-computer interface is one of a single mode interface or a multimodal interface.

7. The method of claim 1, wherein user interaction with the system is conversational.

8. The method of claim 1, wherein user interaction with the system is performed using at least one of a keyboard, a mouse and a monitor.

9. The method of claim 1, wherein user interaction with the system is performed using gesturing and pointing.

10. The method of claim 1, wherein user interaction with the system is performed using electroencephalogram input.

11. The method of claim 1, wherein user interaction with the system is performed using one or more biometric sensors.

12. An automated method of generating a skill level classifier for use in classifying users interacting with a system via a computer, the method comprising the computer performing the steps of:

obtaining input from multiple users having various skill levels;

training a classifier using the obtained input from the multiple users such that the classifier automatically detects in which category of interaction skills a subsequent user belongs;

switching a type of interaction between the subsequent user and the system to one of a plurality of pre-trained interaction models for a pre-defined skill level in accordance with the classifier; and

presenting the switched type of interaction to the subsequent user.

13. The method of claim 12, wherein the classifier comprises individual models for interaction skill categories, each model being trained from labeled user data.

14. The method of claim 12, wherein the classifier comprises one or more artificial neural networks.

15. The method of claim 12, wherein the classifier comprises a support vector machine.

16. The method of claim 12, wherein the classifier comprises a pattern recognition method.

17. Apparatus for managing a user interface between a user and a system, wherein the user interface and the system are implemented via a computer, comprising:

a memory; and

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

observe one or more behaviors associated with a user as the user interacts with the system;

automatically determine a skill level of the user accessing the system in real time based on the observed one or more behaviors;

modify a user interaction profile based on the determined skill level of the user;

switch the user interface as the user interacts with the system to one of a plurality of pre-trained interaction models for a pre-defined skill level in accordance with the user interaction profile; and

present the switched user interface to the user.

18. Apparatus for generating a skill level classifier for use in classifying users interacting with a system via a computer, comprising:

a memory; and

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

obtain input from multiple users having various skill levels;

train a classifier using the obtained input from the multiple users such that the classifier automatically detects in which category of interaction skills a subsequent user belongs;

switch a type of interaction between the subsequent user and the system to one of a plurality of pre-trained interaction models for a pre-defined skill level in accordance with the classifier; and

present the switched type of interaction to the subsequent user.

19. An article of manufacture for managing a user interface between a user and a system, wherein the user interface and the system are implemented via a computer, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

observing one or more behaviors associated with a user as the user interacts with the system;

automatically determining a skill level of the user accessing the system in real time based on the observed one or more behaviors;

modifying a user interaction profile based on the determined skill level of the user;

switching the user interface as the user interacts with the system to one of a plurality of pre-trained interaction models for a pre-defined skill level in accordance with the user interaction profile; and

presenting the switched user interface to the user.

20. An article of manufacture for generating a skill level classifier for use in classifying users interacting with a system via a computer, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

obtaining input from multiple users having various skill levels;

training a classifier using the obtained input from the multiple users such that the classifier automatically detects in which category of interaction skills a subsequent user belongs;

switching a type of interaction between the subsequent user and the system to one of a plurality of pre-trained interaction models for a pre-defined skill level in accordance with the classifier; and

presenting the switched type of interaction to the sub subsequent user.

21. A method of providing a service for managing a user interface between a user and a system, wherein the user interface and the system are implemented via a computer, the method comprising the computer performing the step of:

a service provider enabling the steps of;

observing one or more behaviors associated with a user as the user interacts with the system;

automatically determining a skill level of the user accessing the system in real time based on the observed one or more behaviors;

causing modification of a user interaction profile based on the determined skill level of the user;

switching the user interface as the user interacts with the system to one of a plurality of pre-trained interaction models for a pre-defined skill level in accordance with the user interaction profile; and

presenting the switched user interface to the user.

22. A method of providing a service for generating a skill level classifier for use in classifying users interacting with a system via a computer, comprising the step of:

a service provider enabling the steps of;

obtaining input from multiple users having various skill levels;

training a classifier using the obtained input from the multiple users such that the classifier automatically detects in which category of interaction skills a subsequent user belongs;

switching a type of interaction between the subsequent user and the system to one of a plurality of pre-trained interaction models for a pre-defined skill level in accordance with the classifier; and

presenting the switched type of interaction to the subsequent user.