Systems and methods for estimating and integrating measures of human cognitive load into the behavior of computational applications and services

• US 7,139,742 B2
• Filed: 02/03/2006
• Issued: 11/21/2006
• Est. Priority Date: 04/20/1999
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Horvitz, Eric J.
• Primary Examiner(s): STARKS, WILBERT L
• Application Number:
  US11/347,616
• Publication Number:
  US 20060184485A1
• Time in Patent Office: 291 Days
• Field of Search: 706/45, 726/23, 370/203
• US Class Current: 706/45
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

The present invention relates to a system and methodology for extending and making more appropriate the interactive decisions made by automated services by taking into consideration estimates of the time required by users for the cognitive processing of problems, visualizations, and content based on several factors, including the competency and familiarity of the user with the output and nature of the sequences of output, the complexity of the output and overall tasks being considered, and the context of the user. The methods allow automated applications to control the rate at which the applications interact with users. Portions of automated services are controlled in view of limited human processor capabilities in design/operation of such services, and/or visualizations/output from the services (e.g., amount of dwell time provided/considered before a next automated sequence is displayed/invoked). Models can be formulated and utilized in conjunction with automated services such as automatically determining and pausing a period of time before a next sequence in a service is enabled or disabled. The models can also be employed to determine multiple dwells for comprehension, as a function of complexity of graphical/conceptual relationships, at different phases of an animation.

Claims

1. A system that provides automated services and scheduling, comprising:

a receiver that acquires a message for analysis;

an analyzer that calculates a probability corresponding to a likelihood that the message has subject matter relevant to a scheduling task; and

a scheduler that determines and implements a scheduling decision based at least in part on the calculated probability.

2. The system of claim 1, the receiver reads at least one of a live message and an archived message.

3. The system of claim 2, the receiver reads at least one of an e-mail, a voicemail, an instant message, and a telephone message.

4. The system of claim 1, the receiver selects the message based on at least one of a currently active window, a currently active message, a currently open message, and a user input.

5. The system of claim 1, the scheduler parses the message and classifies the parsed portions of the message based on at least one attribute of the message.

6. The system of claim 5, the scheduler locates a corresponding time from the message in a calendar, and inserts relevant information from the message into the calendar.

7. The system of claim 1, the scheduling decision is at least one of inaction, action with user approval, and automatic action.

8. A method for automated scheduling, comprising:

receiving a message;

deriving a probability that indicates a likelihood that the message contains subject matter relevant to a scheduling task;

determining a scheduling decision based on the derived probability; and

implementing the scheduling decision.

9. The method of claim 8, further comprising reading at least one of a live message and an archived message.

10. The method of claim 9, further comprising acquiring at least one of an e-mail, a voicemail, an instant message, and a telephone message.

11. The method of claim 8, further comprising selecting the message based on at least one of a currently active window, a currently active message, a currently open message, and a user input.

12. The method of claim 8, further comprising:

parsing the message; and

classifying the parsed portions of the message based on message content.

13. The method of claim 12, further comprising:

locating a time corresponding to the message in a calendar; and

inputting relevant information from the message into the calendar.

14. The method of claim 8, the scheduling decision as indicated by the derived probability is at least one of inaction, action with user approval, and automatic action.

15. A system that facilitates automatic calendar scheduling, comprising:

means for obtaining a message;

means for determining a probability that identifies a likelihood that a scheduling inquiry will be desired based on the message;

means for selecting a scheduling decision based at least in part on the determined probability; and

means for implementing the scheduling decision.

16. The system of claim 15, further comprising means for interpreting at least one of a live message and an archived message.

17. The system of claim 16, further comprising means for analyzing at least one of an e-mail, a voicemail, an instant message, and a telephone message.

18. The system of claim 15, further comprising means for properly selecting the message based on at least one of a currently active window, a currently active message, a currently open message, and a user input.

19. The system of claim 15, further comprising:

means for parsing the message;

means for classifying the parsed portions of the message based on at least one attribute of the message;

means for identifying a proper appointment time from the message;

means for locating the proper appointment time in a calendar; and

means for inserting applicable information from the message into the proper appointment time in the calendar.

20. The system of claim 15, the scheduling decision as identified by the determined probability is at least one of inaction, action with user approval, and automatic action.