Integration of a computer-based message priority system with mobile electronic devices

• US 7,444,384 B2
• Filed: 03/08/2004
• Issued: 10/28/2008
• Est. Priority Date: 07/30/1999
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Horvitz, Eric
• Primary Examiner(s): Nguyen; Thu Ha T
• Application Number:
  US10/795,695
• Publication Number:
  US 20040172457A1
• Time in Patent Office: 1,695 Days
• Field of Search: 709206-207, 709/234, 709/238, 370/265, 370/260, 715733-759
• US Class Current: 709/207
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: H04L 51/212 using filtering or selective blocking
• CPC Class Codes: H04L 51/224 providing notification on incoming messages, e.g. pushed notifications of received messages
• CPC Class Codes: H04L 51/226 Delivery according to priorities
• CPC Class Codes: H04L 51/234 for tracking messages
• CPC Class Codes: H04W 4/025 using location based information parameters
• CPC Class Codes: H04W 4/12 Messaging; Mailboxes; Announcements

Abstract

Methods for integrating mobile electronic devices with computational methods for assigning priorities to documents are disclosed. In one embodiment, a computer-implemented method first receives a new document such as an electronic mail message. The method assigns a priority to the document, based on a text classifier such as a Bayesian classifier or a support-vector machine classifier. The method then alerts a user on an electronic device, such as a pager or a cellular phone, based on an alert criteria that can be made sensitive to information about the location, inferred task, and focus of attention of the user. Such information can be inferred under uncertainty or can be accessed directly from online information sources. One embodiment makes use of information from an online calendar to control the criteria used to make decisions about relaying information to a mobile device.

Claims

1. A computer-implemented method comprising:

generating a priority of received text based on a trainable text classifier that classifies the priority of the received text based at least in part on analyzing the received text and inferred or determined user state;

explicitly training the trainable text classifier to determine the priority of the received text to facilitate generating the priority of the received text, the trainable text classifier is explicitly trained using a set of time-critical texts and a set of non-time-critical texts to facilitate training the trainable text classifier to discriminate between time-critical text and non-time-critical text;

implicitly training the trainable text classifier to determine the priority of the received text and updating the trainable text classifier in real time to continually refine the trainable text classifier to facilitate generating the priority of the received text; and

alerting a user on an electronic device based at least in part on an alert criteria upon determining that the priority of the received text is greater than a predetermined threshold.

2. The method of claim 1, the alert criteria is based on information regarding at least one of location, inferred task, or focus of attention of the user.

3. The method of claim 2, the information is inferred under uncertainty.

4. The method of claim 2, the information is accessed directly from online information sources.

5. The method of claim 4, the online information sources comprises an online calendar.

6. The method of claim 1, further comprising:

receiving text comprising receiving an email.

7. The method of claim 1, alerting a user on an electronic device comprises alerting the user on the electronic device comprising a pager.

8. The method of claim 1, alerting a user on an electronic device comprises alerting the user on the electronic device comprising a cellular phone.

9. The method of claim 1, alerting a user on an electronic device based at least in part on an alert criteria comprises:

determining whether the priority of the received text is greater than a predetermined threshold;

determining whether the user has been away for more than a predetermined amount of time; and

upon determining that the priority of the received text is greater than the predetermined threshold and that the user has been away for more than the predetermined amount of time, alerting the user.

10. The method of claim 1, alerting a user on an electronic device based at least in part on an alert criteria comprises:

determining whether a current time is within a predetermined range of times; and

upon determining that the current time is within the predetermined range of times, alerting the user.

11. The method of claim 1, alerting a user on an electronic device based at least in part on an alert criteria comprises:

determining whether the user is in a meeting;

upon determining that the user is in a meeting, determining whether the priority of the received text is greater than a predetermined meeting threshold; and

upon determining that the priority of the received text is greater than the predetermined meeting threshold, alerting the user.

12. A computer-implemented method comprising:

training a text classifier comprising at least one of a Bayesian classifier or a support-vector machine classifier, or a combination thereof, the training of the text classifier comprising;

explicitly training the text classifier to determine a priority of received text to facilitate generating the priority of received text, the text classifier is explicitly trained using a set of time-critical texts and a set of non-time-critical texts to facilitate training the text classifier to discriminate between time-critical text and non-time-critical text, and

implicitly training the text classifier to determine the priority of received text based in part on observed user activity with regard to previously received text and updating the text classifier in real time to continually refine the text classifier to facilitate generating the priority of received text;

receiving a text comprising an email;

generating the priority of the received text based on the text classifier that classifies the priority of the received text based at least in part on analyzing the received text, and inferred or determined user state; and

alerting a user on an electronic device based at least in part on an alert criteria, comprising;

determining whether the priority of the received text is greater than a predetermined threshold; and

alerting the user upon determining that the priority of the received text is greater than the predetermined threshold.

13. The method of claim 12, alerting a user on an electronic device comprises alerting the user on the electronic device comprising at least one of a pager or a cellular phone, or a combination thereof.

14. The method of claim 12, alerting a user on an electronic device based at least in part on an alert criteria comprises:

determining whether the priority of the received text is greater than a predetermined threshold;

determining whether the user has been away for more than a predetermined amount of time; and

upon determining that the priority of the received text is greater than the predetermined threshold and that the user has been away for more than the predetermined amount of time, alerting the user.

15. The method of claim 12, alerting a user on an electronic device based at least in part on an alert criteria comprises:

determining whether the priority of the received text is greater than a predetermined threshold;

determining whether the user has been away for more than a predetermined amount of time;

determining whether a current time is within a predetermined range of times; and

upon determining that the priority of the received text is greater than the predetermined threshold, that the user has been away for more than the predetermined amount of time, and that the current time is within the predetermined range of times, alerting the user.

16. The method of claim 12, alerting a user on an electronic device based at least in part on an alert criteria comprises:

determining whether the user is in a meeting;

upon determining that the user is in a meeting, determining whether the priority of the received text is greater than a predetermined meeting threshold, and

upon determining that the priority of the received text is greater than the predetermined meeting threshold, alerting the user.

17. A machine-readable medium having instructions stored thereon for execution by a processor to perform a method comprising:

explicitly training a text classifier to determine a priority of received text to facilitate generating the priority of the received text, the text classifier is explicitly trained using a set of time-critical texts and a set of non-time-critical texts to facilitate training the text classifier to discriminate between time-critical text and non-time-critical text;

implicitly training the text classifier to determine the priority of the received text and updating the text classifier in real time to continually refine the text classifier to facilitate generating the priority of the received text;

receiving a text;

generating the priority of the received text based on the text classifier that analyzes the received text and a focus of attention of a user; and

alerting the user on an electronic device based at least in part on an alert criteria, comprising;

determining whether the priority of the received text is greater than a predetermined threshold; and

alerting the user upon determining that the priority of the received text is greater than the predetermined threshold.

18. The medium of claim 17, receiving a text comprises receiving an email.

19. The medium of claim 17, alerting the user on an electronic device comprises alerting the user on the electronic device comprising a pager.

20. The medium of claim 17, alerting the user on an electronic device comprises alerting the user on the electronic device comprising a cellular phone.

21. The medium of claim 17, alerting the user on an electronic device based at least in part on an alert criteria comprises:

determining whether the priority of the received text is greater than the predetermined threshold;

determining whether the user has been away for more than a predetermined amount of time; and

upon determining that the priority of the received text is greater than the predetermined threshold and that the user has been away for more than the predetermined amount of time, alerting the user.

22. The medium of claim 17, alerting the user on an electronic device based at least in part on an alert criteria comprises:

determining whether a current time is within a predetermined range of times; and

upon determining that the current time is within the predetermined range of times, alerting the user.

23. The medium of claim 17, alerting the user on an electronic device based at least in part on an alert criteria comprises:

determining whether the user is in a meeting;

upon determining that the user is in a meeting, determining whether the priority of the received text is greater than a predetermined meeting threshold; and

upon determining that the priority of the received text is greater than the predetermined meeting threshold, alerting the user.

24. A computer-implemented system stored on a computer-readable medium comprising:

a trainable text classifier that generates a priority of received text based at least in part on analyzing the received text and user presence information, the trainable text classifier is;

explicitly trained to determine the priority of the received text to facilitate generation of the priority of received text, the trainable text classifier is explicitly trained using a set of time-critical texts and a set of non-time-critical texts to facilitate training the trainable text classifier to discriminate between time-critical text and non-time-critical text, and

implicitly trained to determine the priority of the received text and updated in real time to continually refine the trainable text classifier to facilitate generation of the priority of the received text; and

an alert mechanism that alerts a user on an electronic device based at least in part on an alert criteria that comprises a determination of whether the priority of the received text is greater than a predetermined threshold.

25. The system of claim 24, the trainable text classifier classifies text associated with e-mail.

26. The system of claim 24, the trainable text classifier comprises a Bayesian text classifier.

27. The system of claim 24, the trainable text classifier comprises a support-vector-machine classifier.

28. The system of claim 24, the electronic device comprises at least one of a pager or a cellular phone, or a combination thereof.

29. The system of claim 24, the alert criteria comprises a determination of whether the priority of the received text is greater than a predetermined threshold and whether the user has been away for more than a predetermined amount of time.

30. The system of claim 24, the alert criteria comprises a determination of whether a current time is within a predetermined range of times.

31. The system of claim 24, the alert criteria comprises a determination of whether the user is in a meeting and whether the priority of the received text is greater than a predetermined meeting threshold.

32. The system of claim 24, at least one of the alert mechanism, or the trainable text classifier comprise a computer program executed by a processor from a computer-readable medium.