USING A CONTENT DATABASE TO INFER CONTEXT INFORMATION FOR ACTIVITIES FROM MESSAGES

• US 20090077027A1
• Filed: 09/18/2007
• Published: 03/19/2009
• Est. Priority Date: 09/18/2007
• Status: Active Grant

• Current Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Ducheneaut, Nicolas, Partridge, Kurt E., Fang, Ji, King, Tracy Holloway
• Granted Patent: US 8,661,046 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/157 using dictionaries or tables
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/109 Time management, e.g. calendars, reminders, meetings or time accounting

Abstract

Some embodiments of the present invention provide a system that infers activity-related context information from a message. Upon receiving the message, the system looks for activity-related keywords in the message, wherein the activity-related keywords are from a content database. If one or more activity-related keywords are found in the message, the system infers message-related context information from the one or more activity-related keywords. Next, the system uses the message-related context information to facilitate recommending an activity to a user.

Claims

1. A method for inferring activity-related context information from a message, comprising:

receiving the message;

looking for activity-related keywords in the message, wherein the activity-related keywords are from a content database;

if one or more activity-related keywords are found in the message, inferring message-related context information from the one or more activity-related keywords; and

using the message-related context information to facilitate recommending an activity to a user.

2. The method of claim 1, wherein using the message-related context information to facilitate recommending an activity to the user involves:

using the message-related context information while constructing an activity model for one or more activities associated with the message-related context information;

using the message-related context information while constructing a user preference model for the user; and

using the activity model and the user preference model to recommend an activity to the user.

3. The method of claim 1, wherein looking for the activity-related keywords in the message involves using the content database for guidance and looking for surrounding text which indicates the presence of the activity-related keywords in the message.

4. The method of claim 3, wherein looking for the surrounding text which indicates the presence of the activity-related keywords in the message involves looking for verbs which indicate specific types of activities in text surrounding prospective activity-related keywords in the message.

5. The method of claim 1, wherein the method further comprises:

identifying location and time indicators in the message; and

using the identified location and time indicators to facilitate recommending an activity to the user.

6. The method of claim 1, wherein using the message-related context information to facilitate recommending the activity to the user involves using the message-related context information and the content database to enhance a keyword search to identify activities of interest for the user.

7. The method of claim 1, wherein the message-related context information includes typed terms.

8. The method of claim 7, wherein typed terms are associated with confidence weights.

9. The method of claim 7, wherein typed terms include one or more of the following:

an activity category;

an activity location;

an activity time;

an uncertainty for the activity time;

a tense associated with the message; and

a user opinion about the activity.

10. The method of claim 1, wherein the content database includes activity-specific content related to one or more of the following activities:

eating at restaurants;

seeing movies and/or live performances;

shopping at physical or online stores;

reading books or online content; and

performing other activities.

11. The method of claim 1, wherein the message is one of:

a text message;

or

an email message.

12. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for inferring activity-related context information from a message, the method comprising:

receiving the message;

looking for activity-related keywords in the message, wherein the activity-related keywords are from a content database;

if one or more activity-related keywords are found in the message, inferring message-related context information from the one or more activity-related keywords; and

using the message-related context information to facilitate recommending an activity to a user.

13. The computer-readable storage medium of claim 12, wherein using the message-related context information to facilitate recommending an activity to the user involves:

using the message-related context information while constructing an activity model for one or more activities associated with the message-related context information;

using the message-related context information while constructing a user preference model for the user; and

using the activity model and the user preference model to recommend an activity to the user.

14. The computer-readable storage medium of claim 12, wherein looking for the activity-related keywords in the message involves using the content database for guidance and looking for surrounding text which indicates the presence of the activity-related keywords in the message.

15. The computer-readable storage medium of claim 14, wherein looking for the surrounding text which indicates the presence of the activity-related keywords in the message involves looking for verbs which indicate specific types of activities in text surrounding prospective activity-related keywords in the message.

16. The computer-readable storage medium of claim 12, wherein the method further comprises:

identifying location and time indicators in the message; and

using the identified location and time indicators to facilitate recommending an activity to the user.

17. The computer-readable storage medium of claim 12, wherein using the message-related context information to facilitate recommending the activity to the user involves using the message-related context information and the content database to enhance a keyword search to identify activities of interest for the user.

18. The computer-readable storage medium of claim 12, wherein the message-related context information includes typed terms.

19. The computer-readable storage medium of claim 18, wherein typed terms are associated with confidence weights.

20. The computer-readable storage medium of claim 18, wherein typed terms include one or more of the following:

an activity category;

an activity location;

an activity time;

an uncertainty for the activity time;

a tense associated with the message; and

a user opinion about the activity.

21. The computer-readable storage medium of claim 12, wherein the content database includes activity-specific content related to one or more of the following activities:

eating at restaurants;

seeing movies and/or live performances;

shopping at physical or online stores;

reading books or online content; and

performing other activities.

22. The computer-readable storage medium of claim 12, wherein the message is one of:

a text message;

or

an email message.

23. An apparatus that infers activity-related context information from a message, comprising:

a parser configured to look for activity-related keywords in the message, wherein the activity-related keywords are from a content database;

an inference mechanism, wherein if one or more activity-related keywords are found in the message, the inference mechanism is configured to infer message-related context information from the one or more activity-related keywords; and

a recommendation mechanism configured to use the message-related context information to facilitate recommending an activity to a user.

24. The apparatus of claim 23, wherein while using the message-related context information to facilitate recommending an activity to the user, the recommendation mechanism is configured to:

use the message-related context information while constructing an activity model for one or more activities associated with the message-related context information;

use the message-related context information while constructing a user preference model for the user; and

use the activity model and the user preference model to recommend an activity to the user.

25. The apparatus of claim 23, wherein while looking for the activity-related keywords in the message, the parser is configured to look for surrounding text which indicates the presence of the activity-related keywords in the message.