PERSONAL LONG-TERM AGENT FOR PROVIDING MULTIPLE SUPPORTIVE SERVICES

• US 20130006904A1
• Filed: 06/30/2011
• Published: 01/03/2013
• Est. Priority Date: 06/30/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Horvitz, Eric, Paparizos, Stelios, Barga, Roger, Burger, Doug, Gupta, Vinay
• Granted Patent: US 9,317,834 B2
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G01C 21/3679 Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities G01C21/3611 takes precedence
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A long-term personal agent program, executable as network service and/or on one or more user computing devices and related method for identifying opportunities and making recommendations on behalf of one or more users, are disclosed herein. In one example, the personal agent program includes a monitoring engine configured to monitor and interpret a user'"'"'s activities over time with a plurality of sensing and logging methodologies according to user authorization, the use of statistical methods for learning to understand a user'"'"'s goals and behavioral patterns from data, and the use of procedures for computing the expected value of information guiding sensing and logging in different contexts. The personal agent further may include a recommendation methodology configured to make suggestions and to take actions on behalf of the user, in the present moment as well as for future times, based on inferences about user goals and opportunities in the world.

Claims

1. A personal agent program executable on a user computing device for retrieving recommendations on behalf of a user, comprising:

a setup module configured to receive a user authorization to monitor user activity across a plurality of computer programs used by the user on the user computing device and/or one or more other user computing devices, and one or more user recommendation preferences indicating product or service recommendations that the user would like the personal agent program to retrieve from a recommendation server;

a monitoring engine configured to monitor the user activity with the plurality of computer programs according to the user authorization, the user activity including a detected current location of the user, the monitoring engine being configured to learn a behavioral pattern from the user activity; and

a recommendation engine configured to;

make an inference that a trigger condition for the one or more user recommendation preferences will arise, based on the detected current location of the user, the behavioral pattern of the user, and one or more contextual factors;

send a request to the recommendation server for a recommendation for a target product or service according to the one or more user recommendation preferences;

receive the recommendation from the recommendation server; and

display the recommendation on a display associated with the user computing device.

2. The personal agent program of claim 1, wherein the setup module is further configured to receive a user privacy setting indicating a category of data that the user authorizes the personal agent program to examine.

3. The personal agent program of claim 2, wherein the user privacy setting specifies an examine-only category of the user activity that the user authorizes the personal agent program to examine from the plurality of computer programs but not share externally.

4. The personal agent program of claim 2, wherein the user privacy setting;

specifies a sharing-authorized category of the user activity that the user authorizes the personal agent program to send to the recommendation server with the request for the recommendation.

5. The personal agent program of claim 1, wherein:

the monitoring engine is configured to;

determine that the user and a friend are traveling in directional trajectories that will intersect at an intersecting location; and

determine whether the user and the friend are available; and

the target service is located within a threshold distance of the intersecting location.

6. The personal agent program of claim 1, wherein the plurality of programs includes an email program, a calendar program, a telephone/messaging program, a mobile device location tracking program, a browser program, a map program, or a social networking program, and the one or more contextual factors includes a date, a day of a week, a time of day, or a time period that the user computing device has been in the detected current location.

7. The personal agent program of claim 1, wherein the monitoring engine is further configured to dynamically monitor the user activity by selectively activating or accessing at least one of the plurality of computer programs based on computing an expected value of information that may be gleaned from the user activity.

8. The personal agent program of claim 1, wherein the monitoring engine is configured to learn a behavioral pattern of the user by receiving aggregate behavioral patterns from the recommendation server, and examining the user activity in the computer programs for user activity that matches the aggregate behavioral patterns within a threshold degree.

9. The personal agent program of claim 1, wherein the monitoring engine is configured to create an additional user recommendation preference based on the behavioral pattern from the user activity.

10. The personal agent program of claim 1, wherein the trigger condition comprises a future location of the user.

11. A method for retrieving recommendations on behalf of a user, comprising

receiving a user authorization to monitor user activity across a plurality of computer programs used by the user on a user computing device and one or more other user computing devices;

receiving one or more user recommendation preferences indicating product or service recommendations that the user would like to receive from a recommendation server;

monitoring the user activity with the plurality of computer programs according to the user authorization, the user activity including a detected current location of the user;

learning a behavioral pattern from the user activity;

making an inference that;

a trigger condition for the one or more user recommendation preferences will arise, based on the detected current location of the user, the behavioral pattern of the user, and one or more contextual factors;

sending a request to the recommendation server for a recommendation for a target product or service according to the one or more user recommendation preferences;

receiving the recommendation from the recommendation server; and

displaying the recommendation on a display associated with the user computing device.

12. The method of claim 11, further comprising receiving a user privacy setting indicating a category of data that the user authorizes the personal agent program to examine.

13. The method of claim 12, wherein the user privacy setting specifies an examine-only category of the user activity that the user authorizes the personal agent program to examine from the plurality of computer programs but not share externally.

14. The method of claim 12, wherein the user privacy setting specifies a sharing-authorized category of the user activity that the user authorizes the personal agent program to send to the recommendation server with the request for the recommendation.

15. The method of claim 11, wherein the user computing device is a location-aware mobile computing device.

16. The method of claim 11, wherein the plurality of programs includes an email program, a calendar program, a telephone/messaging program, a mobile device location tracking program, a browser program, a map program, or a social networking program, and the one or more contextual factors includes a date, a day of a week, a time of day, or a time period that the user computing device has been in the detected current location.

17. The method of claim 11, wherein the monitoring the user activity with the plurality of computer programs further comprises selectively activating or accessing at least one of the plurality of computer programs based on computing an expected value of information that may be gleaned from the user activity.

18. The method of claim 11, learning a behavioral pattern includes receiving aggregate behavioral patterns from the recommendation server, and examining the user activity in the computer programs for user activity that matches the aggregate behavioral patterns within a threshold degree.

19. The method of claim 11, further comprising creating an additional user preference based on the behavioral pattern from the user activity.

20. A personal agent program executable on a user computing device, comprising:

a setup module configured to;

receive a user authorization to monitor user activity across a plurality of computer programs used by the user on the user computing device and one or more other user computing devices, and one or more user recommendation preferences indicating product;

or service recommendations that the user would like the personal agent program to retrieve from a recommendation server;

a monitoring engine configured to monitor the user activity with the plurality of computer programs according to the user authorization, the monitoring engine being configured to learn a behavioral pattern from the user activity; and

a recommendation engine configured to;

make an inference that a trigger condition for the one or more user recommendation preferences will arise, based on the behavioral pattern of the user and one or more contextual factors;

send a request to the recommendation server for a recommendation for a target product or service according to the one or more user recommendation preferences;

receive the recommendation from the recommendation server, the recommendation generated according to the one or more user recommendation preferences and/or the behavioral pattern of the user;

take an action on behalf of the user with respect to an opportunity occurring in the future; and

display the recommendation and information related to the opportunity on a display associated with the user computing device.