Combining predictive models of forgetting, relevance, and cost of interruption to guide automated reminding

• US 8,195,584 B2
• Filed: 06/29/2011
• Issued: 06/05/2012
• Est. Priority Date: 06/27/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Horvitz, Eric J., Kamar, Semiha Ece
• Primary Examiner(s): Starks, Wilbert L
• Application Number:
  US13/172,405
• Publication Number:
  US 20110258153A1
• Time in Patent Office: 342 Days
• Field of Search: 706/12, 706/45
• US Class Current: 706/12
• CPC Class Codes: G06Q 10/109 Time management, e.g. calendars, reminders, meetings or time accounting

Abstract

The claimed matter provides systems and/or techniques that develop or use predictive models of human forgetting to effectuate automated reminding. The system includes the use of predictive models that infer the probability that aspects of items will be forgotten, models that evaluate the relevance of recalling aspects of items in different settings, based on contextual information related to user attributes associated with the items, and models of the context-sensitive cost of interrupting users with reminders. The system can combine the probability of users forgetting aspects of an item with an assessed cost of forgetting those aspects to ascertain expected costs for not being reminded about events, compare expected costs for not being reminded with expected costs for interrupting users, and based on comparisons between expected costs for being reminded and expected costs for interrupting users regarding events, generate and deliver reminder notifications to users about items.

Claims

1. A system comprising:

a memory jogger component configured to utilize a predictive model of human memory to effectuate automated reminding a user of an event;

a priority predictor configured to classify the event according to priority based at least in part on attributes associated with the event;

a memory predictor configured to predict whether or not the user remembers the event; and

the memory jogger component further configured to automatically send a reminder to the user of the event based on the priority of the event and an ability of the user to remember the event.

2. The system of claim 1, wherein the event includes at least one of a task, a meeting, an appointment, a sporting event, a concert, or a recital.

3. The system of claim 1, wherein:

classifying the event indicates a high, a medium, or a low priority; and

automatically sending the reminder based on the classifying the event as a high or a medium priority.

4. The system of claim 1, wherein the automatically sending the reminder includes determining an appropriate time to send a notification to the user.

5. The system of claim 1, further comprising:

a details predictor configured to predict whether or not the user remembers details regarding the event; and

the memory jogger component further configured to determine an amount of information about the event to send to the user based on the ability of the user to remember the event or an ability of the user to remember details regarding the event.

6. The system of claim 1, further comprising a personal information manager configured to send impending or approaching events to the memory jogger component.

7. The system of claim 1, further comprising an observation device configured to provide contextual information indicating activities or inactivities of the user to the memory jogger component.

8. The system of claim 1, further comprising an attendance predictor configured to predict a probability of the user attending the event based on a record of whether the event is a recurring event.

9. The system of claim 1, further comprising an attendance predictor configured to keep a record or document of events associated with the user, the record includes at least one of an event time and date, a duration, a subject, a location, an organizer of the event, a number of invitees, or a role of the user in relation to the event.

10. The system of claim 1, further comprising a cost component configured to contrast a cost for not being reminded about the event with a cost for interrupting the user about the event.

11. A system comprising:

a memory jogger component configured to assess an event for relevance based on contextual information associated with a user, the contextual information includes activities or inactivities associated with the user;

an attendance predictor configured to predict a probability of the user remembering one or more aspects of the event; and

a cost component configured to ascertain a user specific cost for not being reminded about the one or more aspects of the event.

12. The system of claim 11, wherein the cost component is further configured to compare the cost for not being reminded about the one or more aspects of the event with a cost for interrupting the user by sending a notification about the event.

13. The system of claim 11, wherein the cost component is further configured to use a history of contextual information of low-level or high-level actions performed by the user to compile a library of cases and to apply Bayesian learning techniques to build a personalized Bayesian structure to ascertain a cost for interrupting the user by sending a notification about the event.

14. The system of claim 11, further comprising an interface component configured to send a reminder notification about the event to the user and to determine an appropriate time on when to send the reminder notification about the event.

15. The system of claim 11, further comprising a traffic predictor configured to provide live traffic conditions, to determine travel routes, or to determine expected travel durations for the event.

16. The system of claim 11, further comprising a timing component configured to predict a duration of travel to a location for the event, when given a departure time for the user to leave a current location, a mode of transportation, and a time from the mode of transportation to arrive at a destination.

17. A method implemented at least in part by a processing unit, the method comprising:

assessing an event for relevance based on a user assessment of the event;

determining a user specific cost to ascertain a cost for not being reminded about one or more aspects of the event; and

sending or refraining from sending a reminder notification about the event to the user based on the relevance of the event and the user specific cost for not being reminded about the event.

18. The method of claim 17, wherein the sending or the refraining from sending the reminder notification is based at least in part on live traffic conditions, travel route updates, or an expected travel duration.

19. The method of claim 17, further comprising:

constructing Bayesian structures to predict a probability that the user will forget about the event or that the user will forget details associated with the event; and

producing a decision tree to isolate and identify key variables as to whether the user forgets about the event or that the user forgets the details associated with the event.

20. The method of claim 17, further comprising:

determining a priority of the event based on a cost for missing the event; and

predicting the priority of the event through use of a probabilistic model that takes into account properties of the event.