Busy day inference for users

Patent metadata

Field	Value
Publication number	US-10853768-B2
Application number	US-201615367784-A
Country	US
Kind code	B2
Filing date	Dec 2, 2016
Priority date	Dec 2, 2016
Publication date	Dec 1, 2020
Grant date	Dec 1, 2020

Abstract

An inference is made regarding whether or not an upcoming day is going to be a busy day for a user. One or more different user-specific event parameters are utilized to compute a user busyness score for the upcoming day, where these parameters are based in part on a history of events for the user and their past behavior. Then, whenever the user busyness score for the upcoming day is greater than a busy day threshold, it is inferred that the upcoming day is going to be a busy day for the user. Whenever the user busyness score for the upcoming day is less than a quiet day threshold, it is inferred that the upcoming day is going to be a quiet day for the user.

First claim

Wherefore, what is claimed is:

1. A system for inferring whether or not an upcoming day is going to be a busy day for a user, the system comprising:
a busy day inferrer comprising one or more computing devices, said one or more computing devices being in communication with each other via a computer network whenever there is a plurality of computing devices, and a computer program having a plurality of sub-programs executable by said one or more computing devices, wherein the plurality of sub-programs configure said one or more computing devices to:
utilize one or more different user-specific event parameters to compute a user busyness score for the upcoming day, said user-specific event parameters being based in part on a history of events for the user and their past behavior;
if the user busyness score for the upcoming day is greater than a busy day threshold, infer that the upcoming day is going to be busy for the user;
output a notification to the user to notify the user whether the upcoming day is going to be busy; and
present to the user one or more busy day actions when the upcoming day is going to be busy.

2. The system of claim 1 , wherein said user-specific event parameters comprise one or more of:
one or more explicit user-specific event parameters; or
one or more inferred user-specific event parameters.

3. The system of claim 2 , wherein the one or more explicit user-specific event parameters comprises one or more of:
a number of meetings scheduled for the user on a specific day of a specific week; or
a cumulative duration of said meetings; or
a number of reminders existing for the user on the specific day of the specific week.

4. The system of claim 2 , wherein the one or more inferred user-specific event parameters comprises one or more of:
a number of pending tasks the user is assigned to complete on a specific day of a specific week; or
a number of commutes made by the user on the specific day of the specific week; or
a cumulative duration of said commutes.

5. The system of claim 1 , wherein the upcoming day coincides with a specific day of a week and a sub-program for utilizing the one or more different user-specific event parameters to compute the user busyness score for the upcoming day comprises sub-programs for:
for each of said user-specific event parameters,
computing a first value for the user-specific event parameter on the upcoming day,
computing a second value for the user-specific event parameter on said specific day of each of a prescribed number of past weeks,
computing an historic weighted average of the user-specific event parameter over the prescribed number of past weeks, and
using the first value for the user-specific event parameter on the upcoming day and the historic weighted average of the user-specific event parameter over the prescribed number of past weeks to compute a parameter-related user busyness score for the user-specific event parameter, and
using a weighted combination of parameter-related user busyness scores that are computed for said user-specific event parameters to compute the user busyness score for the upcoming day.

6. The system of claim 5 , wherein the prescribed number of past weeks is nine.

7. The system of claim 5 , wherein the weight applied to each user-specific event parameter to compute the historic weighted average is initialized to a value defined by a prescribed function that decreases over the prescribed number of past weeks.

8. The system of claim 7 , wherein the prescribed function comprises one of:
a linear function having a negative slope; or
an exponentially decreasing function.

9. The system of claim 5 , wherein the weight applied to each parameter-related user busyness score is initialized to a generic value which is subsequently adjusted over time based upon explicit feedback that is received from the user.

10. The system of claim 9 , wherein the generic value is computed as one divided by a total number of said user-specific event parameters that are utilized.

11. The system of claim 9 , wherein the generic value is based upon one of:
an analysis of the history of events for the user and their past behavior; or
a study that asks one or more users to, for each user-specific event parameter, rank the user-specific event parameter with regard to how good a busyness indicator the user-specific event parameter is in comparison to other user-specific event parameters.

12. The system of claim 1 , wherein the busy day threshold is dynamically determined based on factors comprising the history of events for the user, their past behavior, and past user busyness scores that were computed for the user.

13. The system of claim 1 , wherein the plurality of sub-programs further configure said one or more computing devices to, whenever the user busyness score for the upcoming day is less than a quiet day threshold, infer that the upcoming day is going to be quiet for the user.

14. The system of claim 13 , wherein the quiet day threshold is dynamically determined based on factors comprising the history of events for the user, their past behavior, and past user busyness scores that were computed for the user.

15. The system of claim 13 , wherein a sub-program for inferring that the upcoming day is going to be quiet for the user is configured to notify the user that the upcoming day is going to be quiet.

16. A system for inferring whether or not an upcoming day is going to be a busy day for a user, the system comprising:
a busy day inferrer comprising a computing device that is utilized by the user, and a computer program having a plurality of sub-programs executable by said computing device, wherein the plurality of sub-programs configure said computing device to:
utilize one or more different user-specific event parameters to compute a user busyness score for the upcoming day, said user-specific event parameters being based in part on a history of events for the user and their past behavior;
whenever the user busyness score for the upcoming day is greater than a busy day threshold, infer that the upcoming day is going to be busy for the user;
output a notification to the user to notify the user whether the upcoming day is going to be busy; and
present to the user one or more busy day actions when the upcoming day is going to be busy.

17. The system of claim 16 , wherein said user-specific event parameters comprise one or more of:
a number of meetings scheduled for the user on a specific day of a specific week; or
a cumulative duration of said meetings; or
a number of reminders existing for the user on the specific day of the specific week; or
a number of pending tasks the user is assigned to complete on the specific day of the specific week; or
a number of commutes made by the user on the specific day of the specific week; or
a cumulative duration of said commutes.

18. The system of claim 16 , wherein the upcoming day coincides with a specific day of a week and a sub-program for utilizing the one or more different user-specific event parameters to compute the user busyness score for the upcoming day comprises sub-programs for:
for each of said user-specific event parameters,
computing a first value for the user-specific event parameter on the upcoming day,
computing a second value for the user-specific event parameter on said specific day of each of a prescribed number of past weeks,
computing an historic weighted average of the user-specific event parameter over the prescribed number of past weeks, and
using the first value for the user-spe

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Dehaghani Azar Rahimi
• Wascher Michael
• Gedge Nick

Classifications

• G06Q10/1093 Primary

  Calendar-based scheduling for persons or groups · CPC title

• G06N5/04

  Inference or reasoning models · CPC title