Adaptive threshold for user absence prediction for power state transitions

Patent metadata

Field	Value
Publication number	US-12554308-B2
Application number	US-202418742147-A
Country	US
Kind code	B2
Filing date	Jun 13, 2024
Priority date	Jun 13, 2024
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

Systems and methods are provided for implementing an adaptive threshold for user absence prediction for power state transitions. A controller of a device monitors a user presence and/or absence of a user, in some cases, correlated with time, and determines whether the user presence and/or absence at the correlated time is consistent with a power management model that is based on a time-based probability of user absence relative to a dynamic probability threshold. The dynamic probability threshold is a function (e.g., a sum) of a base probability threshold corresponding to device-specific time-usage characteristics and a heuristic probability threshold corresponding to user-specific time-usage characteristics. When inconsistent, the controller adjusts the dynamic probability threshold to account for the user presence and/or absence at the correlated time. The controller updates the power management model based on the dynamic probability threshold, and sets a sleep or wake state of the device accordingly.

First claim

What is claimed is:

1 . A system that executes computer executable instructions that cause the system to perform operations comprising:
monitoring, on a device, a user presence state, the user presence state including at least one of user presence or user absence; determining whether the user presence state is consistent with a power management model based on a time-based probability of user presence or user absence relative to a dynamic probability threshold, the dynamic probability threshold being a function of a base probability threshold that corresponds to device-specific time-usage characteristics and a heuristic probability threshold that corresponds to user-specific time-usage characteristics; and based on a determination that the user presence state is inconsistent with the power management model,
adjusting the dynamic probability threshold by adjusting the heuristic probability threshold to account for the user presence state;
updating the power management model based on the dynamic probability threshold; and
causing implementation of power management settings of the device based on the update to the power management model.

2 . The system of claim 1 , wherein monitoring the user presence state is based on at least one of a detection of a user presence signal correlated with time or a detection of a user absence signal correlated with time.

3 . The system of claim 1 , wherein the user presence corresponds to a first period during which a user is determined to be interacting with the device, wherein the user absence corresponds to a second period during which the user is determined to be away from the device, wherein the time with which the user presence state is correlated corresponds to a system time of the device, wherein the user presence state is determined to be inconsistent with the power management model when at least one of user presence states is detected by the device:
when the device detects that the user is away from the device when the power management model indicates that the user is supposed to be interacting with the device; or when the device detects that the user is interacting with the device when the power management model indicates that the user is supposed to be away from the device.

4 . The system of claim 1 , wherein at least one of the base probability threshold or the heuristic probability threshold varies over time,
wherein the power management model indicates user absence at a first time when a probability value of the time-based probability of user absence, for the first time, is above the dynamic probability threshold, wherein the power management model indicates user presence at a second time when a probability value of the time-based probability of user absence, for the second time, is below the dynamic probability threshold.

5 . The system of claim 1 , wherein the base probability threshold is set or adjusted by an operating system (“OS”) producer of an OS of the device, an original equipment manufacturer (“OEM”) of the device, a system administrator for the device, or a software module operating on the device.

6 . The system of claim 1 , wherein the power management model is further based on at least one of calendar information or task scheduler information corresponding to periods during which user presence is expected.

7 . The system of claim 1 , wherein the power management model is specific to both a user and the device.

8 . The system of claim 1 , wherein the correlated time includes time-of-day within a third period including at least one of a day, a weekday, a weekend, a week, a month, a season, an annual quarter, a year, or a decade.

9 . The system of claim 1 , wherein the operations are performed using one of an OS of the device or software running on the OS.

10 . The system of claim 1 , wherein the operations further comprise:
identifying at least one of a user presence trend or a user absence trend, based on analysis of at least one of historical user presence information or historical user absence information; adjusting the dynamic probability threshold by adjusting the heuristic probability threshold based on the at least one of the user presence trend or the user absence trend; updating the power management model based on the dynamic probability threshold; and causing implementation of power management settings of the device based on the update to the power management model.

11 . The system of claim 1 , wherein the operations further comprise:
identifying a fourth period during which power being supplied to the device is determined to be generated by a renewable energy source; identifying a fifth period within the fourth period during which the power management model indicates user absence; adjusting the dynamic probability threshold by adjusting the heuristic probability threshold corresponding to the fifth period to enable system background operations during user absence; updating the power management model based on the dynamic probability threshold; causing implementation of power management settings of the device based on the update to the power management model; and causing the system background operations for the device to be scheduled during the fifth period.

12 . The system of claim 11 , wherein the system background operations for the device include one of system updates, background maintenance operations, software installation operations, or data backup operations.

13 . A computer-implemented method, comprising:
causing implementation of power management of a device in accordance with a power management model based on a time-based probability of user absence relative to a dynamic probability threshold, the dynamic probability threshold being a function of a base probability threshold that corresponds to device-specific time-usage characteristics and a heuristic probability threshold that corresponds to user-specific time-usage characteristics; monitoring, on the device, changes with respect to a user presence state, the user presence state including at least one of user presence or user absence; dynamically adjusting the power management model by adjusting the dynamic probability threshold in response to monitored changes with respect to the user presence state; and updating the power management of the device based on the dynamic adjustments to the power management model.

14 . The computer-implemented method of claim 13 , wherein the dynamic probability threshold is a sum of the base probability threshold and the heuristic probability threshold.

15 . The computer-implemented method of claim 13 , wherein adjusting the dynamic probability threshold comprises adjusting the heuristic probability threshold.

16 . The computer-implemented method of claim 13 , wherein at least one of the base probability threshold or the heuristic probability threshold varies over time,
wherein the power management model indicates user absence at a first time when a probability value of the time-based probability of user absence, for the first time, is above the dynamic probability threshold, wherein the power management model indicates user presence at a second time when a probability value of the time-based probability of user absence, for the second time, is below the dynamic probability threshold, wherein the base probability threshold is set or adjusted by an operating system (“OS”) producer of an OS of the device, an original equipment manufacturer (“OEM”) of the device, a system administrator for the device, or a software module operating on the device.

17 . A syst

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Guan Aobo
• Gupta Rachita
• Kwak Henry Minseok
• Cross Drew
• Barkelew Jonathan Bret
• Smith Jacob

Classifications

• G06F1/3228

  Monitoring task completion, e.g. by use of idle timers, stop commands or wait commands · CPC title

• G06F1/329

  by task scheduling · CPC title

• G06F1/3231 Primary

  Monitoring the presence, absence or movement of users · CPC title