IP Library Granted Patent US 12,439,120
Granted Patent B2
US 12,439,120 · App. 18/009,648 · Granted Oct 7, 2025

Predictive power management using machine learning

Inventors: George Thomas Des Jardins (Isleworth, GB); Adam Rees (Isleworth, GB); Stephen Craig (Isleworth, GB)
Assignee: Sky CP Limited
H04N21/4436H04N21/42202H04N21/44218
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,439,120
App. No.
18/009,648
Granted
Oct 7, 2025
Kind
B2
Abstract

Systems and methods are described for power control in a media receiver device having a plurality of electronic components, using a trained model. Input signals are received from at least one electronic component. An alertness state of the device is determined using a machine learning based determiner trained to process the received input signals and predict a subsequent alertness state identifying at least one additional component or device. Power consumption by the identified components and devices is controlled based on the predicted alertness state.

Claims (20)

1. A media receiver device comprising:

a plurality of discrete circuitry units, each providing a respective device function when supplied with power, the circuitry units including:

a presence detection unit having a plurality of sensor components, and a corresponding control module operable to control power supply to the plurality of sensor components in response to a received command;

a power button monitor unit having a remote control interface component, and a corresponding control module operable to control power supply to the remote control interface component in response to a received command; and

an output unit having a plurality of output device interface components, and a corresponding control module operable to control power supply to the plurality of output device interface components in response to a received command; and

one or more processors configured to:

predict, using a machine learning based trained model, a subsequent operating state of the media receiver device based on a current operating state and one or more device parameters, wherein the trained model includes data defining a hierarchy of operating states of the device and transition conditions therebetween based on one or more device parameters, each operating state in the hierarchy being associated with an increasing number of said discrete circuitry units that are to be supplied with power, the hierarchy of operating states including:

a first operating state associated with the presence detection unit;

a second operating state further associated with the power button monitor unit, having a conditional transition from the first operating state based on at least one or more device parameters received from the presence detection unit; and

a third operating state further associated with the output unit, having a conditional transition from the second operating state based on at least one or more device parameters received from the power button monitor unit; and

transmit a command to the discrete circuitry units associated with the predicted subsequent operating state of the device to cause power to be supplied to the corresponding components thereof.

2. The device of claim 1 , wherein the transmitted command is a command to control a transition between low and high powered operating states of the corresponding plurality of components.

3. The device of claim 1 , wherein the data defining transition conditions of the trained model comprises probability values of transitioning between operating states based on input device parameter values.

4. The device of claim 3 , wherein the one or more processors is configured to predict the subsequent operating state further based on a predicted end operating state.

5. The device of claim 1 , wherein the one or more processors is further configured to monitor an actual operational state of the device, wherein the trained model is updated based on the monitored actual operational state.

6. The device of claim 1 , wherein the trained model is received from a remote server.

7. The device of claim 1 , wherein the presence detection unit includes one or more of: a proximity sensor, a light, a camera, a proximal device detection module, and a connected device communications interface.

8. The device of claim 7 , wherein the one or more device parameters includes data received from the connected device communications interface identifying the presence of a plurality of devices in proximity of the media receiver device.

9. The device of claim 1 , wherein the one or more processors is further configured to output control signals to one or more connected devices, the control signals including one or more of: a power control signal, a volume control signal, and a display brightness control signal.

10. A non-transitory storage medium comprising machine readable instructions stored thereon for operating the media receiver device of claim 1 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 19, 2023
From: DES JARDINS, GEORGE THOMAS; REES, ADAM; CRAIG, STEPHEN
To: SKY CP LIMITED
Reel/Frame 063381/0846 →
Priority Claims (1)
GB 2011093 · Jul 17, 2020 · national
Continuity (1)
Related Publication 20230224541A1 · Jul 13, 2023
References Cited (19)
US 7411631B1 · Joshi et al. · 2008 [cited by applicant]
US 9791910B1 · Brown et al. · 2017 [cited by applicant]
US 10374863B2 · Xu et al. · 2019 [cited by applicant]
US 20030210271A1 · King · 2003 [cited by examiner]
US 20090002217A1 · Kryze · 2009 [cited by examiner]
US 20100191350A1 · Ohno · 2010 [cited by applicant]
US 20110317078A1 · Johns et al. · 2011 [cited by applicant]
US 20130326250A1 · Sullivan · 2013 [cited by examiner]
US 20190050049A1 · Qawami · 2019 [cited by examiner]
US 20190098067A1 · Sandoval · 2019 [cited by applicant]
US 20200383625A1 · Han · 2020 [cited by examiner]
EP 3629297A1 · 2020 [cited by applicant]
WO 2017123334A1 · 2017 [cited by applicant]
International Search Report and Written Opinion dated Oct. 1, 2021, issued in connection with International App. No. PCT/GB2021/051836 (11 pages). [cited by applicant]
Combined Search and Examination Report dated Mar. 23, 2021, issued in connection with UK App. No. GB2011093.8 (6 pages). [cited by applicant]
George Nott, “AI used to predict phone unlocking, saving battery and bandwidth,” CIO, article dated Feb. 27, 2019, available at https://www.cio.com/article/208184/ai-used-to-predict-phone-unlocking-saving-battery-and-ba… [cited by applicant]
G. Weiss et al., “Safe Adaptation for Reliable and Energy Efficient E/E Architectures—Section 1.3.4: Automated Design Process,” in Comprehensive Energy Management—Safe Adaptation, Predictive Control and Thermal Manageme… [cited by applicant]
N. Nedjah et al., “Evolutionary Synthesis of Synchronous Finite State Machines—Section 5.2: Synchronous Finite State Machines,” in Evolvable Machines: Theory & Practice, Springer, 2005 (6 pages). [cited by applicant]
S. Lee et al., “Automatic Standby Power Management Using Usage Profiling and Prediction,” in IEEE Transactions on Human-Machine Systems, vol. 43, No. 6, Nov. 2013 (12 pages). [cited by applicant]