EP-4738068-A1 - METHODS AND APPARATUS TO SAVE POWER BASED ON USER PRESENCE

Abstract

Systems, apparatus, articles of manufacture, and methods are disclosed to perform power-saving based on user presence, including a network interface to communicate with a cloud device, user presence detector circuitry to determine if a user is present or not present; workload distributor circuitry to distribute an AI workload to either first AI inference circuitry or second AI inference circuitry; and power circuitry to charge a battery at either a first charge level or a second charge level.

Inventors

• KOKI, TARAKESAVA REDDY
• SUBRAHMANYAM, Prabhakar
• WANG, ZHONGSHENG
• KHAN, Feroze
• ALAPARTHI, PHANI
• SHAHAPUR, SHREEDHAR
• GUNNAM, VENKATA MAHESH
• SAHA, KRISHNENDU

Assignees

• INTEL Corporation

Dates

Publication Date

20260506

Application Date

20250911

Claims (15)

1. An apparatus to conserve battery power comprising: a network interface to communicate with a remote device, the remote device to perform artificial intelligence (AI) inference; computer readable instructions; and programmable circuitry to instantiate: user presence detector circuitry to determine if a user is present or not present, the user presence detector circuitry to generate a user presence detection determination; workload distributor circuitry to distribute, to either a first location or a second location, at least one portion of an AI workload based on the user presence detection determination; and power circuitry to select a first charging level or a second charging level for charging the apparatus based on the user presence detection determination.
2. The apparatus of claim 1, wherein, in response to the user presence detector circuitry determining that a user is present: the workload distributor circuitry is to distribute at least one portion of the AI workload to local AI inference circuitry, wherein the local AI inference circuitry is local to the apparatus; and the power circuitry is to select the first charging level.
3. The apparatus of claim 1 or claim 2, wherein, in response to the user presence detector circuitry determining that a user is not present: the workload distributor circuitry is to distribute at least one portion of the AI workload to a remote device; and the power circuitry is to select the second charge level, the second charge level higher than the first charge level.
4. The apparatus of any one preceding claim, wherein the user presence detector circuitry is to periodically monitor user presence.
5. The apparatus of any one preceding claim, wherein the user presence detector circuitry determines if a user is present or not present based on at least one of a camera visually detecting a user in front of the apparatus, commands input from a human-interface device connected to the apparatus, or a determination from a motion sensor connected to the apparatus.
6. The apparatus of any one preceding claim, wherein in response to detecting that a charging cable is attached to the apparatus, the workload distributor circuitry is to distribute at least one portion of the AI workload to AI inference circuitry, the AI inference circuitry which is local to the apparatus.
7. The apparatus of any one preceding claim, wherein in response to detecting that a charging cable is attached to the apparatus, the workload distributor circuitry is to distribute at least one portion of the AI workload to a cloud device, the cloud device includes AI inference circuitry that is external from the apparatus.
8. A method comprising: determining if a user is present or not present; generating a user presence detection determination; distributing, to either a first location or a second location, at least one portion of an AI workload based on the user presence detection determination; and selecting a first charging level or a second charging level for charging an apparatus based on the user presence detection determination.
9. The method of claim 8, wherein, in response to the user presence detector circuitry determining that a user is present: the workload distributor circuitry is to distribute at least one portion of the AI workload to local AI inference circuitry, wherein the local AI inference circuitry is local to the apparatus; and the power circuitry is to select the first charging level.
10. The method of claim 8 or claim 9, further comprising, in response to determining that a user is not present: distributing at least one portion of the AI workload to a remote device; and selecting the second charge level, the second charge level higher than the first charge level.
11. The method of any one of claims 8 to 10, further comprising periodically monitoring user presence.
12. The method of any one of claims 8 to 11, further comprising determining if a user is present or not present based on at least one of a camera visually detecting a user in front of the apparatus, command input from a human-interface device connected to the apparatus, or a determination from a motion sensor connected to the apparatus.
13. The method of any one of claims 8 to 12, further comprising, in response to detecting that a charging cable is attached to the apparatus, distributing at least one portion of the AI workload to AI inference circuitry, the AI inference circuitry which is local to the apparatus.
14. The method of any one of claims 8 to 13, further comprising, in response to detecting a charging cable, distributing at least one portion of the AI workload to a cloud device, the cloud device includes AI inference circuitry.
15. A machine readable medium comprising instructions that, when executed, cause an processor to implement the method of any one of claims 8-14.

Description

BACKGROUND As computing technology has improved, the development and use of artificial intelligence on computing devices has increased. Such artificial intelligence processes may analyze input data to infer a result about the input data (e.g., perform classification, cluster data, etc.). Computing devices may take many forms such as portable devices, servers, battery powered devices, etc. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram of an example environment in which an example computing device operates to implement power-saving based on user presence.FIG. 2 is a block diagram of an example implementation of power saving circuitry of the computing device of FIG. 1.FIG. 3 is a flowchart representative of example machine readable instructions and/or example operations that may be executed, instantiated, and/or performed by example programmable circuitry to implement the power saving circuitry of FIG. 2 to change a charging rate based on a determination of user presence.FIG. 4 is a flowchart representative of example machine readable instructions and/or example operations that may be executed, instantiated, and/or performed by example programmable circuitry to implement the power saving circuitry of FIG. 2 to change a charging rate based on a determination of user presence.FIG. 5 is a flowchart representative of example machine readable instructions and/or example operations that may be executed, instantiated, and/or performed by example programmable circuitry to implement the power saving circuitry of FIG. 2 to distribute an artificial intelligence (AI) workload based on a determination of user presence.FIG. 6 is a flowchart representative of example machine readable instructions and/or example operations that may be executed, instantiated, and/or performed by example programmable circuitry to implement the power saving circuitry of FIG. 2 to distribute an AI workload based on a determination of user presence.FIG. 7 is a flowchart representative of example machine readable instructions and/or example operations that may be executed, instantiated, and/or performed by example programmable circuitry to implement the power saving circuitry of FIG. 2 to, based on a determination of user presence, distribute an AI workload and select a charging level.FIG. 8 is a graph that compares a first charging rate based on user presence and temperature of the computing device and a second charging rate based on temperature of the computing device.FIG. 9 is a graph that compares, for a specified period of time, a percentage of a battery charged by the first charging rate of FIG. 8 and a percentage of the battery charged the second charging rate of FIG. 8.FIG. 10 is a graph that compares an amount of time to charge a battery for the first charging rate of FIG. 8 and an amount of time to charge the battery for the second charging rate of FIG. 8.FIG. 11 is an illustration which describes how the power saving circuitry of FIG. 2 distributes an AI workload based on a determination that a user is present at the computing device.FIG. 12 is an illustration which describes how the power saving circuitry of FIG. 2 distributes an AI workload based on a determination that a user is not present at the computing device.FIG. 13 is a graph that compares an amount of time to distribute the AI workload to an external device compared to an amount of time to distribute the AI workload to the local computing device.FIG. 14 is a block diagram of an example processing platform including programmable circuitry structured to execute, instantiate, and/or perform the example machine readable instructions and/or perform the example operations of FIGS. 4-7 to implement the power saving circuitry of FIG. 2.FIG. 15 is a block diagram of an example implementation of the programmable circuitry of FIG. 14.FIG. 16 is a block diagram of another example implementation of the programmable circuitry of FIG. 14.FIG. 17 is a block diagram of an example software/firmware/instructions distribution platform (e.g., one or more servers) to distribute software, instructions, and/or firmware (e.g., corresponding to the example machine readable instructions of FIGS. 4-7) to client devices associated with end users and/or consumers (e.g., for license, sale, and/or use), retailers (e.g., for sale, re-sale, license, and/or sub-license), and/or original equipment manufacturers (OEMs) (e.g., for inclusion in products to be distributed to, for example, retailers and/or to other end users such as direct buy customers). In general, the same reference numbers will be used throughout the drawing(s) and accompanying written description to refer to the same or like parts. The figures are not necessarily to scale. DETAILED DESCRIPTION Methods and apparatus disclosed herein utilize information about user presence at a computing device to control operation of the computing device (e.g., to conserve power based on user presence). Some techniques disclosed herein relate to inc