IP Library › Granted Patent US 12,638,943
Granted Patent B2
US 12,638,943 · App. 17/849,282 · Granted May 26, 2026

Methods and apparatus to process touch data

Inventors: Zhenyu Zhu (Folsom, CA); Satheesh Chellappan (Folsom, CA); Antonio Cheng (Portland, OR); Kar Leong Wong (Folsom, CA)
Assignee: Intel Corporation
G06F3/04186G06F3/0412G06N3/02
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 12,638,943
App. No.
17/849,282
Granted
May 26, 2026
Kind
B2
Abstract

Methods, apparatus, systems, and articles of manufacture are disclosed to process touch data. An example apparatus includes machine learning accelerator circuitry to execute a machine learning algorithm on touch data from touch sensor circuitry; and determine, based on an output of the machine learning algorithm, whether a touch input corresponding to the touch data was intentional; transceiver circuitry to, after a determination that the touch input was intentional, provide touch coordinates to memory; and processor circuitry to, after the determination that the touch input was intentional: access the touch coordinates in the memory; and perform an action based on the touch coordinates.

Claims (69)

1 . An apparatus to process touch data, the apparatus comprising:

machine learning accelerator circuitry to:

execute a machine learning algorithm on first touch data from touch sensor circuitry; and

determine, based on an output of the machine learning algorithm, whether a touch input corresponding to the first touch data was intentional;

controller circuitry to:

store the first touch data in a buffer separate from a memory; and

after a determination that the touch input was intentional, generate an indication that the buffer can store additional touch data;

transceiver circuitry to, after the determination that the touch input was intentional, provide touch coordinates associated with the first touch data to the memory; and

processor circuitry to, after the determination that the touch input was intentional:

access the touch coordinates in the memory; and

perform an action based on the touch coordinates.

2 . The apparatus of claim 1 , wherein the first touch data is a first touch frame, including touch host controller circuitry to:

in response to the indication, provide a second touch frame from the touch sensor circuitry to the machine learning accelerator circuitry.

3 . The apparatus of claim 1 , wherein the first touch data is a first touch frame, wherein the memory is a first memory, including touch host controller circuitry to:

in response to a determination that the buffer is unable to store additional touch frame data, store second touch frame from the touch sensor circuitry in a second memory separate from both the buffer and the first memory.

4 . The apparatus of claim 2 , wherein the machine learning accelerator circuitry is to determine whether the touch input corresponding to the first touch frame was intentional asynchronously from when the touch host controller circuitry receives the second touch frame.

5 . The apparatus of claim 1 , wherein the machine learning accelerator circuitry is to:

in response to a determination that the touch input was intentional, calculate updated touch coordinates using a display frequency as an input to a touch smoothing algorithm; and

provide the updated touch coordinates to the transceiver circuitry.

6 . The apparatus of claim 1 , wherein the machine learning algorithm includes a gaussian neural network accelerator to determine whether the touch input was intentional.

7 . The apparatus of claim 1 , wherein:

the processor circuitry is in a sleep mode; and

the transceiver circuitry is to, in response to a determination that the touch input was unintentional, prevent the processor circuitry from exiting the sleep mode.

8 . The apparatus of claim 1 , wherein, to perform the action, the processor circuitry is to update a graphic on a display based on the touch coordinates.

9 . At least one non-transitory machine-readable medium comprising instructions that, when executed, cause at least one processor to at least:

execute a machine learning algorithm on first touch data;

determine, based on an output of the machine learning algorithm, whether a touch input corresponding to the first touch data was intentional;

store the first touch data in a buffer separate from a memory;

after a determination that the touch input was intentional, generate an indication that the buffer can store additional touch data; and

in response to the determination that the touch input was intentional, provide touch coordinates associated with the first touch data to memory.

10 . The at least one non-transitory machine-readable medium of claim 9 , wherein the first touch data is a first touch frame, wherein the instructions are to cause one or more of the at least one processor to, in response to the indication, store a second touch frame in the buffer.

11 . The at least one non-transitory machine-readable medium of claim 9 , wherein the first touch data is a first touch frame, the memory is a first memory, and the instructions are to cause one or more of the at least one processor to in response to a determination that the buffer is unable to store additional touch frame data, store a second touch frame in a second memory separate from both the buffer and the first memory.

12 . The at least one non-transitory machine-readable medium of claim 10 , wherein the instructions are to cause one or more of the at least one processor to determine whether the touch input corresponding to the first touch frame was intentional asynchronous with receiving the second touch frame.

13 . The at least one non-transitory machine-readable medium of claim 9 , wherein the instructions are to cause one or more of the at least one processor to, after a determination that the touch input was intentional:

calculate updated touch coordinates using a display frequency as an input to a touch smoothing algorithm; and

provide the updated touch coordinates to the memory.

14 . The at least one non-transitory machine-readable medium of claim 9 , wherein the machine learning algorithm is to use a gaussian neural network accelerator to determine whether the touch input was intentional.

15 . The at least one non-transitory machine-readable medium of claim 9 , including a second processor separate from the at least one processor, wherein:

the second processor is in a sleep mode; and

the instructions are to cause one or more of the at least one processor to, after a determination that the touch input was unintentional, prevent the second processor from exiting the sleep mode.

16 . The at least one non-transitory machine-readable medium of claim 9 , including a second processor separate from the at least one processor, the second processor to:

obtain the touch coordinates from the memory; and

update a graphic on a display based on the touch coordinates.

17 . A method to process touch data, the method comprising:

executing a machine learning algorithm on first touch data;

determining, based on an output of the machine learning algorithm, whether a touch input corresponding to the first touch data was intentional;

storing the first touch data in a buffer separate from a memory;

after a determination that the touch input was intentional, generating an indication that the buffer can store additional touch data; and

after the determination that the touch input was intentional, providing touch coordinates associated with the first touch data to memory;

accessing the touch coordinates in the memory; and

performing an action based on the touch coordinates.

18 . The method of claim 17 , wherein the first touch data is a first touch frame, including after receiving the indication, storing a second touch frame in the buffer.

19 . The method of claim 17 , wherein the first touch data is a first touch frame, wherein the memory is a first memory, including after determining that the buffer is unable to store additional touch frame data, storing a second touch frame in a second memory separate from both the buffer and the first memory.

20 . The method of claim 18 , including receiving the second touch frame asynchronous with determining whether the touch input corresponding to the first touch frame was intentional.

21 . The method of claim 17 , including:

calculating updated touch coordinates using a display frequency as an input to a touch smoothing algorithm; and

providing the updated touch coordinates to the memory.

22 . The method of claim 17 , including, after determining that the touch input was unintentional, preventing a processor from exiting a sleep mode.

23 . An apparatus to process touch data, the apparatus comprising:

means for learning to:

execute a machine learning algorithm on a first touch frame;

determine, based on an output of the machine learning algorithm, whether a touch input corresponding to the first touch frame was intentional;

send an indication that a buffer separate from a memory can store additional touch frames, the indication to be sent after the determination that the touch input corresponding to the first touch frame was intentional; and

provide, after the determination that the touch input was intentional, touch coordinates associated with the first touch frame to the memory; and

means for processing to:

access the touch coordinates in the memory; and

perform an action based on the touch coordinates.

24 . The apparatus of claim 23 , including means for controlling touch data to, after receiving the indication, send a second touch frame to the means for learning, the means for learning to store the second touch frame in the buffer.

25 . The apparatus of claim 24 , wherein the memory is a first memory, the means for controlling is to, in response to a determination that the buffer is unable to store additional touch frame data, store a second touch frame in a second memory separate from both the buffer and the first memory.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 7, 2023
From: ZHU, ZHENYU
To: INTEL CORPORATION
Reel/Frame 063265/0309 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 18, 2023
From: WONG, KAR LEONG
To: INTEL CORPORATION
Reel/Frame 063117/0346 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 27, 2023
From: CHENG, ANTONIO; CHELLAPPAN, SATHEESH
To: INTEL CORPORATION
Reel/Frame 062526/0703 →
Continuity (1)
Related Publication 20220317855A1 · Oct 6, 2022
References Cited (7)
US 20170185212A1 · Jeong · 2017 [cited by examiner]
US 20180188938A1 · Deselaers · 2018 [cited by examiner]
US 20180314536A1 · Wang · 2018 [cited by examiner]
US 20210117152A1 · Deisher · 2021 [cited by examiner]
US 20210132769A1 · Parikh · 2021 [cited by examiner]
US 20210142214A1 · Maalouf · 2021 [cited by examiner]
US 20210223780A1 · Bramley · 2021 [cited by examiner]