Surface classifications

Patent metadata

Field	Value
Publication number	US-11726570-B2
Application number	US-202117476077-A
Country	US
Kind code	B2
Filing date	Sep 15, 2021
Priority date	Sep 15, 2021
Publication date	Aug 15, 2023
Grant date	Aug 15, 2023

Abstract

In some examples, an electronic device includes a tip pressure sensor to capture tip pressure data based on a writing surface. In some examples, the electronic device includes a processor to produce a classification of the writing surface based on the tip pressure data via a machine learning model. In some examples, the electronic device may include a haptic device to control haptic feedback based on the classification.

First claim

What is claimed is:

1. An electronic device, comprising:
a tip pressure sensor to capture tip pressure data based on a writing surface;
a processor to produce, during a prediction stage, a classification of the writing surface based on the tip pressure data via a machine learning model, the classification of the writing surface including a value indicating a degree of roughness of the writing surface, the machine learning model having weights tuned, during a training stage, to produce the classification of the writing surface, wherein the machine learning model is an artificial neural network; and
a haptic device to control haptic feedback based on the classification,
wherein the haptic device is to control haptic feedback with an inverse relationship relative to the value indicating the degree of roughness of the writing surface.

2. The electronic device of claim 1 , wherein the classification indicates a surface type of the writing surface.

3. The electronic device of claim 1 , wherein the machine learning model is trained using training data labeled with a surface type.

4. The electronic device of claim 1 , further comprising an internal bus to communicate the classification from the processor to the haptic device.

5. The electronic device of claim 1 , wherein the haptic device is to control haptic feedback further based on user setting data.

6. The electronic device of claim 1 , further comprising a grip sensor to capture grip data, wherein the processor is to produce the classification based on the grip data.

7. The electronic device of claim 1 , wherein the processor is to produce the classification based on orientation data, coordinate data, or speed data.

8. An apparatus, comprising:
a communication interface to receive tip pressure data from a stylus device;
a touchscreen controller to determine information comprising coordinate data, orientation data, or speed data corresponding to the stylus device; and
a processor to produce, during a prediction stage, a writing surface classification using a machine learning model based on the tip pressure data and the information, the writing surface classification including a value indicating a degree of roughness of the writing surface to control haptic feedback with an inverse relationship relative to the value indicating the degree of roughness of the writing surface, the machine learning model having weights tuned, during a training stage, to produce the writing surface classification, wherein the machine learning model is an artificial neural network.

9. The apparatus of claim 8 , wherein the communication interface is to send the writing surface classification to the stylus device.

10. The apparatus of claim 8 , wherein the machine learning model is a multilayer perceptron (MLP) model.

11. A non-transitory tangible computer-readable medium comprising instructions when executed cause a processor of an electronic device to:
receive tip pressure data captured by a tip pressure sensor, wherein the tip pressure data is captured while a stylus tip is in contact with a writing surface;
predict, during a prediction stage, using a machine learning model, a classification of the writing surface based on the tip pressure data, the classification of the writing surface including a value indicating a degree of roughness of the writing surface, the machine learning model having weights tuned, during a training stage, to produce the classification of the writing surface, wherein the machine learning model is an artificial neural network; and
send the classification to a haptic device to control haptic feedback with an inverse relationship relative to the value indicating the degree of roughness of the surface.

12. The non-transitory tangible computer-readable medium of claim 11 , wherein the classification is sent to the haptic device via a wireless communication interface.

13. The non-transitory tangible computer-readable medium of claim 11 , wherein the classification is sent to the haptic device via an internal bus.

Assignees

• Hewlett Packard Development Co

Inventors

• Chen Tai Hsiang
• Stancil Charles J
• Lin Wei-Hung
• Lin Kun-Hung

Classifications

• G06F3/016 Primary

  Input arrangements with force or tactile feedback as computer generated output to the user · CPC title

• G06F3/0383

  Signal control means within the pointing device · CPC title

• G06F3/03546

  using a rotatable ball at the tip as position detecting member · CPC title

• G06F3/04162

  for exchanging data with external devices, e.g. smart pens, via the digitiser sensing hardware · CPC title

• G06N3/02

  Neural networks · CPC title