Electronic device and operating method of the same

Patent metadata

Field	Value
Publication number	US-11977699-B2
Application number	US-202217694155-A
Country	US
Kind code	B2
Filing date	Mar 14, 2022
Priority date	Apr 19, 2021
Publication date	May 7, 2024
Grant date	May 7, 2024

Abstract

Provided is a method of identifying a touch type of a user touch input with respect to an electronic device, the method including: obtaining touch data from a touch input received from a user; determining a touch recognition model set consisting of touch recognition models to be used to identify a touch type of the touch input of the user from among a plurality of touch recognition models corresponding to a plurality of partial time periods included in a time in which the touch input is maintained; obtaining touch type probability values with respect to the touch input of the user by applying the touch data to the touch recognition models included in the touch recognition model set; and identifying a touch type of the touch input, based on the obtained touch type probability values.

First claim

What is claimed is:

1. A method of identifying a touch type of a touch input of a user with respect to an electronic device, the method comprising:
obtaining touch data from the touch input of the user;
selecting at least one touch recognition model from among a plurality of touch recognition models, the at least one touch recognition model corresponding to each partial time period of a plurality of partial time periods included in a time period during which the touch input is maintained, resulting in a touch recognition model set,
wherein each of the touch recognition model set is trained to identify a touch type of the touch input from the touch data obtained during a corresponding partial time period of the plurality of partial time periods during which the touch input is maintained;
applying the touch data to the touch recognition models included in the touch recognition model set to obtain touch type probability values of the touch input according to the plurality of partial time periods respectively corresponding to the touch recognition model set; and
identifying the touch type of the touch input by combining the obtained touch type probability values to which weights have been applied, each of the weights corresponding to a partial time period of the plurality of partial time periods.

2. The method of claim 1 , further comprising:
obtaining sample touch data corresponding to a first type touch and a second type touch, by guiding the user to provide a sample touch input corresponding to the first type touch and the second type touch; and configuring, with respect to the user, the plurality of touch recognition models based on the sample touch data,
wherein the determining the touch recognition model set comprises determining the touch recognition model set, based on the configured plurality of touch recognition models.

3. The method of claim 2 , wherein the determining the touch recognition model set comprises:
applying the sample touch data to the plurality of touch recognition models;
obtaining, from the plurality of touch recognition models, sample touch type probability values indicating results of inferences with respect to a touch type of the sample touch input;
determining accuracy of the inferences with respect to the touch type of the sample touch input, the inferences being respectively performed by the plurality of touch recognition models, based on the sample touch type probability values, and a corresponding touch type that the electronic device guided to the user; and
configuring, based on the accuracy of the inferences, the touch recognition model set.

4. The method of claim 2 , wherein the first type touch is a force touch identified based on a strength of a touch force applied to the electronic device, and the second type touch is a long touch identified based on a touch time applied to the electronic device.

5. The method of claim 2 , further comprising:
obtaining other touch data from different touch inputs being input by the user using the electronic device.

6. The method of claim 5 , further comprising:
labeling, with respect to the other touch data, a label value indicating the touch type;
obtaining, according to the labeling, training data to train the touch recognition models comprised in the touch recognition model set; and
updating the touch recognition models included in the touch recognition model set using the training data.

7. The method of claim 6 , further comprising:
obtaining, from the other touch data, touch occurrence area data indicating an area where the touch input of the user occurs,
wherein the updating the touch recognition models included in the touch recognition model set using the training data comprises updating the touch recognition models included in the touch recognition model set using the training data and the touch occurrence area data.

8. The method of claim 5 , further comprising:
updating a touch type identification threshold value for each of the touch recognition models included in the touch recognition model set, based on the sample touch data and the other touch data.

9. The method of claim 1 , further comprising:
applying the touch data to a base touch recognition model; and
determining whether to identify the touch type of the touch input of the user using the touch recognition models included in the touch recognition model set,
wherein the base touch recognition model is trained to identify a touch type of a touch input of the user, based on touch data corresponding to the time period during which the touch input of the user is maintained.

10. The method of claim 1 , further comprising:
obtaining, from the plurality of touch recognition models, touch type probability values of time periods respectively corresponding to the plurality of touch recognition models;
generating pattern information of the user applying a force to the electronic device, based on the touch type probability values obtained from the plurality of touch recognition models; and
determining a primary time period, based on the pattern information,
wherein the identifying the touch type of the touch input comprises combining touch type probability values obtained from the touch recognition models included in the touch recognition model set by applying a weight to the primary time period.

11. An electronic device for identifying a touch type of a touch input of a user, the electronic device comprising:
a user interface configured to obtain touch data from the touch input of the user;
a memory storing one or more instructions; and
at least one processor configured to execute the one or more instructions stored in the memory to:
select at least one touch recognition model from among a plurality of touch recognition models, the at least one touch recognition model corresponding to each partial time period of a plurality of partial time periods included in a time period during which the touch input is maintained, resulting in a touch recognition model set,
wherein each of the touch recognition model set is trained to identify a touch type of the touch input from the touch data, obtained during a corresponding partial time period of the plurality of partial time periods during which the touch input is maintained,
apply the touch data to the touch recognition models comprised in the touch recognition model set to obtain touch type probability values of the touch input according to the plurality of partial time periods respectively corresponding to the touch recognition model set, and
identify a touch type of the touch input by combining the obtained touch type probability values to which weights have been applied, each of the weights corresponding to a partial time period of the plurality of partial time periods.

12. The electronic device of claim 11 , wherein the at least one processor is further configured to execute the one or more instructions to:
obtain sample touch data corresponding to a first type touch and a second type touch, by guiding the user to provide a sample touch input corresponding to the first type touch and the second type touch,
configure, with respect to the user, the plurality of touch recognition models based on the obtained sample touch data, and
determine the touch recognition model set, based on the configured plurality of touch recognition models.

13. The electronic device of claim 12 , wherein the at least one processor is further configured to execute the one or more instructions to:
apply the sample touch data to the plurality of touch recognition models;
obtain, from the plurality of touch recognition models, sample touch type probability values

Assignees

• Samsung Electronics Co Ltd

Inventors

• Hwang Jinyoung
• Kim Dongchan
• Byun Dongnam

Classifications

• G06F3/0416 Primary

  Control or interface arrangements specially adapted for digitisers · CPC title

• G06F3/04883

  for inputting data by handwriting, e.g. gesture or text · CPC title

• G06F3/04186

  Touch location disambiguation · CPC title