# US 2025/0094003 A1 · Method for recognizing material, interactive board, and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0094003 A1
- Document ID: US20250094003A1
- Status: Published application
- Kind: A1
- Application number: 18/969,269
- Filed: 2024-12-05
- Published: 2025-03-20
- Earliest claimed: 2023-03-09
- Assignees: Guangzhou Shiyuan Electronic Technology Company Limited; Guangzhou Shiyuan Artificial Intelligence Innovation Research Institute Co., Ltd.
- Applicants: Guangzhou Shiyuan Electronic Technology Company Limited; Guangzhou Shiyuan Artificial Intelligence Innovation Research Institute Co., Ltd.
- Inventors: Fei WANG; Cai CHEN; Jianxin LIN
- Web page: https://patentgrep.com/patent/US20250094003A1

## CPC

- G06F 3/042: by opto-electronic means
- G06F 3/0421: {by interrupting or reflecting a light beam, e.g. optical touch-screen}
- G06F 3/0354: with detection of two-dimensional [2D] relative movements between the device, or an operating part thereof, and a plane or surface, e.g. 2D mice, trackballs, pens or pucks
- G06F 3/04142: {the force sensing means being located peripherally, e.g. disposed at the corners or at the side of a touch sensing plate}
- G06F 3/043: using propagating acoustic waves
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06F 3/0416: {Control or interface arrangements specially adapted for digitisers}
- G06F 2203/04106: Multi-sensing digitiser, i.e. digitiser using at least two different sensing technologies simultaneously or alternatively, e.g. for detecting pen and finger, for saving power or for improving position detection
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present disclosure provides a method for recognizing a material, an interactive board, and a storage medium, which is applied to an interactive board, and the interactive board includes an operation panel, an infrared touch sensor, and an elastic wave sensor. The infrared touch sensor is arranged on at least one edge of the operation panel to form a touch detection region of the interactive board, and the elastic wave sensor is configured to detect vibration of the operation panel and generate an electrical signal.

## Claims

### Claim 1

A method for recognizing a material, performed by an interactive board, wherein the interactive board comprises:
an operation panel;
an infrared touch sensor; and
an elastic wave sensor, wherein the infrared touch sensor is arranged on at least one edge of the operation panel to form a touch detection region of the interactive board, and the elastic wave sensor is configured to detect vibration of the operation panel and generate an electrical signal, and
wherein the method comprises:
generating an infrared blocking electrical signal by the infrared touch sensor from a first moment when a touch object performs a touch operation in the touch detection region;
generating an original touch electrical signal by the elastic wave sensor from the first moment;
calculating an average energy value of the original touch electrical signals within a current time window;
calculating a ratio of the average energy value to an historical average energy value, wherein the historical average energy value is an average energy value of the original touch electrical signals within a previous time window;
determining whether the ratio is greater than a preset threshold;
acquiring an initial moment of the current time window as a starting moment of an effective touch electric signal when the ratio is greater than the preset threshold;
acquiring an effective touch electrical signal within a preset time length after the starting moment as elastic wave data; and
determining first material information of the touch object based on the infrared blocking electrical signal and the elastic wave data.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
dynamically updating the preset threshold based on a first electrical signal generated by the infrared touch sensor and a second electrical signal generated by the elastic wave sensor.

### Claim 3 (depends on 2)

The method of claim 2, wherein the dynamically updating the preset threshold based on the first electrical signal generated by the infrared touch sensor and the second electrical signal generated by the elastic wave sensor comprises:
determining in real time whether instantaneous amplitude of the second electrical signal generated by the elastic wave sensor is greater than the preset threshold when it is determined that there is no touch object based on the first electrical signal generated by the infrared touch sensor;
setting the preset threshold to a first preset threshold when the instantaneous amplitude of the second electrical signal is greater than the preset threshold; and
setting the preset threshold to a second preset threshold when the instantaneous amplitude of the second electrical signal is less than the preset threshold.

### Claim 4 (depends on 1)

The method of claim 1, wherein the determining first material information of the touch object based on the infrared blocking electrical signal and elastic wave data comprises:
generating probabilities corresponding to different materials based on the elastic wave data;
adjusting the probabilities based on the infrared blocking electrical signal to obtain a target probability; and
generating the first material information of the touch object based on the target probability.

### Claim 5 (depends on 4)

The method of claim 4, wherein the adjusting the probabilities based on the infrared blocking electrical signal to obtain the target probability comprises:
calculating an area of the touch object based on the infrared blocking electrical signal;
determining weights corresponding to different materials based on the area of the touch object; and
adjusting the probability based on the weight to obtain the target probability.

### Claim 6 (depends on 4)

The method of claim 4, wherein the generating probabilities corresponding to different materials based on the elastic wave data comprises:
preprocessing the elastic wave data to obtain target data; and
inputting the target data into a preset neural network to obtain probabilities corresponding to different materials.

### Claim 7 (depends on 6)

The method of claim 6, wherein the elastic wave data is generated based on the effective contact electrical signals corresponding to multiple elastic wave sensors, and the preprocessing the elastic wave data to obtain the target data comprises:
performing time-frequency transformation on the elastic wave data of multiple elastic wave sensors to obtain the frequency domain data corresponding to the elastic wave data;
performing multi-channel signal fusion on frequency domain data to obtain fused data; and
filtering the fused data to obtain the target data.

### Claim 8 (depends on 7)

The method of claim 7, wherein the performing multi-channel signal fusion on frequency domain data to obtain fused data comprises:
performing weighted averaging on frequency domain data to obtain the fused data.

### Claim 9 (depends on 7)

The method of claim 7, wherein the performing multi-channel signal fusion on frequency domain data to obtain fused data comprises:
inputting the frequency domain data into the preset first neural network to obtain fused data.

### Claim 10 (depends on 6)

The method of claim 6, wherein the preprocessing elastic wave data to obtain target data comprises:
calculating a system function of elastic waves propagating to respective elastic wave sensors;
dividing the elastic wave data corresponding to each elastic wave sensor by the corresponding system function to obtain the first data corresponding to each elastic wave sensor; and
calculating the average of the first data to obtain the target data.

### Claim 11 (depends on 6)

The method of claim 6, wherein the neural network comprises:
a multi-layer fully connected network, further comprising: a first fully connected layer, a second fully connected layer, a third fully connected layer, a first BN layer, a second BN layer, a Dropout layer, and a Softmax layer, wherein the first fully connected layer, the first BN layer, the second fully connected layer, the second BN layer, the Dropout layer, the third fully connected layer, and the Softmax layer are connected in sequence.

### Claim 12 (depends on 11)

The method of claim 11, wherein training parameters and weight parameters of the multi-layer fully connected network are obtained by training the multi-layer fully connected network with cross-entropy loss function and Adam optimization algorithm.

### Claim 13 (depends on 12)

The method of claim 12, wherein the training parameters and weight parameters are obtained through the following:
collecting the first preset volume of target data as training data, and collecting the second preset volume of target data as validation data;
receiving material labels corresponding to respective training data and validation data;
training the multi-layer fully connected network by using cross-entropy loss function and Adam optimization algorithm based on the rounds, wherein the training data corresponding to the preset data volume is trained in each round, and the corresponding initial network model is obtained by each round of training; and
verifying the initial network model through validation data, confirming that the training parameters and weight parameters of the initial network model are the training parameters and weight parameters of the multi-layer fully connected network when the validation recognition rate of the initial network model reaches a preset indicator, and finishing the training.

### Claim 14 (depends on 1)

The method of claim 1, further comprising:
acquiring the infrared blocking electrical signal at the previous moment when the first material information has not been acquired within the first duration after the first moment, and determining whether the current touch operation is associated with the touch operation at the previous moment based on the current infrared blocking electrical signal, and acquiring the corresponding material type at the previous moment as the material type of the touch event when being associated.

### Claim 15 (depends on 14)

The method of claim 14, wherein the acquiring the infrared blocking electrical signal at the previous moment and determining whether the current touch operation is associated with the touch operation at the previous moment based on the current infrared blocking electrical signal comprises:
determining a touch point based on the current infrared blocking electrical signal, and determining a historical touch point based on the infrared blocking electrical signal at the previous moment;
calculating a distance between the touch point and the historical touch point, and determining a time interval between the first moment and the previous moment; and
determining that the current touch operation is associated with the touch operation at the previous moment when the distance is less than a preset distance and the time interval is less than a preset time interval.

### Claim 16

An interactive board, comprising:
an operation panel;
an infrared touch sensor;
an elastic wave sensor; and
at least one processing device, wherein the infrared touch sensor is arranged on at least one edge of the operation panel to form a touch detection region of the interactive board, the elastic wave sensor is configured to detect vibration of the operation panel and generate an electrical signal, and the at least one processing device is configured to:
generate an infrared blocking electrical signal by the infrared touch sensor from a first moment when a touch object performs a touch operation in the touch detection region;
generate an original touch electrical signal by the elastic wave sensor from the first moment;
calculate an average energy value of the original touch electrical signals within a current time window;
calculate a ratio of the average energy value to an historical average energy value, wherein the historical average energy value is an average energy value of the original touch electrical signals within a previous time window;
determine whether the ratio is greater than a preset threshold;
acquire an initial moment of the current time window as a starting moment of an effective touch electric signal when the ratio is greater than the preset threshold;
acquire an effective touch electrical signal within a preset time length after the starting moment as elastic wave data; and
determine first material information of the touch object based on the infrared blocking electrical signal and the elastic wave data.

### Claim 17 (depends on 16)

The interactive board of claim 16, wherein a plurality of the elastic wave sensors are directly or indirectly installed on the back of the operation panel.

### Claim 18

A non-transitory computer-readable storage medium storing computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, cause the computer processor to perform a method for recognizing a material, wherein the method comprises:
generating an infrared blocking electrical signal by an infrared touch sensor of an interactive board from a first moment when a touch object performs a touch operation in a touch detection region of the interactive board;
generating an original touch electrical signal by an elastic wave sensor of the interactive board from the first moment;
calculating an average energy value of the original touch electrical signals within a current time window;
calculating a ratio of the average energy value to an historical average energy value, wherein the historical average energy value is an average energy value of the original touch electrical signals within a previous time window;
determining whether the ratio is greater than a preset threshold;
acquiring an initial moment of the current time window as a starting moment of an effective touch electric signal when the ratio is greater than the preset threshold;
acquiring an effective touch electrical signal within a preset time length after the starting moment as elastic wave data; and
determining first material information of the touch object based on the infrared blocking electrical signal and the elastic wave data.
