# US 2021/0333945 A1 · Semiconductor device, character recognition device, and character recognition methods

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

- Number: US 2021/0333945 A1
- Document ID: US20210333945A1
- Status: Published application
- Kind: A1
- Application number: 17/190,975
- Filed: 2021-03-03
- Published: 2021-10-28
- Earliest claimed: 2020-04-23
- Assignees: Renesas Electronics Corporation
- Applicants: Renesas Electronics Corporation
- Inventors: Shoichi HAMADA; Koji HIRANO; Kakeru KIMURA
- Web page: https://patentgrep.com/patent/US20210333945A1

## CPC

- G06F 3/04166: {Details of scanning methods, e.g. sampling time, grouping of sub areas or time sharing with display driving (Synchronisation with the driving of the display or the backlighting unit to avoid interferences generated internally G06F3/04184)}
- G06F 3/0446: {using a grid-like structure of electrodes in at least two directions, e.g. using row and column electrodes}
- G06F 3/0412: {Digitisers structurally integrated in a display}
- G06F 3/044: by capacitive means
- 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)

## Abstract

A semiconductor device includes: a sensor detecting electric capacitance of a touch key group comprising a plurality of touch keys arranged in a matrix; and a control device configured to perform character recognition based on a change in the electric capacitance of the plurality of touch keys detected by the sensor and on a sampling pattern that is time-series data of a loci.

## Claims

### Claim 1

A semiconductor device comprising:
a sensor detecting electric capacitance of a touch key group, the touch key group comprising a plurality of touch keys arranged in a matrix; and
a control device configured to perform character recognition based on a change in electric capacitance of the plurality of touch keys detected by the sensor and on a sampling pattern that is time-series data of a locus.

### Claim 2 (depends on 1)

The semiconductor device according to claim 1,
wherein the control device is configured to detect an ON or OFF state of each of the touch keys by comparing the detected electric capacitance with a predetermined threshold value, and
the sampling pattern is a binary time-series data of the ON or OFF state.

### Claim 3 (depends on 1)

The semiconductor device according to claim 1,
wherein the control device sets a virtual key to an interval between electrodes used for the touch keys, and performs character recognition based on a change in electric capacitance of the virtual key and on a sequence pattern in which the time-series data of the locus is contained in the sampling pattern.

### Claim 4 (depends on 3)

The semiconductor device according to claim 3,
wherein the control device is configured so that the electric capacitance of the virtual key is calculated based on electric capacitance of the electrodes of the adjacent touch keys.

### Claim 5 (depends on 4)

The semiconductor device according to claim 4,
wherein the control device is configured to detect the ON or OFF state of each of the touch keys by comparing the detected electric capacitance with a predetermined threshold value,
the sampling pattern is binary time-series data of the ON or OFF state, and
the control device is configured to calculate the ON or OFF state of the virtual key by a binary logical operation of the ON or OFF states of the adjacent touch keys.

### Claim 6 (depends on 1)

The semiconductor device according to claim 1,
wherein the control device is configured to perform the character recognition based on a change in electric capacitance prepared for each character, a reference pattern that is time-series data of a locus, and the sampling pattern.

### Claim 7 (depends on 1)

The semiconductor device according to claim 1,
wherein the control device has a learned model, and is configured to perform the character recognition by inferring from the sampling pattern by the leaned model.

### Claim 8 (depends on 7)

The semiconductor device according to claim 7,
wherein the control device is configured to standardize a time axis that matches the number of samples of the sampling pattern with a data size of an input layer of the learned model.

### Claim 9 (depends on 7)

The semiconductor device according to claim 7,
wherein the control device sets a virtual key to an interval between electrodes used for the touch keys, and is configured to perform character recognition by inferring from the learned model, the learned model including in the sampling pattern a change in the electric capacitance of the touch keys at a position of the virtual key and the time-series data of the locus.

### Claim 10 (depends on 1)

The semiconductor device according to claim 1,
wherein when detecting that a predetermined touch key in the touch key group is turned ON, the control device is configured to switch between a touch key mode due to inputting one of the touch keys and a character recognition mode due to inputting the plurality of touch keys.

### Claim 11

A character recognition device comprising:
a touch key group having a plurality of touch keys arranged in a matrix;
a sensor detecting electric capacitance of each of the touch keys; and
a control device configured to perform character recognition based on a change in the electric capacitance of each of the touch keys detected by the sensor and on time-series data of a locus.

### Claim 12 (depends on 11)

The character recognition device according to claim 11,
wherein the touch key group has a touch key mode state due to inputting one of the touch keys and a character recognition mode state due to inputting the plurality of touch keys, and
the character recognition device is configured to display a function of each of the touch keys in the touch key mode state and display a reference point for an input in the character recognition mode state.

### Claim 13 (depends on 12)

The character recognition device according to claim 12,
wherein the touch key group has a mode key for switching between the touch key mode state and the character recognition mode state.

### Claim 14 (depends on 13)

The character recognition device according to claim 13,
wherein the mode key is configured to be used for inputting characters in the character recognition mode state.

### Claim 15

A character recognition method comprising:
detecting electric capacitance of each of a plurality of touch keys traced;
expanding the electric capacitance of each of the detected touch keys into a sampling pattern of time-series data; and
performing the character recognition based on the sampling pattern.

### Claim 16 (depends on 15)

The character recognition method according to claim 15, further comprising:
setting a virtual key to an interval between the electrodes used for the touch keys;
calculating electric capacitance of the virtual key based on the electric capacitance detected from the electrodes of the adjacent touch keys;
expanding the electric capacitance of each of the detected touch keys and the electric capacitance of the virtual key into the sampling pattern of the time-series data; and
performing the character recognition based on the sampling pattern.

### Claim 17 (depends on 15)

The character recognition method according to claim 15, further comprising:
performing the character recognition by comparing the sampling pattern with a reference pattern of time-series data provided in advance for each character to be recognized.

### Claim 18 (depends on 15)

The character recognition method according to claim 15, further comprising:
performing the character recognition by inferring from the sampling pattern through a learned model.
