System and method for detecting handwriting problems
A system for detecting handwriting problems may include a handwriting instrument including a body extending longitudinally between a first end and a second end, the first end having a writing tip which is able to write on a support, the handwriting instrument further including at least one motion sensor configured to acquire data on the handwriting of the user when a user is using the handwriting instrument, and one calculating unit communicating with the motion sensor and configured to analyze the data by an artificial intelligence trained to detect whether the user has handwriting problems.
1. A system for detecting handwriting problems comprising:
a handwriting instrument including a body extending longitudinally between a first end and a second end, the first end having a writing tip which is able to write on a support;
a detection device distinct from the handwriting instrument, the detection device comprising a body configured to be mounted on the second end of the handwriting instrument and a protuberant tip extending from the body of the detection device and configured to be inserted in the body of the handwriting instrument;
wherein the detection device comprises:
two motion sensors configured to acquire data on handwriting of a user when the user is using the handwriting instrument, said two motion sensors being three-axis accelerometers, or one three-axis accelerometer and
one three-axis gyroscope; and-one calculating unit communicating with the two motion sensors and configured to analyze the data by an artificial intelligence trained to detect whether the user has handwriting problems;
wherein a first motion sensor of the two motion sensors is provided on the protuberant tip of the detection device that is configured to be inserted in the body of the handwriting instrument and a second motion sensor of the two motion sensors is provided in the body of the detection device;
wherein the artificial intelligence is at least one neural network configured to be trained by segmentation and classification of strokes to determine timestamps of the strokes on the support based upon motion signals sensed by the two motion sensors.
2. The system according to claim 1 , wherein the detection device further includes a short-range radio communication interface configured to communicate raw data acquired by the two motion sensors and a battery.
3. The system according to claim 1 , wherein the one three-axis gyroscope comprises a wake-up input suited for receiving a wake-up signal from the one calculating unit when a movement is detected by the one three-axis accelerometer, the one three-axis gyroscope being configured for switching into an active state when the wake-up signal is received.
4. The system according to claim 1 , further comprising a pressure sensor, wherein the one calculating unit is configured to receive the data acquired by the pressure sensor.
5. The system according to claim 1 , further comprising a stroke sensor configured to acquire stroke data while the user is using the handwriting instrument, the artificial intelligence being further trained with the stroke data to determine the handwriting problems.
6. The system according to claim 5 , wherein the stroke sensor is the two motion sensors.
7. The system according to claim 1 , wherein the artificial intelligence is further configured to determine when the user is actually using the handwriting instrument on the support and to differentiate data corresponding to an actual use of the handwriting instrument from data acquired while the handwriting instrument is only being held in air.
8. The system according to claim 1 , wherein the handwriting instrument is a pen, a pencil a brush or any other element allowing the user to write or draw with it on the support.
9. The system according to claim 1 , wherein the artificial intelligence is further configured to transcribe raw data acquired by the two motion sensors into handwriting characters depicted on a mobile device.
10. The system according to claim 1 , wherein the support is a non-electronic surface.
11. The system according to claim 1 , wherein the one calculating unit comprises a volatile memory to store data acquired by the two motion sensors and a non-volatile memory to store a model enabling the detection of the handwriting problems.
12. The system according to claim 1 , wherein the at least one neural network is further configured to acquire data during use of the handwriting instrument and to determine if the user is forming letters and numbers correctly.