US-12621668-B2 - Providing data integrity and user privacy in neuromuscular-based gesture recognition at a wearable device, and systems and methods of use thereof

US12621668B2US 12621668 B2US12621668 B2US 12621668B2US-12621668-B2

Abstract

A method of providing data integrity to a system that includes a neuromuscular-signal-sensing component of a wearable device is described. The operations of the method can be performed at a neuromuscular-signal-sensing component of a wearable device. The method includes detecting a neuromuscular signal via one or more electrodes. The method further includes generating a digital signal by converting the neuromuscular signal. The method further includes generating an encrypted signal to a controller component of the wearable device, the controller component being distinct from the neuromuscular-signal-sensing component.

Inventors

Charles Liam Goudge

Assignees

META PLATFORMS TECHNOLOGIES, LLC

Dates

Publication Date: 20260505
Application Date: 20230801

Claims (20)

1 . A method of providing data integrity, the method comprising: at a neuromuscular-signal-sensing component of a wearable device: detecting a neuromuscular signal via one or more electrodes; generating a digital signal by converting the neuromuscular signal; generating an encrypted signal by encrypting the digital signal; transmitting the encrypted signal to a controller component of the wearable device, the controller component being distinct from the neuromuscular-signal-sensing component; and in accordance with the neuromuscular-signal-sensing component being validated, adjusting performance of the wearable device based on one or more capabilities of the neuromuscular-signal-sensing component.
2 . The method of claim 1 , wherein the neuromuscular-signal-sensing component and the controller component are arranged on a wrist-wearable device.
3 . The method of claim 1 , wherein: the wearable device comprises one or more additional neuromuscular-signal-sensing components; and each additional neuromuscular-signal-sensing component comprising a respective encryption component.
4 . The method of claim 1 , wherein the neuromuscular-signal-sensing component comprises the one or more electrodes, an analog frontend (AFE), an analog-to-digital converter (ADC), and encryption logic.
5 . The method of claim 4 , wherein: the analog frontend, the analog-to-digital converter, and the encryption logic are arranged on electrode silicon coupled to the one or more electrodes; and the electrode silicon is enclosed in a housing.
6 . The method of claim 1 , further comprising, at the controller component: receiving the encrypted signal from the neuromuscular-signal-sensing component; generating a decrypted signal by decrypting the encrypted signal; and validating the neuromuscular-signal-sensing component based on the decrypted signal.
7 . The method of claim 6 , wherein validating the neuromuscular-signal-sensing component comprises identifying one or more capabilities of the neuromuscular-signal-sensing component.
8 . The method of claim 6 , further comprising, in accordance with the neuromuscular-signal-sensing component not being validated, generating a notification for a user of the wearable device.
9 . The method of claim 6 , further comprising, at the controller component: receiving a signal from an additional neuromuscular-signal-sensing component; validating the additional neuromuscular-signal-sensing component based on the received signal; in accordance with the additional neuromuscular-signal-sensing component being validated, activating an operating mode of the wearable device; and in accordance with the additional neuromuscular-signal-sensing component not being validated, forgoing activating the operating mode of the wearable device.
10 . The method of claim 9 , further comprising adjusting a machine-learning model based on a number and type of neuromuscular-signal-sensing components coupled to the controller component.
11 . The method of claim 1 , wherein adjusting performance of the wearable device includes adjusting a machine-learning model based on one or more capabilities of the neuromuscular-signal-sensing component.
12 . The method of claim 1 , further comprising, at the neuromuscular-signal-sensing component: receiving a secret; and storing the secret for use with subsequent encryption operations.
13 . A wearable device, comprising: one or more processors; and memory, comprising instructions, which, when executed by the one or more processors, cause operations at the wearable device for: at a neuromuscular-signal-sensing component of a wearable device: detecting a neuromuscular signal via one or more electrodes; generating a digital signal by converting the neuromuscular signal; generating an encrypted signal by encrypting the digital signal; transmitting the encrypted signal to a controller component of the wearable device, the controller component being distinct from the neuromuscular-signal-sensing component; and in accordance with the neuromuscular-signal-sensing component being validated, adjusting performance of the wearable device based on one or more capabilities of the neuromuscular-signal-sensing component.
14 . The wearable device of claim 13 , wherein the neuromuscular-signal-sensing component and the controller component are arranged on a wrist-wearable device.
15 . The wearable device of claim 13 , further comprising: one or more additional neuromuscular-signal-sensing components, each additional neuromuscular-signal-sensing component comprising a respective encryption component.
16 . The wearable device of claim 13 , wherein: the neuromuscular-signal-sensing component comprises the one or more electrodes, an analog frontend (AFE), an analog-to-digital converter (ADC), and encryption logic.
17 . The wearable device of claim 16 , wherein: the analog frontend, the analog-to-digital converter, and the encryption logic are arranged on electrode silicon coupled to the one or more electrodes; and the electrode silicon is enclosed in a housing.
18 . The wearable device of claim 13 , wherein the memory further comprises instructions for: at the controller component: receiving the encrypted signal from the neuromuscular-signal-sensing component; generating a decrypted signal by decrypting the encrypted signal; and validating the neuromuscular-signal-sensing component based on the decrypted signal.
19 . The wearable device of claim 18 , wherein validating the neuromuscular-signal-sensing component comprises identifying one or more capabilities of the neuromuscular-signal-sensing component.
20 . A non-transitory computer-readable storage medium, comprising instructions, which, when executed by one or more processors of an electronic device, cause performance of operations for: at a neuromuscular-signal-sensing component of a wearable device: detecting a neuromuscular signal via one or more electrodes; generating a digital signal by converting the neuromuscular signal; generating an encrypted signal by encrypting the digital signal; transmitting the encrypted signal to a controller component of the wearable device, the controller component being distinct from the neuromuscular-signal-sensing component; and in accordance with the neuromuscular-signal-sensing component being validated, adjusting performance of the wearable device based on one or more capabilities of the neuromuscular-signal-sensing component.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Prov. App. No. 63/486,448, filed on Feb. 22, 2023, and entitled “Providing Data Integrity and User Privacy in Neuromuscular-Based Gesture Recognition at a Wearable Device, and Systems and Methods of Use Thereof,” which is hereby incorporated by reference in its entirety. TECHNICAL FIELD The present disclosure relates generally to biopotential-signal-sensing devices, systems, and methods, including but not limited to techniques for providing data integrity for wearable biopotential-signal-sensing devices (e.g., validation of encrypted signals provided to a controller component from a neuromuscular-signal sensor of a wearable device). BACKGROUND Biopotential-signal-sensing applications, such as electromyography (EMG) and electrocardiography (ECG), detect and interpret small electrical signals in the body (e.g., neuromuscular signals). For example, users of wearable devices can perform gestures that are detected by neuromuscular-signal-sensing components (e.g., biopotential-signal sensors that include neuromuscular-signal-sensing electrodes) and interpreted to provide a man-machine interface. As another example, the biopotential signals can be used to monitor a user's vitals (e.g., while the user is working out). Each of these biopotential signals may be more personal to users than other signals and/or computer inputs (e.g., keyboard/mouse activity). Therefore, it is important to protect the biopotential signals and/or data generated from the biopotential signals. SUMMARY As described herein, protecting the biopotential signals can include preventing a malicious actor from obtaining the signals and/or generated data, as well as inserting fake biopotential signals to confuse/manipulate the man-machine interface. Additionally, providing security between sensors and a compute core (e.g., a central processing unit (CPU) configured to receive data from sensors of a wearable device) can prevent insertion of invalid components that lack the capabilities of valid components and can therefore cause system failures. For example, encrypting data obtained by and/or translated from biopotential-signal sensors allows for such data to be protected from nefarious actors. A validation process based on such encryption also provides source identification when components related to biopotential-signal sensing are replaced on and/or added to a wearable device. Additionally, once a common encryption scheme is established for biopotential-signal sensing at a wearable device (e.g., via a secret, key, seed, and/or token), more sophisticated functionality (e.g., trained artificial intelligence and/or machine-learning models) can be provided directly to sensors and other constituent components that have more limited computing functionality without sacrificing data protection goals. Such localization techniques can also reduce overhead time and/or bandwidth for certain computational tasks by reducing the amount of communication between separate hardware components of the wearable device. The methods, systems, and devices described herein allow users and manufacturers of wearable devices that include biopotential-signal sensors, and constituent components thereof, to ensure that data is protected and/or meets performance criteria (e.g., with respect to encryption, durability, sensing capability, and/or data integrity) via decryption and validation of the biopotential signals by a controller component of the wearable device. One example of a method for providing data integrity at a wearable device is provided. Operations of this example method are performed at a neuromuscular-signal-sensing component of the wearable device. The example method includes detecting a neuromuscular signal via one or more electrodes. The example method includes generating a digital signal by converting the neuromuscular signal. The example method includes generating an encrypted signal by encrypting the digital signal. And the example method includes transmitting the encrypted signal to a controller component of the wearable device, the controller component being distinct from the neuromuscular-signal-sensing component. Several examples that can be actuated so as to cause the operations described above to be performed are shown in the sequences of FIGS. 1A-3B. In some embodiments, a computing device (e.g., a wrist-wearable device or a head-mounted device, or an intermediary device, such as a smartphone or desktop or laptop computer) includes one or more processors, memory, a display (in some embodiments, the display can be optional, such as for certain example intermediary devices that can coordinate operations at the wrist-wearable device and the head-mounted device, and thus have ample processing and power resources, but need not have its own display), and one or more programs stored in the memory. The programs are configured for execution by the one or more processors. The one or