IP Library Granted Patent US 12,411,754
Granted Patent B2
US 12,411,754 · App. 18/283,542 · Granted Sep 9, 2025

Device performance monitoring system

Inventors: Guenael Thomas Strutt (San Francisco, CA); Steven Paul Lewis (Los Angeles, CA)
Assignee: Elliptic Laboratories ASA
G06F11/3612G06F11/3006G06F11/3447
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,411,754
App. No.
18/283,542
Granted
Sep 9, 2025
Kind
B2
Abstract

The present invention is related to a system and corresponding method and computer implemented software for improving performance of at least one electronic devices, said devices including at least one sensors and a model defining the device reaction in response to data produced by at least one of said sensors. The system includes a model generator configured to analyze the data produced from said sensors and the reactions to the data, and register errors in the reactions as compared with the intended reactions, wherein the model generator is configured to adjust the device model by minimizing errors between the actual output of the model and the desired output of the model, based on a set of samples recorded on said at least one electronic devices, wherein the recorded samples include information related to which of a number of predefined states the device is in at the occurrence of the error, the time of the occurred error, and the number of errors at the specified time and/or state.

Claims (69)

1. A system for improving performance of at least one electronic device, the at least one electronic device comprising at least one sensor and a model defining device reaction in response to data produced by at least one of the at least one sensor, the system comprising:

a model generator configured to analyze the data produced from the at least one sensor and the reactions to the data and register errors in the reactions as compared with intended reactions;

wherein the model generator is configured to adjust the device model by minimizing errors between an actual output of the model and a desired output of the model, based on a set of samples recorded on at least one of the at least one electronic device;

wherein the recorded samples include information related to:

which of a number of predefined states a device is in at the occurrence of the error;

the time of the occurred error; and

the number of errors at at least one of a specified time and state; and

wherein the predefined states are related to transition and include a steady state, a pre-transition state, a transition state, and a post-transitions state.

2. The system according to claim 1 , wherein the model generator is a network system communicating with a number of devices.

3. The system according to claim 1 , wherein the device is provided with a user interface configured to receive error reports from a device user.

4. The system according to claim 1 , wherein the errors are registered at a measured deviation between the expected reaction of the device and the measured reaction.

5. The system according to claim 1 , being configured to analyze the error detections and related measurements in the sampled data based on a predetermined set of rules, the system being configured to iteratively reconfigure the model so as to reduce the number of error detections.

6. The system according to claim 1 , wherein the sensors include at least one of the following: cameras, acoustic sensors, inertial sensors, radar or optical measurements.

7. A system for improving performance of at least one electronic device, the at least one electronic device comprising at least one sensor and a model defining device reaction in response to data produced by at least one of the at least one sensor, the system comprising:

a model generator configured to analyze the data produced from the at least one sensor and the reactions to the data and register errors in the reactions as compared with intended reactions;

wherein the model generator is configured to adjust the device model by minimizing errors between an actual output of the model and a desired output of the model, based on a set of samples recorded on at least one of the at least one electronic device;

wherein the recorded samples include information related to:

which of a number of predefined states a device is in at the occurrence of the error;

the time of the occurred error; and

the number of errors at at least one of a specified time and state; and

wherein the specific times include the beginning of a state, the middle of a state, the end of a state, the entirety of a state, or a combination thereof.

8. A system for improving performance of at least one electronic device, the at least one electronic device comprising at least one sensor and a model defining device reaction in response to data produced by at least one of the at least one sensor, the system comprising:

a model generator configured to analyze the data produced from the at least one sensor and the reactions to the data and register errors in the reactions as compared with intended reactions;

wherein the model generator is configured to adjust the device model by minimizing errors between an actual output of the model and a desired output of the model, based on a set of samples recorded on at least one of the at least one electronic device;

wherein the recorded samples include information related to:

which of a number of predefined states a device is in at the occurrence of the error;

the time of the occurred error; and

the number of errors at at least one of a specified time and state; and

wherein the count of errors includes a boolean count, and aggregate count, or a duration ratio.

9. A system for improving performance of at least one electronic device, the at least one electronic device comprising at least one sensor and a model defining device reaction in response to data produced by at least one of the at least one sensor, the system comprising:

a model generator configured to analyze the data produced from the at least one sensor and the reactions to the data and register errors in the reactions as compared with intended reactions;

wherein the model generator is configured to adjust the device model by minimizing errors between an actual output of the model and a desired output of the model, based on a set of samples recorded on at least one of the at least one electronic device;

wherein the recorded samples include information related to:

which of a number of predefined states a device is in at the occurrence of the error;

the time of the occurred error; and

the number of errors at at least one of a specified time and state;

wherein the model generator is a network system communicating with a number of devices; and

wherein the generator is also adapted to communicate with the manufacturer, being provided with an initial model and expected performance of the device.

10. A method for improving the performance of a device of a specific type, the method comprising:

in at least one device, sampling information related to error detections and measurements related to the error detections, the error detections including reports from users or errors detected by device software;

in model generator, receiving the information sampled by the device, the model generator also including storage means including information related to the device software and performance, as well as a model specifying the device performance;

in the generator, adjusting the model based on the reported errors and related measurements;

transmitting the adjusted model to the device, the device updating the device software to correspond with the adjusted model; and

wherein the model generator adjusts the device model by minimizing errors between the actual output of the model and the desired output of the model, based on a set of samples recorded on the at least one electronic devices, wherein the recorded samples include information related to:

which of a number of predefined states the device is in at the occurrence of the error;

the time of the occurred error; and

the number of errors at at least one of the specified time and state; and

wherein the predefined states are related to transition and include a steady state, a pre-transition state, a transition state, and a post-transitions state.

11. A method for improving the performance of a device of a specific type, the method comprising:

in at least one device, sampling information related to error detections and measurements related to the error detections, the error detections including reports from users or errors detected by device software;

in model generator, receiving the information sampled by the device, the model generator also including storage means including information related to the device software and performance, as well as a model specifying the device performance;

in the generator, adjusting the model based on the reported errors and related measurements;

transmitting the adjusted model to the device, the device updating the device software to correspond with the adjusted model;

wherein the model generator adjusts the device model by minimizing errors between the actual output of the model and the desired output of the model, based on a set of samples recorded on the at least one electronic devices, wherein the recorded samples include information related to:

which of a number of predefined states the device is in at the occurrence of the error,

the time of the occurred error, and

the number of errors at at least one of the specified time and state; and

wherein the specific times include the beginning of a state, the middle of a state, the end of a state, the entirety of a state, or a combination thereof.

12. A method for improving the performance of a device of a specific type, the method comprising:

in at least one device, sampling information related to error detections and measurements related to the error detections, the error detections including reports from users or errors detected by device software;

in model generator, receiving the information sampled by the device, the model generator also including storage means including information related to the device software and performance, as well as a model specifying the device performance;

in the generator, adjusting the model based on the reported errors and related measurements;

transmitting the adjusted model to the device, the device updating the device software to correspond with the adjusted model;

wherein the model generator adjusts the device model by minimizing errors between the actual output of the model and the desired output of the model, based on a set of samples recorded on the at least one electronic devices, wherein the recorded samples include information related to:

which of a number of predefined states the device is in at the occurrence of the error,

the time of the occurred error, and

the number of errors at at least one of the specified time and state; and

wherein the count of errors includes a boolean count, and aggregate count, or a duration ratio.

13. A computer-program product comprising a non-transitory computer-usable medium having computer-readable program code embodied therein, the computer-readable program code adapted to be executed to implement the method of claim 10 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 8, 2023
From: STRUTT, GUENAEL THOMAS; LEWIS, STEVEN PAUL
To: ELLIPTIC LABORATORIES ASA
Reel/Frame 065496/0773 →
Priority Claims (1)
NO 20210589 · May 11, 2021 · national
Continuity (2)
Provisional Application 63165369 · Mar 24, 2021
Related Publication 20240176725A1 · May 30, 2024
References Cited (8)
US 10162693B1 · Contino · 2018 [cited by examiner]
US 10353764B1 · Cazzanti · 2019 [cited by examiner]
US 20230236927A1 · Tang · 2023 [cited by examiner]
Lid, Eirik, “Sensor Fusion of Ultrasound and Motion Data for Gesture Recognition on Smartphones,” Master of Science in Cybernetics and Robotics, Department of Engineering Cybernetics, Norwegian University of Science and… [cited by examiner]
Patent Cooperation Treaty, International Application No. PCT/EP2022/057423, “International Search Report,” Aug. 18, 2022, 2 pages. [cited by applicant]
Lid, Eirik, “Sensor Fusion of Ultrasound and Motion Data for Gesture Recognition on Smartphones,” Master of Science in Cybernetics and Robotics, Department of Engineering Cybernetics, Norwegian University of Science and… [cited by applicant]
Wang, Zhengjie et al., “Hand Gesture Recognition Based on Active Ultrasonic Sensing of Smartphone: A Survey,” IEEE Access, vol. 7, Aug. 8, 2019, pp. 111897-111922, DOI: 10.1109/ACCESS.2019.2933987. [cited by applicant]
Zhang, Jie M. et al., “Machine Learning Testing: Survey, Landscapes and Horizons,” arXiv:1906.10742, Jun. 19, 2019, Cornell University Library, Ithaca, NY, 37 pages. [cited by applicant]