IP Library Granted Patent US 12,646,344
Granted Patent B1
US 12,646,344 · App. 19/313,189 · Granted Jun 2, 2026

Machine learning framework to detect and monitor compliance matters

Inventors: Christopher Carson (Boca Raton, FL); Sergey Sukov (Livermore, CA); Bo Shen (Fremont, CA)
Assignee: EchoTwin AI, Inc.
G06V20/70G06N20/20G06V20/52G06V2201/07
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 12,646,344
App. No.
19/313,189
Granted
Jun 2, 2026
Kind
B1
Abstract

System apparatus, article of manufacture, method and/or computer program embodiments are provided for detecting and monitoring compliance matters. An example method may include obtaining a first set of image data corresponding to an environment from one or more image sensors; processing the first set of image data using a first machine learning algorithm to yield annotated image data that identifies at least one object within the environment; processing the annotated image data using a second machine learning algorithm to determine one or more attributes associated with the at least one object within the environment; and generating, based on the one or more attributes, an evidence package corresponding to the at least one object within the environment, the evidence package being configured to facilitate a determination of one or more action items associated with the at least one object.

Claims (49)

1 . A computer-implemented method comprising:

obtaining, from one or more image sensors, a first set of image data corresponding to an environment;

processing the first set of image data using a first machine learning algorithm to yield annotated image data that identifies at least one object within the environment;

processing the annotated image data using a second machine learning algorithm to determine one or more attributes associated with the at least one object within the environment;

generating, based on the one or more attributes, an evidence package corresponding to the at least one object within the environment, the evidence package being configured to facilitate a determination of one or more action items associated with the at least one object;

obtaining, from one or more image sensors, a second set of image data corresponding to the environment;

processing the second set of image data to identify a change in the one or more attributes associated with the at least one object within the environment; and

determining, based on the change in the one or more attributes, that the one or more action items associated with the at least one object are complete.

2 . The computer-implemented method of claim 1 , further comprising:

providing the evidence package to a computing system, the computing system implementing one or more operations to determine the one or more action items based on the evidence package.

3 . The computer-implemented method of claim 1 , further comprising:

capturing the first set of image data in response to a trigger condition.

4 . The computer-implemented method of claim 1 , wherein the evidence package corresponds to at least one of a safety compliance matter, a regulatory compliance matter, a service compliance matter, a traffic compliance matter, a permit compliance matter, and a community compliance matter.

5 . The computer-implemented method of claim 1 , wherein the first machine learning algorithm corresponds to an object detection model and the second machine learning algorithm corresponds to a vision language model (VLM).

6 . The computer-implemented method of claim 5 , wherein the second machine learning algorithm the annotated image data to determine the one or more attributes based on domain relevant data stored in one or more contextual knowledge databases.

7 . The computer-implemented method of claim 1 , further comprising:

sending the first set of image data from an edge device to a cloud server, wherein the cloud server is configured to implement at least one of the first machine learning algorithm and the second machine learning algorithm.

8 . The computer-implemented method of claim 1 , further comprising:

sending the evidence package to a third-party system corresponding to an entity that is responsible for addressing the one or more action items.

9 . A system comprising:

at least one memory; and

at least one processor coupled to the at least one memory, the at least one processor is configured to perform operations comprising:

obtaining, from one or more image sensors, a first set of image data corresponding to an environment;

processing the first set of image data using a first machine learning algorithm to yield annotated image data that identifies at least one object within the environment;

processing the annotated image data using a second machine learning algorithm to determine one or more attributes associated with the at least one object within the environment;

generating, based on the one or more attributes, an evidence package corresponding to the at least one object within the environment, the evidence package being configured to facilitate a determination of one or more action items associated with the at least one object;

obtaining, from one or more image sensors, a second set of image data corresponding to the environment;

processing the second set of image data to identify a change in the one or more attributes associated with the at least one object within the environment; and

determining, based on the change in the one or more attributes, that the one or more action items associated with the at least one object are complete.

10 . The system of claim 9 , wherein the at least one processor is configured to perform operations further comprising:

providing the evidence package to a computing system, the computing system implementing one or more operations to determine the one or more action items based on the evidence package.

11 . The system of claim 9 , wherein the at least one processor is configured to perform operations further comprising:

capturing the first set of image data in response to a trigger condition.

12 . The system of claim 9 , wherein the evidence package corresponds to at least one of a safety compliance matter, a regulatory compliance matter, a service compliance matter, a traffic compliance matter, a permit compliance matter, and a community compliance matter.

13 . The system of claim 9 , wherein the first machine learning algorithm corresponds to an object detection model and the second machine learning algorithm corresponds to a vision language model (VLM).

14 . The system of claim 9 , wherein the at least one processor is configured to perform operations further comprising:

providing the first set of image data from an edge device to a cloud server, wherein the cloud server is configured to implement at least one of the first machine learning algorithm and the second machine learning algorithm.

15 . The system of claim 9 , wherein the at least one processor is configured to perform operations further comprising:

providing the evidence package to a third-party system corresponding to an entity that is responsible for addressing the one or more action items.

16 . A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, causes the at least one computing device to perform operations comprising:

obtaining, from one or more image sensors, a first set of image data corresponding to an environment;

processing the first set of image data using a first machine learning algorithm to yield annotated image data that identifies at least one object within the environment;

processing the annotated image data using a second machine learning algorithm to determine one or more attributes associated with the at least one object within the environment;

generating, based on the one or more attributes, an evidence package corresponding to the at least one object within the environment, the evidence package being configured to facilitate a determination of one or more action items associated with the at least one object;

obtaining, from one or more image sensors, a second set of image data corresponding to the environment;

processing the second set of image data to identify a change in the one or more attributes associated with the at least one object within the environment; and

determining, based on the change in the one or more attributes, that the one or more action items associated with the at least one object are complete.

17 . The non-transitory computer-readable medium of claim 16 , wherein the at least one computing device further performs operations comprising:

providing the evidence package to a computing system, the computing system implementing one or more operations to determine the one or more action items based on the evidence package.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 28, 2025
From: CARSON, CHRISTOPHER; SUKOV, SERGEY; SHEN, BO
To: ECHOTWIN AI, INC.
Reel/Frame 072710/0256 →
Continuity (1)
Provisional Application 63770777 · Mar 12, 2025
References Cited (6)
US 11003919B1 · Ghadiok et al. · 2021 [cited by applicant]
US 20190164019A1 · Djiofack · 2019 [cited by examiner]
US 20250299463A1 · Shin · 2025 [cited by examiner]
Yuan, Zihao, Fangfang Xie, and Tingwei Ji. “Patrol agent: An autonomous uav framework for urban patrol using on board vision language model and on cloud large language model.” In 2024 6th International Conference on Rob… [cited by examiner]
Ding H, Du Y, Xia Z. Urban Road Anomaly Monitoring Using Vision-Language Models for Enhanced Safety Management. Applied Sciences. Feb. 26, 2025;15(5):2517. (Year: 2025). [cited by examiner]
Ahmed, Afaq, Muhammad Farhan, Hassan Eesaar, Kil To Chong, and Hilal Tayara. “From detection to action: A multimodal AI framework for traffic incident response.” Drones 8, No. 12 (2024): 741. (Year: 2024). [cited by examiner]
Cited By (1)
US 12,737,374