# US 12,689,674 B1 · Edge computing initialization kit > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,689,674 B1 - Document ID: US12689674B1 - Status: Granted - Kind: B1 - Application number: 18/967,835 - Filed: 2024-12-04 - Granted: 2026-07-21 - Earliest claimed: 2023-12-08 - Assignees: ClearObject Corporation - Applicants: ClearObject Corporation - Inventors: Craig Pauga; Derek Bleyle; Chase Weaver; Aaron Nall - Web page: https://patentgrep.com/patent/US12689674B1 ## CPC - H04L 67/12: specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks - H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A sensing device has a sensor. An edge device that has a processor and memory receives a data stream from the sensor. A communication device connects the edge device to a cloud computing system over a network for processing the data stream and for sending the processed data stream to the cloud computing system. The memory includes instructions for execution by the processor to deploy an inference engine using a pipeline. A capture module receives and stores the data stream within the memory. A pre-processing module modifies the data stream in the memory to compensate for defects contained therein, thereby forming a modified data stream. A deep learning module identifies inferences within the modified data stream, trains a model based upon the inferences, and combines the modified data stream, the model, and the inferences to form the processed data stream. A logging module stores the processed data stream. ## Claims ### Claim 1 An edge computing initialization kit for enabling the processing of sensor data comprising: a sensing device having at least one sensor; an edge device for receiving a data stream from the at least one sensor with the edge device having a processor and memory thereon; and a communication device for connecting the edge device to a cloud computing system over a network, so that the edge device can process the data stream and send the processed data stream to the cloud computing system; wherein the edge device memory includes instructions for execution by the edge device processor to deploy an inference engine using a pipeline having: a capture module for receiving the data stream and storing the data stream within the edge device memory; a pre-processing module for modifying the data stream in the edge device memory to compensate for defects contained therein, thereby forming a modified data stream; a deep learning module for identifying inferences within the modified data stream, for training a model based upon the inferences, and for combining the modified data stream, the model, and the inferences to form the processed data stream; and a logging module for storing the processed data stream. ### Claim 2 (depends on 1) The edge computing initialization kit of claim 1, further comprising: a network switch for connecting the edge device to the communication device. ### Claim 3 (depends on 1) The edge computing initialization kit of claim 1, wherein the at least one sensor is a camera having a lens. ### Claim 4 (depends on 3) The edge computing initialization kit of claim 3, wherein the camera is a camera selected from the group consisting of a security camera and a machine vision camera. ### Claim 5 (depends on 1) The edge computing initialization kit of claim 1, wherein the capture module receives the data stream indirectly from the at least one sensor. ### Claim 6 (depends on 1) The edge computing initialization kit of claim 1, wherein the pipeline includes a customization module for adding at least one data layer to the data stream. ### Claim 7 (depends on 1) The edge computing initialization kit of claim 1, wherein the deep learning module utilizes augmentation to identify inferences within the modified data stream and to train the model. ### Claim 8 (depends on 1) The edge computing initialization kit of claim 1, wherein the deep learning module utilizes segmentation to identify inferences within the modified data stream and to train the model. ### Claim 9 (depends on 1) The edge computing initialization kit of claim 1, wherein the edge device sends output relating to the modified data stream to a visualization hub residing on the cloud computing system. ### Claim 10 (depends on 1) The edge computing initialization kit of claim 1, wherein the output includes inferences. ### Claim 11 An edge computing apparatus for enabling the processing of sensor data comprising: a sensing device having at least one sensor; an edge device coupled to the sensing device to receive a data stream from the at least one sensor with the edge device having a processor and memory thereon; a communication device connected to the edge device; and a cloud computing system connected to the communication device over a network; wherein the edge device memory includes instructions for execution by the edge device processor to deploy an inference engine using a pipeline; and wherein the edge device inference engine pipeline converts data stream into processed data stream to send to the cloud computing system utilizing: a capture module for storing the data stream within the edge device memory after the data stream is received from the at least one sensor; a pre-processing module for modifying the data stream in the edge device memory to compensate for defects contained therein, thereby forming a modified data stream; a deep learning module for identifying inferences within the modified data stream, for training a model based upon the inferences, and for combining the modified data stream, the model, and the inferences to form the processed data stream; and a logging module for storing the processed data stream. ### Claim 12 (depends on 11) The edge computing apparatus of claim 11, further comprising: a network switch for connecting the edge device to the communication device. ### Claim 13 (depends on 11) The edge computing apparatus of claim 11, wherein the at least one sensor is a camera having a lens. ### Claim 14 (depends on 13) The edge computing apparatus of claim 13, wherein the camera is a camera selected from the group consisting of a security camera and a machine vision camera. ### Claim 15 (depends on 11) The edge computing apparatus of claim 11, wherein the capture module receives the data stream indirectly from the at least one sensor. ### Claim 16 (depends on 11) The edge computing apparatus of claim 11, wherein the pipeline includes a customization module for adding at least one data layer to the data stream. ### Claim 17 (depends on 11) The edge computing apparatus of claim 11, wherein at least one of the deep learning module and the capture module utilizes augmentation to identify inferences within the modified data stream and to train the model. ### Claim 18 (depends on 11) The edge computing apparatus of claim 11, wherein at least one of the deep learning module and the capture module utilizes segmentation to identify inferences within the modified data stream and to train the model. ### Claim 19 (depends on 11) The edge computing apparatus of claim 11, wherein the cloud computing system includes a visualization hub for viewing output related to the processed data stream. ### Claim 20 A method for processing of sensor data at the edge comprising: sending a data stream from at least one sensor to an edge device; storing the data stream within the edge device memory; modifying the data stream in the edge device memory to compensate for defects contained therein, thereby forming a modified data stream; identifying inferences within the modified data stream; training a model based upon the inferences; combining the modified data stream, the model, and the inferences to form a processed data stream; logging the processed data stream; and uploading the processed data stream to a cloud computing system through a communication device connected to the edge device over a network.