US-12626161-B2 - Dynamic inferencing at an IoT edge

US12626161B2US 12626161 B2US12626161 B2US 12626161B2US-12626161-B2

Abstract

A method is provided for performing dynamic inferencing at a node configured to communicate with other nodes of an IoT hierarchy. In the method, a schema for an asset object associated with one or more of at least one physical process and at least one physical device is received at the node. The schema is formatted according to an inferencing engine model format. An artificial intelligence model capable of being executed in an inferencing engine is received at the node. Data indicative of one or more of a current state of at least one physical process and a current state of at least one physical device is received at the node. The received data according to the schema and an inferencing engine are processed at the node. The inferencing engine generates a new predictive attribute based on the set of attributes, and the processing normalizes the received data according to the schema to generate normalized data, the normalized data includes the predictive attribute from the inferencing engine. A notification is then provided based on one or more rules for the physical process and physical device.

Inventors

David Aaron Allsbrook
Eric Michael Simone
Rajas Sanjay Deshpande

Assignees

CLEARBLADE, INC.

Dates

Publication Date: 20260512
Application Date: 20240822

Claims (20)

1 . A method for performing dynamic inferencing at a node configured to communicate with other nodes of an internet of things (IOT) hierarchy, comprising: receiving, at the node, a schema for an asset object, wherein the schema is formatted according to an inferencing engine model format; receiving, at the node, an artificial intelligence model capable of being executed in an inferencing engine; receiving data, at the node, indicative of a current state of the asset object; processing, at the node, the received data according to the schema and the inferencing engine, wherein the schema comprises a set of attributes specific to the current state of the asset object, wherein the inferencing engine generates a new predictive attribute based on the set of attributes, and wherein the processing comprises normalizing the received data according to the schema to generate normalized data; and providing, from the node, the normalized data, wherein the normalized data is provided via an API stored at the node, and wherein the normalized data includes the predictive attribute from the inferencing engine.
2 . The method of claim 1 , wherein the asset object is associated with at least one of a physical process, a physical device, a virtual process, or a virtual device.
3 . The method of claim 2 , wherein the current state of the asset object comprises a current state of at least one of the physical process, the physical device, the virtual process, or the virtual device.
4 . The method of claim 3 , wherein the current state of the physical process is indicative of at least one attribute of the physical process, and wherein the current state of the physical device is indicative of at least one attribute of the physical device, and wherein the current state of the virtual process is indicative of at least one attribute of the virtual process, and wherein the current state of the virtual device is indicative of at least one attribute of the virtual device.
5 . The method of claim 4 , wherein the at least one attribute of at least one of the physical process, the physical device, the virtual process, or the virtual device is defined by an end user.
6 . The method of claim 2 , wherein the method further includes determining, at the node, that a notification should be provided based on one or more rules of physical process, the physical device, the virtual process, or the virtual device.
7 . The method of claim 6 , wherein the method further includes providing, from the node, the notification.
8 . The method of claim 1 , wherein the asset object is defined by an end user.
9 . The method of claim 1 , wherein the method further includes updating, at the node, the schema based on the received data.
10 . The method of claim 9 , wherein updating the schema includes adjusting an attribute of the asset object.
11 . The method of claim 1 , wherein the asset object is associated with a physical process.
12 . The method of claim 1 , wherein the asset object is associated with a physical device.
13 . The method of claim 1 , wherein the asset object is associated with a virtual process.
14 . The method of claim 1 , wherein the asset object is associated with a virtual device.
15 . A method for performing dynamic inferencing at a node configured to communicate with other nodes of an internet of things (IoT) hierarchy, comprising: defining at least one physical process or virtual process and at least one physical device or virtual device associated with an asset object; receiving, at a node, an AI model capable of being executed in an inferencing engine; receiving, at the node, received process data indicative of a current state of the at least one physical process or virtual process, the current state of the at least one physical process or virtual process is indicative of at least one attribute of the at least one physical process; receiving, at the node, received device data indicative of a current state of the at least one physical device or virtual device, the current state of the at least one physical device or virtual device is indicative of at least one attribute of the at least one physical device or virtual device; processing the received process data and the received device data according to an inferencing engine; generating a new predictive attribute based on the received process data and received device data; and providing a notification using the new predictive attribute.
16 . The method of claim 15 , wherein the step of processing the received process data and the received device data according to the inferencing engine comprises normalizing the received process data and the received device data to generate normalized data.
17 . The method of claim 15 , further comprising automatically modifying the at least one physical process based upon the new predictive attribute.
18 . The method of claim 15 , wherein the notification comprises an indication of service needed on the asset object.
19 . The method of claim 15 , wherein the method further includes receiving, at the node, a schema for the asset object, wherein the schema is formatted according to an inferencing engine model format.
20 . The method of claim 19 , wherein the method further includes updating, at the node, the schema based on the received process data and the received device data, and wherein updating the schema includes adjusting an attribute of the asset object.

Description

CROSS REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. patent application Ser. No. 18/131,987, entitled “Dynamic Inferencing at an IoT Edge,” and filed Apr. 7, 2023, which is a continuation in part of U.S. patent application Ser. No. 17/032,955, entitled “Edge Synchronization Systems and Methods,” and filed Sep. 25, 2020, which claims priority to U.S. patent application Ser. No. 16/357,779, titled “A Method for Receiving a Request for an API in an IoT Hierarchy” and filed on Mar. 19, 2019, which claims priority to U.S. Provisional Application Ser. No. 62/647,447, titled “System and Method for IoT Systems of Logic Across a Continuum of Computers,” filed on Mar. 23, 2018. This application is also a continuation-in-part of and claims priority to U.S. patent application Ser. No. 17/856,411, entitled “User Configurable IoT Interface,” and filed on Jul. 1, 2022, which claims priority to U.S. Provisional Patent Application Ser. No. 63/217,550, titled “User-Configurable IoT Interface” and filed on Jul. 1, 2021. This application also claims priority to U.S. Provisional Patent Application Ser. No. 63/328,798, titled “Systems and Methods for Dynamic Inferencing at an IoT Edge” and filed on Apr. 8, 2022. The entire contents of each of the foregoing are incorporated herein by reference in their entireties. FIELD OF THE INVENTION The field of the invention relates to a system and method for using OT Dynamic Inferencing to make predictions on demand across an Internet of Things (IoT) hierarchy. BACKGROUND IoT is becoming more prevalent, and solutions are beginning to be a part of our everyday lives. Over the last few years, there are trends like MQTT, API-first, IoT Platform, Intelligent Edge. As the number of software applications have grown, many developers and application owners have stored and run their applications in the “cloud”, e.g., in large remote server farms accessible over the internet. While many of these cloud providers are structured to house and protect large amounts of data and applications, having applications run remotely has some disadvantages, including the cost of communicating to and from the cloud, as well as requiring an internet connection, and the time it takes to send or receive information from the cloud that may be hundreds or thousands of miles away. Moreover, in most instances, there is not a direct “connection” between a user of a particular software or app and the cloud. Rather, there may be a large number of hubs or “hops” for a user to ultimately connect to the desired cloud location. This can cause particular problems when there is a large amount of data or there are a lot of requests to and from the cloud. Considering the internet infrastructure, there may be a server that a person interacts with, but there are lots of “hops” along the way between a user's browser and that content. When looking at a static website a user may never actually even communicate with actual hosting server but instead a cached version stored in a CDN. One example outside of the IoT space is NETFLIX Open Connect CDN. It takes a long time to pull all those movies and television shows from a central cloud to homes around the world. Thus, to address this, the NETFLIX Open Connect hardware local ISPs keep caches of content. This is a massive hardware/software build for NETFLIX specific to its use case, but moves the data from a single central location, to having multiple copies of content distributed geographically closer to its users. While IoT is different than streaming static video, IoT will be a tremendous user of bandwidth and demand high speeds. Another potential disadvantage of running applications on remote devices is that there may be times when a remote device is not able to communicate with other devices of the network, a developmental or operational platform, or the cloud. This is problematic because the “disconnected” device cannot send or receive information which may be critical to functioning of the device and on which other devices of the system may depend. In addition, when a connection is restored, an application running on the device may have experience problems providing the appropriate data, and may lack updates needed to allow the application to run properly. Improved techniques for monitoring and managing assets from edge devices are desired. SUMMARY Applicant has developed systems and methods involving Edge Computer Continuum, representing many layers of computer infrastructure made available to be used as part of the whole IoT application to provide a hierarchy-based, fastest path to every device. The various hardware located at the various hubs between a user and the server that the user interacts with, for example, the routing gear, the cell phone towers, and the satellites, all represent computing opportunities for IoT applications. Applicant's systems and methods utilize the ubiquitous computing in today's IoT capable world to implement an edge compute c