How a Cloud Server Manages AI Services on Local Edge Devices
This patent describes a system where a central cloud server helps set up and run Artificial Intelligence tasks on local devices, like smart cameras, by sending them specific AI programs and then displaying the results.
Original patent title: “Service management method and system, and configuration server and edge computing device”
This patent describes a system where a central cloud server helps set up and run Artificial Intelligence tasks on local devices, like smart cameras, by sending them specific AI programs and then displaying the results. Owned by BOE Technology Group Co with 23 claims, and it is expected to expire in 2043.
Coverage
What does this patent actually cover?
This system allows a cloud-based configuration server to manage Artificial Intelligence (AI) services on local edge computing devices. The configuration server provides a web page where a user can specify which edge computing device, terminal device, and AI service are needed. An AI service, which includes one or more 'edge applications,' is then deployed by the cloud server onto the chosen edge computing device, as described in claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1. The edge computing device then acquires a multimedia data stream from a terminal device, like a camera, and uses the deployed AI application to process this data, performing 'application inference' to get a result. This result is sent back to the configuration server and then displayed on a connected display device. For example, a cloud server could deploy a facial recognition AI application to a local smart camera (edge device) to analyze video (multimedia data stream) from the camera (terminal device), then display alerts on a screen.
The gap
What does this patent NOT cover?
- Does not cover systems where the AI service runs entirely on the cloud server without deployment to a local edge computing device, as claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1 specifies the edge device performs inference.
- Does not cover systems where the terminal device does not provide a 'multimedia data stream,' as this is explicitly required by claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1 for the edge device to acquire.
- Does not cover deployment methods that do not involve generating a configuration file, acquiring an executable file, a dynamic library, and an algorithm model, as specified in claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more → 2 and 3.
- Does not cover systems where the configuration server, edge computing device, terminal device, and display device are all located in the same cloud environment, as claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1 specifies edge, terminal, and display are 'local devices' and the server is a 'cloud device'.
- Does not cover systems deploying non-AI services or applications that are not considered 'edge applications' within an AI service context.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The clever aspect is the centralized, streamlined management of complex AI services on distributed edge devices. It allows for flexible deployment and updates of AI applications, potentially as containerized images, from a single cloud interface, simplifying the operational burden of managing many remote AI-powered systems.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
Smart city surveillance cameras performing real-time traffic analysis
Factory automation systems using AI for quality control on the production line
Retail store analytics systems tracking customer behavior with local cameras
Home security systems with AI-powered object detection on the camera itself
Agricultural monitoring systems using AI to analyze crop health from local sensors
Why it matters
The bigger picture
This patent addresses a key challenge in modern computing: efficiently deploying and managing complex AI applications on many distributed local devices, often called 'edge computing.' By centralizing the configuration and deployment from a cloud server, it simplifies the process for businesses and organizations that need to run AI close to where data is generated, like in factories or smart cities. This approach can reduce network latency and improve data privacy by processing data locally.
Filed
May 5, 2023
Market context
Who's building on this
Companies in this space
Major cloud providers like Amazon (AWS Greengrass), Microsoft (Azure IoT Edge), and Google (Google Cloud IoT) are actively developing platforms for deploying and managing AI workloads on edge devices. Companies specializing in industrial IoT, smart city solutions, and enterprise AI, such as NVIDIA and various startups in the AIoT space, are also building solutions that leverage similar cloud-to-edge deployment models.
Market impact
This type of technology is central to the growing edge AI market, enabling the proliferation of smart devices and systems that can perform complex AI tasks without constant cloud connectivity. It has driven the development of specialized hardware for edge computing and software platforms for remote AI management. This approach allows for new product categories in areas like real-time analytics, autonomous systems, and enhanced security, by bringing AI processing closer to the data source.
Claim 1 — Plain English
What this patent covers
This system allows a cloud-based configuration server to manage Artificial Intelligence (AI) services on local edge computing devices. The configuration server provides a web page where a user can specify which edge computing device, terminal device, and AI service are needed. An AI service, which includes one or more 'edge applications,' is then deployed by the cloud server onto the chosen edge computing device, as described in claim 1. The edge computing device then acquires a multimedia data stream from a terminal device, like a camera, and uses the deployed AI application to process this data, performing 'application inference' to get a result. This result is sent back to the configuration server and then displayed on a connected display device. For example, a cloud server could deploy a facial recognition AI application to a local smart camera (edge device) to analyze video (multimedia data stream) from the camera (terminal device), then display alerts on a screen.
The clever bit
The clever aspect is the centralized, streamlined management of complex AI services on distributed edge devices. It allows for flexible deployment and updates of AI applications, potentially as containerized images, from a single cloud interface, simplifying the operational burden of managing many remote AI-powered systems.
What it does not cover
- Does not cover systems where the AI service runs entirely on the cloud server without deployment to a local edge computing device, as claim 1 specifies the edge device performs inference.
- Does not cover systems where the terminal device does not provide a 'multimedia data stream,' as this is explicitly required by claim 1 for the edge device to acquire.
- Does not cover deployment methods that do not involve generating a configuration file, acquiring an executable file, a dynamic library, and an algorithm model, as specified in claims 2 and 3.
- Does not cover systems where the configuration server, edge computing device, terminal device, and display device are all located in the same cloud environment, as claim 1 specifies edge, terminal, and display are 'local devices' and the server is a 'cloud device'.
- Does not cover systems deploying non-AI services or applications that are not considered 'edge applications' within an AI service context.
Patent timeline
Application submitted to the patent office
Patent enters public domain
PatentBrief Score
Impact Score
Limited data
Citation count
0/40
No citations yet
Claim breadth
15/20
Broad claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more →
Recency
0/20
Older than 20 years
Assignee scale
0/20
Independent or smaller assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$37K – $120K
Midpoint $75K · 16.5 yr remaining · industry ×1.6
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
23 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Zhang, S., & Hu, P. How a Cloud Server Manages AI Services on Local Edge Devices (U.S. Patent No. 20,260,156,193). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/20260156193/service-management-method-and-system-and-configuration-server-and-edge-computing
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US20260156193"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
Semantically similar
You might also find these interesting
US 11876858 · 2024 · Armada Systems
Managing and Updating AI on Many Smart Devices from the Cloud
US 12111744 · 2024 · Armada Systems
Managing AI and Machine Learning on Many Devices from the Cloud
US 12033006 · 2024 · Armada Systems
Running AI Models Locally on Edge Devices with Cloud Updates
US 20250363357 · Ubotica Technologies
How to Update AI on Small Devices with Slow Internet
More to explore
More in Consumer Electronics
US 7657849 · 2010 · Apple Inc
How the iPhone's Slide-to-Unlock Gesture Works
US 7479949 · 2009 · Apple Inc
How Touchscreens Understand Your Finger Swipes and Scrolls
US 4528643 · 1985 · FPDC Inc
How Stores Make Custom Products On-Demand with Remote Approval
US 7469381 · 2008 · Apple Inc
How Touchscreens Show and Snap Back When You Scroll Past an Edge
New to patents?
Common Questions
Frequently Asked Questions
What does How a Cloud Server Manages AI Services on Local Edge Devices cover?
This patent describes a system where a central cloud server helps set up and run Artificial Intelligence tasks on local devices, like smart cameras, by sending them specific AI programs and then displaying the results.
Who owns patent US 20260156193?
This patent is owned by BOE Technology Group Co.
When does this patent expire?
This patent is expected to expire on May 5, 2043, when the invention enters the public domain.
What problem does this patent solve?
This patent addresses a key challenge in modern computing: efficiently deploying and managing complex AI applications on many distributed local devices, often called 'edge computing.' By centralizing the configuration and deployment from a cloud server, it simplifies the process for businesses and organizations that need to run AI close to where data is generated, like in factories or smart cities. This approach can reduce network latency and improve data privacy by processing data locally.
What does this patent NOT cover?
Does not cover systems where the AI service runs entirely on the cloud server without deployment to a local edge computing device, as claim 1 specifies the edge device performs inference.
Patent monitoring