Dynamic management method and system based on AI algorithm reasoning capability of IoT platform

Abstract

The present invention relates to a dynamic management method based on the AI ​​algorithm reasoning capability of an Internet of Things platform, including encapsulating program components into standardized model executable files to form independent AI algorithm modules, and uploading the model executable files to the cloud of the Internet of Things platform; using the AI ​​algorithm module as the basic functional module of the Internet of Things platform, relying on the existing OTA capability of the Internet of Things platform to remotely download and / or update the model executable files; moving the scene linkage function of the Internet of Things platform to the edge gateway, so that the edge gateway can dynamically start or stop the AI ​​algorithm module according to the configuration information; after acquiring the device data, the edge gateway parses the configuration information of the scene linkage in real time to complete the scheduling of the AI ​​algorithm module. Through this application, hot plugging and full-scene coverage of the AI ​​algorithm are realized, and at the same time, the scene linkage function is moved down to the edge gateway, the edge computing capability is improved, the complexity of the center processing is reduced, and intelligent real-time data processing is realized.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a dynamic management method and system based on the AI ​​algorithm reasoning capability of an Internet of Things platform. Background Art

[0002] As an extended application of communication networks and the Internet, the Internet of Things (IoT) technology connects objects to the Internet through information sensing devices such as radio frequency identification (RFID), sensors, cameras, locators, laser scanners, etc. Its core value lies in realizing the perception, recognition, control, network interconnection and intelligent processing of objects, thereby realizing the interaction and seamless connection between people, objects and information, and achieving the purpose of real-time perception, precise management and scientific decision-making of the physical world. However, the existing technical solutions have obvious defects: the IoT platform only performs basic processing on the collected information, such as frequency reduction, accumulation, delay, etc., which cannot meet the needs of intelligent processing, resulting in frequent false alarms and manual intervention, and increasing operation and maintenance costs. In addition, the AI ​​algorithm SDK of the intelligent imaging system is limited by the deployment of edge gateways and cannot cover all access scenarios. As the number of algorithm models increases, the complexity of the combination of edge gateways and algorithms and the diversity of deployment will increase sharply, greatly increasing the deployment and maintenance costs. Summary of the invention

[0003] To address the shortcomings of existing technologies, this technology encapsulates AI algorithms as standard sub-functions of the IoT platform to achieve hot-swap and full-scenario coverage of AI algorithm functions. At the same time, it moves the scene linkage function to the edge gateway and deeply integrates it with the AI ​​algorithm to enhance edge computing capabilities, reduce the complexity of center processing, and realize intelligent real-time data processing.

[0004] The present invention provides a dynamic management method based on the AI ​​algorithm reasoning capability of the Internet of Things platform, which is characterized by comprising:

[0005] S1. Standardized packaging of AI algorithm models: encapsulating program components into standardized model executable files, shielding differences, retaining only necessary input and output interfaces, forming an independent AI algorithm module, and uploading the model executable files to the IoT platform cloud;

[0006] S2. Integration and management of the IoT platform, using the AI ​​algorithm module as the basic functional module of the IoT platform, and relying on the existing OTA capability of the IoT platform to remotely download and / or update the model executable file;

[0007] S3. Implement scenario linkage configuration, move the scenario linkage function of the IoT platform to the edge gateway, so that the edge gateway can dynamically start or stop the AI ​​algorithm module according to the configuration information;

[0008] S4, the edge gateway works together with the scene linkage of the IoT platform cloud. After obtaining the device data, the edge gateway parses the configuration information of the scene linkage in real time, and automatically processes messages and schedules AI algorithm modules.

[0009] Exemplarily, the program components include: model files, model dynamic libraries, and runtime dependencies.

[0010] Exemplarily, the integration and management of the Internet of Things platform also includes visually managing the model executable file, managing the version of the AI ​​algorithm module and maintaining input parameters and output parameters.

[0011] Exemplarily, the implementation of scene linkage configuration also includes adding model scene configuration on the cloud scene linkage configuration page to achieve mapping of the IoT platform object model and the AI ​​algorithm module.

[0012] Exemplarily, the method also includes: the main process of the edge gateway or IoT platform is responsible for loading each independent AI algorithm module as a sub-process, and independently scheduling the running of the sub-process; passing input parameters and receiving output results between the main process and the sub-process, and realizing information interaction through inter-process communication.

[0013] Exemplarily, the implementation of the scene linkage configuration also includes: providing two methods on the cloud scene linkage configuration page: manual adjustment of the AI ​​module running device and automatic selection of the running device; if not checked, the default rule is used through the preset priority logic, that is, when the edge gateway cannot handle it, the AI ​​algorithm module reasoning task is automatically transferred to the cloud of the Internet of Things platform.

[0014] The present invention also provides a dynamic management system based on the AI ​​algorithm reasoning capability of the Internet of Things platform, which is characterized by comprising:

[0015] The encapsulation module encapsulates the program components into a standardized model executable file, shields the differences, and only retains the necessary input and output interfaces to form an independent AI algorithm module. At the same time, the model executable file is uploaded to the cloud of the IoT platform;

[0016] An integration and management module uses the AI ​​algorithm module as a basic functional module of the IoT platform and relies on the existing OTA capability of the IoT platform to remotely download and / or update the model executable file;

[0017] The scenario linkage configuration module moves the scenario linkage function of the IoT platform to the edge gateway, so that the edge gateway can dynamically start or stop the AI ​​algorithm module according to the configuration information;

[0018] In the linkage and collaboration module, after obtaining device data, the edge gateway parses the configuration information of scene linkage in real time, and automatically processes messages and schedules AI algorithm modules.

[0019] The present invention also provides a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

[0020] The present invention also provides an electronic device, characterized in that it includes a processor and a memory;

[0021] The memory is used to store computer programs;

[0022] The processor is configured to execute the method according to any one of claims 1 to 6 by calling a stored computer program.

[0023] The present invention also relates to a computer program product, comprising a computer program and / or instructions, characterized in that the computer program and / or instructions implement the steps of the above method when executed by a processor.

[0024] The beneficial effects of the present invention are: (1) The AI ​​algorithm model reasoning function is encapsulated and integrated as a standard sub-function of the IoT platform, which means that the AI ​​algorithm capability is designed as an independent and pluggable module, which can be flexibly called and managed on the cloud and edge of the IoT platform. (2) The scene linkage function is moved down to the edge gateway and deeply integrated with the AI ​​algorithm function, so that the edge gateway can dynamically schedule the AI ​​algorithm module according to the configuration of the scene linkage, realize more intelligent and automated data processing, reduce the amount and complexity of messages centrally processed by the IoT platform, and improve the real-time nature of messages. (3) By decoupling the algorithm module from the edge gateway, the maintenance cost is reduced, the flexible scheduling and independent operation capabilities of the algorithm module are increased, and the foundation is provided for the dynamic configuration of the cloud-edge collaboration of the AI ​​algorithm, so that the AI ​​algorithm module can be flexibly operated on different device platforms, whether on the cloud of the IoT platform or on the edge gateway. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flow chart of the dynamic management method based on the AI ​​algorithm reasoning capability of the Internet of Things platform of the present invention.

[0026] Figure 2 It is a structural diagram of the dynamic management system based on the AI ​​algorithm reasoning capability of the Internet of Things platform of the present invention.

[0027] Figure 3 This is a schematic diagram of the encapsulation module structure of the dynamic management system based on the AI ​​algorithm reasoning capability of the Internet of Things platform of the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0030] Embodiment 1

[0031] The present invention provides a dynamic management method based on the AI ​​algorithm reasoning capability of the Internet of Things platform, such as Figure 1 As shown, specifically including:

[0032] S1. Standardized packaging of AI algorithm models: encapsulating program components into standardized model executable files, shielding differences, retaining only necessary input and output interfaces, forming an independent AI algorithm module, and uploading the model executable files to the IoT platform cloud;

[0033] S2. Integration and management of the IoT platform, using the AI ​​algorithm module as the basic functional module of the IoT platform, and relying on the existing OTA capability of the IoT platform to remotely download and / or update the model executable file;

[0034] S3. Implement scenario linkage configuration, move the scenario linkage function of the IoT platform to the edge gateway, so that the edge gateway can dynamically start or stop the AI ​​algorithm module according to the configuration information;

[0035] S4, the edge gateway works together with the scene linkage of the IoT platform cloud. After obtaining the device data, the edge gateway parses the configuration information of the scene linkage in real time, and automatically processes messages and schedules AI algorithm modules.

[0036] Part 1: The process of implementing encapsulation

[0037] 1.1 Packaging goals and requirements analysis

[0038] The goal of the packaging process is to integrate the AI ​​algorithm model and its dependencies (including model files, model dynamic libraries, and runtime dependencies) into a standardized executable file, such as Figure 3 As shown, the purpose of doing this is to achieve independent operation and flexible deployment of the algorithm module while reducing the coupling with the edge gateway.

[0039] 1.2 Select packaging technology

[0040] Choose the appropriate packaging technology, such as containerization technology (such as Docker) or directly compile into an executable file. Containerization technology can provide environment consistency, while direct compilation can reduce runtime overhead.

[0041] 1.3 Integrate model files and dependencies

[0042] Integrate the trained AI model files, model dynamic libraries (such as binary files of frameworks such as TensorFlow and PyTorch), and runtime dependencies (such as operating system libraries, third-party libraries, etc.). This may involve modifying the model code so that it can run as a standalone program and only expose necessary input and output interfaces.

[0043] 1.4 Upload to IoT platform

[0044] Upload the executable files that pass the test to the cloud IoT platform for management and distribution.

[0045] Part II: Configuration Management

[0046] 2.1 Configuration Management System Design

[0047] Design a configuration management system to manage the version, input and output parameters of the AI ​​algorithm module. This system should be able to integrate with the OTA capability of the IoT platform to remotely update the AI ​​algorithm module on the edge gateway.

[0048] 2.2 Visual interface development

[0049] Develop a visual interface that allows users to view, edit and manage the configuration of AI algorithm modules. This interface should provide intuitive operation methods so that users can easily update the parameters of algorithm modules.

[0050] 2.3 Parameter Mapping and Version Control

[0051] Implement parameter mapping function to associate the information collected by the device with the input parameters of the AI ​​algorithm module. At the same time, implement version control function to track and manage different versions of the algorithm module.

[0052] 2.4OTA update mechanism

[0053] The integrated OTA update mechanism enables the IoT platform to remotely push new AI algorithm module executable files to the edge gateway and update them.

[0054] Part 3: Implementing scene linkage configuration

[0055] 3.1 Scene linkage function moved down

[0056] Move the scene linkage function of the IoT platform to the edge gateway, so that the edge gateway can dynamically start or stop the AI ​​algorithm module based on the configuration information.

[0057] 3.2 Configuring the model scene

[0058] Add model scene configuration on the cloud scene linkage configuration page, associate device collection information with AI algorithm modules one by one, and realize the mapping between IoT platform object model and AI model module.

[0059] Part 4: Scenario-based collaboration between edge gateway and IoT platform cloud

[0060] 4.1 Implementing Configuration Delivery

[0061] Implement an automatic distribution mechanism for configuration information, push the configuration information in the cloud to the edge gateway, and the edge gateway schedules the AI ​​algorithm module based on this information.

[0062] 4.2 Edge Gateway and IoT Platform Cloud Computing Collaboration

[0063] Design a collaborative mechanism between the edge gateway and the IoT platform cloud, and dynamically schedule AI algorithm modules between the cloud and edge based on load and scenario requirements.

[0064] For example, in the area of ​​movable property control, through the standardized encapsulation of AI algorithm models (S1), we can encapsulate the algorithms required for movable property monitoring into independent AI algorithm modules and upload them to the cloud of the IoT platform. By utilizing the integration and management of the IoT platform (S2), these modules can be remotely downloaded and updated through OTA capabilities to achieve intelligent perception, identification, positioning, tracking and monitoring of movable property. For example, banking institutions can use IoT technologies such as electronic fences and biometrics to improve the intelligence level of collateral management. By implementing scene linkage configuration (S3), the edge gateway can dynamically start or stop the AI ​​algorithm module according to the configuration information. For example, when the movable property leaves the designated area, the edge gateway can automatically start the monitoring module and notify the banking institution. The edge gateway works in coordination with the scene linkage of the IoT platform cloud (S4). After obtaining device data, it parses the configuration information of the scene linkage in real time, and automatically processes messages and schedules the AI ​​algorithm module to achieve real-time monitoring and risk warning of movable property.

[0065] Embodiment 2

[0066] The present invention also provides a dynamic management system based on the AI ​​algorithm reasoning capability of the Internet of Things platform, such as Figure 2 As shown, including:

[0067] The encapsulation module encapsulates the program components into a standardized model executable file, shields the differences, and only retains the necessary input and output interfaces to form an independent AI algorithm module. At the same time, the model executable file is uploaded to the cloud of the IoT platform;

[0068] An integration and management module uses the AI ​​algorithm module as a basic functional module of the IoT platform and relies on the existing OTA capability of the IoT platform to remotely download and / or update the model executable file;

[0069] The scenario linkage configuration module moves the scenario linkage function of the IoT platform to the edge gateway, so that the edge gateway can dynamically start or stop the AI ​​algorithm module according to the configuration information;

[0070] In the linkage and collaboration module, after obtaining device data, the edge gateway parses the configuration information of scene linkage in real time, and automatically processes messages and schedules AI algorithm modules.

[0071] By using this system, the above-mentioned processing method can be executed and the corresponding technical effects can be achieved.

[0072] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0073] An embodiment of the present invention also provides an electronic device for executing the above method. As an implementation device of the method, the electronic device has at least a processor and a memory, and in particular, the memory stores data and related computer programs required for executing the method, and the processor calls the data and programs in the memory to execute all steps of the implementation method and obtains the corresponding technical effect.

[0074] Preferably, the electronic device may include a bus architecture, the bus may include any number of interconnected buses and bridges, and the bus will include various circuits linked together by one or more processors and memories. The bus may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are all well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the receiver and transmitter. The receiver and transmitter may be the same component, i.e., a transceiver, providing a unit for communicating with various other systems over a transmission medium. The processor is responsible for managing the bus and general processing, while the memory may be used to store data used by the processor when performing operations.

[0075] In addition, the electronic device may further include components such as a communication module, an input unit, an audio processor, a display, and a power supply. The processor (or controller, operation control) used may include a microprocessor or other processor device and / or a logic device, which receives input and controls the operation of various components of the electronic device; the memory may be one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices, which may store the above-mentioned related data information, and may also store a program for executing related information, and the processor may execute the program stored in the memory to realize information storage or processing, etc.; the input unit is used to provide input to the processor, for example, it may be a key or a touch input device; the power supply is used to provide power to the electronic device; the display is used to display display objects such as images and text, for example, it may be an LCD display. The communication module is a transmitter / receiver that sends and receives signals via an antenna. The communication module (transmitter / receiver) is coupled to the processor to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal. Based on different communication technologies, multiple communication modules may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless local area network module, etc. The communication module (transmitter / receiver) is also coupled to a speaker and a microphone via an audio processor to provide an audio output via the speaker and receive an audio input from the microphone, thereby realizing a common telecommunication function. The audio processor may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor is also coupled to a central processor, so that recording can be performed on the machine through the microphone, and the sound stored on the machine can be played through the speaker.

[0076] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0078] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0080] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A dynamic management method based on the AI ​​algorithm reasoning capability of the Internet of Things platform, characterized in that: include: S1. Standardized packaging of AI algorithm models: encapsulating program components into standardized model executable files, shielding differences, retaining only necessary input and output interfaces, forming an independent AI algorithm module, and uploading the model executable files to the IoT platform cloud; S2. Integration and management of the IoT platform, using the AI ​​algorithm module as the basic functional module of the IoT platform, and relying on the existing OTA capability of the IoT platform to remotely download and / or update the model executable file; S3. Implement scenario linkage configuration, move the scenario linkage function of the IoT platform to the edge gateway, so that the edge gateway can dynamically start or stop the AI ​​algorithm module according to the configuration information; S4, the edge gateway works together with the scene linkage of the IoT platform cloud. After obtaining the device data, the edge gateway parses the configuration information of the scene linkage in real time, and automatically processes messages and schedules AI algorithm modules.

2. The method according to claim 1, characterized in that: The program components include: model files, model dynamic libraries and runtime dependencies.

3. The method according to claim 1, characterized in that The integration and management of the Internet of Things platform also includes visual management of the model executable file, managing the version of the AI ​​algorithm module and maintaining input parameters and output parameters.

4. The method according to claim 1, characterized in that: The implementation of scene linkage configuration also includes adding model scene configuration on the cloud scene linkage configuration page to achieve mapping of the IoT platform object model and AI algorithm module.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: The main process of the edge gateway or IoT platform is responsible for loading each independent AI algorithm module as a sub-process and independently scheduling the operation of the sub-process; Input parameters are passed and output results are received between the main process and the subprocess, and information interaction is achieved through inter-process communication.

6. The method according to claim 4, characterized in that The implementation of scene linkage configuration also includes: The cloud scene linkage configuration page provides two methods: manual adjustment of AI module running devices and automatic selection of running devices; If this option is not checked, the default rule will be used through the preset priority logic, that is, when the edge gateway cannot handle it, the AI ​​algorithm module reasoning task will be automatically transferred to the IoT platform cloud.

7. A dynamic management system based on the AI ​​algorithm reasoning capability of the Internet of Things platform, characterized by: include: The encapsulation module encapsulates the program components into a standardized model executable file, shields the differences, and only retains the necessary input and output interfaces to form an independent AI algorithm module. At the same time, the model executable file is uploaded to the cloud of the IoT platform; An integration and management module uses the AI ​​algorithm module as a basic functional module of the IoT platform and relies on the existing OTA capability of the IoT platform to remotely download and / or update the model executable file; The scenario linkage configuration module moves the scenario linkage function of the IoT platform to the edge gateway, so that the edge gateway can dynamically start or stop the AI ​​algorithm module according to the configuration information; In the linkage and collaboration module, after obtaining device data, the edge gateway parses the configuration information of scene linkage in real time, and automatically processes messages and schedules AI algorithm modules.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 6 by calling a stored computer program.

10. A computer program product comprising a computer program and / or instructions, characterized in that: When the computer program and / or the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images