Multi-system visual IOT intelligent management platform

Abstract

The invention relates to the technical field of intelligent management platforms, in particular to a multi-system visual IOT intelligent management platform which comprises a virtual scene model, a comprehensive sensing module, a distributed processing module and a core control unit. The virtual scene model integrates multi-field data through a digital mapping technology, and supports multi-level display; the comprehensive sensing module collects environment and equipment information in real time by using a distributed sensor network; the distributed processing module classifies and processes the data through the edge computing node and marks a unique identifier; the core control unit coordinates interaction of all the modules and provides a Web-based user interface. According to the invention, through dynamic visualization and cross-domain data integration, the perception capability and the operation efficiency of the user on the system state are improved, and the method is suitable for industrial monitoring, commercial operation, home automation and other scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of IoT intelligent management platforms, and in particular to a multi-system visual IoT intelligent management platform. Background Art

[0002] Current IoT intelligent management platforms include modules for industrial monitoring, commercial operations, and home automation. Each module operates independently, lacking efficient interoperability mechanisms and insufficient integration capabilities for multi-dimensional data, making it difficult to fully visualize the overall system status. When cross-domain data analysis is required, the operational process is complex, and the correlations between modules are weak, making it difficult to intuitively present dynamic changes and deep data relationships. Existing technologies have limitations in multi-system integration, data visualization depth, and versatility. Therefore, a multi-system visual IoT intelligent management platform is proposed to address these issues. Summary of the Invention

[0003] The purpose of this invention is to provide a multi-system visual IoT intelligent management platform, aiming to address the existing issues of isolated multi-system data operation, lack of efficient intercommunication mechanisms, and insufficient visualization depth. By integrating data from multiple domains, such as industrial monitoring modules, commercial operations modules, and home automation modules, and combining them with dynamic visualization technology, this platform achieves organic integration and multi-level display of cross-domain data, thereby improving users' perception of the overall system status and operational efficiency.

[0004] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a multi-system visual IOT intelligent management platform, including a virtual scene model constructed based on digital mapping technology, a comprehensive perception module that collects environmental parameters, equipment status and personnel activity information in real time through a distributed sensor network, a distributed processing module that processes and classifies and stores various types of data through edge computing nodes, and a core control unit that coordinates the data interaction of each sub-module. The virtual scene model, the comprehensive perception module, and the distributed processing module are all equipped with independent storage devices and computing units. Each computing unit transmits the processed data to the core control unit and integrates them into a Web-based interactive interface. This technical solution supports users in quickly locating problems, analyzing data change trends, and optimizing decision-making processes by modeling the correlation and displaying the status information of people, equipment, resources and the environment at multiple levels.

[0005] The virtual scene model includes a building structure diagram, energy distribution map, communication topology map, logistics route map, security monitoring point map, and pedestrian flow heat map. The energy distribution map shows the layout of power, gas, and water supply pipelines and the locations of key nodes. Users can use interactive commands to view the connection relationships and operating status of specific pipelines. The communication topology map marks wireless access points, fiber nodes, and signal coverage areas, allowing users to click on specific nodes to view their connection status and traffic load information. These layers can be activated individually or displayed as a stack, facilitating analysis of potential issues in complex scenarios.

[0006] In a preferred embodiment of the present invention, the integrated perception module includes a facial recognition terminal, a vehicle identification barrier, environmental monitoring equipment, and a device status detector. Both the facial recognition terminal and the vehicle identification barrier have integrated audio and visual alert components. When abnormal behavior or unauthorized access is detected, an alert function is triggered and the relevant event is recorded. Environmental monitoring equipment is deployed at key locations in the target area to collect parameters such as temperature, humidity, air pressure, light intensity, and air quality index. The device status detector uses vibration sensors, current sensors, and temperature sensors to monitor the operating status of the target device in real time and uploads the collected data to the distributed processing module.

[0007] Furthermore, the distributed processing module comprises multiple edge computing nodes, each responsible for processing a specific type of data stream. For example, environmental monitoring data is cleaned and preprocessed by a dedicated node, extracting outliers and generating trend analysis reports. Equipment status data is processed by another node for fault diagnosis, using algorithms based on time series analysis to predict potential failure risks. All processed data is tagged with a unique identifier, stored in a local cache, and then transmitted to the core control unit via wired or wireless communication protocols.

[0008] Further describing the aforementioned solution, the environmental monitoring equipment includes temperature and humidity sensors, anemometers, noise monitors, gas concentration detectors, and light intensity meters, providing comprehensive awareness of the target area's environmental conditions. The gas concentration detectors can distinguish between various hazardous gas components and, combined with wind speed and direction data, assess pollution spread trends. The noise monitors use spectrum analysis to identify noise sources in different frequency bands, providing a basis for noise control. These devices connect to edge computing nodes via the LoRa communication protocol, ensuring stable data transmission and low power consumption.

[0009] Even better, the fault diagnosis algorithm in the distributed processing module utilizes a random forest-based machine learning model. By learning from historical fault data, it establishes association rules between equipment operating status and failure modes. When an anomaly is detected, the system automatically identifies the most likely cause and pushes relevant information to the designated maintenance personnel's mobile device. The maintenance personnel can view fault details and suggested solutions through the device, and can also remotely control the target device to verify the repair results.

[0010] Furthermore, the core control unit includes a task scheduling module, a data analysis module, and a user interaction module. The task scheduling module allocates resources based on priority, ensuring that high-priority tasks are processed promptly. The data analysis module uses multidimensional data cube technology to support users in analyzing data trends from different dimensions. The user interaction module uses a drag-and-drop interface design, allowing users to freely combine chart types and data sources to generate customized visual reports. Supported chart types include heat maps, scatter plots, bar charts, and 3D scene models.

[0011] The client connected to the core control unit is preferably equipped with an augmented reality (AR) display module. This module uses mixed reality technology to overlay a virtual scene model with the real environment. Users can intuitively view the real-time status of the target area and compare it with historical data by wearing an AR device. Data exchange between the integrated perception module and the distributed processing module is achieved through the MQTT protocol, ensuring low latency and high reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a schematic diagram of the system architecture of the multi-system visual IOT intelligent management platform of the present invention;

[0013] Figure 2 A schematic diagram showing the hierarchical display of a virtual scene model;

[0014] Figure 3 This is a schematic diagram of the workflow of the comprehensive perception module;

[0015] Figure 4 It is a structural diagram of the distributed processing module;

[0016] Figure 5 Schematic diagram of the functional modules of the core control unit. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] The present invention provides a multi-system visual IOT intelligent management platform, and its specific implementation method is combined with Figures 1 to 5 The platform includes a virtual scene model, a comprehensive perception module, a distributed processing module, and a core control unit. These components are connected and collaborated through data streams to achieve cross-domain data integration and multi-level display.

[0019] like Figure 1 As shown, the virtual scene model, as one of the platform's foundational components, connects to the integrated perception module and distributed processing module via data interfaces, receiving real-time data from these modules and dynamically updating them. The virtual scene model includes a building structure diagram, energy distribution map, communication topology map, logistics route map, security monitoring point map, and pedestrian flow heat map. These layers are managed by independent storage devices and computing units and can be activated individually or displayed as a stack. For example, if a user needs to analyze energy usage in a specific area, they can use interactive commands to activate the energy distribution map and view the layout of power, gas, and water pipelines and the locations of key nodes. Meanwhile, the communication topology map illustrates wireless access points, fiber nodes, and signal coverage. Users can click on a specific node to view its connection status and traffic load information. This layered design enables rapid identification of potential issues in complex scenarios. Data from the virtual scene model is ultimately transmitted to the core control unit, providing the underlying data for generating visualization reports.

[0020] The comprehensive perception module consists of a face recognition terminal, a vehicle recognition barrier, an environmental monitoring device, and a device status detector. Figure 3As shown, both the facial recognition terminal and the vehicle identification barrier have integrated audio and visual alert components, triggering alerts and recording related events when abnormal behavior or unauthorized access is detected. The facial recognition terminal uses a camera to capture facial features and compares them with a pre-stored database. If unauthorized access is detected, an audio and visual alarm is immediately triggered and the event log is uploaded to the distributed processing module. The vehicle identification barrier uses license plate recognition technology to determine whether a vehicle has access rights. Unauthorized vehicles are denied access and the relevant information is recorded. Environmental monitoring equipment, including temperature and humidity sensors, anemometers, noise monitors, gas concentration detectors, and light intensity meters, is deployed at key locations in the target area to comprehensively monitor the environmental conditions in the target area. The gas concentration detector can distinguish between various harmful gas components and, combined with wind speed and direction data, assess pollution diffusion trends. The noise monitor uses spectrum analysis technology to identify noise sources in different frequency bands, providing a basis for noise control. The equipment status detector uses vibration sensors, current sensors, and temperature sensors to monitor the operating status of target equipment in real time and upload the collected data to the distributed processing module. All devices in the integrated perception module establish connections with the distributed processing module through the LoRa communication protocol to ensure the stability and low power consumption of data transmission.

[0021] The distributed processing module contains multiple edge computing nodes, each of which is responsible for processing a specific type of data flow. Figure 4 As shown, environmental monitoring data is cleaned and preprocessed by a dedicated edge computing node, which extracts outliers and generates trend analysis reports. Equipment status data is then processed for fault diagnosis by another edge computing node. A random forest-based machine learning model is used to learn from historical fault data and establish association rules between equipment operating status and fault modes. When an anomaly is detected, the system automatically matches the most likely cause of the fault and pushes the relevant information to the designated maintenance personnel's mobile terminal. Maintenance personnel can view fault details and recommended solutions through the terminal, and remote control of the target device is also supported to verify the repair effect. All processed data is marked with a unique identifier and stored in a local cache. It is then transmitted to the core control unit via wired or wireless communication protocols.

[0022] The core control unit includes a task scheduling module, a data analysis module and a user interaction module, such as Figure 5As shown. The task scheduling module allocates resources according to priority to ensure that high-priority tasks can be processed in a timely manner. The data analysis module uses multi-dimensional data cube technology to support users to analyze data change trends from different dimensions. The user interaction module uses a drag-and-drop interface design to allow users to freely combine chart types and data sources to generate customized visual reports. Supported chart types include heat maps, scatter plots, bar charts and three-dimensional scene models. The user interaction module is also connected to the augmented reality AR display module, which uses mixed reality technology to superimpose virtual scene models with real environments. Users can wear AR devices to intuitively view the real-time status of the target area and compare it with historical data. Data interaction is achieved between the comprehensive perception module and the distributed processing module through the MQTT protocol to ensure low latency and high reliability.

[0023] In practical applications, this platform can be deployed in industrial parks, commercial complexes, or smart home scenarios. Taking an industrial park as an example, a virtual scene model can construct the park's overall layout, including plant structures, energy pipelines, and communication networks. Environmental monitoring devices in the integrated perception module are deployed inside and outside the workshop, collecting real-time parameters such as temperature, humidity, air pressure, light intensity, and air quality index. Equipment status detectors are installed on key production equipment to monitor their operating status and predict potential failure risks. Edge computing nodes in the distributed processing module classify and process collected data, generating trend analysis reports or fault warnings, and transmitting the results to the core control unit. The core control unit's task scheduling module allocates resources based on task priority, the data analysis module generates multidimensional data reports, and the user interaction module displays visualization results through a web interface. Users can generate customized reports by dragging and dropping, or use the augmented reality (AR) display module to view overlaid virtual and real scenes, quickly locating problems and optimizing decision-making processes.

[0024] In this embodiment, the connectivity and collaborative mechanisms between modules ensure the efficient operation of the platform. The virtual scene model dynamically updates and displays the integrated results of multi-domain data. The integrated perception module collects real-time environmental and device status information. The distributed processing module classifies and processes data and performs fault diagnosis. The core control unit implements multi-level data display and decision support through task scheduling, data analysis, and user interaction modules. Each module interacts with data through standardized protocols, ensuring system stability and scalability.

[0025] In order to better enable relevant personnel in this technical field to fully understand and implement the present invention, the specific implementation principle of the present invention is supplemented below with reference to a specific application scenario.

[0026] In the industrial park scenario, the overall layout of the park is first constructed using a virtual scene model. The building structure diagram in the virtual scene model illustrates the physical distribution of the factory buildings. The energy distribution map indicates the locations of key nodes in the power, gas, and water pipelines. The communication topology map shows the connection status of wireless access points and fiber nodes. Users can use interactive commands to activate individual layers of the map. For example, clicking on the energy distribution map to view the power load in a specific area or overlaying a security monitoring point map with a pedestrian flow heat map to analyze security risks in a specific area. This layered design allows potential issues in complex scenarios to be quickly identified and provides foundational support for subsequent data analysis.

[0027] Environmental monitoring equipment in the integrated sensing module is deployed inside and outside the workshop, collecting parameters such as temperature, humidity, air pressure, light intensity, and air quality index in real time. The temperature and humidity sensors transmit the collected data to the edge computing node in the distributed processing module via the LoRa communication protocol. The edge computing node cleans and preprocesses the received environmental data, removes outliers, and generates a trend analysis report. Simultaneously, the gas concentration detector 13 combines data from the anemometer to assess pollution diffusion trends, tags the results with a unique identifier, and stores them in a local cache. This processed data is then transmitted to the core control unit via a wired communication protocol.

[0028] Equipment status detectors, installed on key production equipment, monitor the equipment's operating status in real time using vibration, current, and temperature sensors. When abnormal vibration or current fluctuations are detected, the equipment status detector uploads the data to another edge computing node in the distributed processing module. This node uses a random forest-based machine learning model to learn from historical fault data and establish association rules between equipment operating status and failure modes. Once a potential failure risk is detected, the system automatically matches the most likely cause and pushes relevant information to the designated maintenance personnel's mobile terminal. Maintenance personnel can use the terminal to view fault details and suggested solutions, and can also remotely control the target equipment to verify the effectiveness of the repair.

[0029] The task scheduling module in the core control unit allocates resources according to task priority to ensure that high-priority tasks can be processed in a timely manner. For example, when an emergency failure occurs in a certain device, the task scheduling module prioritizes the allocation of resources for fault diagnosis and early warning information generation. The data analysis module uses multidimensional data cube technology to support users in analyzing data change trends from different dimensions. For example, users can freely combine chart types and data sources through drag-and-drop interface design to generate customized visual reports. Supported chart types include heat maps, scatter plots, bar charts, and three-dimensional scene models. The user interaction module is also connected to the augmented reality (AR) display module, which superimposes virtual scene models on real environments through mixed reality technology. Users can wear AR devices to intuitively view the real-time status of the target area and compare it with historical data, thereby quickly locating problems and optimizing decision-making processes.

[0030] During actual operation, data exchange between the integrated perception module and the distributed processing module is achieved through the MQTT protocol, ensuring low latency and high reliability. For example, when the facial recognition terminal detects the entry of an unauthorized person, it immediately triggers an audible and visual alarm and uploads the event record to the distributed processing module. The edge computing nodes in the distributed processing module classify and process the event data and transmit the results to the core control unit. The task scheduling module of the core control unit allocates resources according to task priority, the data analysis module generates multidimensional data reports, and the user interaction module displays visual results through a web interface. Users can generate customized reports by dragging and dropping, or view superimposed virtual and real scenes through the augmented reality (AR) display module, allowing them to quickly locate problems and optimize decision-making processes.

[0031] Through these steps, the collaborative mechanism between modules is fully demonstrated. The virtual scene model dynamically updates and displays the integrated results of multi-domain data. The integrated perception module collects real-time environmental and device status information. The distributed processing module classifies and processes data and performs fault diagnosis. The core control unit implements multi-level data display and decision support through task scheduling, data analysis, and user interaction modules. Each module interacts with data through standardized protocols, ensuring system stability and scalability.

[0032] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0033] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. Multi-system visual IOT intelligent management platform, featuring: It includes a comprehensive perception module, a distributed processing module and a core control unit. The comprehensive perception module is constructed through digital mapping technology and contains a building structure diagram, an energy distribution diagram, a communication topology diagram, a logistics path diagram, a security monitoring point map and a pedestrian flow heat map. The comprehensive perception module collects environmental parameters, equipment status and personnel activity information in real time through a distributed sensor network. The distributed processing module classifies, processes and stores data through multiple edge computing nodes. The core control unit coordinates the data interaction of each module and integrates the data into a Web-based interactive interface.

2. The multi-system visual IOT intelligent management platform according to claim 1 is characterized by: The energy distribution map in the comprehensive perception module includes the layout of power pipelines, gas pipelines and water supply pipelines and the locations of their key nodes. Users can view the connection relationship and operating status of specific pipelines through interactive instructions.

3. The multi-system visual IOT intelligent management platform according to claim 1 is characterized by: The communication topology diagram in the comprehensive perception module marks wireless access points, fiber nodes and signal coverage, and users can view the connection status and traffic load information of a specific node by clicking on it.

4. The multi-system visual IOT intelligent management platform according to claim 1 is characterized by: The comprehensive perception module includes a face recognition terminal, a vehicle recognition barrier, an environmental monitoring device and an equipment status detector. The face recognition terminal and the vehicle recognition barrier are both integrated with sound and light prompt components.

5. The multi-system visual IOT intelligent management platform according to claim 4 is characterized by: The environmental monitoring equipment includes a temperature and humidity sensor, an anemometer, a noise monitor, a gas concentration detector and a light intensity meter. The gas concentration detector can distinguish multiple harmful gas components and evaluate the pollution diffusion trend in combination with wind speed and direction data.

6. The multi-system visual IOT intelligent management platform according to claim 4 is characterized by: The device status detector monitors the operating status of the target device in real time through a vibration sensor, a current sensor and a temperature sensor, and uploads the collected data to the distributed processing module.

7. The multi-system visual IOT intelligent management platform according to claim 1 is characterized by: The distributed processing module includes multiple edge computing nodes, each of which is responsible for processing a specific type of data stream. Environmental monitoring data is cleaned and preprocessed by a dedicated node, while equipment status data is used for fault diagnosis by another node.

8. The multi-system visual IOT intelligent management platform according to claim 7 is characterized by: The fault diagnosis algorithm in the distributed processing module adopts a machine learning model based on random forest, and establishes association rules between equipment operating status and fault mode by learning historical fault data.

9. The multi-system visual IOT intelligent management platform according to claim 1 is characterized by: The core control unit includes a task scheduling module, a data analysis module and a user interaction module. The task scheduling module allocates resources according to priority, and the data analysis module uses multidimensional data cube technology to support users in analyzing data change trends from different dimensions.

10. The multi-system visual IOT intelligent management platform according to claim 9 is characterized by: The user interaction module allows users to freely combine chart types and data sources to generate customized visualization reports through a drag-and-drop interface design. Supported chart types include heat maps, scatter plots, bar charts and three-dimensional scene models.

Images