Smart park digital management system based on digital twinborn technology

Abstract

The invention provides a smart park digital management system based on a digital twinborn technology, and relates to the technical field of digital management, the smart park digital management system comprises a multi-dimensional digital twinborn modeling module, an analysis and prediction module, a self-adaptive compensation module, an interaction module and an ecological integration module, the multi-dimensional digital twinborn modeling module uses a scanning combined remote sensing technology to carry out digital twinborn modeling on the basis of the multi-dimensional digital twinborn modeling module; an initial three-dimensional model of the park is constructed, and environment monitoring, facility states, personnel activities and energy use are integrated through the Internet of Things; according to the method, the holographic digital twinborn body is constructed, the change trend in the holographic digital twinborn body in the aspects of environment, facilities and energy is predicted through the prediction model, and future action tracks and interaction behaviors of people with different identities are predicted through the person behavior model according to normal behavior modes of the people with different identities. According to the method, the environment, the facility and the energy which are influenced by the personnel activity are synchronously predicted, so that adjustment measures are conveniently generated, multi-level response is carried out on personnel behaviors in combination with risk rules and threshold values, and the method has perspectiveness and initiative.

Description

Technical Field

[0001] The present invention relates to the technical field of digital management, and particularly to a digital management system for smart parks based on digital twin technology. Background Art

[0002] With the rapid development of technology and the advancement of digital transformation, smart parks have become an important trend in future urban development. Smart parks utilize new-generation information technology means such as cloud computing, the Internet of Things, big data, and artificial intelligence to achieve the intelligence of various aspects such as park infrastructure, security guarantee, management, and services. The realization of this intelligence helps to improve the management efficiency of the park, optimize resource allocation, reduce operating costs, and at the same time provide more efficient and convenient services for the enterprises in the park, promoting the sustainable development of the park. Smart park solutions are committed to achieving the intelligent management and operation of the park by integrating advanced information technology and enhancing the overall competitiveness of the park;

[0003] With the development of smart parks, digital twin technology has gradually become an important means of application. This technology can provide a platform for managers to simulate, analyze, and predict actual situations in a virtual environment by constructing a virtual model highly similar to the real world, thereby assisting them in making more informed decisions. However, in the actual use of smart parks, digital twin technology usually only focuses on providing simulation, analysis, and prediction functions for static targets such as facilities and energy, and has very limited management functions for people. The subjective initiative of people is often the key factor affecting static targets such as facilities and energy. The existing management systems are relatively weak in predicting and managing personnel behavior and its potential risks, relying on post-event processing, lacking foresight and initiative, and also lacking the linkage positioning function for other static targets affected by abnormal behavior, which affects the timeliness of response. Therefore, the present invention proposes a digital management system for smart parks based on digital twin technology to solve the problems existing in the prior art. Summary of the Invention

[0004] In view of the above problems, the present invention proposes a digital management system for smart parks based on digital twin technology. The digital management system for smart parks based on digital twin technology has perfect functions for predicting and managing personnel behavior and its potential risks, has foresight and initiative, and the prediction encompasses the environment, facilities, and energy affected by personnel activities, facilitating linkage positioning and improving the timeliness of response.

[0005] To achieve the objectives of the present invention, the present invention is implemented through the following technical solutions: A smart park digital management system based on digital twin technology, including a multi-dimensional digital twin modeling module, an analysis and prediction module, an adaptive compensation module, an interaction module, and an ecological integration module. The multi-dimensional digital twin modeling module uses scanning combined with remote sensing technology to construct an initial 3D model of the park, and integrates environmental monitoring, facility status, personnel activities, and energy usage through the Internet of Things, and fuses with the initial 3D model to generate a holographic digital twin;

[0006] The analysis and prediction module constructs a prediction model and a personnel behavior model based on machine learning algorithms. The prediction model is used to predict the change trends in the environment, facilities, and energy in the holographic digital twin. The personnel behavior model is used to learn and identify the normal behavior patterns of personnel in the holographic digital twin, predict their future action trajectories and interaction behaviors, and synchronously predict the environment, facilities, and energy affected by personnel activities. The adaptive compensation module is used to combine strategy algorithms, generate adjustment measures for the change trends in the environment, facilities, and energy according to the predictions of the prediction model, and perform multi-level responses to personnel behaviors in combination with the personnel behavior model and risk rules and thresholds. The interaction module provides visual interaction for management personnel, and the ecological integration module is used to provide external integration connection functions.

[0007] A further improvement lies in that: The multi-dimensional digital twin modeling module includes a collection and modeling module, an integration module, and a rendering module. The collection and modeling module uses high-precision 3D scanning, drone aerial photography, and satellite remote sensing technology, combined with Internet of Things sensor data, to construct an initial 3D model of the park. The integration module is used to integrate environmental monitoring: including air quality, temperature and humidity, fire warning; facility status: including equipment health, energy consumption; personnel activities: including personnel identity, personnel location, movement speed, stay time, interaction behavior; energy usage: including electricity consumption, water consumption, and combines them into a multi-dimensional data packet, which is fused into the initial 3D model to generate a holographic digital twin. The rendering module is used to perform multi-resolution rendering on the holographic digital twin.

[0008] A further improvement lies in that: the analysis and prediction module includes a prediction model unit and a personnel behavior model unit. The prediction model unit includes a data storage module, a model construction module, and a result analysis module. The data storage unit is used to access the holographic digital twin body, store real-time data using a distributed architecture, and simultaneously perform tagging processing according to the type of data. The model construction module constructs models for the changing trends of the environment, facilities, and energy in the park based on time series analysis, regression analysis, and classification algorithms, and conducts training and verification based on historical data and real-time data to obtain a prediction model. The result analysis module constructs line charts and bar charts based on the prediction model, analyzes the changing trends of various indicators in terms of the environment, facilities, and energy, and predicts potential problems and risks.

[0009] A further improvement lies in that: the personnel behavior model unit includes a feature extraction module and a model prediction system. The feature extraction module is used to extract features useful for predicting personnel behavior from the original data of the data storage module, including the movement trajectory of personnel, the nature of the staying area, the interaction frequency with other personnel, and the associated facilities and energy projects. The model prediction system uses recurrent neural networks (RNNs) and long short-term memory networks (LSTMs) to process time series data and convolutional neural networks (CNNs) to process image data to construct a personnel behavior model, and trains the model with the original data in the data storage module. In this way, it predicts the future action trajectory and interaction behavior of personnel, and at the same time, associates the equipment in terms of the environment, facilities, and energy affected by the personnel's action trajectory and interaction behavior with the action data of this personnel.

[0010] A further improvement lies in that: the adaptive compensation module includes an external influence factor strategy unit and a personnel influence factor strategy unit. The external influence factor strategy unit is used to access the prediction model, generate adaptive management strategies for the environment, facilities, and energy in the park according to the changing prediction trend of the prediction model, including energy optimization scheduling strategies, facility preventive maintenance strategies, and temperature and humidity control strategies. The external influence factor strategy unit also accesses weather forecast websites to conduct real-time strategy planning based on the impact of future weather on the environment, facilities, and energy.

[0011] A further improvement lies in that: the holographic digital twin incorporates risk rules and thresholds related to the identities of all personnel in the park. The personnel influence factor strategy unit is used to access the personnel behavior model, bring the current behavior of the personnel, the predicted future action trajectories, and interaction behaviors into the risk rules and thresholds, and synchronously establish three-level strategies. The first-level strategy is that the current behavior and future predicted behavior of the personnel are normal and no marking is done. The second-level strategy is that the current behavior of the personnel is normal but the future predicted behavior triggers the risk rules and thresholds. In the holographic digital twin, mark the personnel and the equipment in aspects of the environment, facilities, and energy affected by their related behaviors. The third-level strategy is that both the current behavior and future predicted behavior of the personnel trigger the risk rules and thresholds. In the holographic digital twin, mark the personnel and the equipment in aspects of the environment, facilities, and energy affected by their related behaviors, and synchronously send an alarm to the terminal device of the management personnel. During the alarm process, upload the parameter change values of the equipment in aspects of the environment, facilities, and energy affected by the personnel and their related behaviors.

[0012] A further improvement lies in that: the interaction module includes a holographic projection module and a custom management module. The holographic projection module uses holographic projection technology to present the holographic digital twin in an immersive manner in front of the manager, providing an intuitive display of the park operation status, and providing the function for the manager to interact through gesture and voice interaction methods to achieve remote monitoring and management of the facilities and personnel in the park.

[0013] A further improvement lies in that: the custom management module is used to identify the level of the current management personnel and open different custom view, alarm prompt, and data report functions according to the level of the management personnel.

[0014] A further improvement lies in that: the ecological integration module includes an integration unit and a data sharing platform. The integration unit is used to provide an open API interface for seamless integration with other intelligent park management systems, Internet of Things devices, and big data platforms.

[0015] A further improvement lies in that: the data sharing platform is used to upload and share the data in the holographic digital twin based on the permission control of the management personnel while the integration unit integrates other systems for data collaboration.

[0016] The beneficial effects of the present invention are:

[0017] 1. The present invention constructs a holographic digital twin through multi-dimensional data collection, predicts the changing trends of the internal environment, facilities, and energy in the holographic digital twin through a prediction model, and predicts the future action trajectories and interaction behaviors of different identity personnel according to the normal behavior patterns of personnel through a personnel behavior model, and synchronously predicts the environment, facilities, and energy affected by personnel activities. Thus, it is convenient to generate adjustment measures for the changing trends of the environment, facilities, and energy, and combined with risk rules and thresholds, multi-level responses are made to personnel behaviors, with perfect prediction and management functions for personnel behaviors and their potential risks, being forward-looking and proactive, and the prediction encompasses the environment, facilities, and energy affected by personnel activities, facilitating linkage positioning and improving the timeliness of response.

[0018] 2. The risk rules and thresholds related to the identities of all personnel in the park are built into the holographic digital twin of the present invention, and three-level strategies are synchronously established. The current behaviors of personnel and the predicted future action trajectories and interaction behaviors are brought into the risk rules and thresholds for processing. According to the differences in the three-level strategies, no processing, marking, and alarming are carried out respectively. During the alarming process, the parameter change values of the equipment in the aspects of the environment, facilities, and energy affected by this personnel and their related behaviors are uploaded, facilitating different responses by management personnel.

[0019] 3. The present invention provides an open API interface, which is convenient for seamless integration with other intelligent park management systems, Internet of Things devices, and big data platforms, promotes data sharing and collaborative work among different systems, and improves the overall intelligent level of the park. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a composition diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with embodiments. These embodiments are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0022] Embodiment 1

[0023] According to Figure 1 As shown, this embodiment proposes an intelligent park digital management system based on digital twin technology, including a multi-dimensional digital twin modeling module, an analysis and prediction module, an adaptive compensation module, an interaction module, and an ecological integration module. The multi-dimensional digital twin modeling module uses scanning combined with remote sensing technology to construct an initial three-dimensional model of the park, and through Internet of Things integration of environmental monitoring, facility status, personnel activities, and energy use, it is fused with the initial three-dimensional model to generate a holographic digital twin.

[0024] The analysis and prediction module constructs a prediction model and a personnel behavior model based on machine learning algorithms. The prediction model is used to predict the change trends in the internal environment, facilities, and energy of the holographic digital twin. The personnel behavior model is used to learn and identify the normal behavior patterns of the personnel in the holographic digital twin, predict their future action trajectories and interaction behaviors, and synchronously predict the environment, facilities, and energy affected by the personnel activities. The adaptive compensation module is used to generate adjustment measures for the change trends in the environment, facilities, and energy according to the predictions of the prediction model by combining policy algorithms, and to perform multi-level responses to personnel behaviors by combining the personnel behavior model, risk rules, and thresholds. The interaction module provides visual interaction for management personnel, and the ecological integration module is used to provide external integration connection functions. A holographic digital twin is constructed through multi-dimensional data collection. The change trends in the internal environment, facilities, and energy of the holographic digital twin are predicted through the prediction model. The future action trajectories and interaction behaviors of personnel are predicted through the personnel behavior model according to the normal behavior patterns of personnel with different identities, and the environment, facilities, and energy affected by the personnel activities are synchronously predicted. Thus, it is convenient to generate adjustment measures for the change trends in the environment, facilities, and energy, and to perform multi-level responses to personnel behaviors by combining risk rules and thresholds. It has a perfect prediction and management function for personnel behaviors and their potential risks, is forward-looking and proactive, and the prediction includes the environment, facilities, and energy affected by personnel activities, which is convenient for linkage positioning and improves the timeliness of response.

[0025] The multi-dimensional digital twin modeling module includes a collection and modeling module, an integration module, and a rendering module. The collection and modeling module uses high-precision 3D scanning, UAV aerial photography, and satellite remote sensing technologies, combined with Internet of Things sensor data, to construct an initial 3D model of the park. The integration module is used to integrate environmental monitoring: including air quality, temperature and humidity, fire warning; facility status: including equipment health, energy consumption; personnel activities: including personnel identity, personnel location, movement speed, stay time, interaction behavior; energy use: including electricity consumption, water consumption, and merge them into a multi-dimensional data packet, which is integrated into the initial 3D model to generate a holographic digital twin. The rendering module is used to perform multi-resolution rendering on the holographic digital twin. It has a dynamic update function to adapt to the management needs at different levels and in different scenarios.

[0026] The analysis and prediction module includes a prediction model unit and a personnel behavior model unit. The prediction model unit includes a data storage module, a model construction module, and a result analysis module. The data storage unit is used to access the holographic digital twin body, store real-time data using a distributed architecture, and synchronously perform tagging processing according to the type of data. The model construction module constructs models for the change trends of the environment, facilities, and energy in the park based on time series analysis, regression analysis, and classification algorithms, and conducts training and verification based on historical data and real-time data to obtain a prediction model. The result analysis module constructs line charts and bar charts based on the prediction model, analyzes the change trends of various indicators in terms of the environment, facilities, and energy, and predicts potential problems and risks. In terms of facility management, the module can predict the operating status and failure risks of facilities and perform maintenance and repair in advance; in terms of energy management, the module can predict energy consumption trends and formulate energy-saving and consumption-reducing strategies; in terms of environmental management, the module can predict potential fire risks and hazards and take preventive measures in a timely manner. Through the application of this module, the smart park can achieve more accurate and efficient operation management and decision support. This can not only improve the operation efficiency and service quality of the park, but also reduce operation costs and safety risks, providing strong guarantee for the sustainable development of the park.

[0027] The described personnel behavior model unit includes a feature extraction module and a model prediction system. The feature extraction module is used to extract features useful for predicting personnel behavior from the raw data in the data storage module, including the movement trajectory of personnel, the nature of the staying area, the interaction frequency with other personnel, as well as the associated facilities and energy projects. The model prediction system uses a recurrent neural network (RNN) and a long short-term memory network (LSTM) to process time series data, and uses a convolutional neural network (CNN) to process image data, thereby constructing a personnel behavior model. The model is trained with the raw data in the data storage module. In this way, the future action trajectory and interaction behavior of personnel are predicted. At the same time of prediction, the equipment in terms of the environment, facilities, and energy affected by the personnel action trajectory and interaction behavior is associated with the action data of this personnel. During the process of constructing the personnel behavior model, hyperparameter tuning is carried out: Hyperparameters are parameters that need to be set before model training, including learning rate, batch size, number of network layers, etc. Through methods such as grid search, random search, or Bayesian optimization, the optimal combination of hyperparameters is found to improve the performance of the model. Regularization and overfitting handling: To prevent the model from overfitting on the training data, regularization techniques such as L1 regularization and L2 regularization are used. In addition, methods such as dropout and early stopping are used to reduce the risk of overfitting. Ensemble learning: The overall prediction accuracy and stability are improved by combining the prediction results of multiple models. Ensemble learning methods include bagging, boosting, and stacking, etc. Continuous learning and updating: Personnel behavior is dynamically changing, so the model continuously learns new data and updates its parameters. This is achieved through methods such as online learning or incremental learning.

[0028] The described adaptive compensation module includes an external influence factor strategy unit and a personnel influence factor strategy unit. The external influence factor strategy unit is used to access the prediction model, generate adaptive management strategies for the environment, facilities, and energy in the park according to the change prediction trend of the prediction model, including energy optimization scheduling strategies, facility preventive maintenance strategies, and temperature and humidity control strategies. The external influence factor strategy unit also accesses the weather forecast website and conducts real-time strategy planning according to the impact of future weather on the environment, facilities, and energy. The system automatically adjusts the environment, facilities, and energy usage strategies of the park according to the real-time data and prediction results, thereby ensuring that the operation of the park is more efficient, energy-saving, and environmentally friendly. It can significantly improve the utilization efficiency of resources. Through accurate prediction and intelligent adjustment, the system can ensure that the environmental, facility, and energy resources in the park are fully utilized, avoiding waste and idleness. This not only helps to reduce the operation cost of the park, but also can enhance the sustainable development ability of the park.

[0029] The holographic digital twin contains risk rules and thresholds related to the identities of all personnel in the park. The personnel influence factor policy unit is used to access the personnel behavior model, bring the current behavior of the personnel, the predicted future action trajectory, and interaction behavior into the risk rules and thresholds, and synchronously establish three-level policies. The first-level policy is that the current behavior and future predicted behavior of the personnel are normal and no marking is done. The second-level policy is that the current behavior of the personnel is normal but the future predicted behavior triggers the risk rules and thresholds. In the holographic digital twin, mark the personnel and the equipment in the aspects of the environment, facilities, and energy affected by their relevant behaviors. The third-level policy is that both the current behavior and future predicted behavior of the personnel trigger the risk rules and thresholds. In the holographic digital twin, mark the personnel and the equipment in the aspects of the environment, facilities, and energy affected by their relevant behaviors, and synchronously send an alarm to the terminal device of the management personnel. During the alarm process, upload the parameters of the equipment in the aspects of the environment, facilities, and energy affected by the personnel and their relevant behaviors, so as to facilitate the management personnel to understand whether the abnormal behavior has a significant impact on the equipment in the aspects of the environment, facilities, and energy. The holographic digital twin contains risk rules and thresholds related to the identities of all personnel in the park, synchronously establishes three-level policies, brings the current behavior of the personnel and the predicted future action trajectory and interaction behavior into the risk rules and thresholds for processing, and according to the differences in the three-level policies, respectively, no processing, marking, and alarming are carried out. During the alarm process, upload the parameter change values of the equipment in the aspects of the environment, facilities, and energy affected by the personnel and their relevant behaviors to facilitate the management personnel to take different responses. At the same time, when the system predicts external personnel, since there are no risk rules and thresholds related to the identities of external personnel, density and stagnation monitoring are carried out. When the system detects that the density of external personnel in a certain area is too high, the early warning mechanism is automatically triggered to remind the management personnel to take corresponding safety measures, such as increasing security personnel and evacuating the crowd. When the external personnel stay at a device in a certain environment, facility, or energy for a time reaching the set threshold and the parameters of the device in the environment, facility, or energy are abnormal, the early warning mechanism is automatically triggered to remind the management personnel to take corresponding safety measures.

[0030] Embodiment 2

[0031] According to Figure 1 As shown, this embodiment proposes a smart park digital management system based on digital twin technology, including a multi-dimensional digital twin modeling module, an analysis and prediction module, an adaptive compensation module, an interaction module, and an ecological integration module. The multi-dimensional digital twin modeling module uses scanning combined with remote sensing technology to construct an initial 3D model of the park, and through the Internet of Things, integrates environmental monitoring, facility status, personnel activities, and energy use, and fuses them with the initial 3D model to generate a holographic digital twin;

[0032] The analysis and prediction module constructs a prediction model and a personnel behavior model based on machine learning algorithms. The prediction model is used to predict the change trends in the internal environment, facilities, and energy of the holographic digital twin. The personnel behavior model is used to learn and identify the normal behavior patterns of the personnel in the holographic digital twin, predict their future action trajectories and interaction behaviors, and synchronously predict the environment, facilities, and energy affected by the personnel activities. The adaptive compensation module is used to combine policy algorithms, generate adjustment measures for the change trends in the environment, facilities, and energy according to the predictions of the prediction model, and multi-level respond to the personnel behaviors in combination with the personnel behavior model, risk rules, and thresholds. The interaction module provides visual interaction for management personnel. The ecological integration module is used to provide external integration connection functions. A holographic digital twin is constructed through multi-dimensional data collection. The change trends in the internal environment, facilities, and energy of the holographic digital twin are predicted through the prediction model. The future action trajectories and interaction behaviors of personnel are predicted through the personnel behavior model according to the normal behavior patterns of personnel with different identities, and the environment, facilities, and energy affected by the personnel activities are synchronously predicted. Thus, it is convenient to generate adjustment measures for the change trends in the environment, facilities, and energy, and multi-level respond to the personnel behaviors in combination with the risk rules and thresholds, with perfect prediction and management functions for personnel behaviors and their potential risks, being forward-looking and proactive. Moreover, the prediction includes the environment, facilities, and energy affected by the personnel activities, facilitating linkage positioning and improving the timeliness of response.

[0033] The interactive module includes a holographic projection module and a custom management module. The holographic projection module uses holographic projection technology to present the holographic digital twin in an immersive manner to the manager, providing an intuitive display of the park operation status and enabling the manager to interact through gesture and voice interaction, so as to realize remote monitoring and management of the facilities and personnel in the park. The custom management module is used to identify the level of the current management personnel and open different custom views, alarm prompts, and data report functions according to the level of the management personnel. Advanced holographic projection technology is used to present the holographic digital twin in an immersive manner to the manager. This technology can create a three-dimensional and stereoscopic visual effect, making the manager seem to be in the real environment of the park. Through holographic projection, the manager can intuitively see key information such as the overall layout of the park, facility distribution, and personnel flow, so as to better understand the operation status of the park. The manager can perform operations such as zooming and rotating on the projection screen through gestures to view a certain area or facility of the park in more detail. At the same time, the voice interaction function also enables the manager to communicate with the system more conveniently, issue instructions or query information. With the help of the holographic projection module, the manager can realize remote monitoring and management of the facilities and personnel in the park. No matter where the manager is, as long as through the holographic projection module, the manager can view the operation of the park in real time, discover problems in time and take corresponding measures. This ability of remote monitoring and management greatly improves the operation efficiency and management level of the park. The core function of the custom management module is to identify the level of the current management personnel and open different custom views, alarm prompts, and data report functions according to the level of the management personnel. This mechanism of level identification and permission management ensures that management personnel at different levels can only access information related to their responsibilities, thus improving the security and confidentiality of the system. It allows management personnel to set personalized views according to their own needs and preferences. For example, senior management personnel may be more concerned about the overall operation of the park and key indicators, while grass-roots management personnel may be more concerned about the operation status of specific facilities and personnel flow. Through the custom view function, management personnel can obtain the information they care about more conveniently and improve work efficiency. Alarm prompts and data report functions are also provided. When an abnormal situation occurs in the park or a facility fails, the system will automatically trigger an alarm prompt to notify the relevant management personnel to handle it in time. At the same time, the system can also generate various data reports to help management personnel better understand the operation situation and trends of the park. These reports can not only be used for internal management and decision support, but also serve as an important tool for communicating with external partners or investors.

[0034] The ecological integration module includes an integration unit and a data sharing platform. The integration unit is used to provide open API interfaces for seamless integration with other intelligent park management systems, Internet of Things devices, and big data platforms. The data sharing platform is used to upload and share the data in the holographic digital twin based on the permission control of the management personnel while the integration unit integrates other systems for data collaboration. The open API (Application Programming Interface) interface is the core. By providing standardized interfaces, the intelligent park management system can be seamlessly integrated with various other systems. These systems may include other intelligent park management systems, Internet of Things devices (such as sensors, cameras, intelligent access control, etc.), big data platforms, cloud computing services, etc. This seamless integration capability ensures smooth communication and data exchange among various devices and systems in the park. The open API interface also promotes data sharing among different systems. In an intelligent park, various devices and systems generate a large amount of data. Through the open API interface, this data can be uniformly collected, integrated, and analyzed, providing comprehensive data support for the operation and management of the park. At the same time, collaborative work among different systems is also achieved, improving the overall operation efficiency of the park. The intelligent park ecosystem refers to a complex network composed of multiple interconnected and interdependent intelligent systems and devices. These systems and devices work together to provide intelligent services and management for the park. In this ecosystem, the open API interface plays the role of a bridge and link, ensuring smooth communication and data exchange among different systems. Through the open API interface, new applications and services can be easily connected to the ecosystem, thus enriching the functions and services of the park. At the same time, data sharing and collaborative work among different systems also stimulate new innovation points, promoting the continuous development of the intelligent park. Through the collaborative work of Internet of Things devices and big data platforms, the park can achieve functions such as intelligent environmental monitoring, energy management, and security monitoring; through cloud computing services, the park can provide more flexible and scalable IT infrastructure support.

[0035] The intelligent park digital management system based on digital twin technology constructs a holographic digital twin through multi-dimensional data collection, predicts the change trends in the environment, facilities, and energy within the holographic digital twin through a prediction model, and predicts the future action trajectories and interaction behaviors of different identity personnel according to the normal behavior patterns of personnel through a personnel behavior model, and synchronously predicts the environment, facilities, and energy affected by personnel activities. Thus, it is convenient to generate adjustment measures for the change trends in the environment, facilities, and energy, and combined with risk rules and thresholds, multi-level responses are made to personnel behaviors, with perfect prediction and management functions for personnel behaviors and their potential risks, being forward-looking and proactive, and the prediction includes the environment, facilities, and energy affected by personnel activities, facilitating linkage positioning and improving the timeliness of response. At the same time, the holographic digital twin of the present invention has risk rules and thresholds related to the identities of all personnel in the park, and three-level strategies are synchronously set up. The current behaviors of personnel and the predicted future action trajectories and interaction behaviors are brought into the risk rules and thresholds for processing. According to the differences in the three-level strategies, no processing, marking, and alarming are carried out respectively. During the alarming process, the parameter change values of the equipment in the aspects of the environment, facilities, and energy affected by the personnel and their related behaviors are uploaded, facilitating different responses by management personnel. In addition, the present invention provides an open API interface, which is convenient for seamless integration with other intelligent park management systems, Internet of Things devices, and big data platforms, promoting data sharing and collaborative work among different systems and improving the overall intelligent level of the park.

[0036] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital management system for a smart park based on digital twin technology, including a multi-dimensional digital twin modeling module, an analysis and prediction module, an adaptive compensation module, an interaction module and an ecological integration module, characterized in that: The multi-dimensional digital twin modeling module uses scanning combined with remote sensing technology to build an initial three-dimensional model of the park, and integrates environmental monitoring, facility status, personnel activities, and energy use through the Internet of Things, and merges them with the initial three-dimensional model to generate a holographic digital twin; The analysis and prediction module constructs a prediction model and a personnel behavior model based on a machine learning algorithm. The prediction model is used to predict the changing trends of the environment, facilities, and energy in the holographic digital twin. The personnel behavior model is used to learn and identify the normal behavior patterns of personnel in the holographic digital twin, predict their future action trajectories and interactive behaviors, and simultaneously predict the environment, facilities, and energy affected by personnel activities. The adaptive compensation module is used to combine the strategy algorithm to generate adjustment measures for the changing trends of the environment, facilities, and energy according to the prediction of the prediction model, and combine the personnel behavior model and risk rules and thresholds to respond to personnel behavior at multiple levels. The interaction module provides visual interaction for management personnel, and the ecological integration module is used to provide external integration connection functions.

2. According to claim 1, a digital management system for a smart park based on digital twin technology is characterized by: The multi-dimensional digital twin modeling module includes an acquisition modeling module, an integration module and a rendering module. The acquisition modeling module uses high-precision three-dimensional scanning, drone aerial photography, satellite remote sensing technology, combined with IoT sensor data to build an initial three-dimensional model of the park. The integration module is used for integrated environmental monitoring: including air quality, temperature and humidity, and fire warning; Facility status: including equipment health and energy consumption; personnel activities: including personnel identity, personnel location, movement speed, residence time, and interactive behavior; energy use: including electricity and water volume, which are merged into multi-dimensional data packets and integrated into the initial three-dimensional model to generate a holographic digital twin. The rendering module is used to perform multi-resolution rendering of the holographic digital twin.

3. According to claim 2, a digital management system for a smart park based on digital twin technology is characterized in that: The analysis and prediction module includes a prediction model unit and a personnel behavior model unit. The prediction model unit includes a data storage module, a model construction module, and a result analysis module. The data storage unit is used to access the holographic digital twin, adopt a distributed architecture to store real-time data, and simultaneously label the data according to its type. The model construction module constructs a model for the changing trends of the environment, facilities, and energy in the park based on time series analysis, regression analysis, and classification algorithms, and trains and verifies based on historical data and real-time data to obtain a prediction model. The result analysis module constructs line charts and bar charts based on the prediction model, analyzes the changing trends of various indicators in the environment, facilities, and energy, and predicts potential problems and risks.

4. According to claim 3, a digital management system for a smart park based on digital twin technology is characterized in that: The personnel behavior model unit includes a feature extraction module and a model prediction system. The feature extraction module is used to extract features useful for predicting personnel behavior from the original data of the data storage module, including the movement trajectory of the personnel, the nature of the stay area, the frequency of interaction with other personnel, and the facilities and energy projects associated with them. The model prediction system uses a recurrent neural network (RNN) and a long short-term memory network (LSTM) to process time series data, and uses a convolutional neural network (CNN) to process image data to construct a personnel behavior model, and trains the model with the original data in the data storage module to predict the future movement trajectory and interaction behavior of the personnel. At the same time, the environment, facilities, and energy equipment affected by the movement trajectory and interaction behavior of the personnel are associated with the movement data of the personnel.

5. According to claim 2, a digital management system for a smart park based on digital twin technology is characterized in that: The adaptive compensation module includes an external influencing factor strategy unit and a personnel influencing factor strategy unit. The external influencing factor strategy unit is used to access the prediction model, and generate adaptive management strategies for the environment, facilities, and energy in the park according to the change prediction trend of the prediction model, including energy optimization scheduling strategy, facility preventive maintenance strategy, and temperature and humidity control strategy. The external influencing factor strategy unit is also connected to the weather forecast website to perform real-time strategy planning based on the impact of future weather on the environment, facilities, and energy.

6. According to claim 5, a digital management system for a smart park based on digital twin technology is characterized in that: The holographic digital twin has built-in risk rules and thresholds related to the identities of all personnel in the park. The personnel influencing factor strategy unit is used to access the personnel behavior model, bring the personnel's current behavior and predicted future action trajectory and interactive behavior into the risk rules and thresholds, and simultaneously establish a three-level strategy. The first-level strategy is that the personnel's current behavior and future predicted behavior are normal and no marking is made. The second-level strategy is that the personnel's current behavior is normal but the future predicted behavior triggers risk rules and thresholds, and the personnel and the environment, facilities, and energy equipment affected by their related behaviors are marked in the holographic digital twin. The third-level strategy is that the personnel's current behavior and future predicted behavior both trigger risk rules and thresholds, and the personnel and the environment, facilities, and energy equipment affected by their related behaviors are marked in the holographic digital twin, and an alarm is simultaneously issued and sent to the terminal device of the manager. During the alarm process, the parameter change values ​​of the environment, facilities, and energy equipment affected by the personnel and their related behaviors are uploaded.

7. According to claim 1, a digital management system for a smart park based on digital twin technology is characterized by: The interactive module includes a holographic projection module and a custom management module. The holographic projection module uses holographic projection technology to present the holographic digital twin to the manager in an immersive manner, providing an intuitive display of the park's operating status, and providing the manager with the function of interacting through gestures and voice interactions, thereby realizing remote monitoring and management of facilities and personnel in the park.

8. According to claim 7, a digital management system for a smart park based on digital twin technology is characterized in that: The custom management module is used to identify the level of the current manager and open different custom views, alarm prompts, and data reporting functions according to the level of the manager.

9. According to claim 1, a digital management system for a smart park based on digital twin technology is characterized by: The ecological integration module includes an integration unit and a data sharing platform. The integration unit is used to provide an open API interface for seamless integration with other smart park management systems, Internet of Things devices, and big data platforms.

10. The smart park digital management system based on digital twin technology according to claim 9, characterized in that: The data sharing platform is used to upload and share data in the holographic digital twin based on the authority control of managers while the integration unit integrates other systems to carry out data collaboration.

Images