Integrated Multi-Dimensional Monitoring Method and System for Construction Sites

Abstract

The present invention relates to the technical field of construction site monitoring and intelligent management, and particularly to an integrated multi-dimensional monitoring method and system for construction sites. The present invention collects multi-dimensional data of the construction site environment through multi-spectral imaging technology, acoustic wave detection technology and LIDAR technology, and conducts dynamic analysis and prediction through a multi-level spatio-temporal graph convolutional network and an adaptive Bayesian-Markov model to generate comprehensive environmental prediction data; uses an interactive dynamic game model to optimize the resource allocation and strategy execution of construction site monitoring nodes to ensure the efficient operation of the system in a complex construction site environment; continuously optimizes the monitoring strategy through a multi-level intelligent feedback network to enhance the response speed and accuracy of the system and ensure the safety and efficiency of construction site operation.

Description

Technical Field

[0001] The present invention relates to the technical field of construction site monitoring and intelligent management, and particularly to an integrated multi-dimensional monitoring method and system for construction sites. Background Art

[0002] With the expansion of the scale of construction sites and the increase in construction complexity, traditional single monitoring means can no longer meet the all-round and all-weather safety management requirements of construction sites. In order to ensure safety and efficiency during the construction process, it is necessary to establish a monitoring system that covers comprehensively, responds quickly, and can perform multi-dimensional data analysis. Through multi-dimensional monitoring, not only can various dynamics of the construction site be monitored in real time, but also potential safety hazards can be predicted and prevented to ensure the smooth operation of the construction site.

[0003] Existing construction site monitoring systems (Chinese invention patent, publication number: CN118055214A, title: An integrated intelligent monitoring system, method and device for a smart construction site) usually use technical means such as video monitoring and sensor monitoring for data collection and analysis. However, these systems have many deficiencies in practical applications:

[0004] In the prior art, the data between the video monitoring system and the sensor system is relatively independent, lacking effective integration across systems; video monitoring is mainly used for the monitoring of personnel and equipment, while the sensor system focuses on the collection of environmental data, and there is no effective linkage mechanism between the two, resulting in low data utilization efficiency;

[0005] Although existing systems can collect a large amount of monitoring data, they still rely on simple rules and threshold judgments in data analysis, lacking intelligent analysis capabilities and being difficult to accurately predict and manage risks in complex construction site environments;

[0006] When facing emergencies, existing systems usually can only rely on preset alarm mechanisms, lacking the adaptive ability to dynamic changing environments and being unable to adjust monitoring strategies in a timely manner, resulting in slow emergency responses. Summary of the Invention

[0007] In view of the many problems existing in the above-mentioned prior art, the present invention provides an integrated multi-dimensional monitoring method and system for construction sites. Through advanced data collection technologies, multi-level intelligent analysis models, and dynamic optimization algorithms, the present invention realizes comprehensive monitoring and real-time adjustment of the construction site environment. Through technologies such as multi-spectral imaging, acoustic wave detection, and LIDAR, the system can comprehensively collect multi-dimensional data of the construction site, and perform data analysis and prediction through a multi-level spatio-temporal graph convolutional network and an adaptive Bayesian-Markov model. Finally, through an interactive dynamic game model, optimal allocation of resources and strategy adjustment are realized to ensure the safety and efficiency of the construction site operation.

[0008] An integrated multi-dimensional monitoring method for construction sites, comprising the following steps:

[0009] Collect environmental data, acoustic feature data, and three-dimensional spatial data at key positions on the construction site through multi-spectral imaging technology, acoustic wave detection and analysis technology, and LIDAR technology, and preprocess and format the collected data to generate a processed comprehensive dataset;

[0010] Input the processed comprehensive dataset into a multi-level spatio-temporal graph convolutional network for multi-level spatio-temporal correlation modeling and feature extraction to generate multi-level spatio-temporal correlation data, and perform uncertainty analysis and state transition prediction on the multi-level spatio-temporal correlation data through an adaptive Bayesian-Markov model to generate comprehensive environmental prediction data;

[0011] Based on the comprehensive environmental prediction data, use an interactive dynamic game model to optimize the resource allocation and monitoring strategies of the construction site monitoring nodes, generate global collaborative strategy data, and execute monitoring tasks according to the global collaborative strategy data, including real-time adjustment of monitoring device parameters and priority configuration;

[0012] During the execution of the monitoring task, collect and process real-time monitoring feedback data, and perform multi-level iterative optimization on the real-time monitoring feedback data and historical data through a multi-level intelligent feedback network to generate optimization data for updating the global collaborative strategy data.

[0013] Preferably, the preprocessing and formatting include the following steps: denoise the environmental data through a filtering algorithm to eliminate environmental noise interference; normalize the acoustic feature data to standardize the signal intensities of different sound sources; perform data format conversion on the three-dimensional spatial data to convert point cloud data into a raster data format, thereby generating a comprehensive dataset suitable for the multi-level spatio-temporal graph convolutional network.

[0014] Preferably, the multi-level spatio-temporal graph convolutional network includes the following steps: construct a multi-layer convolutional neural network to perform multi-level spatio-temporal correlation modeling on the processed comprehensive dataset, where each layer of the convolutional network processes data with different time scales and spatial resolutions to extract dynamic change features in the construction site environment, and finally generate multi-level spatio-temporal correlation data containing multi-dimensional spatio-temporal relationships.

[0015] Preferably, the adaptive Bayesian-Markov model performs state transition analysis on the multi-level spatio-temporal correlation data through the following steps:

[0016] Based on historical observation data and current observation data, recursively update the state transition probability and uncertainty parameters using the Bayesian inference method;

[0017] Based on the state transition model of Markov chain, predict the state of the construction site environment at future moments, so as to generate comprehensive environmental prediction data including short-term and medium-term prediction results.

[0018] Preferably, the state transition probability of the adaptive Bayesian-Markov model is calculated by the following formula:

[0019]

[0020] Wherein, represents the probability that the state transfers to the state at time ; the probability; represents the conditional probability of the state under the observation ; represents the probability of the observation ; represents the conditional probability of the observation under the state ;

[0021] Quantify the state transition relationship in the multi-level spatio-temporal correlation data through this formula to generate comprehensive environmental prediction data.

[0022] Preferably, the interactive dynamic game model models the resource allocation and strategy optimization of the construction site monitoring nodes through the following steps:

[0023] Construct a resource allocation game model, where the resource allocation decision of each monitoring node is based on the principle of maximizing the global utility function to generate an optimal resource allocation vector;

[0024] Based on the output of the resource allocation game model, further construct a strategy optimization game model, and generate a strategy selection vector for each monitoring node through a dynamic game process, and finally generate global collaborative strategy data.

[0025] Preferably, the interactive dynamic game model determines the optimal resource allocation through the following formula in the resource allocation game:

[0026]

[0027] Wherein, represents the resource allocation vector of the th node; represents the strategy selection vector of the th node; represents the utility function of the th node; represents the total amount of available resources;

[0028] Through this formula, the optimization of resource allocation among monitoring nodes is realized, and global collaborative policy data is generated.

[0029] Preferably, during the execution of the monitoring task, the following iterative optimization steps are performed on the real-time monitoring feedback data and historical data through a multi-level intelligent feedback network:

[0030] In the first-layer feedback mechanism, preliminary feedback optimization data is generated based on the current monitoring results;

[0031] In the second-layer feedback mechanism, the preliminary feedback optimization data is compared and analyzed with the historical monitoring data to generate second feedback optimization data;

[0032] In the third-layer feedback mechanism, combined with the abnormal situation handling records and long-term trend analysis, multi-level feedback optimization data is generated for adjusting the parameters and strategies of the construction site monitoring nodes.

[0033] Preferably, the multi-level intelligent feedback network includes multiple feedback levels, and each level analyzes and optimizes data for different dimensions. Among them, the first level is for the current monitoring results, the second level is for the historical monitoring data, and the third level is for the abnormal handling records, so as to generate comprehensive feedback optimization data for further optimizing the global collaborative policy data.

[0034] A system for implementing the integrated multi-dimensional monitoring method for construction sites includes:

[0035] A multi-spectral imaging module, an acoustic wave detection and analysis module, and a LIDAR module, which are used to collect environmental data, acoustic wave characteristic data, and three-dimensional space data at key positions on the construction site, and preprocess and format the environmental data, acoustic wave characteristic data, and three-dimensional space data to generate a processed comprehensive data set;

[0036] A multi-level spatio-temporal graph convolutional network module, which is used to receive the processed comprehensive data set, perform multi-level spatio-temporal correlation modeling and feature extraction to generate multi-level spatio-temporal correlation data;

[0037] An adaptive Bayesian-Markov model module, which is used to perform uncertainty analysis and state transition prediction on the multi-level spatio-temporal correlation data to generate comprehensive environmental prediction data;

[0038] An interactive dynamic game model module, which is used to optimize the resource allocation and monitoring strategy of the construction site monitoring nodes based on the comprehensive environmental prediction data, generate global collaborative policy data, and execute the monitoring task according to the global collaborative policy data, including real-time adjustment of the monitoring device parameters and priority configuration;

[0039] The multi-level intelligent feedback network module is used to collect and process real-time monitoring feedback data during the execution of the monitoring task, and perform multi-level iterative optimization on the real-time monitoring feedback data and historical data through the multi-level intelligent feedback network to generate optimized data for updating the global collaborative policy data.

[0040] Compared with the prior art, the advantages and beneficial effects of the present invention are as follows:

[0041] Through the combination of multi-spectral imaging technology, acoustic wave detection and analysis technology, and LIDAR technology, the comprehensive collection and preprocessing of multi-dimensional data are realized, and the data integration and utilization efficiency are improved;

[0042] Through the multi-level spatio-temporal graph convolutional network for multi-level spatio-temporal correlation modeling and feature extraction, the accurate capture of the dynamic change characteristics of the construction site environment is realized, and combined with the adaptive Bayesian-Markov model, the high-precision prediction of the future environmental state is realized;

[0043] Through the interactive dynamic game model, the resource allocation and monitoring strategy of the construction site monitoring nodes are dynamically optimized, the real-time response ability in complex environments is realized, and the emergency response speed of the system is significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic flow chart of the method of the present invention;

[0045] Figure 2 It is a schematic diagram of spatio-temporal correlation modeling and prediction in the present invention;

[0046] Figure 3 It is a schematic diagram of resource allocation and strategy optimization in the present invention;

[0047] Figure 4 It is a schematic diagram of multi-level intelligent feedback in the present invention;

[0048] Figure 5 It is a structural block diagram of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, obviously, one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0050] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0051] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0052] As Figure 1 shown, an integrated multi-dimensional monitoring method for a construction site includes the following steps:

[0053] Through multi-spectral imaging technology, acoustic detection and analysis technology, and LIDAR technology, environmental data, acoustic feature data, and three-dimensional spatial data are collected at key positions on the construction site, and the collected data is preprocessed and formatted to generate a processed comprehensive data set.

[0054] Preferably, the preprocessing and formatting include the following steps: denoising the environmental data through a filtering algorithm to eliminate environmental noise interference; normalizing the acoustic feature data to standardize the signal intensity of different sound sources; and converting the data format of the three-dimensional spatial data to convert the point cloud data into a raster data format, thereby generating a comprehensive data set suitable for a multi-level spatio-temporal graph convolutional network.

[0055] Multi-spectral imaging technology is used to capture the environmental data of the construction site. By imaging in multiple spectral bands, this technology can not only capture visible light information but also obtain information in other bands such as near-infrared and infrared, thus providing richer environmental data. These data can include parameters directly related to the construction site environment such as temperature, humidity, and vegetation coverage. In the application of this technology, multi-spectral imaging can not only identify changes invisible to the naked eye but also help detect potential risks such as overheating of equipment or abnormal heat sources, thus giving early warnings.

[0056] Acoustic detection and analysis technology is mainly used to capture the sound signals in the construction site, including mechanical operation sounds, personnel activity sounds, and other environmental sounds. By collecting acoustic feature data, the system can monitor the normal operation of the construction site and identify abnormal sounds such as precursors of equipment failures or the occurrence of unexpected events. The advantage of this technology is that it can provide a non-visual contact monitoring means in a complex construction site environment, especially suitable for those occasions with blind spots in visual monitoring or limited line of sight.

[0057] In addition, LIDAR technology is used to obtain three-dimensional spatial data of the construction site. By emitting laser light and receiving the reflected signals, it measures the distances of objects, thereby generating high-precision three-dimensional point cloud data. These data are used to construct an accurate three-dimensional model of the construction site, providing real-time information on the construction site layout, equipment positions, and dynamic changes. In the construction site environment, LIDAR technology can quickly and accurately capture site changes, such as material accumulation, equipment movement, or structural changes, thus providing basic data for subsequent monitoring and analysis.

[0058] In the data preprocessing and formatting step, first, the environmental data are denoised through a filtering algorithm. This step aims to eliminate the noise interference caused by environmental factors (such as wind, rain, dust, etc.), thereby improving the accuracy and reliability of the data. The denoised data can more truly reflect the actual situation of the construction site, avoiding misjudgments caused by noise interference.

[0059] For the acoustic feature data, the system performs normalization to standardize the signal intensities of different sound sources. Since there may be significant differences in the signal intensities and frequencies of different sound sources on the construction site, normalization can unify the sound data of different sound sources on the same scale, thus facilitating subsequent analysis and processing. This standardization not only improves the comparability of the data but also enables the system to more effectively detect and distinguish different sound characteristics, such as distinguishing normal operating sounds from potential abnormal sounds.

[0060] The three-dimensional spatial data undergo format conversion, converting the point cloud data generated by LIDAR into a raster data format. This process transforms the irregular point cloud data into a regular raster format, making the data easier to combine with other two-dimensional or three-dimensional data for processing. The rasterized data can better meet the modeling requirements of the multi-level spatio-temporal graph convolutional network, ensuring that these spatial data can be effectively utilized in spatio-temporal correlation modeling to generate accurate monitoring results.

[0061] As Figure 2 shown, the processed comprehensive dataset is input into the multi-level spatio-temporal graph convolutional network for multi-level spatio-temporal correlation modeling and feature extraction, generating multi-level spatio-temporal correlation data, and performing uncertainty analysis and state transition prediction on the multi-level spatio-temporal correlation data through an adaptive Bayesian-Markov model to generate comprehensive environmental prediction data;

[0062] The processed comprehensive dataset is input into a multi-level spatio-temporal graph convolutional network. The multi-level spatio-temporal graph convolutional network is a deep learning model for processing spatio-temporal data, capable of capturing the complex correlations in the data in the temporal and spatial dimensions. In the present invention, the network analyzes and extracts the spatio-temporal features in the comprehensive dataset through multiple convolutional layers. Each layer of the convolutional network processes data with different time scales and spatial resolutions respectively, ensuring that the system can identify various information from short-term changes to long-term trends. For example, in a construction site environment, this spatio-temporal correlation modeling can identify the movement trajectories of equipment, the gradual changes in environmental parameters, and the dynamic adjustments of the construction site layout. This multi-level analysis enables the system not only to grasp the current construction site status but also to model and predict potential change trends, thereby making responses in advance.

[0063] Based on the spatio-temporal correlation modeling, the system further performs uncertainty analysis and state transition prediction on the multi-level spatio-temporal correlation data through an adaptive Bayesian-Markov model. The Bayesian-Markov model is a statistical model for dealing with uncertainty and state transitions, combining the characteristics of Bayesian inference and Markov chains, and capable of predicting future states based on historical data and current observations. In the present invention, the application of the adaptive Bayesian-Markov model enables the system to dynamically predict the state changes of the construction site environment. Especially in the face of a complex and changeable environment, the model can capture the uncertainties existing in the system by recursively updating the state transition probabilities. For example, on a construction site, factors such as weather changes, equipment failures, or personnel transfers will introduce uncertainties in the environment. The model generates comprehensive environment prediction data by quantifying these uncertainties and predicting their impacts, thereby providing data support for subsequent decision-making and optimization.

[0064] This prediction ability has significant effects in practical applications. For example, when the system identifies an abnormal fluctuation in the running trajectory of a certain piece of equipment through the multi-level spatio-temporal graph convolutional network, the adaptive Bayesian-Markov model can further analyze whether this fluctuation will lead to equipment failure and predict the likelihood and time of the failure. This comprehensive environment prediction data can not only help construction site managers take preventive measures in advance to avoid accidents but also optimize the scheduling and allocation of resources, ensuring the stability and efficiency of the construction site operation.

[0065] Preferably, the multi-level spatio-temporal graph convolutional network includes the following steps: By constructing a multi-layer convolutional neural network, perform multi-level spatio-temporal correlation modeling on the processed comprehensive dataset, where each layer of the convolutional network processes data with different time scales and spatial resolutions respectively to extract the dynamic change features in the construction site environment, and finally generate multi-level spatio-temporal correlation data containing multi-dimensional spatio-temporal relationships.

[0066] The multi-level spatiotemporal graph convolutional network processes the spatiotemporal information in the dataset through multiple convolutional layers. Each layer of the convolutional network processes different time scales and spatial resolutions to ensure that the system can capture a variety of dynamic features in the construction site environment, from micro changes to macro trends. For example, in a multi-layer convolutional network, the first layer may focus on capturing high-frequency changes in a short period of time, such as vibration or noise of mechanical equipment, while the second layer may process low-frequency changes in a longer time span, such as the day-to-night changes in the overall temperature of the construction site or the slow increase in material accumulation. This hierarchical processing method enables the system to effectively extract different levels of spatiotemporal features, which often have important decision-making significance in construction site management.

[0067] In the application of multi-level spatiotemporal graph convolutional networks, the basic principles of convolutional neural networks (CNNs) are further extended to the spatiotemporal dimension. Traditional CNNs are usually used to process two-dimensional image data and capture spatial features through local perception domains. In the present invention, the spatiotemporal convolutional network combines time and space for modeling, so that it can handle continuous changes in the construction site environment. For example, when monitoring the safety status of a construction site, the temperature rise and abnormal changes in the sound wave frequency at a certain moment, combined with historical data, can indicate potential risks of equipment overheating or mechanical failure. Through the processing of multi-layer convolutional networks, the system can not only identify this risk, but also analyze its possible development trend, providing a decision-making basis for construction site management.

[0068] The application of multi-level spatiotemporal graph convolutional networks significantly improves the system's depth of understanding and predictive capabilities for complex construction site environments. Since the processing objectives of each layer of the convolutional network are different, the system can analyze the data on the construction site from multiple angles and levels, thereby generating multi-level spatiotemporal correlation data containing rich information. These data can be used for real-time monitoring, risk warning, and resource optimization in practical applications. For example, the system can identify whether the operating mode of a certain equipment is abnormal by analyzing multi-level spatiotemporal correlation data, thereby timely warning of possible failures and avoiding losses caused by downtime.

[0069] In the specific implementation, suppose the operating data of a piece of equipment on a construction site is input into a multi-level spatiotemporal graph convolutional network. The first layer of the network may capture the high-frequency vibration data of the equipment in a short period of time, indicating that the equipment may have abnormal operation; the second layer of the network processes data over a longer time span and finds that the temperature of the equipment is gradually rising. Through these hierarchical analyses, the system can generate detailed multi-level spatiotemporal correlation data to describe the state change trend of the equipment, and make early warning and scheduling decisions based on this to ensure the safety and efficiency of construction site operations.

[0070] Preferably, the adaptive Bayesian-Markov model performs state transition analysis on multi-level spatiotemporal correlation data by the following steps:

[0071] Based on historical observation data and current observation data, the state transition probability and uncertainty parameters are recursively updated using the Bayesian inference method;

[0072] Based on the state transition model of the Markov chain, the construction site environment state at a future time is predicted, thereby generating comprehensive environment prediction data including short-term and medium-term prediction results.

[0073] The application of Bayesian inference in this model aims to perform continuous dynamic modeling of the construction site environment state by recursively updating the state transition probability and uncertainty parameters. In a complex construction site environment, there is often a certain degree of uncertainty in the observation of various data. For example, the sensor data of equipment is affected by external interference and generates noise, or environmental factors (such as weather) cause fluctuations in the observation data. The Bayesian inference method can use historical observation data and current observation data to quantify these uncertainties and reflect the real changes in the construction site environment by updating the state transition probability. Through this recursive update mechanism, the system can dynamically adjust its understanding of the construction site state, thereby more accurately capturing the changing trend of the environment.

[0074] The state transition model of the Markov chain is used in this invention to predict the construction site environment state at a future time. The core idea of the Markov chain is that the prediction of the future state depends only on the current state and is independent of the past states. This state transition model has strong adaptability in dealing with the dynamic changes of the construction site environment. Especially when facing multiple possible states, it can predict the future state based on the current state and the known transition probability. For example, in construction site management, if an abnormal fluctuation in the operating state of a certain piece of equipment is currently observed, the system can use the Markov chain model to predict the possible future states of the equipment and determine whether it will further deteriorate into a failure state or return to normal.

[0075] Combining these two parts, the comprehensive environment prediction data generated by the system through the adaptive Bayesian - Markov model not only contains the current state information of the construction site environment but also provides predictions of the future short-term and medium-term states. This kind of prediction data has important guiding significance for construction site management, which can help managers make decisions in advance and prevent the occurrence of potential risks. For example, the system may predict that due to continuous high-temperature environments, some mechanical equipment may overheat and fail within the next few hours. Based on this prediction, construction site managers can adjust the working load of the equipment in advance or arrange regular inspections to avoid work stoppages and safety accidents caused by equipment failures.

[0076] Preferably, the state transition probability of the adaptive Bayesian - Markov model is calculated by the following formula:

[0077]

[0078] wherein, represents the probability of the state transferring from time to time state; The probability; represents the conditional probability of the state under the observation ; represents the probability of the observation ; represents the conditional probability of the observation under the state ;

[0079] Quantify the state transition relationship in the multi-level spatio-temporal correlation data through this formula to generate comprehensive environment prediction data.

[0080] In practical applications, this formula first utilizes the principle of Bayesian inference to update the system's understanding of the current state based on the current observation data and historical state information. Through recursive calculation, these conditional probabilities can dynamically reflect the changes in the construction site environment. For example, if it is observed that the temperature in a certain area of the construction site suddenly rises , the system will use this observation data to re-evaluate the current operating state of the equipment , and calculate the possible changes in the future state of the equipment through the formula, such as further temperature increase, stabilization, or cooling.

[0081] This analysis based on state transition probability has important practical effects in construction site management. Through accurate prediction of state transitions, managers can better understand and master the dynamic changes of construction site equipment or environment, and thus take corresponding measures in advance. For example, when the formula calculates that the probability of the equipment failing in the future is relatively high, the system can issue an alarm and recommend that the manager conduct equipment inspections or maintenance to avoid potential shutdown risks.

[0082] A typical example is that during the concrete pouring process of a construction site, the temperature data collected by sensors shows that the temperature in a certain area rises rapidly. The system analyzes the current state through an adaptive Bayesian-Markov model, combines the observation data and historical temperature records, and predicts the risk of concrete cracking in the future period . If the calculated is relatively high, the system will recommend that the construction site management personnel take measures, such as increasing cooling or covering measures, to prevent material quality problems.

[0083] Such as Figure 3As shown, based on the comprehensive environmental prediction data, an interactive dynamic game model is used to optimize the resource allocation and monitoring strategies of the construction site monitoring nodes, generate global collaborative strategy data, and execute the monitoring tasks according to the global collaborative strategy data, including real-time adjustment of monitoring device parameters and priority configuration;

[0084] The comprehensive environmental prediction data is obtained through previous data collection and analysis (such as through a multi-level spatio-temporal graph convolutional network and an adaptive Bayesian-Markov model). These data provide the dynamic state information of the construction site environment, including possible risk points, the working status of equipment, the distribution of personnel activities, etc. This information is the basis for the system to perform resource allocation and strategy optimization.

[0085] The interactive dynamic game model plays a key role in this process. The game model is a mathematical tool widely used to analyze the strategic interactions among multiple participants (in this invention, the monitoring nodes). In the construction site monitoring system, each monitoring node such as a camera, a sensor, etc. can be regarded as a "participant". These nodes need to coordinate their work under limited resource conditions, such as power, bandwidth, and computing resources, etc., to achieve the overall optimal monitoring effect. The dynamic game model allows these nodes to adjust their strategies according to the comprehensive environmental prediction data to maximize the overall benefit.

[0086] Specifically, the interactive dynamic game model generates the global collaborative strategy data through a two-step optimization process. The first step is resource allocation optimization. The model determines the optimal resource allocation plan by calculating the utility function of each monitoring node (i.e., the monitoring effect that can be achieved under different resource allocation situations) while ensuring that the total amount of resources does not exceed the system's allowable range. For example, if the risk in a certain construction area during a certain period is relatively high, the model may allocate more power and bandwidth to the camera responsible for that area to improve its monitoring quality.

[0087] The second step is monitoring strategy optimization. After the resource allocation is determined, the game model further optimizes the specific strategies of each monitoring node, including the perspective adjustment of the camera, the sensitivity setting of the sensor, the data transmission priority, etc. This step ensures that under the current resource configuration, the monitoring behaviors of all nodes can be coordinated with each other, so as to achieve the overall optimal monitoring effect.

[0088] The generation of global collaborative policy data is the final result of the game model calculation, and these data directly guide the system to execute the monitoring task. The key during the execution process lies in real-time adjustment, that is, when the monitoring task is in progress, the system can dynamically adjust the parameters of the monitoring devices and the task priorities according to the actual situation and feedback data. For example, if a monitoring node discovers frequent and abnormal personnel activities in a certain area during the task execution, the system may immediately adjust the monitoring perspective of this node, or increase the priority of the data transmitted by it to ensure a timely response to potential security risks.

[0089] Through the interactive dynamic game model, the present invention can achieve the intelligent allocation of resources of the construction site monitoring system and the adaptive optimization of the policy, enabling the entire system to always maintain efficient and accurate monitoring capabilities in the face of complex and changeable construction site environments. This model can not only adjust the monitoring policy according to real-time data, but also maximize the monitoring effect, reduce resource waste, and improve the overall efficiency and safety of construction site management under limited resources.

[0090] For example, in a large construction site, if the system predicts that there is a risk of collapse in a certain construction area in the next few hours, the interactive dynamic game model will preferentially allocate more resources to the devices responsible for monitoring this area, and at the same time adjust the monitoring policies of these devices, such as increasing the resolution and data acquisition frequency of the cameras, and transmitting their data to the central monitoring system in real time for key analysis. Through this optimization process, the system can not only detect and warn of risks in a timely manner, but also effectively respond to emergencies through flexible resource management and policy adjustment to ensure the safe operation of the construction site.

[0091] Preferably, the interactive dynamic game model models the resource allocation and policy optimization of the construction site monitoring nodes through the following steps:

[0092] Construct a resource allocation game model, where the resource allocation decision of each monitoring node is based on the principle of maximizing the global utility function to generate an optimal resource allocation vector;

[0093] Based on the output of the resource allocation game model, further construct a policy optimization game model, and generate a strategy selection vector for each monitoring node through a dynamic game process, and finally generate global collaborative policy data.

[0094] The first step of the interactive dynamic game model is to construct a resource allocation game model. In a construction site monitoring system, resources (such as electricity, bandwidth, computing power, etc.) are limited, and each monitoring node (such as cameras, sensors, etc.) requires these resources to perform its monitoring tasks. The resource allocation game model treats each monitoring node as a "player" in the game, enabling these nodes to make resource allocation decisions based on their own needs and the overall system goals. Specifically, the goal of the resource allocation decision is to maximize the global utility function, which measures the overall monitoring effect and resource utilization rate of the system. By calculating the utility values of each node under different resource allocation scenarios, the model can generate an optimal resource allocation vector to ensure that the resource allocation in the global scope of the system reaches the optimal state. For example, in a large construction site, if the monitoring demand in a certain area suddenly increases (such as a dense population of people or abnormal equipment), the system will preferentially allocate more resources to the monitoring nodes responsible for that area to improve the monitoring quality.

[0095] After completing the resource allocation, the interactive dynamic game model enters the second step, which is to construct a strategy optimization game model. At this time, each monitoring node has obtained the corresponding resources, and then it needs to decide how to best utilize these resources for monitoring. The strategy optimization game model generates a strategy selection vector for each node through a dynamic game. In this process, the nodes will consider each other's strategies and behaviors, and gradually adjust their own strategies through mutual games to achieve the overall optimal monitoring effect. For example, during the monitoring process after resource allocation, if a certain camera detects abnormal activities in the area it is responsible for, while another camera in a neighboring area does not detect any abnormalities, the two may adjust their monitoring directions and focal lengths through the game process to cover a larger monitoring range and ensure that any abnormal activities can be captured in a timely manner.

[0096] Through the coordinated action of these two steps, the interactive dynamic game model finally generates global collaborative strategy data. These data include the resource allocation scheme and specific monitoring strategies of each monitoring node, ensuring that the entire system can operate in the best state. The generation of global collaborative strategy data means that the system not only optimizes the performance of individual nodes, but more importantly, it realizes the collaborative work of all nodes in the global scope, thus maximizing the overall efficiency of construction site monitoring.

[0097] In practical applications, the effect of this process is particularly remarkable. For example, in a high-risk construction site environment, the monitoring requirements around a certain key piece of equipment are usually high. Through the resource allocation game model, the system can preferentially allocate more resources to the nodes monitoring this equipment, and at the same time, through the strategy optimization game model, ensure that these nodes can reasonably adjust their monitoring strategies, such as increasing the monitoring frequency, adjusting the camera angle, etc., to fully cover the surrounding area of the equipment. The finally generated global collaborative strategy data can ensure that even in the case of resource constraints, the system can still conduct efficient and accurate monitoring of key areas and avoid potential accidents.

[0098] Preferably, the interactive dynamic game model determines the optimal resource allocation in the resource allocation game through the following formula:

[0099]

[0100] Where, represents the resource allocation vector of the th node, that is, among the total amount of limited resources, the amount of resources actually allocated to this node; represents the strategy selection vector of the th node, representing the specific strategy adopted by this node in the monitoring task, such as the angle of the camera, the setting of the focal length, or the adjustment of the sensitivity of the sensor, etc.; represents the utility function of the th node. This function measures the monitoring effect or benefit that the node can achieve under different resource allocations and strategy selections. Usually, the utility function is proportional to the effect of the node completing the monitoring task; represents the total amount of available resources, which is a constant representing the upper limit of resources that can be allocated in the entire monitoring system;

[0101] Through this formula, the resource allocation optimization among monitoring nodes is realized, and global collaborative strategy data is generated.

[0102] The goal of this formula is to maximize the total utility of all monitoring nodes on the premise of meeting the total system resource limit. In other words, the system should ensure that each node obtains the resources it needs while ensuring that the resource utilization of the entire system reaches the optimal. This is crucial for the construction site monitoring system, especially in the case of limited resources, it is necessary to ensure that the monitoring of key areas is given priority.

[0103] In practical applications, the complexity of construction site monitoring lies in the fact that the requirements and importance of each monitoring node vary. For example, in a large-scale construction site, certain areas may require more monitoring resources such as high-definition cameras, fast-response sensors, etc. due to intensive construction activities or high potential risks; while other areas may be relatively stable and require fewer resources. Therefore, the system needs to conduct refined management of the resource allocation for each node to ensure the overall monitoring efficiency.

[0104] By applying the above formula, the system can dynamically adjust the resource allocation of each node. For example, if during a certain period, the system detects a sudden increase in construction activities in the north area of the construction site while the south area is relatively quiet, the system may adjust the resource allocation vector , and allocate more resources such as power and bandwidth to the monitoring nodes responsible for the north area to increase the monitoring frequency and clarity in the north area. While the monitoring nodes in the south area may temporarily reduce resource usage, thus ensuring that the total resource usage does not exceed the upper limit of the system .

[0105] The global collaborative policy data generated in this process not only includes the resource allocation plan for each monitoring node but also the optimal monitoring strategies of these nodes under the current resource conditions. These policy data play a guiding role in the execution of monitoring tasks, ensuring that each node of the system can work in coordination, maximizing the monitoring coverage and response speed, and avoiding resource waste or the emergence of monitoring blind spots.

[0106] Through this optimized resource allocation and policy adjustment, the construction site monitoring system can continuously operate efficiently in a complex and changing environment. Especially in the case of resource constraints, the system can flexibly dispatch resources, prioritize the monitoring requirements of key areas, and ensure the safety and efficiency of the construction site operation. For example, after a monitoring node near a key device detects a possible fault signal, the system can immediately concentrate more resources on the monitoring of this area, enhance the monitoring intensity, and issue an early warning in a timely manner, thus avoiding potential accidents.

[0107] During the execution of the monitoring task, real-time monitoring feedback data is collected and processed, and through a multi-level intelligent feedback network, multi-level iterative optimization is performed on the real-time monitoring feedback data and historical data to generate optimization data for updating the global collaborative policy data.

[0108] As Figure 4 shown, preferably, during the execution of the monitoring task, the following iterative optimization steps are performed on the real-time monitoring feedback data and historical data through a multi-level intelligent feedback network:

[0109] In the first-level feedback mechanism, preliminary feedback optimization data is generated based on the current monitoring results;

[0110] In the second - layer feedback mechanism, the preliminary feedback - optimized data is compared and analyzed with historical monitoring data to generate second - layer feedback - optimized data;

[0111] In the third - layer feedback mechanism, by combining the abnormal - situation handling records and long - term trend analysis, multi - level feedback - optimized data is generated for adjusting the parameters and strategies of the construction - site monitoring nodes.

[0112] During the execution of the monitoring task, the system will collect feedback data from each monitoring node in real - time. These feedback data include the latest environmental information captured by the monitoring nodes, the operating status of equipment, the activities of personnel, etc. The real - time collection of monitoring feedback data is the basis for the dynamic adjustment of the system, ensuring that the system can promptly reflect the latest changes in the construction - site environment.

[0113] These real - time monitoring feedback data will be processed and optimized through a multi - level intelligent feedback network. This network consists of multiple feedback mechanisms, and each layer of the feedback mechanism has its specific function in data processing and optimization, gradually enhancing the accuracy and adaptability of the feedback data.

[0114] In the first - layer feedback mechanism, the system generates preliminary feedback - optimized data based on the current monitoring results. At this stage, rapid analysis and processing are mainly carried out on the real - time monitoring data. The generated preliminary feedback - optimized data can reflect the preliminary effectiveness of the current monitoring task and the parts that need immediate adjustment. For example, in a certain area of the construction site, if the real - time data shows a significant increase in personnel activities, the system may adjust the camera angle or increase the monitoring frequency at this stage to better cover this area.

[0115] The second - layer feedback mechanism further compares and analyzes the preliminary feedback - optimized data with historical monitoring data to generate more in - depth second - layer feedback - optimized data. Through the comparison and analysis, the system can identify the differences between the current state and historical patterns, thus better predicting possible future development trends. For example, if a certain piece of equipment has gradually shown abnormal trends in the past few days of monitoring, the comparison between the current monitoring results and this historical data can enable the system to detect the signs of potential failures earlier and thus take countermeasures in advance.

[0116] In the third - layer feedback mechanism, the system combines the abnormal - situation handling records and long - term trend analysis to generate the final multi - level feedback - optimized data. The analysis at this level not only considers the current and historical data but also incorporates the system's past experience in handling similar abnormal situations and the trend changes reflected in the long - term data. This process ensures the comprehensiveness and accuracy of the feedback - optimized data. For example, the system can identify the potential impact of certain environmental changes (such as seasonal climate changes) on equipment operation based on long - term trend analysis, and thus adjust the monitoring strategy to prevent these changes from having an adverse impact on the construction - site operation.

[0117] The generated multi-level feedback optimization data is used to update the global collaborative policy data in real time. This means that the system can dynamically adjust the parameters and policies of the monitoring nodes according to the latest feedback information to ensure that the system is always in the best operating state during the execution of the monitoring task. For example, during the night monitoring of a construction site, if the system detects that the lighting conditions are gradually deteriorating, the real-time feedback data and historical data will prompt the system to automatically adjust the exposure settings of the camera, and may also adjust the working priorities of the monitoring nodes to ensure that key areas are still fully monitored.

[0118] Through the iterative optimization of the multi-level intelligent feedback network, the system can effectively adapt to the rapid changes in the construction site environment and continuously improve the accuracy and response speed of monitoring during the execution of the monitoring task. This not only improves the system's response ability to emergencies, but also ensures the stability and effectiveness of long-term monitoring tasks.

[0119] For example, during the night construction of a large construction site, the system discovers a change in light conditions through the first-layer feedback mechanism, generates preliminary feedback optimization data, and prompts the need to adjust the sensitivity of the camera. Subsequently, the second-layer mechanism compares this real-time data with the monitoring data of the previous few night constructions and finds that the current light change is similar to the light change pattern during the previous constructions, thus generating more detailed feedback optimization data to further adjust the camera angle and shooting frequency. Finally, the third-layer mechanism combines the experience of night construction in long-term monitoring and predicts that this light change may be accompanied by abnormal operation of some equipment. Therefore, the system decides to adjust the priority configuration of the monitoring nodes and increase the monitoring intensity of key equipment. Ultimately, through these hierarchical feedbacks and optimizations, the system successfully ensures the safety and smooth progress of the entire night construction process.

[0120] Preferably, the multi-level intelligent feedback network includes multiple feedback levels, each level analyzes and optimizes data for different dimensions. The first level is for the current monitoring results, the second level is for historical monitoring data, and the third level is for abnormal handling records, so as to generate comprehensive feedback optimization data for further optimizing the global collaborative policy data.

[0121] The multi-level intelligent feedback network contains multiple feedback levels, each of which performs specific analysis and optimization on data of different dimensions to provide multi-faceted information support. The first-level feedback mechanism focuses on data analysis of current monitoring results. This level mainly processes real-time collected data to quickly identify and respond to changes in the current construction site environment. Through this level, the system can instantly adjust the working parameters of the monitoring nodes, such as the focal length of the camera, the sensitivity of the sensor, etc., to ensure that the effectiveness of monitoring is improved in a short period of time. For example, when the system detects that a certain construction site area is crowded with people, the first-level feedback mechanism can immediately adjust the camera's viewing angle to cover a larger area to ensure that all personnel activities are within the monitoring range.

[0122] The second level of feedback mechanism focuses on the comparison and analysis of historical monitoring data. By comparing the current monitoring data with historical data, the system can identify the difference between the current state and the previous pattern, thereby predicting potential risks or trends. For example, if the system finds that the current equipment temperature is slightly higher than the historical level during the same period, and the temperature is gradually rising, the system can infer that the equipment may be facing the risk of overheating and issue an early warning. This level of feedback mechanism enables the system to not only respond to current changes, but also make more accurate medium-term forecasts based on historical data, providing forward-looking decision support for site management.

[0123] The third level of feedback mechanism focuses on the comprehensive analysis of exception handling records and long-term trends. This level mainly processes long-term accumulated data and records of abnormal situations, identifies periodic or sudden events that may occur during site operations, and incorporates this information into the adjustment of monitoring strategies. For example, the system may find through analyzing the monitoring data of the past few months that the performance of a particular device often fluctuates during the rainy season. Therefore, when the rainy season is about to begin, the system will automatically increase the monitoring of the device and adjust the monitoring strategy to adapt to possible abnormal situations. This level of feedback mechanism ensures that the system can effectively manage the site environment in the long term and maintain stable operation under complex conditions.

[0124] Through the collaborative work of these three levels, the multi-level intelligent feedback network can generate comprehensive feedback optimization data. These data not only include responses to the current state, but also integrate the comparison results of historical data and analysis of abnormal records, thus providing a multi-dimensional optimization solution for the system. These feedback optimization data are used to further adjust and optimize the global collaborative strategy data to ensure that the system achieves optimal resource allocation and strategy coordination among all monitoring nodes.

[0125] In practical applications, the effect of this multi-level feedback mechanism is very significant. For example, in a large construction site, the system discovers through the first-level feedback mechanism that a certain device is operating abnormally in high-temperature weather and immediately adjusts the monitoring parameters for more intensive monitoring. Subsequently, through the second-level feedback mechanism, this anomaly is compared with historical data, and it is confirmed that the temperature rise of the device is consistent with previous similar situations. Furthermore, through the third-level feedback mechanism, the past anomaly handling records are analyzed, and it is found that this situation usually leads to equipment failures. Therefore, the comprehensive feedback optimization data finally generated by the system will not only recommend an immediate inspection of the equipment but also adjust the overall monitoring strategy, increase the monitoring frequency of this equipment, and prioritize the resource allocation in the relevant area to prevent the failure from expanding and affecting the operation of the construction site.

[0126] As Figure 5 shown, a system for implementing the integrated multi-dimensional monitoring method for the construction site includes:

[0127] A multi-spectral imaging module, an acoustic wave detection and analysis module, and a LIDAR module, which are used to collect environmental data, acoustic wave characteristic data, and three-dimensional space data at key positions on the construction site, and preprocess and format the environmental data, acoustic wave characteristic data, and three-dimensional space data to generate a processed comprehensive data set; multi-dimensional data collection is carried out at key positions on the construction site through the multi-spectral imaging module, the acoustic wave detection and analysis module, and the LIDAR module. These modules are respectively responsible for collecting environmental data, acoustic wave characteristic data, and three-dimensional space data, and then preprocessing and formatting these data to generate a processed comprehensive data set. This comprehensive data set provides rich and diverse input data for subsequent multi-level spatio-temporal correlation modeling and feature extraction, thus laying a foundation for the comprehensive monitoring of the system.

[0128] A multi-level spatio-temporal graph convolutional network module, which is used to receive the processed comprehensive data set, perform multi-level spatio-temporal correlation modeling and feature extraction to generate multi-level spatio-temporal correlation data; the multi-level spatio-temporal graph convolutional network module receives and processes these comprehensive data. Through multi-level spatio-temporal correlation modeling, the system can capture the dynamic change characteristics in the construction site environment. This module extracts valuable spatio-temporal correlation data by analyzing the spatio-temporal correlations in the data, further providing a basis for the state analysis and prediction of the system.

[0129] An adaptive Bayesian - Markov model module for performing uncertainty analysis and state transition prediction on the multi - level spatio - temporal correlation data to generate comprehensive environmental prediction data; in the state analysis and prediction stage, the adaptive Bayesian - Markov model module performs uncertainty analysis and state transition prediction on these spatio - temporal correlation data. This module generates comprehensive environmental prediction data by quantifying the uncertainty factors in the data and predicting the future state. These prediction data help the system anticipate possible changes or risks in the future of the construction site, and thus provide an important basis for the adjustment of the monitoring strategy.

[0130] An interactive dynamic game model module for optimizing the resource allocation and monitoring strategy of the construction site monitoring nodes based on the comprehensive environmental prediction data, generating global collaborative strategy data, and performing monitoring tasks according to the global collaborative strategy data, including real - time adjustment of the monitoring device parameters and priority configuration; the interactive dynamic game model module optimizes the resource allocation and monitoring strategy of the construction site monitoring nodes based on the comprehensive environmental prediction data. Through the method of dynamic game, this module generates the optimal global collaborative strategy data and adjusts the parameters and priority configuration of the monitoring devices accordingly to ensure the effective utilization of resources and the efficient execution of monitoring.

[0131] A multi - level intelligent feedback network module for collecting and processing real - time monitoring feedback data during the execution of the monitoring task, and performing multi - level iterative optimization on the real - time monitoring feedback data and historical data through the multi - level intelligent feedback network to generate optimization data for updating the global collaborative strategy data. The multi - level intelligent feedback network module collects and processes the feedback data in real - time during the execution of the monitoring task. Through multi - level iterative optimization, this module compares and analyzes the real - time feedback data with the historical data, generates optimization data and updates the global collaborative strategy. In this way, the system can maintain efficient and accurate monitoring in the dynamically changing construction site environment and can quickly adapt to environmental changes, thus ensuring the safety and operation efficiency of the construction site.

[0132] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0133] The above are only the embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An integrated multi-dimensional monitoring method for a construction site, characterized in that: The following steps are involved: Through multi-spectral imaging technology, acoustic wave detection and analysis technology and LIDAR technology, environmental data, acoustic wave characteristic data and three-dimensional spatial data are collected at key locations on the construction site, and the collected data are pre-processed and formatted to generate a processed comprehensive data set; The processed comprehensive data set is input into a multi-level spatiotemporal graph convolutional network to perform multi-level spatiotemporal correlation modeling and feature extraction to generate multi-level spatiotemporal correlation data. The multi-level spatiotemporal correlation data is then subjected to uncertainty analysis and state transition prediction through an adaptive Bayesian-Markov model to generate comprehensive environmental prediction data. Based on the comprehensive environmental prediction data, the resource allocation and monitoring strategy of the construction site monitoring nodes are optimized using an interactive dynamic game model to generate global collaborative strategy data. The process includes: constructing a resource allocation game model, in which the resource allocation decision of each monitoring node is based on the principle of maximizing the global utility function to generate the optimal resource allocation vector; based on the output of the resource allocation game model, further constructing a strategy optimization game model, generating a strategy selection vector for each monitoring node through a dynamic game process, and finally generating global collaborative strategy data; executing monitoring tasks according to the global collaborative strategy data, including real-time adjustment of monitoring equipment parameters and priority configuration; During the execution of the monitoring task, real-time monitoring feedback data is collected and processed, and multi-level iterative optimization is performed on the real-time monitoring feedback data and historical data through a multi-level intelligent feedback network to generate optimized data for updating the global collaborative strategy data.

2. The integrated multi-dimensional monitoring method for construction sites according to claim 1, characterized in that: The preprocessing and formatting include the following steps: denoising the environmental data through a filtering algorithm to eliminate environmental noise interference; normalizing the sound wave feature data to standardize the signal strength of different sound sources; converting the data format of the three-dimensional space data and converting the point cloud data into a raster data format, thereby generating a comprehensive data set suitable for a multi-level spatiotemporal graph convolutional network.

3. The integrated multi-dimensional monitoring method for construction sites according to claim 1, characterized in that: The multi-level spatiotemporal graph convolutional network includes the following steps: by constructing a multi-layer convolutional neural network, multi-level spatiotemporal correlation modeling is performed on the processed comprehensive data set, wherein each layer of the convolutional network processes data of different time scales and spatial resolutions respectively to extract dynamic change characteristics in the construction site environment, and finally generates multi-level spatiotemporal correlation data containing multi-dimensional spatiotemporal relationships.

4. The integrated multi-dimensional monitoring method for construction sites according to claim 1, characterized in that: The adaptive Bayesian-Markov model performs state transition analysis on multi-level spatiotemporal correlation data by the following steps: Based on historical observation data and current observation data, the Bayesian inference method is used to recursively update the state transition probability and uncertainty parameters; Based on the state transition model of Markov chain, the construction site environmental status at future moments is predicted, thereby generating comprehensive environmental prediction data including short-term and medium-term prediction results.

5. The integrated multi-dimensional monitoring method for construction sites according to claim 4, characterized in that: The state transition probability of the adaptive Bayesian-Markov model is calculated by the following formula: Among them, P(S t+1 , S t ) indicates that the state S at time t t Transfer to state S at time t+1 t+1 The probability of P(S t |O t ) indicates that when observing O t Lower state S t The conditional probability of t ) represents the observation O t The probability of t |S t ) indicates that in state S t Observation O t The conditional probability of This formula is used to quantify the state transition relationship in multi-level spatiotemporal correlation data to generate comprehensive environmental prediction data.

6. The integrated multi-dimensional monitoring method for construction sites according to claim 1, characterized in that: The interactive dynamic game model determines the optimal resource allocation in the resource allocation game through the following formula: Among them, x i represents the resource allocation vector of the i-th node; y i represents the strategy selection vector of the i-th node; u i (x i ,y i ) represents the utility function of the ith node; R represents the total amount of available resources; n represents the total number of monitoring nodes participating in the resource allocation game; This formula is used to optimize resource allocation among monitoring nodes and generate global coordination strategy data.

7. The integrated multi-dimensional monitoring method for construction sites according to claim 1, characterized in that: During the execution of the monitoring task, the following iterative optimization steps are performed on the real-time monitoring feedback data and historical data through a multi-level intelligent feedback network: In the first-level feedback mechanism, preliminary feedback optimization data is generated based on the current monitoring results; In the second-level feedback mechanism, the preliminary feedback optimization data is compared and analyzed with the historical monitoring data to generate the second feedback optimization data; In the third-layer feedback mechanism, the abnormal situation handling records and long-term trend analysis are combined to generate multi-level feedback optimization data for adjusting the parameters and strategies of the construction site monitoring nodes.

8. The integrated multi-dimensional monitoring method for construction sites according to claim 7, characterized in that: The multi-level intelligent feedback network includes multiple feedback levels, each level analyzes and optimizes data of different dimensions, where the first level is for current monitoring results, the second level is for historical monitoring data, and the third level is for exception handling records, thereby generating comprehensive feedback optimization data for further optimizing global collaborative strategy data.

9. A system for implementing the integrated multi-dimensional monitoring method for a construction site according to any one of claims 1 to 8, characterized in that: include: The multispectral imaging module, the acoustic wave detection and analysis module and the LIDAR module are used to collect environmental data, acoustic wave characteristic data and three-dimensional spatial data at key locations on the construction site, and pre-process and format the environmental data, acoustic wave characteristic data and three-dimensional spatial data to generate a processed comprehensive data set; A multi-level spatiotemporal graph convolutional network module, which is used to receive the processed comprehensive data set and perform multi-level spatiotemporal correlation modeling and feature extraction to generate multi-level spatiotemporal correlation data; An adaptive Bayesian-Markov model module, used for performing uncertainty analysis and state transition prediction on the multi-level spatiotemporal correlation data to generate comprehensive environmental prediction data; The interactive dynamic game model module is used to optimize the resource allocation and monitoring strategy of the construction site monitoring nodes based on the comprehensive environmental prediction data using the interactive dynamic game model to generate global collaborative strategy data. The process includes: constructing a resource allocation game model, in which the resource allocation decision of each monitoring node is based on the principle of maximizing the global utility function to generate the optimal resource allocation vector; Based on the output of the resource allocation game model, a strategy optimization game model is further constructed, and a strategy selection vector of each monitoring node is generated through a dynamic game process, and finally global collaborative strategy data is generated; monitoring tasks are executed according to the global collaborative strategy data, including real-time adjustment of monitoring device parameters and priority configuration; The multi-level intelligent feedback network module is used to collect and process real-time monitoring feedback data during the execution of monitoring tasks, and to perform multi-level iterative optimization on real-time monitoring feedback data and historical data through a multi-level intelligent feedback network to generate optimized data for updating global collaborative strategy data.

Images