Construction site safety information supervision system based on Internet of Things

Abstract

The invention provides a construction site safety information supervision system based on the Internet of Things, and relates to the technical field of data processing, the risk assessment accuracy is remarkably improved and the data noise interference is inhibited through a deep reinforcement learning dynamic optimization grading early warning strategy and in combination with a multi-source data compression and federated learning framework; a risk coupling model is constructed based on a complex network theory, a conduction path and a linkage effect between regions are analyzed, a global early warning scheme is optimized, and the adaptability of the system to a complex construction environment is enhanced; the model is continuously optimized through a dynamic weight updating mechanism, high adaptability is kept under the environment change of a construction site, meanwhile, a resource dynamic allocation strategy is adopted, the problem of low high-concurrency processing efficiency is effectively solved, and the overall accident early warning accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and specifically to a construction site safety information supervision system based on the Internet of Things. Background Art

[0002] The construction site safety information supervision system originated in the late 20th century. With the expansion of the construction industry scale and frequent accidents, the traditional manual supervision mode is difficult to meet the requirements. The early systems were based on simple sensors and paper records. In the early 21st century, with the development of technologies such as the Internet of Things (IoT), big data, and artificial intelligence (AI), it gradually evolved into an intelligent supervision platform.

[0003] In the prior art, the publication number is CN114723388A, and the name is an intelligent construction site comprehensive safety operation information supervision system. This invention aims to solve the problem that information of each department is relatively independent and not circulated during the construction process of the construction site; the method includes a user layer, an application layer, a support layer, a data layer, a transmission layer, an equipment layer, and a regulation layer. The user layer facilitates providing a multi-functional intelligent construction site platform service to users. Each subsystem in the support platform can not only operate collaboratively but also independently, which can not only ensure the integrity of the system but also be gradually promoted in stages. The regulation layer can effectively reduce the temperature inside the house, collect each rainfall, make full use of non-conventional water resources, save every drop of tap water as much as possible, recycle the rainwater, and use it for on-site car washing, concrete curing, on-site spraying for dust and haze removal, and can also be used for the linkage of the roof spraying cooling control system for cooling the worker living area board houses, which can save water and electricity energy.

[0004] However, when the above invention is applied to big data analysis and risk prediction, it has the following technical drawbacks: 1. The data noise interference is large, affecting the prediction accuracy; 2. The real-time computing power is insufficient, and the high-concurrency processing efficiency is low; 3. The model generalization ability is weak, and the adaptability to the dynamic environment is poor.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a construction site safety information supervision system based on the Internet of Things to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions: A construction site safety information supervision system based on the Internet of Things, including a regional monitoring module, a data acquisition module, a risk calculation module, and an intelligent early warning module; Area monitoring module: used to provide different area settings for the construction preparation stage and the construction progress stage of the target construction site; In the construction preparation stage, divide the target construction site into multiple monitoring sub-areas; In the construction progress stage, obtain the construction plans and operation types of each monitoring sub-area and analyze them. According to the analysis results, divide these monitoring sub-areas into a core monitoring area set and an auxiliary monitoring area set respectively; Data acquisition module: used to collect multi-source safety monitoring data of each monitoring sub-area in the construction progress stage; Based on the topological relationship of the monitoring sub-areas, adjust the acquisition frequencies of the core monitoring area set and the auxiliary monitoring area set, and monitor the communication quality at the same time; Risk calculation module: used to construct a regional risk assessment model by using federated learning in the construction progress stage. The regional risk assessment model is used to calculate the risk entropy value Re of each monitoring sub-area in the auxiliary monitoring area set, and the risk entropy value Re is used to evaluate whether the corresponding monitoring sub-area is abnormal; Calculate the risk diffusion coefficient Rd of the abnormal monitoring sub-area. The risk diffusion coefficient Rd is used to evaluate the diffusion trend of the risk to the core monitoring area set; Intelligent early warning module: used to calculate and evaluate the risk intervention priority Rp based on the risk diffusion coefficient Rd; then use reinforcement learning to optimize the hierarchical early warning strategy, dynamically adjust the sampling frequencies and resource allocations of the core monitoring area set and the auxiliary monitoring area set, and construct an inter-regional risk coupling model to optimize the global early warning strategy.

[0008] Preferably, the area monitoring module includes a sub-area division unit; The sub-area division unit is used to obtain the total construction site area in the construction preparation stage, and combine the construction drawings to perform site segmentation. Divide the construction site into equal-area independent monitoring sub-areas and assign unique identifiers, including {1, 2, 3,..., n}, where n represents the total number of monitoring sub-areas, n is the index mark of the nth monitoring sub-area, and record the central point coordinates and boundary information of each monitoring sub-area at the same time.

[0009] Preferably, the area monitoring module further includes a monitoring area classification unit; The monitoring area classification unit is used to divide all monitoring sub-areas into a core monitoring area set and an auxiliary monitoring area set; based on the construction plan and operation type, obtain the personnel density Za, structural stability Zb, and equipment influence area Zc of each monitoring sub-area in real time, and after dimensionless processing, use the following formula to calculate and obtain the comprehensive monitoring priority value Zhj:

[0010] In the formula, the dimensionless value ranges of the personnel density Za, the structural stability Zb, and the equipment influence area Zc are [0, 1], and the larger the comprehensive monitoring priority value Zhj, the higher the risk; m is the correction coefficient of the equipment influence area Zc; According to the comprehensive monitoring priority value Zhj of each monitoring sub-region, all monitoring sub-regions are sorted in descending order from high to low. The monitoring sub-regions in the first 50% of the order are divided into the core monitoring area set, and the rest are divided into the auxiliary monitoring area set.

[0011] Preferably, the data acquisition module includes a multi-source data acquisition unit and a dynamic regulation unit; The multi-source security monitoring data collected by the multi-source data acquisition unit includes equipment status, personnel positioning, environmental parameters, and video stream data. The compression sensing algorithm is used to compress and optimize the data. Then, according to the data types including equipment status, personnel positioning, environmental parameters, and video stream data, a hierarchical storage structure is established. The equipment status and personnel positioning data are stored in the high-frequency access database, and the environmental parameters and video stream are stored in the time series database. Secondly, a time tag is attached to each piece of data and the UTC timestamp is used to be accurate to milliseconds, and the construction activity intensity Pa in the monitoring sub-region is extracted; The dynamic regulation unit is used to adjust the acquisition frequencies of the core monitoring area set and the auxiliary monitoring area set based on the topological relationship of the monitoring sub-region, and monitor the communication quality to optimize the transmission strategy. Specifically, when the communication quality is lower than the preset threshold, the data local caching and down-frequency transmission mechanism are started; at the same time, the communication quality Pb in the monitoring sub-region is extracted.

[0012] Preferably, the risk calculation module includes a risk modeling unit; The risk modeling unit is used to construct a regional risk assessment model using the federated learning framework, train the model through distributed node collaboration, and integrate the multi-source security monitoring data of all monitoring sub-regions; Then, the local model parameters of each monitoring sub-region are processed for privacy protection through the homomorphic encryption algorithm. Then, on the central server, the federated average algorithm is used to aggregate the encrypted parameters to update the global model; at the same time, a dynamic weight update mechanism is set, including automatically adjusting the model update period based on the environmental change frequency including equipment movement and work surface expansion on the construction site.

[0013] Preferably, the risk calculation module further includes an entropy value calculation unit; The entropy value calculation unit is used to first calculate the risk entropy value Re of each monitoring sub-region in the auxiliary monitoring area set, use the regional risk assessment model to perform real-time analysis on the multi-source security monitoring data, obtain the abnormal personnel aggregation Ea, the abnormal density equipment Eb, and the vibration amplitude environmental mutation index Ec, and after dimensionless processing, use the following formula to calculate and obtain the risk entropy value Re:

[0014] In the formula, the value range of the abnormal personnel aggregation Ea is Ea ∈ [0, 5]. The larger the value, the more abnormal the personnel aggregation degree; the value range of the abnormal density device Eb is Eb ∈ [0, 3]. The larger the value, the more serious the abnormal distribution of the device; the value range of the vibration amplitude environment mutation index Ec is Ec ∈ [0, 4]. The larger the value, the more violent the environmental vibration fluctuation; Collect historical construction data, extract the dimensionless abnormal personnel aggregation index Ea, the abnormal density device index Eb, and the vibration amplitude environment mutation index Ec, obtain the mean value μRe and the standard deviation σRe, and calculate and obtain the risk entropy threshold E using the following formula:

[0015] In the formula, k is an adjustment coefficient; Compare and evaluate the risk entropy threshold E with each risk entropy value Re one by one. The specific evaluation content is as follows: When the risk entropy value Re < the risk entropy threshold E, it means that the safety risk status in the current monitored sub-region is normal, and the current monitoring strategy remains unchanged; When the risk entropy value Re ≥ the risk entropy threshold E, it means that the safety risk status in the current monitored sub-region is abnormal, and then the current monitored sub-region is marked in red.

[0016] Preferably, the abnormal monitored sub-regions with the risk entropy value Re ≥ the risk entropy threshold E in the auxiliary monitoring area are recorded as i, and i ∈ {1, 2, 3,..., s}, where s represents the total number of monitored sub-regions; When there are two or more adjacent monitored sub-regions marked in red around the monitored sub-region i, it means that regional risk diffusion is formed. At this time, calculate the local average risk entropy value and determine whether it exceeds the local threshold E i : ; In the formula, N(i) represents the number of monitored sub-regions adjacent to the monitored sub-region i; j represents the index of the adjacent monitored sub-region; Re j is the risk entropy value of the adjacent monitored sub-region j; is the local average risk entropy value of the monitored sub-region i; using the same calculation method as the risk entropy threshold E, determine the local threshold of is E i ; When the local average risk entropy value is less than the local threshold E i , it means that the risk of the current monitored sub-region i spreading to the adjacent monitored sub-region is small; When the local average risk entropy value Greater than or equal to the local threshold E i , indicating a high risk of diffusion from the current monitoring sub-region i to adjacent monitoring sub-regions, and calculating the risk diffusion coefficient Rd of all the marked monitoring sub-regions in red.

[0017] Preferably, the risk calculation module further includes a diffusion evaluation unit; The abnormal monitoring sub-regions with the core monitoring area centralized risk entropy value Re ≥ the risk entropy threshold E are denoted as i0, and i0 ∈ {1, 2, 3,..., f}, where f represents the total number of monitoring sub-regions; The diffusion evaluation unit is used to calculate the risk diffusion coefficient Rd and evaluate the diffusion trend of the risk to the core monitoring area set; ; In the formula, max represents the maximum risk entropy value increment between the monitoring sub-region i and the adjacent monitoring sub-region i0 of the core monitoring area set, which is used to measure the strongest local risk diffusion trend; the adjacent monitoring sub-region set includes all the monitoring sub-regions directly connected to the monitoring sub-region i0, and is used to find the maximum risk diffusion direction; Adjacent monitoring sub-region index; Re i represents the risk entropy value of the monitoring sub-region i, represents the risk entropy value of the abnormal monitoring sub-region in the core monitoring area set; Statistically analyze the historical risk diffusion data of each monitoring sub-region during the construction process, calculate the mean and standard deviation of the risk diffusion coefficient Rd, obtain the risk diffusion threshold D, and compare and evaluate it with the risk diffusion coefficient Rd. The specific evaluation content is as follows: When the risk diffusion coefficient Rd ≥ the risk diffusion threshold D: It indicates that the risk diffusion trend of the current monitoring sub-region is abnormal and will affect the core monitoring area set; adjust the monitoring frequency and data acquisition frequency of the current monitoring sub-region and its adjacent monitoring sub-regions; at the same time, additional intervention measures need to be taken, including strengthening construction safety management or optimizing personnel scheduling; When the risk diffusion coefficient Rd < the risk diffusion threshold D: It indicates that the risk diffusion trend of the current monitoring sub-region is normal and the impact on the core monitoring area set can be ignored; at this time, maintain the normal monitoring frequency and continue to observe the risk change trend of the current monitoring sub-region.

[0018] Preferably, the intelligent early warning module includes a risk intervention decision-making unit; The risk intervention decision-making unit is used to calculate and evaluate the risk intervention priority Rp; extract the construction activity intensity Pa and communication quality Pb from the data acquisition module, and after dimensionless processing with the risk diffusion coefficient Rd, use the following formula to calculate and obtain the risk intervention priority Rp by correlation: ; where, -1 ≤ Rp < 1; The numerical value of the risk intervention priority Rp is evaluated, and the specific content is as follows: When the risk intervention priority Rp is less than or equal to 0 and getting closer to -1, it indicates that the risk diffusion in the current monitored sub-region is weaker, the construction activities are fewer, or the communication quality is better; When the risk intervention priority Rp is greater than 0 and getting closer to 1, it indicates that the risk diffusion in the current monitored sub-region is faster, the intensity of construction activities is higher, and the communication quality is more unstable. At this time, intervention is carried out.

[0019] Preferably, the intelligent early warning module further includes a dynamic optimization execution unit; The dynamic optimization execution unit applies the DRL deep reinforcement learning algorithm to continuously optimize the hierarchical early warning strategy; including: According to the real-time risk situation, adjust the sampling frequency of the core monitoring area set to 3 to 5 times that of the auxiliary monitoring area set; automatically calculate and allocate computing resources according to the risk level, and adjust the server resource allocation; construct a risk coupling model based on complex network theory, analyze the risk conduction path between regions, predict the chain reaction effect, and optimize the global early warning response plan.

[0020] Compared with the prior art, the beneficial effects of the present invention are: The present invention dynamically adjusts the monitoring frequency and computing resource allocation according to the real-time risk situation at the construction site, optimizes the hierarchical early warning strategy by introducing the deep reinforcement learning (DRL) algorithm, and effectively solves the problem of data noise interference; by collecting multi-source safety monitoring data and performing compression optimization, combined with the federated learning framework, the accuracy of the regional risk assessment model is improved, and the prediction deviation caused by data noise is effectively suppressed; The present invention also constructs a risk coupling model based on complex network theory, analyzes the risk conduction path and chain reaction effect between regions, optimizes the global early warning response plan, improves the adaptability of the system to complex construction environments, significantly improves the real-time computing ability, and overcomes the problem of low high-concurrency processing efficiency; The present invention ensures the continuous training and optimization of the model through the federated learning and dynamic weight update mechanism, enhances the generalization ability of the model, and under the dynamic environmental changes at the construction site, the system can timely adjust the strategy and maintain high adaptability, solving the problems of weak model generalization ability and poor dynamic environmental adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the overall system framework of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0022] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following further elaborates on the present invention in detail with reference to specific embodiments.

[0023] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second", and similar terms used in the present invention do not denote any order, quantity, or importance, but are only used to distinguish different components. Words such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. Words such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly. Embodiment 1

[0024] Please refer to Figure 1 , the present invention provides a technical solution: an Internet of Things-based construction site safety information supervision system, including a regional monitoring module, a data acquisition module, a risk calculation module, and an intelligent early warning module; Regional monitoring module: used to provide different regional settings for the construction preparation stage and the construction progress stage of the target construction site; In the construction preparation stage, the target construction site is divided into multiple monitoring sub-regions; In the construction progress stage, obtain the construction plans and operation types of each monitoring sub-region and analyze them. According to the analysis results, divide these monitoring sub-regions into a core monitoring area set and an auxiliary monitoring area set respectively; Data acquisition module: used to collect multi-source safety monitoring data of each monitoring sub-region during the construction progress stage; Based on the topological relationship of the monitoring sub-regions, adjust the acquisition frequencies of the core monitoring area set and the auxiliary monitoring area set, and monitor the communication quality at the same time; Risk calculation module: used to construct a regional risk assessment model using federated learning during the construction progress stage. This regional risk assessment model is used to calculate the risk entropy value Re of each monitoring sub-region in the auxiliary monitoring area set, and the risk entropy value Re is used to evaluate whether the corresponding monitoring sub-region is abnormal; Calculate the risk diffusion coefficient Rd of the abnormal monitoring sub-region. The risk diffusion coefficient Rd is used to evaluate the diffusion trend of the risk to the core monitoring area set; Intelligent Early Warning Module: It is used to calculate the risk intervention priority Rp and evaluate it based on the risk diffusion coefficient Rd; then optimize the hierarchical early warning strategy using reinforcement learning, dynamically adjust the sampling frequencies and resource allocations of the core monitoring area set and the auxiliary monitoring area set, and at the same time construct an inter-regional risk coupling model to optimize the global early warning strategy.

[0025] In this embodiment, based on industry standards, experimental data, actual engineering verification data, and academic research results, the regional monitoring module dynamically divides the core monitoring area set and the auxiliary monitoring area set, deploys sensing nodes within each monitoring sub-region, and at the same time establishes the topological relationship between these sensing nodes; realizes precise coverage of the construction area and key risk monitoring; the data acquisition module uses compressive sensing technology with a compression ratio ≥ 60% to collect multi-source safety monitoring data in real time, including equipment status, personnel positioning, environmental parameters, and video stream data; adaptively optimizes the acquisition frequency based on the topological relationship; the risk calculation module constructs a risk assessment model through the federated learning framework, where the model aggregation period ≤ 30 min, calculates the risk entropy value Re and the diffusion coefficient Rd, and is used to predict the risk conduction trend; the intelligent early warning module optimizes the hierarchical early warning strategy based on the DRL deep reinforcement learning algorithm, dynamically adjusts the resource allocation, and constructs a risk coupling model to achieve a rapid response to global early warning and improve the overall accident early warning accuracy. Embodiment 2

[0026] The regional monitoring module includes a sub-region division unit; The sub-region division unit is used to obtain the total construction site area during the construction preparation stage, combine it with the construction drawings for site segmentation, equally divide the construction site into independent monitoring sub-regions, and assign a unique identifier, including {1, 2, 3,..., n}, where n represents the total number of monitoring sub-regions, n is the index mark of the nth monitoring sub-region, and at the same time record the center point coordinates and boundary information of each monitoring sub-region.

[0027] The regional monitoring module also includes a monitoring area classification unit; The monitoring area classification unit is used to divide all monitoring sub-regions into a core monitoring area set and an auxiliary monitoring area set; based on the construction plan and operation type, obtain the personnel density Za, structural stability Zb, and equipment influence area Zc of each monitoring sub-region in real time, and after dimensionless processing, use the following formula to calculate the comprehensive monitoring priority value Zhj:

[0028] In the formula, the dimensionless value ranges of the personnel density Za, structural stability Zb, and equipment influence area Zc are [0, 1], and the larger the comprehensive monitoring priority value Zhj, the higher the risk; m is the correction coefficient of the equipment influence area Zc; According to the comprehensive monitoring priority value Zhj of each monitoring sub-region, all monitoring sub-regions are sorted in descending order from high to low. The monitoring sub-regions in the first 50% of the order are divided into the core monitoring area set, and the rest are divided into the auxiliary monitoring area set.

[0029] In this embodiment, the regional monitoring module realizes the equal-area grid division of the construction site through the sub-region division unit, establishing a structured foundation for precise monitoring; the monitoring area classification unit is based on the three core parameters of the personnel density Za, structural stability Zb, and equipment impact area Zc collected in real time. After dimensionless processing, the dynamic risk assessment is realized through the calculation formula of the comprehensive priority value to intelligently divide the first 50% of the high-risk sub-regions into the core monitoring area set, and the rest as the auxiliary monitoring area set; Among them, the personnel density Za is used to reflect the aggregation risk of operating personnel, the structural stability Zb is used to characterize the safety state of the support system, and the equipment impact area Zc is used to indicate the dangerous range of mechanical operations; This design not only realizes the automatic identification of risk areas (accuracy rate ≥ 90%), but also significantly improves the monitoring resource allocation efficiency through parametric grading (resource utilization rate increased by 35%), providing an accurate spatial positioning basis for the subsequent data acquisition module. At the same time, the continuous update mechanism of Zhj (cycle ≤ 15 min) ensures that the system can dynamically adapt to changes in the construction environment (response delay ≤ 8 s), and overall constructs a complete mapping relationship from the physical space to the digital twin. Embodiment 3

[0030] The data acquisition module includes a multi-source data acquisition unit and a dynamic regulation unit; The multi-source security monitoring data collected by the multi-source data acquisition unit includes equipment status, personnel positioning, environmental parameters, and video stream data. The compression sensing algorithm is used to compress and optimize the data. Then, according to the data types including equipment status, personnel positioning, environmental parameters, and video stream data, a hierarchical storage structure is established. The equipment status and personnel positioning data are stored in the high-frequency access database, and the environmental parameters and video stream are stored in the time series database; secondly, a time tag is attached to each piece of data and the UTC time stamp is used to be accurate to milliseconds, and the construction activity intensity Pa within the monitoring sub-region is extracted; The dynamic regulation unit is used to adjust the acquisition frequencies of the core monitoring area set and the auxiliary monitoring area set based on the topological relationship of the monitoring sub-regions, and monitor the communication quality to optimize the transmission strategy. Specifically, when the communication quality is lower than the preset threshold, the data local caching and down-frequency transmission mechanism is started; at the same time, the communication quality Pb within the monitoring sub-region is extracted.

[0031] In this embodiment, the data acquisition module realizes the all-element acquisition of device status, personnel positioning, environmental parameters and video stream data through the multi-source data acquisition unit, optimizes the transmission efficiency by using a compressive sensing algorithm with a compression ratio ≥ 65%, and establishes a hierarchical storage architecture to achieve accurate data traceability through spatio-temporal tags; the dynamic regulation unit dynamically adjusts the acquisition frequency based on the topological relationship. When the communication quality Pb does not meet the standard, it starts a local cache with a storage capacity ≥ 72 hours and a reduced-frequency transmission with a 40% reduction in bandwidth occupancy; at the same time, it uses time tags to bind the monitoring sub-region ID and the three-dimensional coordinates (x, y, z), and optimizes the storage space through a data compression algorithm; the construction activity intensity Pa is obtained by analyzing the video stream data including the movement frequencies of personnel and machinery to obtain the active pixels, quantifying the device status data including the number of mechanical starts and stops to obtain the device operation status value, and obtaining it through weighted calculation of the active pixels and the device operation status value. The specific formula is: Pa = q1 × video activity index + q2 × device operation index, where q1 and q2 are the weight coefficients of the active pixels and the device operation status value, and q1 + q2 = 1; the communication quality Pb is obtained by comprehensively calculating three indicators: the real-time monitored signal strength RSSI, packet loss rate and transmission delay. The specific formula is Pb = w1 × (1 - packet loss rate) + w2 × RSSI standardized value + w3 × delay standardized value, where w1, w2 and w3 are the weight coefficients of the signal strength RSSI, packet loss rate and transmission delay, and w1 + w2 + w3 = 1; When the communication quality is lower than the preset threshold, the started data local cache and reduced-frequency transmission mechanism is as follows: 1) The local cache uses a circular buffer for storage; 2) The reduced-frequency transmission reduces the video stream frame rate and closes non-critical data channels; 3) Resource reallocation gives priority to ensuring the core monitoring area set, and at the same time suspends unnecessary collection in the auxiliary area; The above mechanism evaluates the channel status every 30 seconds through an adaptive PID controller, dynamically adjusts the reduction ratio, ensures the integrity rate of key data before communication recovery and controls the transmission delay within the preset range; the specific preset threshold and preset range are determined by the user according to the situation; This module not only realizes the efficient fusion processing of multi-source heterogeneous data, but also ensures the stable operation of the system in a complex construction environment through an intelligent regulation mechanism, provides real-time, complete and low-redundancy data support for the upper-layer risk calculation, and significantly improves the overall reliability of the system; in addition, the above data is based on national standards, industry specifications, laboratory test data and engineering empirical data; Among them, starting the data local cache and reduced-frequency transmission mechanism is to give priority to ensuring the data integrity of the core monitoring area set. Embodiment 4

[0032] The risk calculation module includes a risk modeling unit; The risk modeling unit is used to build a regional risk assessment model using a federated learning framework, train the model through distributed node collaboration, and integrate multi-source safety monitoring data from all monitoring sub-areas; Then, the local model parameters of each monitoring sub-area are privacy-protected through a homomorphic encryption algorithm. After that, the encrypted parameters are aggregated using a federated averaging algorithm on the central server to update the global model. At the same time, a dynamic weight update mechanism is set up to automatically adjust the model update cycle based on the frequency of environmental changes, including equipment movement and work surface expansion at the construction site.

[0033] The risk calculation module also includes an entropy value calculation unit; The entropy value calculation unit is used to preferentially calculate the risk entropy value Re of each monitoring sub-area in the auxiliary monitoring area set, and use the regional risk assessment model to perform real-time analysis on the multi-source safety monitoring data to obtain the abnormal gathering of personnel Ea, density equipment abnormality Eb and vibration amplitude environmental mutation index Ec, and after dimensionless processing, use the following formula to calculate the risk entropy value Re:

[0034] In the formula, the range of the abnormal gathering of personnel Ea is Ea∈[0,5], and the larger the value, the more abnormal the degree of personnel gathering; the range of the abnormal density equipment Eb is Eb∈[0,3], and the larger the value, the more serious the abnormal distribution of equipment; the range of the vibration amplitude environmental mutation index Ec is Ec∈[0,4], and the larger the value, the more severe the environmental vibration fluctuation; Collect historical construction data, extract dimensionless personnel abnormal aggregation index Ea, density equipment abnormal index Eb and vibration amplitude environment mutation index Ec, obtain mean μRe and standard deviation σRe, and use the following formula to calculate the risk entropy threshold E:

[0035] In the formula, k is the adjustment coefficient; The risk entropy threshold E is compared and evaluated with each risk entropy value Re one by one. The specific evaluation contents are as follows: When the risk entropy value Re is less than the risk entropy threshold E, it means that the security risk status in the current monitoring sub-area is normal and the current monitoring strategy remains unchanged; When the risk entropy value Re ≥ risk entropy threshold E, it means that the security risk status in the current monitoring sub-area is abnormal, and the current monitoring sub-area is marked in red.

[0036] The abnormal monitoring sub-area with the risk entropy value Re ≥ the risk entropy threshold E in the auxiliary monitoring area is recorded as i, and i∈{1, 2, 3, ..., s}, where s represents the total number of monitoring sub-areas; When there are two or more adjacent monitored sub-regions marked in red around the monitored sub-region i, it indicates the formation of regional risk diffusion. At this time, the local average risk entropy value is calculated , and it is judged whether it exceeds the local threshold E i : ; In the formula, N(i) represents the number of monitored sub-regions adjacent to the monitored sub-region i; j represents the index of the adjacent monitored sub-region; Re j is the risk entropy value of the adjacent monitored sub-region j; is the local average risk entropy value of the monitored sub-region i; using the same calculation method as the risk entropy threshold E, determine The local threshold of is E i ; When the local average risk entropy value is less than the local threshold E i , it indicates that the risk of the current monitored sub-region i spreading to the adjacent monitored sub-region is small; When the local average risk entropy value is greater than or equal to the local threshold E i , it indicates that the risk of the current monitored sub-region i spreading to the adjacent monitored sub-region is large, and the risk diffusion coefficient Rd of all the monitored sub-regions marked in red is calculated.

[0037] The risk calculation module further includes a diffusion evaluation unit; The abnormal monitored sub-regions with the centralized risk entropy value Re≥risk entropy threshold E in the core monitoring area are recorded as i0, and i0∈{1, 2, 3,..., f}, where f represents the total number of monitored sub-regions; The diffusion evaluation unit is used to calculate the risk diffusion coefficient Rd and evaluate the diffusion trend of the risk to the core monitoring area set; ; In the formula, max represents the maximum risk entropy value increment between the monitored sub-region i and the adjacent monitored sub-region i0 of the core monitoring area set, which is used to measure the strongest local risk diffusion trend; the set of adjacent monitored sub-regions includes all the monitored sub-regions directly connected to the monitored sub-region i0, which is used to find the maximum risk diffusion direction; is the index of the adjacent monitored sub-region; Re i represents the risk entropy value of the monitored sub-region i, represents the risk entropy value of the abnormal monitored sub-region in the core monitoring area set; Statistically analyze the historical risk diffusion data of each monitored sub-region during the construction process, calculate the mean and standard deviation of the risk diffusion coefficient Rd, obtain the risk diffusion threshold D, and compare and evaluate it with the risk diffusion coefficient Rd. The specific evaluation content is as follows: When the risk diffusion coefficient Rd ≥ the risk diffusion threshold D: It indicates that the risk diffusion trend in the current monitored sub-region is abnormal and will soon affect the core monitored area set; adjust the monitoring frequency and data collection frequency for the current monitored sub-region and its adjacent monitored sub-regions; at the same time, additional intervention measures need to be taken, including strengthening construction safety management or optimizing personnel scheduling; When the risk diffusion coefficient Rd < the risk diffusion threshold D: It indicates that the risk diffusion trend in the current monitored sub-region is normal and the impact on the core monitored area set is negligible; at this time, maintain the normal monitoring frequency and continue to observe the risk change trend of the current monitored sub-region.

[0038] The intelligent early warning module includes a risk intervention decision-making unit; The risk intervention decision-making unit is used to calculate and evaluate the risk intervention priority Rp; extract the construction activity intensity Pa and communication quality Pb in the data collection module, and after dimensionless processing with the risk diffusion coefficient Rd, use the following formula to calculate and obtain the risk intervention priority Rp through correlation: ; where, -1 ≤ Rp < 1; Evaluate the value of the risk intervention priority Rp, and the specific content is as follows: When the risk intervention priority Rp is less than or equal to 0 and approaches -1, it indicates that the risk diffusion in the current monitored sub-region is weaker, the construction activities are fewer, or the communication quality is better; When the risk intervention priority Rp is greater than 0 and approaches 1, it indicates that the risk diffusion in the current monitored sub-region is faster, the construction activity intensity is higher, and the communication quality is more unstable. At this time, intervention is carried out.

[0039] The intelligent early warning module also includes a dynamic optimization execution unit; The dynamic optimization execution unit applies the DRL deep reinforcement learning algorithm to continuously optimize the hierarchical early warning strategy; including: According to the real-time risk situation, adjust the sampling frequency of the core monitored area set to 3 to 5 times that of the auxiliary monitored area set; automatically calculate and allocate computing resources according to the risk level, and adjust the server resource allocation; construct a risk coupling model based on complex network theory, analyze the risk conduction path between regions, predict the chain reaction effect, and optimize the global early warning response plan.

[0040] In this embodiment, the risk calculation module uses the federated learning framework and homomorphic encryption technology through the risk modeling unit to construct a dynamic risk assessment model, realizing secure collaborative computing of multi-source data; the entropy value calculation unit quantifies the regional risk through the formula of risk entropy value Re based on three core parameters: abnormal aggregation of personnel Ea, abnormal equipment Eb, and environmental mutation Ec, and dynamically calculates the risk threshold E based on historical data to evaluate the risk entropy value Re. Calculate the local average risk entropy value In the process, intelligent identification and quantitative evaluation of regional risk diffusion are realized. The core significance lies in dynamically calculating the local average risk entropy value and comparing it with the local threshold E i to accurately determine the risk conduction trend. When the local average risk entropy value is greater than or equal to the local threshold E i , trigger the calculation of the diffusion coefficient Rd to form a three-level early warning mechanism of "single-point red marking → regional diffusion → global response"; this design significantly improves the system's predictability of chain risks, reduces the false alarm rate through topological correlation analysis, optimizes resource allocation at the same time, and only increases the monitoring frequency for the actual diffusion area, improving the emergency response speed in the core area, and finally realizing all-dimensional security control from isolated risk points to regional linkage, effectively solving the problem that traditional monitoring systems are insensitive to the conduction of hidden risks. Furthermore, the local threshold E i is derived from the risk entropy threshold E, and the calculation logic is exactly the same. However, the local threshold E i is used as the local judgment criterion to determine whether the current area has a risk diffusion possibility higher than the normal range. And the calculation formula of the local threshold E i is: , is the mean value of the historical risk entropy value Re j of the adjacent sub-region set N(i), is the standard deviation of the historical risk entropy value Re j of the adjacent sub-region set N(i), and k is an adjustment coefficient, usually taking 1 ≤ k ≤ 3, which is specifically set according to engineering experience; The diffusion evaluation unit locates the maximum risk conduction direction through the risk diffusion coefficient Rd and judges whether it affects the core area by comparing with the diffusion threshold D; the intelligent early warning module calculates the intervention priority Rp based on the construction activity intensity Pa, communication quality Pb, and Rd value, dynamically optimizes the monitoring strategy according to the evaluation content of the intervention priority Rp, and constructs a complex network model to analyze the risk conduction path, finally realizing the full-chain closed-loop management from risk identification, assessment to early warning, making the system significantly improve the emergency response efficiency while maintaining data privacy.

[0041] Among them, in the formula of the risk intervention priority Rp, the meaning of Rd×Pa is that if the risk diffusion trend in a region is high and the intensity of construction activities is also large, then accidents are more likely to occur in this region. Therefore, the risk intervention priority Rp needs to be increased; the meaning of −Pb is that if the communication quality Pb in this region is high, it indicates that the monitoring data transmission is stable, and the system can effectively monitor and respond. Therefore, the intervention priority can be appropriately reduced.

[0042] It should be noted that all the calculation formulas in this application document adopt, including but not limited to, regression analysis in machine learning algorithms to deeply analyze the relevant parameters collected, identify their natural trends and mutual relationships. Using professional software, such as the Scikit-learn library of Python or the R language, a mathematical model matching the data is automatically generated. Then, the performance of the model is objectively evaluated through methods such as cross-validation, and combined with continuous feedback and optimization, to ensure that the created formula truly reflects the internal laws of the data, thereby ensuring its effectiveness and accuracy, and ensuring that the calculation process conforms to the constraints of natural laws, rather than being based on artificially set rules.

[0043] The technical solution of the present invention can be embodied in the form of a software product in essence or the part that contributes to the prior art. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk, or optical disc of a computer, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0044] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0045] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A construction site safety information supervision system based on the Internet of Things, characterized by: It includes regional monitoring module, data collection module, risk calculation module and intelligent early warning module; Area monitoring module: used to provide different area settings for the construction preparation stage and construction stage of the target construction site; During the construction preparation phase, the target construction site is divided into multiple monitoring sub-areas; During the construction phase, the construction plan and operation type of each monitoring sub-area are obtained and analyzed, and these monitoring sub-areas are divided into a core monitoring area set and an auxiliary monitoring area set according to the analysis results; Data collection module: used to collect multi-source safety monitoring data of each monitoring sub-area during the construction stage; Based on the topological relationship of the monitoring sub-areas, the acquisition frequency of the core monitoring area set and the auxiliary monitoring area set is adjusted, and the communication quality is monitored at the same time; Risk calculation module: used to construct a regional risk assessment model using federated learning during the construction phase. The regional risk assessment model is used to calculate the risk entropy value Re of each monitoring sub-area in the auxiliary monitoring area set. The risk entropy value Re is used to assess whether the corresponding monitoring sub-area is abnormal; Calculate the risk diffusion coefficient Rd of the abnormal monitoring sub-area. The risk diffusion coefficient Rd is used to evaluate the diffusion trend of the risk to the core monitoring area set; Intelligent early warning module: used to calculate and evaluate the risk intervention priority Rp based on the risk diffusion coefficient Rd; then use reinforcement learning to optimize the hierarchical early warning strategy, dynamically adjust the sampling frequency and resource allocation of the core monitoring area set and the auxiliary monitoring area set, and at the same time build an inter-regional risk coupling model to optimize the global early warning strategy.

2. A construction site safety information monitoring system based on the Internet of Things according to claim 1, characterized in that: The regional monitoring module includes a sub-region division unit; The sub-area division unit is used to obtain the total area of ​​the construction site during the construction preparation stage, and to divide the site in combination with the construction drawings, so as to divide the equal area of ​​the construction site into independent monitoring sub-areas and assign unique identifiers, including {1, 2, 3, ..., n}, where n represents the total number of monitoring sub-areas, n is the index mark of the nth monitoring sub-area, and the center point coordinates and boundary information of each monitoring sub-area are recorded at the same time.

3. A construction site safety information monitoring system based on the Internet of Things according to claim 2, characterized in that: The regional monitoring module also includes a monitoring area classification unit; The monitoring area classification unit is used to divide all monitoring sub-areas into core monitoring area sets and auxiliary monitoring area sets; based on the construction plan and operation type, the personnel density Za, structural stability Zb, and equipment impact area Zc of each monitoring sub-area are obtained in real time, and after dimensionless processing, the comprehensive monitoring priority value Zhj is calculated using the following formula: In the formula, the value range of personnel density Za, structural stability Zb and equipment influence area Zc after dimensionless processing is [0,1], and the larger the comprehensive monitoring priority value Zhj, the higher the risk; m is the correction coefficient of the equipment influence area Zc; According to the comprehensive monitoring priority value Zhj of each monitoring sub-area, all monitoring sub-areas are sorted in descending order from high to low, and the top 50% of the monitoring sub-areas are divided into the core monitoring area set, and the rest are divided into the auxiliary monitoring area set.

4. The construction site safety information monitoring system based on the Internet of Things according to claim 3 is characterized in that: The data acquisition module includes a multi-source data acquisition unit and a dynamic control unit; The multi-source safety monitoring data collected by the multi-source data acquisition unit includes equipment status, personnel location, environmental parameters and video stream data, and the compressed sensing algorithm is used to compress and optimize the data. Then, based on the data types including equipment status, personnel location, environmental parameters and video stream data, a hierarchical storage structure is established. The equipment status and personnel location data are stored in the high-frequency access database, and the environmental parameters and video streams are stored in the time series database; secondly, a time tag is added to each data and the UTC timestamp is used to be accurate to milliseconds to extract the construction activity intensity Pa in the monitoring sub-area; The dynamic control unit is used to adjust the collection frequency of the core monitoring area set and the auxiliary monitoring area set based on the topological relationship of the monitoring sub-area, and monitor the communication quality to optimize the transmission strategy, including starting the local data cache and frequency reduction transmission mechanism when the communication quality is lower than the preset threshold; at the same time, extracting the communication quality Pb ​​within the monitoring sub-area.

5. The construction site safety information monitoring system based on the Internet of Things according to claim 4 is characterized in that: The risk calculation module includes a risk modeling unit; The risk modeling unit is used to build a regional risk assessment model using a federated learning framework, train the model through distributed node collaboration, and integrate multi-source safety monitoring data from all monitoring sub-regions; Then, the local model parameters of each monitoring sub-area are privacy-protected through a homomorphic encryption algorithm. After that, the encrypted parameters are aggregated using a federated averaging algorithm on the central server to update the global model. At the same time, a dynamic weight update mechanism is set up to automatically adjust the model update cycle based on the frequency of environmental changes, including equipment movement and work surface expansion at the construction site.

6. The construction site safety information monitoring system based on the Internet of Things according to claim 5 is characterized in that: The risk calculation module also includes an entropy value calculation unit; The entropy value calculation unit is used to preferentially calculate the risk entropy value Re of each monitoring sub-area in the auxiliary monitoring area set, and use the regional risk assessment model to perform real-time analysis on the multi-source safety monitoring data to obtain the abnormal gathering of personnel Ea, density equipment abnormality Eb and vibration amplitude environmental mutation index Ec, and after dimensionless processing, use the following formula to calculate the risk entropy value Re: In the formula, the range of the abnormal gathering of personnel Ea is Ea∈[0,5], and the larger the value, the more abnormal the degree of personnel gathering; the range of the abnormal density equipment Eb is Eb∈[0,3], and the larger the value, the more serious the abnormal distribution of equipment; the range of the vibration amplitude environmental mutation index Ec is Ec∈[0,4], and the larger the value, the more severe the environmental vibration fluctuation; Collect historical construction data, extract dimensionless personnel abnormal aggregation index Ea, density equipment abnormal index Eb and vibration amplitude environment mutation index Ec, obtain mean μRe and standard deviation σRe, and use the following formula to calculate the risk entropy threshold E: In the formula, k is the adjustment coefficient; The risk entropy threshold E is compared and evaluated with each risk entropy value Re one by one. The specific evaluation contents are as follows: When the risk entropy value Re is less than the risk entropy threshold E, it means that the security risk status in the current monitoring sub-area is normal and the current monitoring strategy remains unchanged; When the risk entropy value Re ≥ the risk entropy threshold E, it means that the security risk status in the current monitoring sub-area is abnormal, and the current monitoring sub-area is marked in red.

7. The construction site safety information monitoring system based on the Internet of Things according to claim 6 is characterized by: The abnormal monitoring sub-area with the risk entropy value Re ≥ the risk entropy threshold E in the auxiliary monitoring area is recorded as i, and i∈{1, 2, 3, ..., s}, where s represents the total number of monitoring sub-areas; When there are two or more adjacent monitoring sub-areas marked in red around monitoring sub-area i, it indicates that regional risk diffusion is formed. At this time, the local average risk entropy value is calculated. , and judge whether it exceeds the local threshold E i : ； Where N(i) represents the number of monitoring sub-regions adjacent to monitoring sub-region i; j represents the index of the adjacent monitoring sub-region; Re j is the risk entropy value of the adjacent monitoring sub-area j; is the local average risk entropy value of the monitoring sub-area i; Use the same calculation method as the risk entropy threshold E to determine The local threshold is E i ; When the local average risk entropy Less than the local threshold E i , indicating that the risk of the current monitoring sub-area i spreading to the adjacent monitoring sub-area is small; When the local average risk entropy Greater than or equal to the local threshold E i , indicating that the risk of the current monitoring sub-area i spreading to the adjacent monitoring sub-areas is high, and the risk diffusion coefficient Rd of all the monitoring sub-areas marked in red is calculated.

8. The construction site safety information monitoring system based on the Internet of Things according to claim 7 is characterized by: The risk calculation module also includes a diffusion assessment unit; The abnormal monitoring sub-area with the risk entropy value Re ≥ the risk entropy threshold E in the core monitoring area is recorded as i0, and i0∈{1, 2, 3, ..., f}, where f represents the total number of monitoring sub-areas; The diffusion assessment unit is used to calculate the risk diffusion coefficient Rd and evaluate the diffusion trend of the risk to the core monitoring area set; ； In the formula, max represents the maximum risk entropy increment between the monitoring sub-area i and the adjacent monitoring sub-area i0 in the core monitoring area set, which is used to measure the strongest local risk diffusion trend; the adjacent monitoring sub-area set Contains all monitoring sub-areas directly connected to monitoring sub-area i0, used to find the direction of maximum risk diffusion; is the index of adjacent monitoring sub-areas; Re i represents the risk entropy value of monitoring sub-region i, The risk entropy value of the monitoring sub-area representing the concentrated abnormality in the core monitoring area; The historical risk diffusion data of each monitoring sub-area during the construction process are collected, the mean and standard deviation of the risk diffusion coefficient Rd are calculated, and the risk diffusion threshold D is obtained. The risk diffusion coefficient Rd is compared and evaluated. The specific evaluation contents are as follows: When the risk diffusion coefficient Rd ≥ risk diffusion threshold D: It indicates that the risk diffusion trend of the current monitoring sub-area is abnormal and will soon affect the core monitoring area set; adjust the monitoring frequency and data collection frequency of the current monitoring sub-area and its adjacent monitoring sub-areas; and take additional intervention measures, including strengthening construction safety management or optimizing personnel scheduling; When the risk diffusion coefficient Rd is less than the risk diffusion threshold D: This indicates that the risk diffusion trend in the current monitoring sub-area is normal, and the impact on the core monitoring area set is negligible. At this time, maintain the normal monitoring frequency and continue to observe the risk change trend in the current monitoring sub-area.

9. A construction site safety information monitoring system based on the Internet of Things according to claim 8, characterized in that: The intelligent early warning module includes a risk intervention decision-making unit; The risk intervention decision unit is used to calculate and evaluate the risk intervention priority Rp; the construction activity intensity Pa and communication quality Pb ​​in the data acquisition module are extracted, and after dimensionless processing with the risk diffusion coefficient Rd, the risk intervention priority Rp is calculated using the following formula: ； Among them, −1≤Rp<1; The numerical value of the risk intervention priority Rp is evaluated as follows: When the risk intervention priority Rp is less than or equal to 0, and is closer to -1, it means that the risk diffusion in the current monitoring sub-area is weaker, the construction activities are less, or the communication quality is better; When the risk intervention priority Rp is greater than 0 and is closer to 1, it means that the risk in the current monitoring sub-area spreads faster, the intensity of construction activities is higher, and the communication quality is more unstable, and intervention is carried out at this time.

10. A construction site safety information monitoring system based on the Internet of Things according to claim 9, characterized in that: The intelligent early warning module also includes a dynamic optimization execution unit; The dynamic optimization execution unit applies the DRL deep reinforcement learning algorithm to continuously optimize the hierarchical warning strategy, including: According to the real-time risk situation, adjust the sampling frequency of the core monitoring area set to 3 to 5 times that of the auxiliary monitoring area set; Automatically calculate and allocate computing resources according to risk levels, and adjust server resource allocation; build a risk coupling model based on complex network theory, analyze the risk transmission path between regions, predict chain reaction effects, and optimize the global early warning response plan.

Images