Intelligent construction site equipment control method and system based on internet of things

Abstract

The application discloses a smart construction site equipment control method and system based on Internet of Things, and relates to the technical field of digital construction sites.The method comprises the following steps: collecting environment data and situational data in real time through a perception node network, generating a dynamic environment map, and determining the situational state of each target area based on the dynamic environment map.When an abnormal situational state is detected, the system automatically generates a processing task, and ensures the reliability of data transmission and the timeliness of emergency response based on the task demand through a difference redundancy and dynamic priority redundancy strategy.In addition, the task processing efficiency is improved by controlling the movement of the perception nodes and changing the state of the nodes.The method effectively improves the intelligent level of construction site management, enhances the dynamic response capability to complex situations, and is suitable for efficient management of modern complex construction sites.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital construction sites, and in particular to a smart construction site equipment control method and system based on the Internet of Things. BACKGROUND

[0002] With the increasing complexity and scale of modern construction projects, construction site management is facing more and more challenges. Although some existing construction site management systems based on the Internet of Things can achieve environmental monitoring and equipment control, they still have some shortcomings in dealing with complex and variable construction site environments. For example, the existing systems usually lack the ability to analyze the complex correlation between environmental data and situational data, making it difficult to effectively coordinate between multiple nodes, resulting in insufficient emergency response capabilities. In addition, the flexibility of data redundancy strategies is not high, and the data transmission strategy cannot be dynamically adjusted according to real-time situations, which may cause resource waste or response delay.

[0003] For example, Chinese Patent No. CN117911198A discloses a smart construction site management system, which includes a personnel management module, a device control module, an environmental monitoring module, a site supervision module, and a management platform. The personnel management module is used to collect the personal information and attendance information of workers. The environmental monitoring module is used to collect environmental data and send the environmental data to the management platform. The device control module is used to collect the current state of the equipment and send the device state information to the management platform. The site supervision module is used to identify the personal information and safety information of construction personnel and send the identification information to the management platform. The management platform is used to display the personal information and attendance information of workers, environmental data, device state information, and identification information. If a problem occurs, the abnormality can be seen on the management platform in the first time, thereby improving the safety of construction

[0004] The above method has the problems mentioned in the background, and the existing system lacks the ability to analyze the complex correlation between environmental data and situational data, making it difficult to effectively coordinate between multiple nodes, resulting in insufficient emergency response capabilities. Secondly, the flexibility of data redundancy strategies is not high, and the data transmission strategy cannot be dynamically adjusted according to real-time situations, which may cause resource waste or response delay. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application discloses a smart construction site equipment control method and system based on the Internet of Things.

[0006] In a first aspect, the present application provides a smart construction site equipment control method based on the Internet of Things, comprising:

[0007] Real-time collection of environmental data and situational data of a target construction site using a perception node network, and generation of a dynamic environmental map; wherein the target construction site includes multiple target areas, and each target area is equipped with at least one perception node;

[0008] determine a scenario state of each of the target areas based on the dynamic environment map;

[0009] in response to a target scenario state existing in the scenario state of the target area, generate a control instruction by a perception node equipped with the target area where the target scenario state exists;

[0010] control a target device in the target work site to handle the target scenario state based on the control instruction.

[0011] As an optional implementation, the dynamic environment map comprises static mapping information, dynamic mapping information, and environment mapping information; and the generating the dynamic environment map comprises:

[0012] obtaining static layout information of the target work site to generate the static mapping information;

[0013] determining a dynamic change factor based on the scenario data to generate the dynamic mapping information;

[0014] generating the environment mapping information based on the environment data;

[0015] wherein a mapping frequency of the dynamic mapping information and the environment mapping information is a preset first mapping frequency and a preset second mapping frequency respectively.

[0016] As an optional implementation, the generated control instruction comprises:

[0017] in response to a target scenario state existing in the scenario state of the target area, generating, by the perception node equipped with the target area where the target scenario state exists, marking information of the target area at the time when the target scenario state exists;

[0018] wherein the marking information comprises a target scenario state, time information, geographic information, in-area device operation information, and environment data;

[0019] uploading the marking information to the perception node network.

[0020] As an optional implementation, in response to the perception node network detecting that a first number of the perception nodes upload the same target scenario state, generating the control instruction by global decision making of all the perception nodes.

[0021] As an optional implementation, in response to the perception node network detecting that a certain perception node uploads the target situation state, a local decision is made by using the perception node that uploads the target situation state and perception nodes directly adjacent to the perception node that uploads the target situation state, and the control instruction is generated;

[0022] After the perception node uploads the target situation state, the method further includes:

[0023] Increasing the mapping frequency of the dynamic mapping information from the first mapping frequency to a third mapping frequency;

[0024] Increasing the mapping frequency of the environment mapping information from the second mapping frequency to a fourth mapping frequency.

[0025] As an optional implementation, the making of the local decision to generate the control instruction includes:

[0026] For the perception nodes directly adjacent to the perception node that uploads the target situation state, the target situation state correlation is evaluated, and correlation information of each of the directly adjacent perception nodes is generated;

[0027] Based on the correlation information, a local decision is made to generate the control instruction;

[0028] The correlation information includes environment data correlation and situation data correlation.

[0029] As an optional implementation, based on the correlation information, a data redundancy strategy between the perception node that uploads the target situation state and the directly adjacent perception nodes is determined; the data redundancy strategy includes:

[0030] When the environment data and the situation data of the perception node and its directly adjacent perception nodes both show a first correlation, a difference redundancy strategy is adopted in the data transmission process; the difference redundancy strategy includes introducing data difference in the transmission process.

[0031] When the situation data correlation is high and the environment data correlation is low, a dynamic priority redundancy strategy is adopted in the data transmission process; the dynamic priority redundancy strategy includes preferentially transmitting situation data and dynamically adjusting the data transmission frequency and order.

[0032] As an optional implementation, the method further includes:

[0033] Based on the correlation information, the positions of the perception node that uploads the target situation state and its adjacent perception nodes are controlled.

[0034] The perception node has a mobile capability, and is configured to adjust its physical position based on the correlation information.

[0035] The perception node changes its monitoring angle based on the correlation information.

[0036] The perception node has an adjustable monitoring device.

[0037] In a second aspect, the present application further provides a smart construction site equipment control system based on the Internet of Things, comprising:

[0038] A perception node unit is configured to collect environmental data and situational data of a target construction site in real time by using a perception node network, and generate a dynamic environment map; wherein the target construction site comprises a plurality of target areas, and each target area is provided with at least one perception node.

[0039] A situational analysis unit is configured to determine situational states of each target area based on the dynamic environment map.

[0040] A processing unit is configured to generate a control instruction by using a perception node provided in a target area in which a target situational state exists, in response to the target situational state existing in the situational states of the target areas.

[0041] A control unit is configured to control a target equipment in the target construction site to process the target situational state based on the control instruction.

[0042] In a third aspect, the present application further provides a computer device, a processor and a memory, wherein the memory stores machine readable instructions executable by the processor, the processor is configured to execute the machine readable instructions stored in the memory, and the machine readable instructions are configured to perform the steps of the first aspect or any possible implementation manner of the first aspect when executed by the processor.

[0043] In a fourth aspect, the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is configured to perform the steps of the first aspect or any possible implementation manner of the first aspect when executed.

[0044] Compared with the prior art, the beneficial effects of the present application are that the system can accurately reflect the actual situation of the construction site by real-time collection of environmental data and situational data through the perception node network and generation of a dynamic environment map. Compared with traditional methods, this dynamic mapping can timely identify changes in the environment and equipment, improving the real-time and accuracy of construction site management. Based on dynamic environment mapping and situational recognition, when an abnormal situational state is detected, control instructions can be automatically generated and corresponding response measures can be executed. The introduction of difference redundancy and dynamic priority redundancy strategy makes data transmission more reliable and efficient. By dynamically adjusting the redundancy level and data transmission frequency according to different situations, the system effectively reduces unnecessary network burden while ensuring the priority transmission of critical data. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 A flowchart of a smart construction site equipment control method based on the Internet of Things is provided for the embodiments of the present application.

[0046] Figure 2 A schematic diagram of a smart construction site equipment control system based on the Internet of Things is provided for the embodiments of the present application.

[0047] Figure 3 A computer device structure schematic diagram is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments.

[0049] Referring to Figure 1 The flowchart of a smart construction site equipment control method based on the Internet of Things is provided for the embodiments of the present application, and the method comprises steps S101-S104, wherein:

[0050] S101: Real-time collection of environmental data and situational data of a target construction site by a perception node network, and generation of a dynamic environment map; wherein the target construction site comprises a plurality of target areas, and each target area is equipped with at least one perception node;

[0051] S102: Determination of the situational state of each target area based on the dynamic environment map;

[0052] S103: In response to the existence of a target situational state in the situational state of the target area, generation of a control instruction by the perception node equipped in the target area where the target situational state exists;

[0053] S104: Control of the target equipment in the target construction site to handle the target situational state based on the control instruction.

[0054] For the above S101:

[0055] In specific implementation, multiple sensing nodes can be deployed in multiple target areas of the target construction site. Each target area is equipped with at least one sensing node, and these nodes are connected through a wireless network (such as LoRa, Zigbee, Wi-Fi, etc.) to form a complete sensing node network. Each sensing node is responsible for real-time collection of environmental data and situational data in the area. Each sensing node can transmit the collected data to the central processing unit of the system in real time.

[0056] Among them, the sensing node refers to an intelligent device deployed in the target area, which can collect environmental data (such as temperature and humidity, dust concentration) and situational data (such as worker location, equipment status) in real time. The sensing node usually includes multi-modal sensors, data processing units, wireless communication modules, etc.

[0057] The target construction site refers to the entire management area of the construction site, including multiple different target areas.

[0058] The target area can be a subdivided area of the target construction site, each area having a specific function or characteristic, for example, a construction area, an equipment area, a material storage area, etc. For example, the first construction area, the second construction area, and the like.

[0059] For example, environmental data includes dust concentration, temperature and humidity, noise level, light intensity, etc.; situational data includes worker location, equipment operating status, material storage, etc.

[0060] For the above S102:

[0061] In specific implementation, after the central processing unit of the system receives environmental data and situational data from multiple sensing nodes, it generates a dynamic environment map in combination with static layout information of the target construction site. This dynamic environment map will be continuously updated according to real-time data from the sensing nodes, reflecting the latest status within the construction site. This map is a multi-level construction site environment model, containing the following information:

[0062] Static mapping: fixed layout of construction site infrastructure, such as building location, installation location of fixed equipment, etc.

[0063] Dynamic change mapping: dynamic change factors within the construction site, such as equipment movement path, real-time changes in worker activity area, etc.

[0064] Environmental state mapping: current environmental data distribution, such as dust concentration distribution, temperature and humidity change trend, etc.

[0065] Among them, the target situational state refers to a pre-defined state that needs to be handled, such as equipment failure, high-risk operation, environmental pollution exceeding standard, etc.

[0066] For the above S103:

[0067] In specific implementation, the system identifies the scenario state of each target area through analysis of the dynamic environment mapping. For example, when the dust concentration in a certain target area exceeds the standard and the equipment is running abnormally, the system identifies this state as a "high-risk scenario state". Subsequently, the system generates corresponding control instructions using the sensing nodes in the area.

[0068] For the above S104: Based on the generated control instructions, the system sends instructions to the target equipment (such as ventilation systems, cleaning equipment, alarm devices) to instruct it to start the corresponding processing flow. For example, for the "high-risk scenario state", the system may start the ventilation equipment in the area to reduce the dust concentration, and notify the on-site management personnel to take further safety measures, or start the alarm system to remind workers to stay away from the dangerous area.

[0069] In this way, based on the sensing node network, through dynamic environment mapping and scenario recognition, control instructions are generated and executed, effectively improving the intelligence and safety of construction site management.

[0070] The present application collects environmental data and scenario data in real time through the sensing node network and generates a dynamic environment mapping. Compared with traditional static monitoring systems, it can reflect the dynamic changes of the construction site environment and situation in real time, providing more accurate construction site management information. Through dynamic environment mapping, the scenario state of the target area is identified, solving the problem of difficult comprehensive perception and real-time response to complex construction site environment in traditional systems. After identifying a specific scenario state, control instructions are automatically generated, and related equipment is controlled to respond. This intelligent processing flow reduces manual intervention and improves the efficiency and safety of construction site management.

[0071] As an optional implementation, the dynamic environment mapping includes static mapping information, dynamic mapping information, and environment mapping information; the generation of the dynamic environment mapping includes: obtaining the static layout information of the target construction site to generate the static mapping information; determining the dynamic change factors based on the scenario data to generate the dynamic mapping information; generating the environment mapping information based on the environmental data; wherein the mapping frequencies of the dynamic mapping information and the environment mapping information are respectively a preset first mapping frequency and a second mapping frequency.

[0072] In specific implementation, the static layout information of the construction site can be obtained in a digital manner. These information can come from construction site design drawings, building planning documents or high-precision map data obtained by unmanned aerial vehicle scanning. The layout information includes the specific location of the building, the installation point of the fixed equipment, the distribution of roads and passages, etc.

[0073] These layout information is inputted to form static mapping information. These data is integrated into a static 3D site model, which shows the basic structure and fixed facilities of the site. This mapping can be updated infrequently, only when there are structural changes in the site, and the static mapping is regenerated. For example, if a building is completed and put into use, or a device is permanently removed, the system will regenerate the static mapping.

[0074] The static mapping helps to determine the specific location and meaning of dynamic or environmental information, effectively managing and analyzing the overall situation of the site. It provides a reference framework for dynamic changes and environmental states, ensuring accurate positioning and correlation of all data.

[0075] For example, Building Information Modeling (BIM) software such as Autodesk Revit, Bentley Systems, or CAD tools such as AutoCAD can be used to create or obtain detailed layout drawings of the site. These tools can accurately depict the 3D structure of buildings, roads, and fixed equipment. Use a 3D graphics processing engine (such as Unity 3D, Unreal Engine, or WebGL technology) to convert the input static layout data into a 3D site model. When the site layout changes (such as the addition of a building or equipment), the model can be updated through BIM / CAD tools and re-imported into the system, which will automatically update the static mapping.

[0076] In specific implementations, the dynamic change factors are identified using situational data collected by the perception nodes in real time. For example, the perception nodes track the movement path of equipment through infrared sensors and RFID tags, or analyze the real-time activity area of workers through video, and identify changes in material stacking, etc.

[0077] Based on the above change factors, the system generates dynamic mapping information. This information shows the current activities occurring within the site, such as the movement of a device from one area to another, or an increase in worker activity density in a certain area. Since dynamic factors change quickly, the mapping frequency can be set to a first mapping frequency (such as every 1 minute) to update this information in real time, ensuring that it reflects the latest site conditions. It can be understood that the specific mapping frequency depends on the hardware configuration of the perception nodes, such as through central processing unit scheduling, both hardware configuration and communication quality need to be considered.

[0078] For example, a data integration and analysis platform can be used to integrate the data collected by the sensors. Through pre-set algorithms or machine learning models, these data are analyzed to identify information such as equipment movement paths, worker gathering areas, and dynamic distribution of materials. Use visualization analysis tools (such as ArcGIS, QGIS, or custom-developed site management software) to convert the analysis results into dynamic mapping information.

[0079] After generating the dynamic mapping, the system superimposes it on the static mapping information and displays the dynamic activities of the construction site in real time through a three-dimensional visualization engine (such as Unity 3D, Unreal Engine, or WebGL).

[0080] In specific implementations, the perception nodes collect environmental data of the target construction site in real time through installed sensors (such as temperature and humidity sensors, dust sensors, noise sensors, etc.). These data are automatically recorded by the system and transmitted to the central processing unit.

[0081] The system integrates the collected environmental data to generate environmental mapping information. This mapping shows the current environmental conditions of the construction site, such as the dust concentration distribution, temperature and humidity changes in each area, etc. The update frequency of environmental data is determined by the second mapping frequency (such as every 2 minutes), and can be dynamically adjusted according to actual needs. For example, when detecting a continuous increase in dust concentration, the system can automatically shorten the update frequency of environmental mapping to more intensively monitor and reflect environmental changes.

[0082] For example, the environmental mapping information can include real-time temperature and humidity distribution maps, dust concentration heat maps, noise level distribution maps, etc. The generated environmental mapping information is superimposed with the static layout and dynamic change information of the construction site and displayed through a three-dimensional visualization platform.

[0083] In this way, through the generation and real-time update of static, dynamic, and environmental three-layer mapping information, the system can comprehensively and accurately reflect the real-time conditions of the construction site, ensuring that management personnel can timely grasp and respond to complex construction environments and dynamic changes. This multi-frequency, multi-level mapping mechanism provides an efficient means of construction site monitoring and management.

[0084] As an optional implementation, the generated control instructions include: in response to the presence of a target scenario state in the scenario state of the target area, using the perception node equipped with the target area where the target scenario state exists, generating the current marking information of the target area when the target scenario state exists; wherein the marking information includes: target scenario state, time information, geographic information, regional equipment operation information, and environmental data; uploading the marking information to the perception node network.

[0085] In specific implementations, the scenario state within the target area is identified through dynamic environmental mapping. If the scenario state of a certain area is identified as a target scenario state (such as equipment failure, dust concentration exceeding standard, etc.), it will trigger the generation process of control instructions.

[0086] In the marking information, the target situation records the current situation of the area, such as "equipment failure" or "dust over standard". Time information: records the timestamp when the situation is detected. Geographic information: marks the specific geographic location where the situation is located (such as a specific area of the construction site). Device operation information: records the operation status of the equipment in the area, such as whether the equipment is running normally, whether there is an abnormality, etc. Environmental data: including the current temperature and humidity, dust concentration and other environmental information of the area.

[0087] When a sensing node in a target area detects a target situation, it automatically collects all relevant information (including time, geographic location, device operating status, and environmental data) from the node. Integrate these information to generate a complete marking information package. Upload the generated marking information package to the central processing unit or cloud service through the sensing node network. After uploading, the marking information is distributed in the sensing node network, and other related nodes can access and share this information to make subsequent local or global decisions.

[0088] In this way, through real-time marking and information uploading of the situation, it can quickly respond in the construction site environment, ensuring that management personnel can obtain key information in time and make effective decisions.

[0089] As an optional implementation, in response to the sensing node network detecting that a first number of sensing nodes upload the same target situation, a global decision is made using all the sensing nodes to generate the control instruction.

[0090] In specific implementation, the marking information uploaded by each node is monitored in real time through the sensing node network. When a first number (such as three or more) of sensing nodes upload the same target situation (such as dust concentration over standard, equipment failure, etc.), the system identifies that this situation is a potential global problem.

[0091] The specific value of the first number can be defined according to the size of the construction site and the system settings, for example, it can be set to three or more sensing nodes. When the system confirms that the first number of sensing nodes upload the same target situation, the global decision-making process is automatically triggered. This indicates that the problem may affect the entire construction site, or the situation has spread to multiple areas.

[0092] Integrate all the data of the sensing nodes (including but not limited to situation, time, geographic location, device operation information, environmental data, etc.) to obtain a more comprehensive view of the construction site. Use these data for comprehensive analysis to generate global control instructions. For example, in the case of global dust concentration over standard, the system may command multiple regional ventilation equipment to start simultaneously, or issue a safety evacuation instruction for the entire construction site.

[0093] Based on the integrated global data, corresponding control instructions are generated. These instructions can include starting the global warning system, dispatching emergency resources, controlling or shutting down specific equipment, etc.

[0094] Through the perception node network, the generated control instructions are sent to each relevant device and control unit, ensuring that the instructions are quickly executed throughout the site. For example, when a global device failure is detected, the operation of multiple devices can be stopped simultaneously to prevent the failure from spreading.

[0095] For example, pattern recognition algorithms such as clustering analysis or anomaly detection algorithms can be used to analyze these data. For example, Python's Scikit-learn library, or machine learning platforms such as TensorFlow. A threshold value (such as detecting more than three nodes reporting the same scenario state) is set, and once this threshold is exceeded, the system is automatically marked as a potential global problem.

[0096] For example, a long short-term memory network (LSTM) can be used to identify potential global problems in construction site management in real time. The perception nodes in the construction site continuously collect environmental data (such as dust concentration, temperature and humidity) and scenario state data (such as device status, worker activity). These data are transmitted to the central system in real time for cleaning and standardization processing. The system segments the data by time sequence and divides it into training set and test set.

[0097] After training, the LSTM model is deployed on a cloud server or edge computing device. The system receives scenario state data uploaded by perception nodes in real time and inputs it into the LSTM model. When multiple nodes report the same or similar abnormal state, the LSTM model can quickly identify whether the situation is a potential global problem.

[0098] When the LSTM model identifies a potential global problem, the system immediately triggers a global response mechanism. According to the identified results, the system generates corresponding control instructions, such as starting the whole field ventilation system or issuing an emergency alarm, to ensure the safety of the entire construction site.

[0099] It can be understood that other models can also be used to complete the task of global problem identification, such as convolutional neural networks, which are not limited by the present application.

[0100] In this way, by detecting multiple perception nodes uploading the same target scenario state, the global decision-making process is triggered, ensuring that when a global problem occurs in the construction site, a response can be made quickly and necessary management measures can be taken. This global decision-making mechanism improves the system's ability to respond to large-scale emergencies, ensuring the safety and stability of the construction site.

[0101] As an optional implementation, in response to the perception node network detecting that a certain perception node uploads the target situation state, a local decision is made using the perception node that uploads the target situation state and the perception nodes directly adjacent to the perception node that uploads the target situation state in the perception node network, and the control instruction is generated;

[0102] After the perception node uploads the target situation state, the method further includes:

[0103] Increasing the mapping frequency of the dynamic mapping information from the first mapping frequency to a third mapping frequency;

[0104] Increasing the mapping frequency of the environment mapping information from the second mapping frequency to a fourth mapping frequency.

[0105] As an optional implementation, the making of the local decision to generate the control instruction includes:

[0106] For the perception nodes directly adjacent to the perception node that uploads the target situation state, the target situation state correlation is evaluated, and correlation information of each directly adjacent perception node is generated;

[0107] Based on the correlation information, a local decision is made to generate the control instruction;

[0108] The correlation information includes environment data correlation and situation data correlation.

[0109] In a specific implementation, when a certain perception node (for example, node A) detects a target situation state (such as dust concentration exceeding the standard or equipment failure), the node immediately uploads this state to the perception node network.

[0110] The perception nodes directly adjacent to node A (such as nodes B and C) are identified, which share the geographical or logical proximity of node A. A local decision process is triggered, and data of node A and its adjacent nodes B and C are used for local analysis to determine how to respond to the target situation state.

[0111] The environment data (such as temperature and humidity, noise level, etc.) of node A and its adjacent nodes are compared, and the environment data correlation between these nodes is evaluated. For example, if the dust concentration of adjacent node B also rises, it indicates that environmental factors may have a more extensive impact.

[0112] Meanwhile, the system analyzes the situational data (such as device status, worker location, etc.) of node A and its neighboring nodes to determine the correlation between these data. For example, node A detects a device failure, while nodes B, C detect abnormal device operation or an increase in worker density, indicating that there is a correlation between the situational states of these nodes.

[0113] Based on the above evaluation results, the system generates correlation information for each neighboring node. These information reflects the degree of association of each node with the target situational state, providing a basis for subsequent local decision-making.

[0114] In specific implementation, according to the preset decision-making rules, combined with the correlation information of each node, local response strategies are formulated. For example, if multiple neighboring nodes show high correlation, the system can decide to start local devices (such as ventilation devices) or issue regional alarms, and transmit instructions to related devices through the perception node network for execution

[0115] In addition, in order to more intensively monitor the changes in the target area, the update frequency of dynamic mapping information is increased from the original first mapping frequency to the third mapping frequency. For example, from updating once every 1 minute to updating once every 10 seconds. At the same time, the system increases the update frequency of environmental mapping information from the second mapping frequency to the fourth mapping frequency. For example, from updating once every 3 minutes to updating once every 10 seconds, to reflect the changes in the environment state more finely.

[0116] It can be understood that the specific mapping frequency setting here can be implemented in combination with the target situation, for example, for the detection of natural phenomena such as strong wind and heavy rain, the frequency can be appropriately reduced, while for phenomena such as fire and dust that pose a huge threat, a higher mapping frequency can be set.

[0117] For example, local decision-making can be made using the LSTM model mentioned above. For example, after node A detects the target situational state, it will input its environmental data and situational data (such as temperature and humidity, device status) into the LSTM model together with the data of neighboring nodes B, C. The LSTM model analyzes the time series data to identify the correlation between node A and its neighboring nodes B, C. Based on the analysis results of the LSTM model, the system can determine the potential impact range of the target situational state. For example, if the LSTM model predicts that the device of node B may also experience similar failures, the system can issue an early warning and take preventive measures.

[0118] It should be noted that in the training and construction of this type of neural network model, the data needs to be labeled to identify which data sequences correspond to normal states and which correspond to abnormal situation states (such as device failure, environmental over-standard). In the input layer design of the model, multi-channel input can be introduced, and the environmental data and situation data of different perception nodes are input into different channels. Each channel represents a data sequence of a perception node, which can capture the time dependence and mutual influence between different nodes.

[0119] As an optional implementation, based on the correlation information, a data redundancy strategy between the perception node uploading the target situation state and the directly adjacent perception node is determined; wherein the data redundancy strategy includes:

[0120] When the environmental data and situation data of the perception node and its directly adjacent perception node show the first correlation, a difference redundancy strategy is adopted in the data transmission process; wherein the difference redundancy strategy includes introducing data difference in the transmission process;

[0121] When the situation data correlation is high and the environmental data correlation is low, a dynamic priority redundancy strategy is adopted in the data transmission process; wherein the dynamic priority redundancy strategy includes preferentially transmitting situation data and dynamically adjusting the data transmission frequency and order.

[0122] In specific implementation, the environmental data (such as dust concentration, temperature and humidity) and situation data (such as device status, worker activity) of perception node A and its directly adjacent nodes B and C are monitored in real time. When it is detected that the environmental data and situation data of node A and adjacent nodes show the first correlation (i.e. high correlation), the system automatically triggers the difference redundancy strategy.

[0123] In the data transmission process, by randomly changing the encoding method, data arrangement order or introducing slight noise of the data packet, a differentiated data redundancy packet is generated. These differentiated data packets can improve the robustness of the data, and even if part of the data is lost or damaged in the transmission process, the complete information can be recovered by recombining other redundancy packets.

[0124] For example, node A detects a sharp rise in dust concentration, and nodes B and C also report similar environmental changes. In this case, the system performs multi-version redundancy on the transmitted data and ensures the integrity of information transmission through difference coding.

[0125] When the system detects that the situation data (such as device status or worker activity) of node A and adjacent nodes B and C shows high correlation, but the environmental data correlation is low, the dynamic priority redundancy strategy is triggered.

[0126] Prioritize transmission of critical information related to situational data (e.g., worker location, safety status, etc.) based on their importance, ensuring that these critical data are transmitted with higher priority.

[0127] Adjust the frequency and order of data transmission dynamically based on real-time environmental changes. For example, when detecting an increase in worker activity density, the system increases the redundancy level and shortens the data transmission interval, allowing critical information to reach the destination faster.

[0128] For example, node A detects a device failure, and node C reports an increase in worker concentration. The system decides to adopt a dynamic priority redundancy strategy, prioritizing the transmission of worker safety-related data, and adjusting the transmission frequency to ensure timely delivery of safety information.

[0129] It can be understood that the determination and discrimination of specific relevance can be achieved by the LSTM mentioned above, which will not be repeated here.

[0130] In this way, through the difference redundancy strategy and the dynamic priority redundancy strategy, the system can intelligently select and execute the most suitable redundancy scheme based on the relevance of environmental and situational data between nodes, thereby improving the reliability and emergency response capability of data transmission.

[0131] As an optional implementation, the position of the perception node uploading the target situational state and its adjacent perception nodes can also be controlled based on the relevance information; wherein the perception node has a mobile capability, for adjusting its physical position based on the relevance information; based on the relevance information, the monitoring angle of the perception node is changed; wherein the perception node is equipped with an adjustable monitoring device.

[0132] In specific implementation, by monitoring the target situational state uploaded by perception node A in real time, and evaluating its relevance with the environmental and situational data of adjacent nodes B and C. For example, it is detected that the dust concentration information uploaded by node A is highly relevant to the situational data of adjacent node B, and the system triggers the position adjustment of the perception node according to the relevance information.

[0133] The perception node is equipped with a mobile device, such as a motor-driven tracked chassis or a wheeled mobile platform. This mobile device can automatically adjust the position of the perception node under the control of the system.

[0134] Based on the relevance information, the system instructs node A to move to a more suitable monitoring position. For example, when the dust concentration in the adjacent area increases, node A can move to an area closer to the source, enhancing the monitoring coverage of that area.

[0135] For example, if the environmental data of a certain area in the construction site changes significantly, node A autonomously moves to a higher-risk area according to the system instructions, ensuring real-time monitoring of the changed area. This automated movement function reduces the need for manual adjustment and improves the monitoring flexibility of the system.

[0136] In addition, when the system detects that the monitoring range of the perception node A is insufficient to cover the target area, the system instructs the perception node to adjust its monitoring angle based on the correlation information. For example, when node C detects that workers are gathering and their activities are beyond the current camera monitoring range, the system triggers the adjustment of the monitoring angle.

[0137] In specific implementations, the perception node is equipped with a rotatable camera or sensor that can rotate horizontally or vertically under the control of the system to change the monitoring angle of view. The rotation angle can be achieved through a motorized gimbal or other mechanical structure to ensure that the node can cover a larger monitoring area.

[0138] For example, when the system detects that the changes in the environment or situation do not match the monitoring range of the node, it will instruct the perception node to adjust the monitoring angle. For example, the system can instruct the camera of the node to rotate 30 degrees to cover the new target area.

[0139] For example, in a construction site, if the worker activity range monitored by a certain node exceeds the current camera angle of view, the system will instruct the camera of the node to adjust the angle to ensure real-time monitoring of the worker's activities. This function can reduce dead angles and improve the efficiency of construction site safety management.

[0140] In this way, through the automatic position adjustment and monitoring angle change of the perception node, the system can more flexibly respond to changes in the complex construction site environment and reduce human intervention. The system can also automatically adjust the node position and monitoring angle according to the real-time situation to ensure key monitoring of high-risk areas and timely detection of potential risks.

[0141] Based on the same inventive concept, the embodiments of the present application also provide an Internet of Things-based smart construction site equipment control system corresponding to the Internet of Things-based smart construction site equipment control method. Since the system in the embodiments of the present application solves the problem by a similar principle to the above-mentioned method, the implementation of the system can be referred to the implementation of the method, and the repeated parts will not be described again.

[0142] Referring to Figure 2 The system provided by the embodiments of the present application includes:

[0143] The perception node unit 10 is configured to collect environmental data and situational data of a target construction site in real time by using a perception node network, and generate a dynamic environment map; wherein the target construction site comprises a plurality of target areas, and each target area is provided with at least one perception node;

[0144] The situational analysis unit 20 is configured to determine a situational state of each target area based on the dynamic environment map;

[0145] The processing unit 30 is configured to generate a control instruction by using the perception node provided in the target area where the target situational state exists, in response to the existence of the target situational state in the situational state of the target area;

[0146] The control unit 40 is configured to control a target device in the target construction site to process the target situational state.

[0147] The processing flow of each module in the system and the interaction flow between the modules can be referred to the related description in the above method embodiments, and will not be described in detail here.

[0148] The embodiment of the present application further provides a computer device, as shown in the figure, a structural schematic diagram of the computer device provided by the embodiment of the present application, comprising: Figure 3

[0149] A processor 41 and a memory 42; the memory 42 stores machine readable instructions executable by the processor 41, and the processor 41 is configured to execute the machine readable instructions stored in the memory 42, and when the machine readable instructions are executed by the processor 41, the processor 41 performs the following steps:

[0150] Collecting environmental data and situational data of a target construction site in real time by using a perception node network, and generating a dynamic environment map; wherein the target construction site comprises a plurality of target areas, and each target area is provided with at least one perception node;

[0151] Determining a situational state of each target area based on the dynamic environment map;

[0152] Generating a control instruction by using the perception node provided in the target area where the target situational state exists, in response to the existence of the target situational state in the situational state of the target area;

[0153] Controlling a target device in the target construction site to process the target situational state based on the control instruction.

[0154] ​The memory 42 includes an internal memory 421 and an external memory 422. The internal memory 421 is also referred to as an internal storage, and is used for temporarily storing operation data in the processor 41 and exchanging data with the external memory 422 such as a hard disk. The processor 41 exchanges data with the external memory 422 through the internal memory 421.

[0155] The specific execution process of the above instructions can refer to the steps of the smart construction site equipment control method based on the Internet of Things described in the embodiments of the present disclosure, which will not be repeated here.

[0156] The embodiments of the present disclosure also provide a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the test method described in the method embodiments are executed. The storage medium can be a volatile or non-volatile computer readable storage medium.

[0157] If the technical solution of the present application involves personal information, the product applying the technical solution of the present application has been explicitly informed of the personal information processing rules before processing the personal information, and has obtained the personal independent consent. If the technical solution of the present application involves sensitive personal information, the product applying the technical solution of the present application has obtained the personal independent consent before processing the sensitive personal information, and at the same time meets the requirement of "explicit consent". For example, at the personal information collection device such as camera, a clear and prominent mark is set to inform that the personal information collection range has been entered, and the personal information will be collected. If the individual voluntarily enters the collection range, it is considered to agree to collect the personal information. Or, on the device for processing personal information, through the pop-up information or by uploading the personal information by the individual, the personal authorization is obtained under the condition that the obvious mark / information informs the personal information processing rules. The personal information processing rules can include personal information processor, processing purpose, processing method and processing personal information type.

[0158] It should be understood that, in various embodiments of the present application, the size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0159] It should be understood that according to A, B is determined, which means that B is determined only according to A, but also B can be determined according to A and / or other information.

[0160] Those skilled in the art can realize the units and algorithm steps of each example described in connection with the embodiments disclosed in the present application can be realized in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0161] In the description of the present specification, the description referring to the terms "one embodiment", "an example", "a specific example" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0162] The preferred embodiments of the application disclosed above are only used to help explain the present application. The preferred embodiments do not describe all the details of the application, nor limit the application to the specific embodiments. Obviously, many modifications and variations can be made in light of the contents of the present specification. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and utilize the present application. The present application is limited only by the claims and their full scope and equivalents.

Claims

1. A smart construction site equipment control method based on an Internet of Things, characterized by, The method comprises: collecting environmental data and scenario data of a target construction site in real time by using a perception node network, and generating a dynamic environment map; wherein the target construction site comprises a plurality of target areas, each of which is equipped with at least one perception node; the dynamic environment map comprises static mapping information, dynamic mapping information and environmental mapping information, wherein the dynamic mapping information and the environmental mapping information are updated at a first mapping frequency and a second mapping frequency respectively; determining the scenario state of each target area based on the dynamic environment map; in response to the presence of a target scenario state in the scenario state of the target area, generating a control instruction for controlling a target device to handle the target scenario state, the generation of the control instruction comprising: using the perception node equipped in the target area where the target scenario state exists to generate the current marking information of the target area and upload it to the perception node network, the marking information comprising: target scenario state, time information, geographic information, in-area device operation information and environmental data; in response to the perception node network detecting that a first number of perception nodes have uploaded the same target scenario state, generating the control instruction by using all the perception nodes for global decision-making; in response to the perception node network detecting that a certain perception node has uploaded the target scenario state, generating the control instruction by using the perception node that has uploaded the target scenario state and the perception nodes that are directly adjacent to the perception node that has uploaded the target scenario state for local decision-making; after the perception node uploads the target scenario state, it further comprises: increasing the mapping frequency of the dynamic mapping information from the first mapping frequency to a third mapping frequency; increasing the mapping frequency of the environmental mapping information from the second mapping frequency to a fourth mapping frequency; for the perception nodes directly adjacent to the perception node that has uploaded the target scenario state, performing target scenario state correlation evaluation to generate correlation information of each of the directly adjacent perception nodes; the correlation information comprises environmental data correlation and scenario data correlation; based on the correlation information, determining a data redundancy strategy between the perception node that has uploaded the target scenario state and the directly adjacent perception nodes; when the environmental data and scenario data of the perception node and its directly adjacent perception nodes all show a first correlation, adopting a difference redundancy strategy in the data transmission process; wherein the difference redundancy strategy comprises introducing data difference in the transmission process; when the scenario data correlation is high and the environmental data correlation is low, adopting a dynamic priority redundancy strategy in the data transmission process; wherein the dynamic priority redundancy strategy comprises preferentially transmitting scenario data and dynamically adjusting the data transmission frequency and order; based on the control instruction, controlling the target device in the target construction site to handle the target scenario state. 2.The IoT-based smart construction site device control method of claim 1, wherein, The method of generating a dynamic environment map comprises: obtaining the static layout information of the target construction site to generate static mapping information; Based on the scenario data, a dynamic change factor is determined, and dynamic mapping information is generated; Based on the environmental data, environmental mapping information is generated. 3.The IoT-based smart construction site device control method of claim 1, wherein, Also includes: Based on the correlation information, the position of the perception node on which the target scenario state is uploaded and its adjacent perception nodes is controlled; Wherein, the perception node has a mobile ability, for adjusting its own physical position based on the correlation information; Based on the correlation information, the monitoring angle of the perception node is changed; Wherein, the perception node has an adjustable monitoring device.

4. The intelligent construction site equipment control system based on the Internet of Things, which executes the steps of the intelligent construction site equipment control method based on the Internet of Things according to any one of claims 1 to 3, characterized in that, Includes: A perception node unit is used to collect environmental data and scenario data of a target construction site in real time using a perception node network, and to generate a dynamic environmental map; wherein the target construction site includes multiple target areas, and each target area is equipped with at least one perception node; A scenario analysis unit is used to determine the scenario state of each target area based on the dynamic environmental map; A processing unit is used to generate a control instruction using the perception node provided by the target area in which the target scenario state exists in response to the existence of a target scenario state in the scenario state of the target area; A control unit is used to control the target equipment in the target construction site to handle the target scenario state based on the control instruction.

5. A computer device, comprising: Includes: A processor and a memory, the memory stores machine readable instructions executable by the processor, the processor is used to execute the machine readable instructions stored in the memory, and the machine readable instructions are executed by the processor. The processor executes the steps of the intelligent construction site equipment control method based on the Internet of Things as claimed in any one of claims 1 to 3.

Images