Building construction safety early warning system based on BIM and Internet of Things

Abstract

The invention relates to the technical field of building construction monitoring, in particular to a building construction safety early warning system based on BIM and Internet of Things, comprising: a monitoring system for acquiring various building construction safety monitoring data by integrating various sensors and monitoring equipment; the Internet of Things management system is used for managing the monitoring system and driving the monitoring system to perform building construction data acquisition according to a received data acquisition instruction; the early warning system is used for acquiring the building model data from the BIM database and performing safety risk early warning in combination with the building construction safety monitoring data; the task management system is used for extracting key detection data from the building model in the BIM database and generating a monitoring task instruction matched with the monitoring task according to the type of the key feature; and according to the monitoring data of the monitoring system and the early warning information of the early warning system, the priority and the execution sequence of the monitoring tasks are dynamically adjusted.

Description

Technical Field

[0001] The present invention relates to the technical field of building construction monitoring, and in particular to a building construction safety early warning system based on BIM and the Internet of Things. Background Art

[0002] With the rapid development of information technology, the construction industry is gradually transforming towards intelligence and digitalization. Traditional construction management methods have problems such as information asymmetry and poor communication, which can hardly meet the needs of modern construction projects for efficient and accurate management. The development of BIM technology and Internet of Things technology has provided new ideas and methods for solving these problems. For example, using BIM technology to simulate and optimize the construction process can detect potential problems in advance; using Internet of Things technology to realize real-time data collection at the construction site, including equipment status, construction process parameters, environmental parameters, etc.

[0003] However, in the process of combining BIM technology with IoT technology, the monitoring tasks performed by various sensors and video surveillance equipment connected to IoT are different. Some are used to monitor the construction process of building components in construction, and some are used to monitor the force and stability of building components (shear stress, etc.); some sensors can be used to perform multiple tasks at the same time. Due to the different data collection frequency, duration and data accuracy of different detection tasks. Therefore, how to match data and task types to ensure accurate prediction under different tasks is a problem that must be solved by the existing construction monitoring system. Summary of the invention

[0004] The present invention can identify various data parameters such as process parameters and worker behavior in construction, and issue early warnings for process parameter errors and worker construction behaviors. According to the early warning information, the priority of monitoring tasks is dynamically adjusted, corresponding monitoring tasks are performed first, corresponding early warnings are responded to, and construction quality is ensured.

[0005] The technical solution proposed by the present invention is: a construction safety early warning system based on BIM and the Internet of Things, comprising: A monitoring system, which obtains a variety of construction safety monitoring data by integrating a variety of sensors and monitoring equipment to ensure that the safety conditions of the construction site are monitored in real time; An Internet of Things management system, which is used to manage the monitoring system and drive the monitoring system to collect construction data according to the received data acquisition instructions; An early warning system is used to obtain building model data from the BIM database and, in combination with the building construction safety monitoring data obtained by the monitoring system, to issue early warnings for safety risks in building construction; A task management system, wherein the task management system is used to extract key detection data from a building model in a BIM database, extract key data features from the key detection data, and generate monitoring task instructions that match the monitoring task according to the type of the key features; The task management system is also used to dynamically adjust the priority and execution order of monitoring tasks according to the monitoring data of the monitoring system and the warning information of the warning system; the monitoring task instructions include data acquisition instructions, model call instructions and data reset instructions.

[0006] Preferably, the monitoring system comprises a video monitoring unit and a sensor unit, wherein the video monitoring unit is used to obtain video data of a construction process in a construction area, and the sensor unit is used to measure process parameters of the construction.

[0007] Preferably, the Internet of Things management system includes a monitoring layer, a gateway layer, a server layer and an application layer; Connecting the monitoring system through the monitoring layer, driving the sensor unit and the video monitoring unit to obtain the video data of the construction site and the process parameter data of the construction according to the received data acquisition instruction; The gateway layer obtains the data obtained by the monitoring layer, packages them into data packets, and sends the data packets to the central server; Receive data packets through the server layer, assign time tags to the data packets, unpack the data packets, and pre-process the unpacked data to form a monitoring data set; The application layer is used to provide a user interface, through which the acquired monitoring data set is displayed.

[0008] Preferably, the early warning system is used to obtain building model data from the BIM database, which is specifically achieved through the following steps: Obtain the corresponding building model from the BIM database through an API interface or database query voice, and extract building data from the building model, wherein the building data includes geometric information, material properties, and structural information of the building; Clean, format and process missing values ​​of the acquired building data to form a reference data set; Extracting a plurality of key parameter features from a reference data set to form a key reference feature data set, wherein the key parameter features include key building components and the size, weight and material type of each key component; Based on the key parameter characteristics obtained, the stress distribution and deformation data of each component are calculated and obtained, and the stress distribution characteristics are extracted from the stress distribution, and the deformation characteristics are extracted from the deformation data; The acquired stress distribution features and deformation features are merged with the key reference feature data set to form a reference feature data set.

[0009] Preferably, the construction safety monitoring data obtained by the monitoring system is combined to warn of safety risks in construction, which is specifically achieved through the following steps: Extracting multiple video frames from the video data, and preprocessing the obtained multiple video frames; Extracting key building features from video frames using computer vision technology to form a video feature dataset; the key features include the shape of building components, worker behavior, and equipment status; Extracting parameter key data features from the process parameters of the building construction to form a sensor feature data set, wherein the key data features include size data of the building components and the positions of the building components; Extracting the size data of the corresponding building components from the data in the reference feature data set and comparing them with the size data of the corresponding building components in the sensor feature data set, and determining whether the comparison result exceeds an error threshold; If yes, it is judged that the construction process parameters do not meet the requirements and an alarm message is output; Extracting worker behavior features corresponding to the construction of building components from the video feature dataset; The alarm information, worker behavior characteristics, and building component shape and size information are input into the pre-trained random forest model, the risk level of the worker behavior is output, and the corresponding early warning information is generated according to the risk level.

[0010] Preferably, extracting worker behavior features corresponding to the construction of building components from the video feature data set comprises the following steps: Acquire multiple continuous video frames, and extract texture and shape features of the image by calculating the gradient direction histogram of the local area of ​​each video frame image; the video frames include images of construction workers and images of constructed building components; The texture and image features of the acquired image are input into the pre-trained random forest SVM model, and the posture features of the worker are recognized through the SVM model; The worker's motion trajectory is generated through the inter-frame difference method or the optical flow method.

[0011] Preferably, the step of inputting the alarm information, the worker behavior characteristics, and the shape and size information of the building components into a pre-trained random forest model and outputting the risk level of the worker behavior comprises: Acquire alarm information, including alarm type, alarm time and alarm location; Acquire worker behavior characteristics, where the worker behavior characteristics include direction, speed, standard deviation of the direction of movement, maximum speed, and minimum speed of the worker's movement; Acquire shape and size information of building components, wherein the shape and size information of building components includes length, width, height, and thickness of the building components; Extracting component shape change characteristics from component shape and size information, including component size change rate and component size change direction; The alarm information, the standard deviation of the worker's action direction, the direction of component size change, and the component size change rate are input into the pre-trained random forest model, and the worker's behavior risk is predicted by the random forest model, and the behavior risk is divided into multiple behavior risk levels; The behavioral risk levels include low risk, medium risk, and high risk.

[0012] Preferably, the task management system includes a task scheduling module, a data extraction module and a result storage module; The task management system is used to extract key inspection data from the building model in the BIM database through the following process: Extracting key inspection data from the building model in the BIM database through a data extraction module, wherein the key inspection data includes the size of the building component, the material of the building component, and the deformation of the building component; The step of extracting key data features from key detection data and generating monitoring task instructions matching the monitoring task according to the type of the key features includes: The extracted key test data is stored in the result storage module, and the key test data is classified as follows: The sensors are divided into sensors for structural monitoring and sensors for deformation monitoring; The sensor's measurement data is divided into data for structure monitoring and data for deformation monitoring; The task scheduling module generates monitoring task instructions that match the measurement data type, and adds the corresponding sensor ID and video device ID in each monitoring task instruction, so that the sensors and video devices in the video monitoring unit and sensor unit receive the monitoring task instructions that match their own ID information; The monitoring task instructions include structure monitoring task instructions and deformation monitoring task instructions.

[0013] Preferably, the task management system is also used to dynamically adjust the priority and execution order of the monitoring tasks according to the monitoring data of the monitoring system and the warning information of the warning system, including: Obtain construction safety monitoring data through the monitoring system, and obtain risk level information and corresponding warning information through the early warning system; Obtain the task type currently executed by the monitoring system through the task scheduling module; If the worker's behavior risk level is medium risk or high risk, the priority of the structural monitoring task is adjusted to give priority to the structural monitoring task; If the worker's behavior risk level is low, the existing detection task execution order is maintained.

[0014] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the construction safety early warning system based on BIM and the Internet of Things.

[0015] Beneficial effects of the present invention: 1. In the present invention, the monitoring system obtains a variety of construction safety monitoring data by integrating a variety of sensors and monitoring equipment to ensure that the safety status of the construction site is monitored in real time. The system uses the Internet of Things management system to manage the monitoring process, generates corresponding instructions based on the received data, and then drives the monitoring system to perform the collection of construction data. In addition, the early warning system can extract building model data from the BIM database and combine it with the construction safety monitoring data collected by the monitoring system to issue early warnings for potential construction safety risks.

[0016] 2. In the present invention, the risk level information obtained is used to determine the worker's behavioral risk level. If the worker's behavioral risk level is medium risk or high risk, find a structural monitoring task and adjust its priority to high. Otherwise, maintain the existing detection task execution order. After adjusting the priority, the task scheduling module will rearrange the execution of the task according to the new priority order. High-priority tasks will be preferentially allocated to available resources to ensure that they can be processed quickly. During the execution of the task, the monitoring system will continue to collect data and provide real-time feedback to the task management system and early warning system. If the risk level changes, the priority and execution order of the task will be adjusted again to adapt to the new safety situation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a structural block diagram of a building construction safety early warning system based on BIM and the Internet of Things in the present invention.

[0018] Figure 2 This is a flow chart of the present invention for early warning of safety risks in building construction. DETAILED DESCRIPTION

[0019] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0020] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0021] refer to Figure 1 ,The technical solution provided by the present invention is: a construction safety early warning system based on BIM and the Internet of Things, including: a monitoring system, an Internet of Things management system, an early warning system and a task management system; The monitoring system integrates multiple sensors and monitoring equipment to obtain a variety of construction safety monitoring data to ensure that the safety status of the construction site is monitored in real time; The monitoring system includes a video monitoring unit and a sensor unit. The video monitoring unit is used to obtain video data of the construction process in the construction area, and the sensor unit is used to measure the process parameters of the construction. Specifically, the sensor unit includes a distance sensor, a temperature sensor, a pressure sensor, an angle sensor, a shear force sensor, etc.; the video monitoring unit includes a high-definition camera, a thermal imager, etc.

[0022] The Internet of Things management system is used to manage the monitoring system and drive the monitoring system to collect construction data according to the received data acquisition instructions; the Internet of Things management system includes a monitoring layer, a gateway layer, a server layer and an application layer.

[0023] The monitoring system is connected through the monitoring layer, and the monitoring layer receives the monitoring task instruction, extracts the sensor ID and the video device ID from the monitoring task instruction, drives the sensor inside the sensor unit and the video device in the video monitoring unit to obtain the video data of the construction site and the process parameter data of the construction; obtains the data obtained by the monitoring layer through the gateway layer, packages it into a data packet, and sends the data packet to the central server; receives the data packet through the server layer, assigns a time tag to the data packet, unpacks the data packet, pre-processes the unpacked data, and constitutes a monitoring data set; the application layer is used to provide a user interface, and the acquired monitoring data set is displayed through the user interface.

[0024] The early warning system is used to obtain building model data from the BIM database and combine it with the construction safety monitoring data obtained by the monitoring system to issue early warnings for safety risks in construction; The task management system is used to extract key detection data from the building model in the BIM database, extract key data features from the key detection data, and generate monitoring task instructions that match the monitoring tasks according to the types of key features; The task management system can also be used to dynamically adjust the priority and execution order of monitoring tasks based on the monitoring data of the monitoring system and the warning information of the warning system; the monitoring task instructions include data acquisition instructions, model call instructions and data reset instructions.

[0025] The early warning system can obtain building model data from the BIM database through the following steps: The corresponding building model is obtained from the BIM database through the API interface or database query voice, and the building data is extracted from the building model. The building data includes the building's geometric information, material properties, and structural information; the obtained building data is cleaned, formatted, and missing values ​​are processed to form a reference data set.

[0026] Extracting a plurality of key parameter features from a reference data set to form a key reference feature data set, wherein the key parameter features include key building components and the size, weight and material type of each key component; Based on the acquired key parameter characteristics, the stress distribution and deformation data of each component are calculated and acquired, and the stress distribution characteristics are extracted from the stress distribution, and the deformation characteristics are extracted from the deformation data; the acquired stress distribution characteristics and deformation characteristics are merged with the key reference feature data set to form a reference feature data set.

[0027] The early warning system combines the construction safety monitoring data obtained by the monitoring system to warn of safety risks in construction. This is achieved through the following steps: Extracting multiple video frames from the video data, and preprocessing the obtained multiple video frames; Extract key building features from video frames using computer vision technology (such as OpenCV) to form a video feature dataset; the key features include building component shapes, worker behaviors, and equipment status; match the shapes of the identified building components with the building models in the BIM database, extract components that match the real components from the model, and extract process parameters of the corresponding components from the BIM database; Extracting parameter key data features from the acquired process parameters to form a sensor feature data set, wherein the key data features include size data of the building component and the position of the building component; Extracting the size data of the corresponding building components from the data in the reference feature data set and comparing them with the size data of the corresponding building components in the sensor feature data set, and determining whether the comparison result exceeds an error threshold; If yes, it is judged that the construction process parameters do not meet the requirements and an alarm message is output; Extracting worker behavior features corresponding to the construction of building components from the video feature dataset; The alarm information, worker behavior characteristics, and building component shape and size information are input into the pre-trained random forest model, the risk level of the worker behavior is output, and the corresponding early warning information is generated according to the risk level.

[0028] The early warning system can also extract worker behavior features corresponding to the construction of building components from the video feature dataset, including the following steps: Acquire multiple continuous video frames, and extract texture and shape features (HOG features) of the image by calculating the gradient direction histogram of the local area of ​​each video frame image; the video frames include images of construction workers and images of constructed building components; The texture and image features of the acquired image are input into the pre-trained random forest SVM model, and the posture features of the worker are recognized through the SVM model; The worker's motion trajectory is generated by the inter-frame difference method or the optical flow method. The motion trajectory here includes the motion trajectories of different parts of the worker's body, such as the motion trajectory of the arm, the motion trajectory of the upper body and the motion trajectory of the leg. The motion state of the tool used by the worker can be analyzed from the motion trajectory of the arm; the direction of the worker's force during construction can be analyzed from the motion trajectory of the upper body; and the direction of the worker's movement during construction (close to the building components and away from the building components) can be analyzed from the motion trajectory of the leg.

[0029] The alarm information, worker behavior characteristics, and building component shape and size information are input into the pre-trained random forest model to output the risk level of the worker behavior, including: Get alarm information, which includes alarm type, alarm time and alarm location; the alarm location is the location of the sensor and video surveillance equipment, which can be indirectly obtained through the sensor ID and video device ID. If the sensor and video device used have positioning functions, the positioning information of the sensor and video device can be directly queried to obtain the alarm location data.

[0030] Acquire worker behavior characteristics, where the worker behavior characteristics include direction, speed, standard deviation of the direction of movement, maximum speed, and minimum speed of the worker's movement; Acquire shape and size information of building components, wherein the shape and size information of building components includes length, width, height, and thickness of the building components; Extracting component shape change characteristics from component shape and size information, including component size change rate and component size change direction; The alarm information, the standard deviation of the worker's movement direction, the direction of component size change and the rate of component size change are input into the pre-trained random forest model. The worker's behavior risk is predicted by the random forest model and divided into multiple behavior risk levels; the behavior risk levels include low risk, medium risk and high risk. Among them, the low risk level means that the worker's construction behavior basically meets the construction requirements and has little impact on the structural size error of the component; the medium risk level means that some of the worker's construction behavior does not meet the construction requirements, such as the arm movement speed when drilling, the angle between the arm and the wall, etc., which will affect the hole depth and the drilling angle; the high risk level means that the worker's construction behavior contains construction behaviors that are clearly prohibited in the construction manual.

[0031] In this embodiment, the task management system includes a task scheduling module, a data extraction module and a result storage module; The task management system is used to extract key inspection data from the building model in the BIM database, which is achieved by the following process: extracting key inspection data from the building model in the BIM database through a data extraction module, wherein the key inspection data includes the size of the building component, the material of the building component and the deformation of the building component; The step of extracting key data features from key detection data and generating monitoring task instructions matching the monitoring task according to the type of the key features includes: The extracted key detection data is stored in the result storage module, and the key detection data is classified, specifically: the sensors are divided into structural monitoring sensors and deformation monitoring sensors; the sensor's measurement data is divided into structural monitoring data and deformation monitoring data; the task scheduling module generates monitoring task instructions that match the measurement data type, and adds the corresponding sensor ID and video monitoring unit in each monitoring task instruction, so that each sensor receives a monitoring task instruction that matches its own ID information; the monitoring task instructions include structural monitoring task instructions and deformation monitoring task instructions.

[0032] In some preferred embodiments, the task management system is also used to dynamically adjust the priority and execution order of the monitoring tasks according to the monitoring data of the monitoring system and the warning information of the warning system, including: The monitoring system is used to obtain construction safety monitoring data, and the early warning system is used to obtain risk level information and corresponding early warning information; the task type currently executed by the monitoring system is obtained through the task scheduling module.

[0033] The risk level information obtained is used to determine the worker's behavior risk level. If the worker's behavior risk level is medium risk or high risk, the task list is traversed to find the structure monitoring task and adjust its priority to high.

[0034] If the worker's behavior risk level is low risk, the existing detection task execution order is maintained. After adjusting the priority, the task scheduling module will reschedule the execution of tasks according to the new priority order. High-priority tasks will be allocated to available resources, such as personnel, equipment, etc., to ensure that they can be processed quickly.

[0035] During the execution of the task, the monitoring system will continue to collect data and provide real-time feedback to the task management system and early warning system. If the risk level changes, the system will adjust the priority and execution order of the task again to adapt to the new security situation.

[0036] The present invention also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the construction safety early warning system based on BIM and the Internet of Things.

[0037] In the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium mentioned above in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0038] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0039] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be subject to any changes or modifications.

Claims

1. A construction safety early warning system based on BIM and the Internet of Things, characterized in that: include: A monitoring system, which obtains a variety of construction safety monitoring data by integrating a variety of sensors and monitoring equipment to ensure that the safety conditions of the construction site are monitored in real time; An Internet of Things management system, which is used to manage the monitoring system and drive the monitoring system to collect construction data according to the received data acquisition instructions; An early warning system is used to obtain building model data from the BIM database and, in combination with the building construction safety monitoring data obtained by the monitoring system, to issue early warnings for safety risks in building construction; A task management system, the task management system is used to extract key detection data from the building model in the BIM database, extract key data features from the key detection data, and generate monitoring task instructions matching the monitoring tasks according to the types of key features; The task management system is also used to dynamically adjust the priority and execution order of monitoring tasks according to the monitoring data of the monitoring system and the warning information of the warning system; the monitoring task instructions include data acquisition instructions, model call instructions and data reset instructions.

2. The construction safety early warning system based on BIM and the Internet of Things according to claim 1 is characterized in that: The monitoring system comprises a video monitoring unit and a sensor unit. The video monitoring unit is used to obtain video data of a construction process in a construction area, and the sensor unit is used to measure process parameters of the construction.

3. The construction safety early warning system based on BIM and the Internet of Things according to claim 2 is characterized in that: The Internet of Things management system includes a monitoring layer, a gateway layer, a server layer and an application layer; Connecting the monitoring system through the monitoring layer, driving the sensor unit and the video monitoring unit to obtain the video data of the construction site and the process parameter data of the construction according to the received data acquisition instruction; The gateway layer obtains the data obtained by the monitoring layer, packages them into data packets, and sends the data packets to the central server; Receive data packets through the server layer, assign time tags to the data packets, unpack the data packets, and pre-process the unpacked data to form a monitoring data set; The application layer is used to provide a user interface, through which the acquired monitoring data set is displayed.

4. The construction safety early warning system based on BIM and the Internet of Things according to claim 3 is characterized in that: The early warning system is used to obtain building model data from the BIM database, which is specifically implemented through the following steps: Obtain the corresponding building model from the BIM database through an API interface or database query voice, and extract building data from the building model, wherein the building data includes geometric information, material properties, and structural information of the building; Clean, format and process missing values ​​of the acquired building data to form a reference data set; Extracting a plurality of key parameter features from a reference data set to form a key reference feature data set, wherein the key parameter features include key building components and the size, weight and material type of each key component; Based on the key parameter characteristics obtained, the stress distribution and deformation data of each component are calculated and obtained, and the stress distribution characteristics are extracted from the stress distribution, and the deformation characteristics are extracted from the deformation data; The acquired stress distribution features and deformation features are merged with the key reference feature data set to form a reference feature data set.

5. The construction safety early warning system based on BIM and the Internet of Things according to claim 4 is characterized in that: The construction safety monitoring data obtained by the monitoring system is combined to provide early warning of safety risks in construction, which is specifically achieved through the following steps: Extracting multiple video frames from the video data, and preprocessing the obtained multiple video frames; Extracting key building features from video frames using computer vision technology to form a video feature dataset; the key features include the shape of building components, worker behavior, and equipment status; Extracting parameter key data features from the process parameters of the building construction to form a sensor feature data set, wherein the key data features include size data of the building components and the positions of the building components; Extracting the size data of the corresponding building components from the data in the reference feature data set and comparing them with the size data of the corresponding building components in the sensor feature data set, and determining whether the comparison result exceeds an error threshold; If yes, it is judged that the construction process parameters do not meet the requirements and an alarm message is output; Extracting worker behavior features corresponding to the construction of building components from the video feature dataset; The alarm information, worker behavior characteristics, and building component shape and size information are input into the pre-trained random forest model, the risk level of the worker behavior is output, and the corresponding early warning information is generated according to the risk level.

6. The construction safety early warning system based on BIM and the Internet of Things according to claim 5 is characterized in that: The step of extracting worker behavior features corresponding to the construction of building components from the video feature data set comprises the following steps: Acquire multiple continuous video frames, and extract texture and shape features of the image by calculating the gradient direction histogram of the local area of ​​each video frame image; the video frames include images of construction workers and images of constructed building components; The texture and image features of the acquired image are input into the pre-trained random forest SVM model, and the posture features of the worker are recognized through the SVM model; The worker's motion trajectory is generated through the inter-frame difference method or the optical flow method.

7. The construction safety early warning system based on BIM and the Internet of Things according to claim 6 is characterized in that: The alarm information, worker behavior characteristics, and building component shape and size information are input into the pre-trained random forest model to output the risk level of the worker behavior, including: Acquire alarm information, including alarm type, alarm time and alarm location; Acquire worker behavior characteristics, where the worker behavior characteristics include direction, speed, standard deviation of the direction of movement, maximum speed, and minimum speed of the worker's movement; Acquire shape and size information of building components, wherein the shape and size information of building components includes length, width, height, and thickness of the building components; Extracting component shape change characteristics from component shape and size information, including component size change rate and component size change direction; The alarm information, the standard deviation of the worker's action direction, the direction of component size change, and the component size change rate are input into the pre-trained random forest model, and the worker's behavior risk is predicted by the random forest model, and the behavior risk is divided into multiple behavior risk levels; The behavioral risk levels include low risk, medium risk, and high risk.

8. The construction safety early warning system based on BIM and the Internet of Things according to claim 7 is characterized in that: The task management system includes a task scheduling module, a data extraction module and a result storage module; The task management system is used to extract key inspection data from the building model in the BIM database through the following process: Extracting key inspection data from the building model in the BIM database through a data extraction module, wherein the key inspection data includes the size of the building component, the material of the building component, and the deformation of the building component; The step of extracting key data features from key detection data and generating monitoring task instructions matching the monitoring task according to the type of the key features includes: The extracted key test data is stored in the result storage module, and the key test data is classified as follows: The sensors are divided into sensors for structural monitoring and sensors for deformation monitoring; The sensor's measurement data is divided into data for structure monitoring and data for deformation monitoring; The task scheduling module generates monitoring task instructions that match the measurement data type, and adds the corresponding sensor ID and video device ID in each monitoring task instruction, so that the sensors and video devices in the video monitoring unit and sensor unit receive monitoring task instructions that match their own ID information; the monitoring task instructions include structure monitoring task instructions and deformation monitoring task instructions.

9. The construction safety early warning system based on BIM and the Internet of Things according to claim 1 is characterized in that: The task management system is also used to dynamically adjust the priority and execution order of the monitoring tasks according to the monitoring data of the monitoring system and the warning information of the warning system, including: Obtain construction safety monitoring data through the monitoring system, and obtain risk level information and corresponding warning information through the early warning system; Obtain the task type currently executed by the monitoring system through the task scheduling module; If the worker's behavior risk level is medium risk or high risk, the priority of the structural monitoring task is adjusted to give priority to the structural monitoring task; If the worker's behavior risk level is low, the existing detection task execution order is maintained.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a building construction safety early warning system based on BIM and the Internet of Things as described in any one of claims 1 to 9.

Images