Safety control method, device and system for EPC engineering intelligent construction site

Abstract

The invention relates to an intelligent construction site management technology, discloses a safety management and control method, device and system for an EPC engineering intelligent construction site, and improves the recognition accuracy of the wearing state of a safety device in the actual operation process of constructors. The security management and control method comprises the following steps: sending a broadcast instruction to an unmanned aerial vehicle, wherein the broadcast instruction is used for controlling the unmanned aerial vehicle to broadcast a data extraction instruction; receiving wearing data of each worker sent by the unmanned aerial vehicle, the wearing data including an identity label of the worker and a state time sequence, and the state time sequence representing timeline information of the worker wearing the safety device; the wearing data of all the workers are analyzed, whether historical violation persons exist or not is determined, and the historical violation persons are workers who do not wear safety devices after the last inspection tour moment; the to-be-detected images sent by the unmanned aerial vehicle are received, the to-be-detected images are analyzed, whether immediate violation personnel exist or not is determined, and the immediate violation personnel are workers who do not wear the safety device at present.

Description

Technical Field

[0001] The present invention relates to smart construction site management technology, and in particular to a safety management and control method, device and system for EPC project smart construction sites. Background Art

[0002] With the acceleration of my country's urbanization and the continued advancement of infrastructure construction, the engineering general contracting (EPC) model, a new construction project contracting model that effectively integrates upstream and downstream resources and breaks through the limitations of traditional contracting models, is seeing increasing adoption. EPC projects typically feature diverse project types, tight construction deadlines, widely dispersed work areas, complex section divisions, high mobility of personnel and equipment, and volatile on-site environments. These characteristics pose significant challenges to safety supervision and control during construction, making them a core task throughout the entire project lifecycle.

[0003] In recent years, with the increasing maturity of IoT technology and the country's promotion of the digital technology industry, the concept of "smart construction sites" has gradually penetrated the construction industry. Its advocated information-based, digital, standardized, and intelligent management and control methods have demonstrated significant results in improving mechanical operation safety, personnel operating standards, and construction process compliance. For example, BIM (Building Information Modeling) technology can be used to simulate pipeline conflicts during construction and provide early warnings. Image processing technology can be used to analyze construction site images to screen for personnel not wearing safety equipment such as hard hats and reflective clothing. These have become typical application scenarios for smart construction sites.

[0004] However, existing technologies still have shortcomings in identifying when safety devices are worn. For example, Chinese patent application CN202310382275.5 proposes a method for identifying helmets using drone-captured images. However, construction sites are complex environments, and it's not uncommon for some workers to temporarily wear helmets during drone inspections and then remove them immediately afterward. Relying solely on drone-captured images for identification struggles to capture actual helmet wear at all times and in all scenarios, leading to missed or misidentified helmets and severely impacting the accuracy and effectiveness of safety management.

[0005] Therefore, how to break through the limitations of existing technologies and improve the accuracy of identifying the status of construction workers wearing safety devices during actual operations has become a technical problem that needs to be urgently solved in the field of smart construction site safety management. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a safety management and control method, device and system for EPC engineering smart construction sites, so as to improve the accuracy of identifying the wearing status of safety devices during the actual operation of construction personnel.

[0007] The technical solution adopted by the present invention to solve the above technical problems is: In one aspect, the present invention provides a safety management and control method for an EPC project smart site, comprising: When the drone is in the inspection state, a broadcast instruction is sent to the drone; the broadcast instruction is used to control the drone to broadcast data extraction instructions externally; In response to a data transmission request from the drone, receiving wear data of each worker transmitted by the drone; wherein the wear data is sent to the drone by the safety device worn by each worker after receiving a data extraction instruction, and the wear data includes the worker's identity and a state time series, wherein the state time series is used to represent the time history of the worker wearing the safety device; Analyze each worker's wearing data to determine whether there are any historical violators; historical violators refer to workers who have not worn safety devices since the last inspection; Receive the images to be detected sent by the drone and analyze each image to determine whether there are any immediate violators; the images to be detected are images collected by the drone at the construction site, and immediate violators are workers who are not currently wearing safety equipment.

[0008] Furthermore, the wearable data of each worker is analyzed to determine whether there are any historical violators, including: For the wear data of each worker, extract a state time series in the wear data; Determining a removal time period for a worker to remove the safety device based on the state time series; According to the removal time period, it is determined whether the worker corresponding to the corresponding identity identifier in the wearing data is a person with a history of violating regulations.

[0009] Furthermore, the wearing data also includes a position sequence for characterizing the relationship between position and time; The determining, based on the removal time period, whether the worker corresponding to the corresponding identity identifier in the wearing data is a person with a history of violating regulations includes: Determining, from the position sequence, position information corresponding to the removal time period; determining an effective removal time according to the position information corresponding to the removal time period, wherein the effective removal time represents a time period for a worker to remove the safety device at the construction site; According to the effective removal time, it is determined whether the worker corresponding to the corresponding identity identifier in the wearing data is a person with a history of violating regulations.

[0010] Furthermore, determining whether the worker corresponding to the corresponding identity identifier in the wearing data is a person with a history of violating the law based on the effective removal time includes: If it is determined that the effective removal time exceeds the time threshold, the identity identifier in the wearing data is extracted, and the worker corresponding to the identity identifier is determined as a historical violator; the time threshold is dynamically set based on the average temperature in the current detection period.

[0011] Furthermore, before receiving the image to be detected sent by the drone, the following steps are also included: Sending a position acquisition instruction to the drone, wherein the position acquisition instruction is used to control the drone to broadcast a position acquisition request to obtain the real-time position feedback from each safety device; The real-time position of each safety device sent by the drone is obtained, and an image acquisition instruction is generated based on the real-time position and sent to the drone. The image acquisition instruction is used to control the drone to collect images to be detected at the construction site.

[0012] Furthermore, the method further comprises: A clear command is sent to the drone, where the clear command is used to control the drone to broadcast a data deletion command. After the data deletion command is received by the safety device, it is used to delete the wearing data stored in the safety device.

[0013] Furthermore, the method further comprises: When it is determined that there is a historical offender or an immediate offender, determining the target position of the offender from the position sequence of the offender; Based on the target location and the installation locations of various audio devices at the construction site, determining a target audio device closest to the target location; The voice warning data is sent to the target audio device, and the voice warning data is played by the target audio device.

[0014] In a second aspect, the present invention further provides a safety control device for an EPC engineering smart construction site, comprising: The command sending module is used to send broadcast commands to the drone when the drone is in the inspection state. The broadcast commands are used to control the drone to broadcast data extraction commands; a receiving module, configured to respond to a data transmission request from a drone to receive wear data of each worker sent by the drone, wherein the wear data is sent to the drone by the safety device corresponding to each worker in response to a data extraction instruction; the wear data includes the worker's identity and a state time series, wherein the state time series represents the timeline information of the worker wearing the safety device; and to receive images to be detected sent by the drone, wherein the images to be detected are images captured by the drone at the construction site; The analysis module is used to analyze the wearing data of each worker to determine whether there are any historical violators. Historical violators are workers who have not worn safety devices since the last inspection. It is also used to analyze each image to be detected to determine whether there are any immediate violators. Immediate violators are workers who are not currently wearing safety devices.

[0015] In a third aspect, the present invention further provides a safety management and control system for an EPC project smart construction site, comprising: a safety device, a drone, and a computer device; the safety device is a safety helmet and / or reflective clothing, and is provided with a trigger sensor and a memory, the trigger sensor being used to detect whether a worker is wearing the safety device, and the memory being used to store data collected by the trigger sensor; The drone communicates with the security device and the computer device respectively to respond to instructions from the computer device and broadcast corresponding instructions to the security device; The computer device is used to execute the aforementioned security management and control method.

[0016] Furthermore, the safety device further includes a position sensor, which is used to collect the position of the safety device and store the position information in the memory.

[0017] The beneficial effects of the present invention are: (1) Improve the accuracy of safety device wearing recognition: By combining the wear data (including status time series) stored in safety devices with the images to be inspected captured by drones, dual identification of "historical violators" (those who have not been wearing safety devices since the last inspection) and "immediate violators" (those who are not currently wearing safety devices) is achieved. This not only avoids missed and misidentified issues caused by individuals temporarily wearing and then removing safety devices when relying solely on drone images, but also fills the control gaps between inspections through historical data tracing, significantly improving the accuracy of identifying personnel not wearing safety devices during actual construction.

[0018] (2) Optimizing the rationality of violation determination: By matching the position sequence with the removal and unloading time period, the effective removal and unloading time of workers on the construction site is screened out, and the time threshold is dynamically set in combination with the average temperature. Only removal and unloading behaviors that exceed the reasonable range are judged as violations, reducing misjudgments caused by non-violation behaviors such as temporary adjustments to safety devices (such as wiping sweat, adjusting wearing posture), making management and control more in line with actual construction scenarios.

[0019] (3) Achieve full-cycle and precise management and control: With the help of the status time series and position series of the safety device, the workers' wearing of the safety device in the interval between two inspections can be traced, realizing safety management and control of the entire construction period; at the same time, based on the location information of the violators, the nearest audio device is matched to issue voice warnings, realizing targeted and accurate reminders, and improving the timeliness and effectiveness of safety management and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the application environment of the security management and control method in one embodiment.

[0021] Figure 2 A flowchart of a security management method in one embodiment.

[0022] Figure 3 The figure is a flowchart of determining historical offenders in one embodiment.

[0023] Figure 4 2 is a structural block diagram of a security management and control device in an embodiment.

[0024] Figure 5 2 is a structural block diagram of a security management and control system in one embodiment.

[0025] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0026] The present invention aims to provide a safety management and control method, device, and system for EPC engineering smart construction sites, which can improve the accuracy of identifying the safety device wearing status of construction workers during actual operations. The core concept is: When the drone enters the inspection state, the computer sends a broadcast command to it, which then broadcasts a data extraction command. Upon receiving this command, the safety device sends its stored wear data, including the worker's identity, status time series, and location series, to the drone, which then transmits it to the computer. The computer analyzes this data, determining the time period during which the worker removed the safety device based on the status time series. Combining this with the location series, it determines whether the removal occurred within the construction site and calculates the effective removal duration to determine whether there are any historical violators. Simultaneously, the system sends a command to the drone to obtain the current location of the safety device. Based on this location information, it generates an image capture command, which the drone uses to capture images of the construction site to be inspected and transmits back to the computer. The computer analyzes the images and identifies any current violators who are not wearing their safety devices. Once a violator is identified, the computer determines their location from the location series and, based on the location of various audio devices on the construction site, identifies the audio device closest to the target location and sends a voice alert to that device.

[0027] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0028] The safety control method for EPC engineering smart construction sites provided in the embodiments of the present application can be applied to Figure 1 In the application environment shown, safety device 102 communicates with drone 104 via an RFID (radio frequency identification) module. Safety device 102 can be, but is not limited to, a safety helmet and reflective vest. It can also be other safety devices such as a safety rope and a safety hook. Drone 104 can communicate with computer device 106 via a network. Drone 104 can respond to instructions from computer device 106 by broadcasting corresponding instructions and collecting data.

[0029] Computer device 106 includes, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, smart car devices, and projectors. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Head-mounted devices may include virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Computer device 106 may also be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0030] In specific applications, the above security control method can be implemented in the form of a software program, which is loaded into Figure 1 In the computer device 106, the execution process is shown in FIG. Figure 2 , including steps 110 to 140: Step 110: When the UAV is in the inspection state, a broadcast instruction is sent to the UAV, where the broadcast instruction is used to control the UAV to broadcast data extraction instructions.

[0031] In an embodiment of the present application, a computer device issues an inspection instruction to a drone, wherein the inspection instruction includes inspection route data, which is composed of a position sequence of each inspection point. The drone receives the inspection instruction and parses it to obtain the inspection route data, and then performs an inspection task on the construction site based on the inspection route data. The drone communicates with the computer device in real time and reports its real-time location information. When the computer device determines that the drone has arrived at the first inspection point on the inspection route, the computer device sends a broadcast instruction to the drone. The drone receives the broadcast instruction and broadcasts a data extraction instruction via the RFID module. The data extraction instruction can be received by the safety device of each worker within the communication range of the RFID module.

[0032] Step 120: respond to the data transmission request of the drone to receive the wearing data of each worker sent by the drone.

[0033] For the embodiment of the present application, workers at the construction site are required to wear safety devices, and the safety devices are provided with an RFID module, a trigger sensor, an instruction processing module, a memory, etc.; the trigger sensor is used to detect whether the worker is wearing a safety device, and the memory is used to store the data collected by the trigger sensor, and these data are stored in the form of a state time series and associated with the identity of the worker corresponding to the safety device, wherein the state time series includes each moment when the worker starts to wear the safety device, and the moment when the safety device is removed; the RFID module is used to send and receive instructions / data, and the instruction processing module is used to process instructions and perform corresponding operations. When the RFID module in the safety device receives a data extraction instruction, it sends the data extraction instruction to the instruction processing module, and the instruction processing module uses the state time series stored in the memory and the identity of the worker as wearing data, and sends it to the drone through the RFID module. The drone sends the received wearing data of each safety device to the computer device through the network.

[0034] Step 130: Analyze the wearing data of each worker to determine whether there are any historical violators. Historical violators are workers who have not worn safety devices since the last inspection.

[0035] In the embodiment of the present application, the computer device analyzes the wear data received for each worker. First, the wear data is parsed to extract the state time series in the wear data, and determine whether there is a moment representing the removal of the safety device in the state time series; if not, further analysis of the state time series is abandoned, that is, it is determined that the worker corresponding to the wear data is not a historical violator; if there is a moment representing the removal of the safety device in the state time series, but it cannot be immediately determined that the worker corresponding to the wear data is definitely a historical violator, it is necessary to further analyze the state time series to determine whether the worker corresponding to the wear data is a historical violator. The specific analysis method will be described in detail in the subsequent description. Figure 3 Provide explanation.

[0036] Step 140: Receive the images to be detected sent by the drone, and analyze each image to be detected to determine whether there are any immediate violators; the images to be detected are images collected by the drone at the construction site, and the immediate violators are workers who are not currently wearing safety equipment.

[0037] In an embodiment of the present application, a computer device sends corresponding image acquisition instructions to a drone to capture images of the construction site. After capturing the images of the construction site, the drone sends the captured images to the computer device as images to be detected by the computer device. The computer device retrieves a pre-trained neural network-based recognition model, inputs the images to be detected into the recognition model, and obtains a recognition result, including whether there is a human target not wearing a safety device. The computer device then determines whether there are any immediate violators at the construction site based on the recognition model's recognition results for each image to be detected.

[0038] In addition, as a further optimization solution, after confirming that the drone has transmitted all the wearable data to the computer device, an image acquisition instruction can be sent to the drone. In this way, the images collected by the drone can avoid being transmitted to the computer device at the same time as the wearable data, thereby reducing the chance of data packet loss caused by data transmission congestion and improving the efficiency and integrity of data transmission.

[0039] In the above-mentioned safety management and control method for EPC project smart construction sites, since the last inspection time, the safety device temporarily stores the status time series of workers wearing and removing the safety device; when the drone is in the inspection state, the drone is controlled by the broadcast instruction sent by the computer device and broadcasts the data extraction instruction; the safety device responds to the data extraction instruction and sends the wearing data including the identity identification and the status time series to the drone. The drone sends the wearing data of each safety device to the computer device for analysis, so as to analyze whether there are historical violators who have not worn the safety device since the last inspection time; and by further obtaining the image to be detected collected by the drone for analysis of the construction site, it is determined whether there are immediate violators who are not wearing the safety device based on the real-time on-site image; through the safety management and control method of the present application, not only can the historical data in the safety device be extracted and the historical violators with historical violations be analyzed, but also the immediate violators with real-time violations can be analyzed by analyzing the image, which can reduce the missed identification of historical violations and thus improve the accuracy of identifying people who are actually not wearing safety devices.

[0040] In one embodiment, after the drone transmits all wearable data to the computer device, it sends an identification code indicating that the wearable data has been sent. The computer device determines that the drone's task of sending the wearable data is complete based on the identification code. As a further optimization solution, the security management method provided in this application also includes: sending a clear command to the drone. The clear command is used to control the drone to broadcast a data deletion command. After the data deletion command is received by the security device, it is used to delete the wearable data stored in the security device.

[0041] Because the wear data stored in the safety devices has already been forwarded by the drone to the computer for analysis, this data will no longer be used. However, the memory space in the safety devices is limited. Therefore, after the drone communicates with the computer and confirms that the computer has received the wear data forwarded by the drone for each safety device, the drone broadcasts a clear command. Upon receiving the clear command, these safety devices clear the data stored in their memories, thus making room for subsequent data.

[0042] In one embodiment, in step 130, the wear data of each worker is analyzed to determine whether there are any historical violators. For the specific processing flow, see Figure 3 , including steps 131 to 133: Step 131: For each worker's wear data, extract the state time series in the wear data; Step 132: Determine a time period for removing the safety device according to the state time sequence; Step 133: Determine whether the worker corresponding to the identity identifier in the wearing data is a person with a history of violating regulations based on the removal and removal time period.

[0043] Specifically, in addition to the state time series and the worker's identity, the wearing data also includes a position sequence that represents the relationship between position and time; for each worker's wearing data, the computer equipment determines the position information corresponding to the removal time period from the position sequence; based on the position information corresponding to the removal time period, the effective removal time is determined, and the effective removal time represents the length of time the worker takes off the safety helmet at the construction site; thus, based on the effective removal time, it is determined whether the worker corresponding to the identity in the wearing data is a historical violator.

[0044] The removal time period may include periods when workers are not on the construction site, meaning workers are permitted to not wear safety devices outside of the construction site. However, some workers may carry their safety devices with them and not wear them outside the construction site. Calculating the removal duration directly based on the removal time period may introduce a lot of invalid data, leading to misjudgments of worker violations. Therefore, a location module is also included within the safety device. This location module can obtain the safety device's current location information, enabling the instruction processing module within the safety device to generate a position sequence representing the relationship between position and time based on this location information.

[0045] By analyzing the position sequence, the position range data of the preset construction site is matched with the position sequence to determine the time period when the workers are within the construction site. The time period when the workers are within the construction site is matched with the removal and unloading time period, and the overlapping time period is determined as the effective removal and unloading time period. The effective removal and unloading duration is then determined based on the effective removal and unloading time period.

[0046] After the effective removal time is determined, it is necessary to compare it with a time threshold to determine whether the effective removal time exceeds the time threshold, thereby determining whether the worker has violated the rules. In some cases at the construction site, workers may temporarily remove their helmets to wipe their sweat due to hot weather and heavy sweating, or remove their helmets to adjust their posture due to discomfort. These temporary removals of helmets should not be considered violations. Therefore, a reasonable time threshold can be set to avoid these temporary removals of helmets being judged as violations. Accordingly, the embodiment of the present application adopts a method of dynamically setting the time threshold so that the threshold setting is more in line with the actual situation at the construction site. An exemplary setting method is: the computer device obtains the average temperature of the area where the construction site is located from the last inspection time to the present time based on the location of the construction site, and then determines the corresponding time threshold based on the average temperature. It can be understood that the higher the average temperature, the greater the need for temporary removal of the helmet. Therefore, the time threshold is positively correlated with the average temperature.

[0047] Finally, the effective removal time is compared with the time threshold; if it is determined that the effective removal time exceeds the time threshold, the identity identifier in the wearing data is extracted, and the worker corresponding to the identity identifier is identified as a historical violator.

[0048] In one embodiment, the security management method provided by the present application also includes: when it is determined that there is a historical violator or an immediate violator, determining the target position of the violator from the position sequence of the violator; based on the target position and the setting position of each audio device (such as a sound column) at the construction site, determining the target audio device closest to the target position; sending voice warning data to the target audio device, and using the target audio device to play the voice warning data.

[0049] As a further optimization, when identifying historical offenders, the most recent location of the offender is determined based on the location sequence corresponding to the offender, which serves as the target location for the offender. For immediate offenders, the inspection point corresponding to the image to be detected for the offender is obtained and used as the target location for the offender.

[0050] As a further optimization solution, before receiving the image to be detected sent by the drone, it also includes: sending a position acquisition instruction to the drone, and the position acquisition instruction is used to control the drone to broadcast a position acquisition request to obtain the real-time position feedback of each safety device; obtaining the real-time position of each safety device sent by the drone, and generating an image acquisition instruction based on the real-time position and sending it to the drone, and the image acquisition instruction is used to control the drone to collect the image to be detected at the construction site.

[0051] Specifically, the drone sends the real-time position of each safety position feedback received to the computer device. At the same time, the drone sends its own inspection points and flight posture to the computer device, and the flight posture includes the flight altitude and heading angle; the computer device determines the shooting angle and altitude based on the real-time position and the position of the inspection points, and generates image acquisition instructions based on the shooting angle and altitude and sends them to the drone, so that the images to be detected collected by the drone are more comprehensive and clearer.

[0052] It should be understood that, although the various steps in the flowcharts involved in the above embodiments are shown in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the sub-steps or stages in other steps or other steps. It is understandable that the various steps in different embodiments can be freely combined as needed, and the various non-contradictory schemes formed by the combination all fall within the scope of protection of this application.

[0053] Based on the same inventive concept, the present application also provides a security control device for implementing the above security control method, see Figure 4 The security management and control device 400 includes: an instruction sending module 401, a receiving module 402 and an analysis module 403, wherein: The instruction sending module 401 is used to send a broadcast instruction to the drone when the drone is in the inspection state. The broadcast instruction is used to control the drone to broadcast data extraction instructions.

[0054] The receiving module 402 is used to respond to the data sending request of the drone to receive the wearing data of each worker sent by the drone, wherein the wearing data is sent to the drone by the safety device corresponding to each worker in response to the data extraction instruction; the wearing data includes the worker's identity and status time series, and the status time series represents the timeline information of the worker wearing the safety device; and is used to receive the image to be detected sent by the drone, which is the image collected by the drone at the construction site.

[0055] The analysis module 403 is used to analyze the wearing data of each worker to determine whether there are any historical violators. Historical violators are workers who have not worn safety devices since the last inspection time, and to analyze each image to be detected to determine whether there are any immediate violators. Immediate violators are workers who are not currently wearing safety devices.

[0056] In one embodiment, the analysis module 403 is specifically configured to: For each worker's wearing data, extract the state time series in the wearing data; Determine the time period for workers to remove safety devices based on the state time series; Based on the removal time period, determine whether the worker corresponding to the identity in the wearing data is a person with a history of violating regulations.

[0057] In one embodiment, the wearing data further includes a position sequence representing a relationship between position and time, and the analysis module 403 is specifically configured to: From the position time period, determine the position sequence corresponding to the workers in the removal time period; Determine the effective removal time based on the position sequence and the removal time period. The effective removal time represents the time workers spend removing their helmets at the construction site. Based on the effective removal time, determine whether the worker corresponding to the identity in the wearing data is a person with a history of violation.

[0058] In one embodiment, the analysis module 403 is specifically configured to: If it is determined that the effective removal time exceeds the time threshold, the identity identifier in the wearing data is extracted, and the worker corresponding to the identity identifier is identified as a historical violator; the time threshold is determined based on the average temperature in the current detection period.

[0059] In one embodiment, the instruction sending module 401 is further configured to: Send a clear command to the drone. The clear command is used to control the drone to broadcast a data deletion command. After the data deletion command is received by the safety device, it is used to delete the wearing data stored in the safety device.

[0060] In one embodiment, the analysis module 403 is further configured to: When it is determined that there are historical violators or immediate violators, the target position of the corresponding violator is determined from the position sequence of the violators; based on the target position and the setting positions of various audio devices at the construction site, the target audio device closest to the target position is determined; voice warning data is sent to the target audio device, and the voice warning data is played using the target audio device.

[0061] In one embodiment, the instruction sending module 401 is further configured to: Send a position acquisition command to the drone. The position acquisition command is used to control the drone to broadcast a position acquisition request to obtain the real-time position feedback from each safety device; The receiving module 402 is also used to obtain the real-time position of each safety device sent by the drone, generate image acquisition instructions based on each real-time position, and send image acquisition instructions to the drone. The image acquisition instructions are used to control the drone to collect images to be detected at the construction site.

[0062] Each module in the safety control device 400 for an EPC smart construction site can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a computer processor in hardware form, or stored in a computer memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0063] In an exemplary embodiment, the present application also provides a safety management and control system for an EPC engineering smart site, such as Figure 5 As shown, the system includes a safety device, a drone, and a computer. The safety device is a hard hat and / or reflective vest, and is equipped with a trigger sensor, a command processing module, a positioning module, an RFID module, and a memory. The trigger sensor detects whether a worker is wearing the safety device, and the memory stores data collected by the trigger sensor. The positioning module acquires location information, the command processing module processes commands and executes corresponding tasks, and the RFID module communicates with the drone. The drone can communicate with both the safety device and the computer. In response to commands from the computer, the drone broadcasts corresponding commands or captures images.

[0064] Among them, the various limitations on safety devices and drones in the above-mentioned security management and control method embodiments are also applicable to the various limitations on safety devices and drones in the embodiments of this system.

[0065] In this embodiment, the computer device is used to execute the security management method as described in any of the above security management method embodiments. In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means. The wireless means can be implemented via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a safety management and control method for an EPC project smart construction site. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0066] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0067] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with relevant regulations.

[0068] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0069] The memory, database, or other storage medium used in each embodiment provided herein may include at least one of non-volatile memory and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided herein may include a relational database or a non-relational database. Among them, non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided in this application may be, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, artificial intelligence (AI) processors, etc.

[0070] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to fall within the scope of the present application.

[0071] Therefore, although the embodiments of the present invention have been described above, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the present invention, and all of these changes and modifications do not depart from the scope of protection of the present invention.

Claims

1. A safety management and control method for an EPC engineering smart construction site, characterized in that: include: When the drone is in the inspection state, a broadcast instruction is sent to the drone; the broadcast instruction is used to control the drone to broadcast data extraction instructions externally; In response to a data transmission request from the drone, receiving wear data of each worker transmitted by the drone; wherein the wear data is sent to the drone by the safety device worn by each worker after receiving a data extraction instruction, and the wear data includes the worker's identity and a state time series, wherein the state time series is used to represent the time history of the worker wearing the safety device; Analyze each worker's wearing data to determine whether there are any historical violators; historical violators refer to workers who have not worn safety devices since the last inspection; Receive the images to be detected sent by the drone and analyze each image to determine whether there are any immediate violators; the images to be detected are images collected by the drone at the construction site, and immediate violators are workers who are not currently wearing safety equipment.

2. A safety management and control method for an EPC engineering smart site according to claim 1, characterized in that: The above analysis of each worker's wearable data to determine whether there are any historical violators includes: For the wear data of each worker, extract a state time series in the wear data; Determining a removal time period for a worker to remove the safety device based on the state time series; According to the removal time period, it is determined whether the worker corresponding to the corresponding identity identifier in the wearing data is a person with a history of violating regulations.

3. A safety management and control method for an EPC engineering smart site according to claim 2, characterized in that: The wearing data also includes a position sequence for representing the relationship between position and time; The determining, based on the removal time period, whether the worker corresponding to the corresponding identity identifier in the wearing data is a person with a history of violating regulations includes: Determining, from the position sequence, position information corresponding to the removal time period; determining an effective removal time according to the position information corresponding to the removal time period, wherein the effective removal time represents a time period for a worker to remove the safety device at the construction site; According to the effective removal time, it is determined whether the worker corresponding to the corresponding identity identifier in the wearing data is a person with a history of violating regulations.

4. A safety management and control method for an EPC engineering smart site according to claim 3, characterized in that: The determining, based on the effective removal time, whether the worker corresponding to the corresponding identity identifier in the wearing data is a person with a history of violating regulations includes: If it is determined that the effective removal time exceeds the time threshold, the identity identifier in the wearing data is extracted, and the worker corresponding to the identity identifier is determined as a historical violator; the time threshold is dynamically set based on the average temperature in the current detection period.

5. A safety management and control method for an EPC engineering smart site according to claim 1, characterized in that: Before receiving the image to be detected sent by the drone, it also includes: Sending a position acquisition instruction to the drone, wherein the position acquisition instruction is used to control the drone to broadcast a position acquisition request to obtain the real-time position feedback from each safety device; The real-time position of each safety device sent by the drone is obtained, and an image acquisition instruction is generated based on the real-time position and sent to the drone. The image acquisition instruction is used to control the drone to collect images to be detected at the construction site.

6. A safety management and control method for an EPC engineering smart site according to claim 1, characterized in that: The method further includes: A clear command is sent to the drone, where the clear command is used to control the drone to broadcast a data deletion command. After the data deletion command is received by the safety device, it is used to delete the wearing data stored in the safety device.

7. A safety management and control method for an EPC engineering smart site according to claim 3, characterized in that: The method further includes: When it is determined that there is a historical offender or an immediate offender, determining the target position of the offender from the position sequence of the offender; Based on the target location and the installation locations of various audio devices at the construction site, determining a target audio device closest to the target location; The voice warning data is sent to the target audio device, and the voice warning data is played by the target audio device.

8. A safety control device for an EPC engineering smart site, characterized in that: include: The command sending module is used to send broadcast commands to the drone when the drone is in the inspection state. The broadcast commands are used to control the drone to broadcast data extraction commands; a receiving module, configured to respond to a data transmission request from a drone to receive wear data of each worker sent by the drone, wherein the wear data is sent to the drone by the safety device corresponding to each worker in response to a data extraction instruction; the wear data includes the worker's identity and a state time series, wherein the state time series represents the timeline information of the worker wearing the safety device; and to receive images to be detected sent by the drone, wherein the images to be detected are images captured by the drone at the construction site; The analysis module is used to analyze the wearing data of each worker to determine whether there are any historical violators. Historical violators are workers who have not worn safety devices since the last inspection. It is also used to analyze each image to be detected to determine whether there are any immediate violators. Immediate violators are workers who are not currently wearing safety devices.

9. A safety management and control system for EPC engineering smart construction sites, characterized in that: The system includes: a safety device, a drone, and a computer device; the safety device is a safety helmet and / or reflective clothing, and is provided with a trigger sensor and a memory. The trigger sensor is used to detect whether a worker is wearing the safety device, and the memory is used to store data collected by the trigger sensor. The drone communicates with the security device and the computer device respectively to respond to instructions from the computer device and broadcast corresponding instructions to the security device; The computer device is used to execute the safety management and control method for an EPC project smart site as described in any one of claims 1 to 7.

10. A safety management and control system for an EPC engineering smart site according to claim 9, characterized in that: The safety device further includes a position sensor, which is used to collect the position of the safety device and store the position information in the memory.

Images