Intelligent construction site safety monitoring management method and system based on man-machine cooperation

Abstract

The invention discloses an intelligent construction site safety monitoring management method and system based on man-machine cooperation, and relates to the field of construction safety management, and the method comprises a labeling module which is used for creating a construction site electronic map, and carrying out the risk labeling of each region on the created construction site electronic map; the monitoring module is used for monitoring images of constructors in each area in the construction site electronic map in real time; the identification module is used for synchronously receiving the images of the constructors in each area in the electronic map monitored by the monitoring module, and identifying the number of the constructors in each area in the electronic map and the dynamic risk of each constructor; according to the method, a dynamic risk assessment model fusing equipment layout, personnel postures and environmental parameters is constructed through electronic map risk labeling and construction personnel image monitoring, individual risks are identified, personnel density and regional area are integrated to form a multi-dimensional risk map, space geographic information and real-time image analysis are combined, and the risk assessment efficiency is improved. And a high-risk area can be accurately positioned.

Description

Technical Field

[0001] The present invention relates to the technical field of construction safety management, and specifically to a smart construction site safety monitoring and management method and system based on human-machine collaboration. Background Art

[0002] The invention patent application with application number 202411591708.9 discloses a construction safety monitoring and management method based on a smart construction site, which includes the following steps: collecting safety operation guidelines for construction personnel of each type of construction equipment in the construction site, extracting safety operation data in the safety operation guidelines, sorting the collected safety operation specification data, and building a normal operation database for construction personnel after classification; collecting equipment data when construction equipment fails in history, extracting equipment features, and using equipment features to calculate the fault threshold of each type of construction equipment; collecting feature data values ​​of each type of equipment at the construction site in real time, and using the fault threshold to judge the fault of each type of equipment; collecting feature data values ​​of each type of construction equipment when the construction personnel have different operation data values ​​in history, and using linear regression to calculate the ... The algorithm calculates the correlation function between the characteristic data and operation data of each device; collects the number of equipment failures when each construction equipment fails when the construction personnel have different operation data values ​​in the history, calculates the correlation function between the number of failures and the operation data, and uses the two correlation functions to perform a comprehensive analysis to obtain the optimization function of the operation data of each device. This application aims to solve the problem of "when detecting the behavior of construction personnel at the construction site, the construction personnel need to operate according to the operating specifications of different equipment. When the status of the equipment changes or a failure occurs, the previous operating specifications may not apply. When the construction personnel still use the previous operating specifications to operate the equipment, danger and equipment failure are very likely to occur. Therefore, it is crucial to optimize, update and adjust the operating specifications of the construction personnel according to the status of the equipment."

[0003] However, in construction site scenarios, construction site safety risks are often closely related to the behavior of construction workers and the operation of construction equipment. Currently, there is no good technology to link the two to monitor and manage construction site safety risks.

[0004] To this end, a smart construction site safety monitoring and management method and system based on human-machine collaboration is proposed. Summary of the Invention

[0005] In response to the above-mentioned shortcomings of the prior art, the present invention provides an intelligent construction site safety monitoring and management method and system based on human-machine collaboration, which can effectively solve the problems of the prior art.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] The present invention discloses a smart construction site safety monitoring and management system based on human-machine collaboration, comprising:

[0008] The labeling module is used to create an electronic map of the construction site and label the risks of each area on the created electronic map of the construction site; the monitoring module is used to monitor the images of construction personnel in each area of ​​the electronic map of the construction site in real time; the identification module is used to synchronously receive the images of construction personnel in each area of ​​the electronic map monitored by the monitoring module, identify the number of construction personnel in each area of ​​the electronic map and the dynamic risks of each construction personnel; the analysis module is used to receive the risk labeling results of each area in the electronic map of the construction site from the labeling module and the dynamic risk identification results of construction personnel from the identification module, and analyze the risks of each area in the electronic map of the construction site; the display module is used to receive the images of construction personnel in each area monitored by the monitoring module in real time and display the images of construction personnel; the early warning module is used to issue audio early warnings to remind construction personnel in each area to ensure construction safety.

[0009] Furthermore, the annotation module is provided with an uploading unit and a segmentation unit at a lower level. The uploading unit is used to upload the coordinates of the boundary position of the construction site area, and the segmentation unit is used to receive the electronic map of the construction site created by the annotation module and segment the electronic map of the construction site;

[0010] The uploading unit uploads at least three sets of construction site boundary coordinates, the annotation module receives the construction site boundary coordinates, picks up corresponding coordinates in the electronic map of the construction site area, and connects adjacent coordinates in the electronic map of the construction site area based on the corresponding coordinates to complete the creation of the construction site electronic map;

[0011] Among them, the segmentation processing of the construction site electronic map by the segmentation unit is manually performed by the system end user in the segmentation unit. After the segmentation unit segments the construction site electronic map, the annotation module simultaneously identifies risks in each segmented area and then annotates the risk identification results for each segmented area.

[0012] Furthermore, when the segmentation unit segments the electronic map of the construction site, the minimum segmentation area is no less than 10M. 2 Or 1 / 10 of the electronic map of the construction site;

[0013] The risk identification logic of each segmented area in the annotation module is expressed as follows:

[0014]

[0015] Where: K is the risk value of the segmented area; n is the total amount of construction equipment in the segmented area; s i is the area occupied by the i-th construction equipment; S is the total area of ​​the segmented area; d(i,i+1) is the straight-line distance between the i-th construction equipment and the adjacent i+1-th construction equipment in the segmented area; ti is the current continuous running time of the i-th device; p i is the failure rate of the i-th device; ω i is the configuration weight of the i-th construction equipment; H is the height difference of the segmented area; H max is the maximum height difference in the electronic map of the construction site;

[0016] When there is only one construction equipment in the segmented area, the calculation formula of K is transformed into When there is no construction equipment in the segmented area, the calculation formula of K is transformed into Express The larger the K value is, the greater the risk of segmentation. The device configuration weight follows: The weight of each configuration is proportional to the area occupied by its corresponding construction equipment in the segmented area.

[0017] Furthermore, the monitoring module is integrated by a plurality of monitoring cameras, and at least one monitoring camera is deployed in each of the divided areas. When the monitoring camera monitors the image of the construction workers in the area where it is located, it simultaneously marks the construction workers in the image and simultaneously obtains the dynamic image of the construction workers in the marked frame in the image;

[0018] When identifying the number of construction workers in each area of ​​the electronic map, the recognition module measures the number of construction workers based on the number of box marks in the surveillance images of the corresponding surveillance cameras in each segmented area. When identifying the dynamic risks of each construction worker, the recognition module uses the dynamic images of the construction workers in the corresponding box marks as the recognition targets to perform dynamic risk identification;

[0019] Among them, the identification operations of the number of construction workers in all divided areas and the dynamic risks of each construction worker are performed synchronously based on the preset cycle.

[0020] Furthermore, a selection unit is provided inside the recognition module for traversing the recognition results of the recognition module for the dynamic risks of each construction worker, and selecting the maximum recognition result to indicate that the recognition result points to the dynamic risk of the segmented area;

[0021] The logic of dynamic risk identification of construction personnel in the identification module is expressed as follows:

[0022]

[0023] Where: G is the dynamic risk value of the construction worker; α is the average tilt angle between the construction worker's body and the vertical direction determined based on each frame of the construction worker's dynamic image within the corresponding box annotation; a and b are constants; v max The maximum movement speed of construction workers near construction equipment in the divided area; is the average moving speed of the construction workers; m is the set of construction worker actions in each frame of the dynamic image of the construction workers based on the corresponding box annotation of the construction workers; s j is the risk factor of the jth action; t j is the duration of the j-th action;

[0024] Among them, when working on flat ground, when α>30 degrees, a and b are taken as 30 and 10 and substituted into the calculation formula of G. When working at height, when α>15 degrees, a and b are taken as 15 and 5 and substituted into the calculation formula of G. The construction personnel are judged to be less than or equal to 1m near the construction equipment in the divided area. The risk coefficient of the construction personnel's action is based on the preset construction personnel action and risk coefficient table. Each action in the construction personnel action and risk coefficient table is matched with a specified risk coefficient.

[0025] Furthermore, the risk analysis logic of each area in the electronic map of the construction site in the analysis module is expressed as follows:

[0026]

[0027] Where: F(x) is the risk of region x; K x is the risk value of region x; G x (max) is the maximum dynamic risk of construction workers in area x; M x 、S x is the number of construction workers in region x and the area of ​​region x; M all 、S all The total number of construction workers and the total area of ​​the area corresponding to the electronic map of the construction site;

[0028] Among them, the larger F(x) is, the higher the construction safety risk in area x is.

[0029] Furthermore, the display module is integrated with a display having a split-screen display function. When the display module displays the images of construction workers in each area, the display ratio is 1:1.5:...:C-1.5:C. The number of proportional items is the total number of divided areas. The greater the risk of the area, the larger the corresponding split-screen display area.

[0030] The early warning module is integrated with speakers equal in number to the divided areas, and each speaker is deployed in each divided area. Each speaker stores a preset early warning audio, which is played in a loop. The volume of the playback is determined by the risk of the area. The greater the risk, the louder the playback volume, and vice versa.

[0031] Furthermore, the display module follows the recognition module to run the application cycle and synchronously refreshes the split-screen ratio configuration of the construction worker image when it is displayed.

[0032] Furthermore, the lower level of the labeling module is interactively connected with the uploading unit and the segmentation unit through a wireless network, the labeling module is interactively connected with the monitoring module and the identification module through a wireless network, the internal part of the identification module is interactively connected with the selection unit through a wireless network, the identification module is interactively connected with the analysis module through a wireless network, and the analysis module is interactively connected with the reality module and the early warning module through a wireless network.

[0033] On the other hand, the smart construction site safety monitoring and management method based on human-machine collaboration includes:

[0034] Create an electronic map of the construction site based on the coordinates of the boundary location of the construction site area, divide the electronic map of the construction site, and then identify and mark the risks of each divided area; monitor the images of construction personnel through the monitoring equipment deployed in each divided area, measure the number of construction personnel based on the images of construction personnel, and identify the dynamic risks of each construction personnel in each divided area; comprehensively analyze the risks of each area by combining the risk values ​​marked in the divided areas and the dynamic analysis of each construction personnel in the divided areas; set the display logic of construction personnel images according to the risk of each area, configure the split-screen display of construction personnel images based on the construction personnel image display logic, synchronously broadcast warning audio in a loop in each area, and coordinate the warning audio playback volume based on the regional risk items; refresh the steps according to the predetermined period.

[0035] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects:

[0036] The present invention provides a smart construction site safety monitoring and management method and system based on human-machine collaboration. During the execution of this method and system, a dynamic risk assessment model integrating equipment layout, personnel posture and environmental parameters is constructed through electronic map risk annotation and construction personnel image monitoring. The regional risk value is calculated by quantifying indicators such as equipment spacing and operating time, and individual risks are identified by combining personnel posture data such as tilt angle and movement speed. The personnel density and regional area are then combined to form a multi-dimensional risk map. This method of combining spatial geographic information with real-time image analysis can accurately locate high-risk areas, dynamically feedback the risk level by split-screen size and volume, and realize the transition from "passive monitoring" to "active early warning". It not only improves the risk calculation accuracy through the equipment configuration weight and action risk coefficient table, but also uses the human-machine collaboration mechanism to allow the system to automatically optimize the assessment logic according to the construction scenario, providing a safety management solution for smart construction sites that is both real-time and adaptive, effectively reducing accident hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0038] Figure 1 This is a structural diagram of the smart construction site safety monitoring and management system based on human-machine collaboration;

[0039] Figure 2 This is a flowchart of the smart construction site safety monitoring and management method based on human-machine collaboration. DETAILED DESCRIPTION

[0040] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0041] The present invention will be further described below with reference to the embodiments.

[0042] Example 1:

[0043] The intelligent construction site safety monitoring and management system based on human-machine collaboration in this embodiment is as follows: Figure 1 Shown, including:

[0044] The marking module is used to create an electronic map of the construction site and mark the risks of each area on the created electronic map of the construction site;

[0045] The annotation module is provided with an upload unit and a segmentation unit at the lower level. The upload unit is used to upload the coordinates of the boundary position of the construction site area, and the segmentation unit is used to receive the electronic map of the construction site created by the annotation module and segment the electronic map of the construction site;

[0046] The uploading unit uploads at least three sets of coordinates of the boundary positions of the construction site area. The annotation module receives the coordinates of the boundary positions of the construction site area, picks up the corresponding coordinates in the electronic map of the construction site area, and connects the adjacent coordinates in the electronic map of the construction site area based on the corresponding coordinates to complete the creation of the electronic map of the construction site.

[0047] The segmentation unit segments the electronic map of the construction site manually by the system user. After the segmentation unit segments the electronic map of the construction site, the annotation module simultaneously identifies risks in each segmented area and then annotates the risk identification results for each segmented area.

[0048] When the segmentation unit segments the electronic map of the construction site, it shall comply with the following requirements: the minimum segmentation area shall not be less than 10M 2 Or 1 / 10 of the electronic map of the construction site;

[0049] The risk identification logic of the annotation module for each segmented area is expressed as follows:

[0050]

[0051] Where: K is the risk value of the segmented area; n is the total amount of construction equipment in the segmented area; s i is the area occupied by the i-th construction equipment; S is the total area of ​​the segmented area; d(i,i+1) is the straight-line distance between the i-th construction equipment and the adjacent i+1-th construction equipment in the segmented area; t i is the current continuous running time of the i-th device; p i is the failure rate of the i-th device; ω i is the configuration weight of the i-th construction equipment; H is the height difference of the segmented area; H max is the maximum height difference in the electronic map of the construction site;

[0052] When there is only one construction equipment in the segmented area, the calculation formula of K is transformed into When there is no construction equipment in the segmented area, the calculation formula of K is transformed into Express The larger the K value is, the greater the risk of segmentation. The device configuration weight follows: The weight of each configuration is proportional to the area occupied by its corresponding construction equipment in the segmented area;

[0053] The risk value of each segmented area is identified through the above logic formula, thereby quantifying the risk of each segmented area and providing necessary operation data support for the subsequent module operation of the system in this embodiment;

[0054] Monitoring module, used to monitor the images of construction workers in each area of ​​the electronic map of the construction site in real time;

[0055] The monitoring module is integrated by several monitoring cameras. At least one monitoring camera is deployed in each segmented area. When the monitoring camera monitors the image of the construction workers in its area, it will simultaneously mark the construction workers in the image and simultaneously obtain the dynamic image of the construction workers in the marked frame in the image;

[0056] When identifying the number of construction workers in each area of ​​the electronic map, the recognition module measures the number of boxes marked in the surveillance camera images corresponding to each segmented area. When identifying the dynamic risks of each construction worker, the recognition module uses the dynamic images of the construction workers in the corresponding boxes as the recognition targets for dynamic risk identification.

[0057] The identification of the number of construction workers in all divided areas and the dynamic risks of each construction worker is performed synchronously based on a preset cycle;

[0058] The identification module is used to synchronously receive images of construction workers in each area of ​​the electronic map monitored by the monitoring module, and identify the number of construction workers in each area of ​​the electronic map and the dynamic risk of each construction worker;

[0059] A selection unit is set inside the recognition module to traverse the recognition module's recognition results for the dynamic risks of each construction worker, and select the maximum recognition result to indicate that the recognition result points to the dynamic risk of the segmented area;

[0060] The logic of dynamic risk identification of construction workers in the identification module is expressed as follows:

[0061]

[0062] Where: G is the dynamic risk value of the construction worker; α is the average tilt angle between the construction worker's body and the vertical direction determined based on each frame of the construction worker's dynamic image within the corresponding box annotation; a and b are constants; v max The maximum movement speed of construction workers near construction equipment in the divided area; is the average moving speed of the construction workers; m is the set of construction worker actions in each frame of the dynamic image of the construction workers based on the corresponding box annotation of the construction workers; s j is the risk factor of the jth action; t j is the duration of the j-th action;

[0063] When working on flat ground, if α > 30 degrees, a and b are 30 and 10 respectively and substituted into the calculation formula for G. When working at height, if α > 15 degrees, a and b are 15 and 5 respectively and substituted into the calculation formula for G. The distance between a construction worker and construction equipment in the segmented area is determined to be less than or equal to 1m. The risk factor of the construction worker's action is based on a preset table of construction worker actions and risk factors. Each action in the table is matched with a specified risk factor.

[0064] Through the above logic formula, the dynamic risk of each construction worker in each segmented area is analyzed, providing necessary data support for the risk analysis of each area in the electronic map of the construction site in the analysis module;

[0065] The analysis module is used to receive the risk annotation results of each area in the electronic map of the construction site from the annotation module and the dynamic risk identification results of the construction personnel from the identification module, and analyze the risk of each area in the electronic map of the construction site;

[0066] The risk analysis logic of each area in the construction site electronic map in the analysis module is expressed as follows:

[0067]

[0068] Where: F(x) is the risk of region x; K x is the risk value of region x; G x (max) is the maximum dynamic risk of construction workers in area x; M x 、S x is the number of construction workers in region x and the area of ​​region x; M all 、S all The total number of construction workers and the total area of ​​the area corresponding to the electronic map of the construction site;

[0069] Among them, the larger F(x) is, the higher the construction safety risk in area x is;

[0070] Through the above logic formula, the risk of each area is finally analyzed to provide further operation logic support for the operation of the display module;

[0071] The display module is used to receive the images of construction workers in each area monitored by the monitoring module in real time and display the images of construction workers;

[0072] The display module is integrated with a display with a split-screen display function. When the display module displays the images of construction workers in each area, the display ratio is 1:1.5:...:C-1.5:C. The number of proportional items is the total number of divided areas. The greater the regional risk, the larger the corresponding split-screen display area.

[0073] The warning module is integrated with speakers equal in number to the number of partitioned areas. Each speaker is deployed in each partitioned area. Each speaker stores a preset warning audio. The warning audio is played in a loop. The volume is adjusted according to the risk of the area. The higher the risk, the higher the volume. Conversely, the lower the volume.

[0074] The display module follows the recognition module's application cycle to synchronously refresh the split-screen ratio configuration of the construction worker image when it is displayed;

[0075] The early warning module is used to issue audio warnings to remind construction workers in each area to ensure construction safety;

[0076] The lower level of the labeling module is interactively connected with the uploading unit and the segmentation unit through a wireless network. The labeling module is interactively connected with the monitoring module and the identification module through a wireless network. The identification module is interactively connected with the selection unit through a wireless network. The identification module is interactively connected with the analysis module through a wireless network. The analysis module is interactively connected with the reality module and the early warning module through a wireless network.

[0077] In this embodiment, the labeling module creates an electronic map of the construction site and labels each area on the created electronic map for risk. The uploading unit uploads the coordinates of the boundary locations of the construction site areas in real time. The segmentation unit simultaneously receives the electronic map of the construction site created by the labeling module and segments the electronic map. The monitoring module monitors the images of construction workers in each area of ​​the electronic map in real time. The recognition module then simultaneously receives the images of construction workers in each area of ​​the electronic map monitored by the monitoring module and identifies the number of construction workers in each area of ​​the electronic map and the dynamic risk of each construction worker. The selection unit traverses the dynamic risk identification results of each construction worker by the recognition module in real time and selects the largest recognition result, indicating that the recognition result points to the dynamic risk of the segmented area. The analysis module receives the risk labeling results of each area in the electronic map of the construction site from the labeling module and the dynamic risk identification results of construction workers from the recognition module, and analyzes the risk of each area in the electronic map of the construction site. The display module further receives the images of construction workers in each area monitored by the monitoring module in real time and displays the images of construction workers. Finally, the warning module issues an audio warning to remind construction workers in each area to ensure construction safety.

[0078] Based on the system in the above embodiment, through electronic map risk annotation and construction image monitoring, parameters such as equipment footprint and spacing are quantified to calculate regional risk values. Individual risks are identified by combining dynamic data such as personnel tilt angle and movement speed. The risk assessment results are then formed by combining personnel density and regional area to accurately locate high-risk areas.

[0079] The system integrates risk assessment results with split-screen displays and volume warnings. The higher the risk, the larger the split-screen display and the higher the volume, achieving a transition from passive monitoring to active warnings. Furthermore, it leverages device configuration weights and action risk coefficient tables to improve calculation accuracy. Relying on human-machine collaboration to optimize assessment logic based on specific scenarios, the system provides a real-time, adaptive solution for construction site safety management.

[0080] Example 2:

[0081] In terms of specific implementation, based on Example 1, this example refers to Figure 2 The intelligent construction site safety monitoring and management system based on human-machine collaboration in Example 1 is further described in detail:

[0082] The intelligent construction site safety monitoring and management method based on human-machine collaboration includes:

[0083] Create an electronic map of the construction site based on the coordinates of the site's boundary locations, segment the map, and then identify and label risks in each segmented area;

[0084] The monitoring equipment deployed in each segmented area monitors the images of construction workers, measures the number of construction workers based on the images, and identifies the dynamic risks of each construction worker in each segmented area;

[0085] Comprehensively analyze the risk of each area by combining the risk values ​​marked in the divided areas and the dynamic analysis of each construction worker in the divided areas;

[0086] Set the construction worker image display logic based on the risk level of each area. Based on this logic, configure the split-screen display of construction worker images. Simultaneously play warning audio in each area in a loop, and coordinate the warning audio playback volume based on the regional risk items.

[0087] Refresh steps are executed according to the scheduled cycle.

[0088] In summary, during the execution of the methods and systems in the above embodiments, a dynamic risk assessment model integrating equipment layout, personnel posture and environmental parameters is constructed through electronic map risk annotation and construction personnel image monitoring. The regional risk value is calculated by quantifying indicators such as equipment spacing and operating time, and individual risks are identified by combining personnel posture data such as tilt angle and movement speed. The personnel density and regional area are then combined to form a multi-dimensional risk map. This method of combining spatial geographic information with real-time image analysis can accurately locate high-risk areas, dynamically feedback the risk level through split-screen size and volume, and realize the transition from "passive monitoring" to "active warning". It not only improves the risk calculation accuracy through the equipment configuration weight and action risk coefficient table, but also uses the human-computer collaborative mechanism to allow the system to automatically optimize the evaluation logic according to the construction scenario, providing a real-time and adaptive safety management solution for smart construction sites, effectively reducing accident hazards.

[0089] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. The intelligent construction site safety monitoring and management system based on human-machine collaboration is characterized by: include: The marking module is used to create an electronic map of the construction site and mark the risks of each area on the created electronic map of the construction site; Monitoring module, used to monitor the images of construction workers in each area of ​​the electronic map of the construction site in real time; The identification module is used to synchronously receive images of construction workers in each area of ​​the electronic map monitored by the monitoring module, and identify the number of construction workers in each area of ​​the electronic map and the dynamic risk of each construction worker; The analysis module is used to receive the risk annotation results of each area in the electronic map of the construction site from the annotation module and the dynamic risk identification results of the construction personnel from the identification module, and analyze the risk of each area in the electronic map of the construction site; The display module is used to receive the images of construction workers in each area monitored by the monitoring module in real time and display the images of construction workers; The early warning module is used to issue audio warnings to remind construction workers in each area to ensure construction safety.

2. The intelligent construction site safety monitoring and management system based on human-machine collaboration according to claim 1 is characterized in that: The annotation module is provided with an uploading unit and a segmentation unit at the lower level. The uploading unit is used to upload the coordinates of the boundary position of the construction site area. The segmentation unit is used to receive the electronic map of the construction site created by the annotation module and segment the electronic map of the construction site. The uploading unit uploads at least three sets of construction site boundary coordinates, the annotation module receives the construction site boundary coordinates, picks up corresponding coordinates in the electronic map of the construction site area, and connects adjacent coordinates in the electronic map of the construction site area based on the corresponding coordinates to complete the creation of the construction site electronic map; Among them, the segmentation processing of the construction site electronic map by the segmentation unit is manually performed by the system end user in the segmentation unit. After the segmentation unit segments the construction site electronic map, the annotation module simultaneously identifies risks in each segmented area and then annotates the risk identification results for each segmented area.

3. The intelligent construction site safety monitoring and management system based on human-machine collaboration according to claim 2 is characterized in that: When the segmentation unit segments the electronic map of the construction site, the minimum segmentation area must be no less than 10M. 2 Or 1 / 10 of the electronic map of the construction site; The risk identification logic of each segmented area in the annotation module is expressed as follows: Where: K is the risk value of the segmented area; n is the total amount of construction equipment in the segmented area; s i is the area occupied by the i-th construction equipment; S is the total area of ​​the segmented area; d(i,i+1) is the straight-line distance between the i-th construction equipment and the adjacent i+1-th construction equipment in the segmented area; t i is the current continuous running time of the i-th device; p i is the failure rate of the i-th device; ω i is the configuration weight of the i-th construction equipment; H is the height difference of the segmented area; H max is the maximum height difference in the electronic map of the construction site; When there is only one construction equipment in the segmented area, the calculation formula of K is transformed into When there is no construction equipment in the segmented area, the calculation formula of K is transformed into Express The larger the K value is, the greater the risk of segmentation. The device configuration weight follows: The weight of each configuration is proportional to the area occupied by its corresponding construction equipment in the segmented area.

4. The intelligent construction site safety monitoring and management system based on human-machine collaboration according to claim 2 is characterized in that: The monitoring module is integrated by a plurality of monitoring cameras, and at least one monitoring camera is deployed in each of the divided areas. When the monitoring camera monitors the image of the construction personnel in the area where it is located, the monitoring camera simultaneously marks the construction personnel in the image with a frame, and simultaneously obtains the dynamic image of the construction personnel within the frame mark in the image; When identifying the number of construction workers in each area of ​​the electronic map, the recognition module measures the number of construction workers based on the number of box marks in the surveillance images of the corresponding surveillance cameras in each segmented area. When identifying the dynamic risks of each construction worker, the recognition module uses the dynamic images of the construction workers in the corresponding box marks as the recognition targets to perform dynamic risk identification; Among them, the identification operations of the number of construction workers in all divided areas and the dynamic risks of each construction worker are performed synchronously based on the preset cycle.

5. The intelligent construction site safety monitoring and management system based on human-machine collaboration according to claim 2 is characterized in that: A selection unit is provided inside the recognition module for traversing the recognition module's recognition results for the dynamic risks of each construction worker, and selecting the maximum recognition result to indicate the dynamic risk of the segmented area pointed to by the recognition result; The logic of dynamic risk identification of construction personnel in the identification module is expressed as follows: Where: G is the dynamic risk value of the construction worker; α is the average tilt angle between the construction worker's body and the vertical direction determined based on each frame of the construction worker's dynamic image within the corresponding box annotation; a and b are constants; v max The maximum movement speed of construction workers near construction equipment in the divided area; is the average moving speed of the construction workers; m is the set of construction worker actions in each frame of the dynamic image of the construction workers based on the corresponding box annotation of the construction workers; s j is the risk factor of the jth action; t j is the duration of the j-th action; Among them, when working on flat ground, when α>30 degrees, a and b are taken as 30 and 10 and substituted into the calculation formula of G. When working at height, when α>15 degrees, a and b are taken as 15 and 5 and substituted into the calculation formula of G. The construction personnel are judged to be less than or equal to 1m near the construction equipment in the divided area. The risk coefficient of the construction personnel's action is based on the preset construction personnel action and risk coefficient table. Each action in the construction personnel action and risk coefficient table is matched with a specified risk coefficient.

6. The intelligent construction site safety monitoring and management system based on human-machine collaboration according to claim 2 is characterized in that: The risk analysis logic of each area in the electronic map of the construction site in the analysis module is expressed as follows: Where: F(x) is the risk of region x; K x is the risk value of region x; G x (max) is the maximum dynamic risk of construction workers in area x; M x 、S x is the number of construction workers in region x and the area of ​​region x; M all 、S all The total number of construction workers and the total area of ​​the area corresponding to the electronic map of the construction site; Among them, the larger F(x) is, the higher the construction safety risk in area x is.

7. The intelligent construction site safety monitoring and management system based on human-machine collaboration according to claim 2 is characterized in that: The display module is integrated with a display having a split-screen display function. When the display module displays the images of construction workers in each area, the display ratio is 1:1.5:...:C-1.5:C. The number of proportional items is the total number of divided areas. The greater the risk of the area, the larger the corresponding split-screen display area. The early warning module is integrated with speakers equal in number to the divided areas, and each speaker is deployed in each divided area. Each speaker stores a preset early warning audio, which is played in a loop. The volume of the playback is determined by the risk of the area. The greater the risk, the louder the playback volume, and vice versa.

8. The intelligent construction site safety monitoring and management system based on human-machine collaboration according to claim 7 is characterized in that: The display module follows the recognition module to run the application cycle and synchronously refreshes the split-screen ratio configuration of the construction worker image when it is displayed.

9. The intelligent construction site safety monitoring and management system based on human-machine collaboration according to claim 1 is characterized in that: The lower level of the labeling module is interactively connected with the uploading unit and the segmentation unit through a wireless network, the labeling module is interactively connected with the monitoring module and the identification module through a wireless network, the internal part of the identification module is interactively connected with the selection unit through a wireless network, the identification module is interactively connected with the analysis module through a wireless network, and the analysis module is interactively connected with the reality module and the early warning module through a wireless network.

10. A smart construction site safety monitoring and management method based on human-machine collaboration, wherein the method is an implementation method of the smart construction site safety monitoring and management system based on human-machine collaboration as claimed in any one of claims 1 to 9, characterized in that: include: Create an electronic map of the construction site based on the coordinates of the site's boundary locations, segment the map, and then identify and label risks in each segmented area; The monitoring equipment deployed in each segmented area monitors the images of construction workers, measures the number of construction workers based on the images, and identifies the dynamic risks of each construction worker in each segmented area; Comprehensively analyze the risk of each area by combining the risk values ​​marked in the divided areas and the dynamic analysis of each construction worker in the divided areas; Set the construction worker image display logic based on the risk level of each area. Based on this logic, configure the split-screen display of construction worker images. Simultaneously play warning audio in each area in a loop, and coordinate the warning audio playback volume based on the regional risk items. Refresh steps are executed according to the scheduled cycle.

Images