Safety helmet and construction site safety supervision method

Abstract

The invention relates to the technical field of construction site supervision, and particularly discloses a safety helmet and a construction site safety supervision method, and the method comprises the steps: obtaining the image data of a construction site region, determining a safety supervision data set according to the image data of the construction site region, and determining construction site safety supervision subareas according to the safety supervision data set; acquiring historical safety events of each construction site safety supervision subarea, performing data mining on the historical safety events of the construction site safety supervision subareas, and determining a strong association rule of safety early warning data of each construction site safety supervision subarea according to a data mining result; and obtaining current safety early warning data of each construction site safety supervision subarea, determining a safety early warning level according to the current safety early warning data of each construction site safety supervision subarea, and performing construction site safety early warning according to the safety early warning level. According to the invention, the construction site can be supervised in different areas according to different early warning data in each area in the construction site, early warning can be timely carried out according to security incidents, and the construction safety of the construction site is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of construction site supervision, and more specifically, to a safety helmet and a construction site safety supervision method. Background Art

[0002] With the rise of smart wearable devices, more and more functions are being integrated into clothing or accessories such as watches and glasses. These smart wearable devices can perform functions such as voice and data communication, monitor the wearer's health, and obtain the wearer's location. In the engineering field, smart wearable devices, especially smart helmets, are also gaining attention. These smart helmets can provide image acquisition, voice communication, location positioning, hazard warnings or alarms for the wearer, and other functions. While protecting the wearer as a traditional helmet, they also provide the wearer with a variety of auxiliary functions.

[0003] The smart safety helmets in the existing technology are limited to providing danger warnings when workers enter dangerous areas. They cannot provide effective early warnings for safety incidents and cannot form effective and substantial safety supervision. Summary of the Invention

[0004] The present invention provides a safety helmet and a construction site safety supervision method to solve the problem in the prior art that smart safety helmets cannot provide effective early warning for safety incidents, including:

[0005] Acquire image data of the construction site area, determine a safety supervision data set based on the image data of the construction site area, and determine the safety supervision zones of the construction site based on the safety supervision data set;

[0006] Obtain historical safety events of each construction site safety supervision zone, conduct data mining on the historical safety events of the construction site safety supervision zone, and determine the strong association rules of the safety warning data of each construction site safety supervision zone based on the data mining results;

[0007] Obtain the current safety warning data of each construction site safety supervision zone, determine the safety warning level based on the current safety warning data of each construction site safety supervision zone, and conduct construction site safety warning based on the safety warning level.

[0008] Furthermore, determining the safety supervision data set based on the construction site area image data includes:

[0009] Perform edge detection on the construction site image data based on the Canny edge detection algorithm, and determine the initial safety supervision area based on the edge detection results;

[0010] The center point of each initial safety supervision area is used as the growth seed point, and the growth seed point is regionally grown based on the region growing algorithm to obtain several safety supervision areas;

[0011] Identify the regional type corresponding to each security supervision area, obtain historical security events of each regional type, determine the security risk value and event severity value based on the historical security events of each regional type, and obtain a security supervision data set.

[0012] Furthermore, performing region growing on the growth seed points based on the region growing algorithm includes:

[0013] Traverse the growth seed points and record the locations of the pixels in the eight-connected regions of the growth seed points;

[0014] Traverse the pixel points to be tested in the eight-connected area, calculate the pixel value difference between the pixel point to be tested and the growth seed point, and determine whether the pixel value difference between the pixel point to be tested and the growth seed point is within a preset interval;

[0015] If the pixel value difference between the pixel to be tested and the growth seed point is within the preset interval, the pixel to be tested is set as a new growth seed point;

[0016] With the new growth seed point as the center, continue to detect new pixels to be tested until the area can no longer grow, and obtain several safe supervision areas.

[0017] Furthermore, the identifying of the area type corresponding to each security supervision area includes:

[0018] Obtaining a construction site area type database, extracting safety supervision area images and corresponding area types from the construction site area type database;

[0019] Establishing a training sample set based on the safety supervision area image and the corresponding area type, establishing an initial type recognition model based on the training sample set, and training the initial type recognition model to obtain a trained type recognition model;

[0020] The safety supervision area image of the current construction site is input into the trained type recognition model to obtain the corresponding area type.

[0021] Furthermore, determining the construction site safety supervision zones based on the safety supervision data set includes:

[0022] Randomly select k initial cluster centers of the safety supervision data set, calculate the Euclidean distance between the safety supervision data in the safety supervision data set and the initial cluster centers, and divide the safety supervision areas into corresponding clusters according to the Euclidean distance between the safety supervision data in the safety supervision data set and the initial cluster centers;

[0023] Calculate the mean value of the safety supervision data within each cluster, and recalculate the cluster center based on the mean value of the safety supervision data within each cluster;

[0024] Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset maximum number of iterations, and obtain the partitions corresponding to each safety supervision area.

[0025] Furthermore, the strong association rules of the safety warning data of each construction site safety supervision zone are determined based on the data mining results, including:

[0026] Obtain security warning data of historical security events and pre-process the security warning data;

[0027] Based on the Apriori algorithm, frequent itemsets of security warning data are mined, and strong association rules are determined according to the frequent itemsets of security warning data.

[0028] Furthermore, the method of mining frequent itemsets of security warning data based on the Apriori algorithm and determining strong association rules according to the frequent itemsets of security warning data includes:

[0029] Determine discretized security warning data based on the preprocessed security warning data, set a minimum support threshold, and mine key warning features with support greater than or equal to the minimum support threshold based on the security event type of the security warning data;

[0030] A minimum confidence threshold is set, and according to the security event type of the security warning data, key warning features with confidence greater than or equal to the minimum confidence threshold are mined from the key warning features with support greater than or equal to the minimum support threshold to obtain strong association rules.

[0031] Furthermore, the determination of the safety warning level based on the current safety warning data of each construction site safety supervision zone includes:

[0032] Obtain the current safety warning data of each construction site safety supervision zone, match the current safety warning data of each construction site safety supervision zone with the safety warning data in the strong association rule, and obtain the matching degree between the current safety warning data of each construction site safety supervision zone and the safety warning data in the strong association rule;

[0033] Filter out the security event types corresponding to the security warning data whose matching degree is greater than a preset allowable matching threshold, and obtain the event severity value of the security event type corresponding to the security warning data whose matching degree is greater than the preset allowable matching threshold;

[0034] Multiply the event severity value by the matching degree to obtain the safety warning coefficient of the construction site safety supervision zone, and determine the safety warning level based on the safety warning coefficient.

[0035] Furthermore, determining the safety warning level according to the safety warning coefficient includes:

[0036] Determine the preset allowable warning threshold based on the cluster center of each construction site safety supervision zone, and calculate the difference between the safety warning coefficient and the preset allowable warning threshold;

[0037] Determine whether the difference between the safety warning coefficient and the preset allowable warning threshold is greater than a first preset threshold, and if the difference between the safety warning coefficient and the preset allowable warning threshold is greater than the first preset threshold, set the first level as the safety warning level;

[0038] If the difference between the safety warning coefficient and the preset allowable warning threshold is less than or equal to the first preset threshold, then determining whether the difference between the safety warning coefficient and the preset allowable warning threshold is greater than a second preset threshold;

[0039] If the difference between the safety warning coefficient and the preset allowable warning threshold is greater than the second preset threshold, the second level is set as the safety warning level;

[0040] If the difference between the safety warning coefficient and the preset allowable warning threshold is less than or equal to the second preset threshold, the third level is set as the safety warning level.

[0041] In order to achieve the above object, the present invention further provides a safety helmet, comprising:

[0042] A safety helmet body, wherein the safety helmet body is provided with a partition module, an excavation module and a supervision module;

[0043] The partitioning module is used to obtain the construction site area image data, determine the safety supervision data set according to the construction site area image data, and determine the construction site safety supervision partition according to the safety supervision data set;

[0044] The mining module is used to obtain historical safety events of each construction site safety supervision zone, perform data mining on the historical safety events of the construction site safety supervision zone, and determine strong association rules for safety warning data of each construction site safety supervision zone based on the data mining results;

[0045] The supervision module is used to obtain current safety warning data of each construction site safety supervision zone, determine the safety warning level according to the current safety warning data of each construction site safety supervision zone, and perform construction site safety warning according to the safety warning level.

[0046] The beneficial effects of the present invention are:

[0047] By applying the above technical solution, the present invention obtains image data of the construction site area, determines a safety supervision data set based on the image data of the construction site area, and determines the construction site safety supervision zone based on the safety supervision data set; obtains historical safety events of each construction site safety supervision zone, performs data mining on the historical safety events of the construction site safety supervision zone, and determines the strong association rules of the safety warning data of each construction site safety supervision zone based on the data mining results; obtains the current safety warning data of each construction site safety supervision zone, determines the safety warning level based on the current safety warning data of each construction site safety supervision zone, and performs construction site safety warning based on the safety warning level. The present invention can perform zoned supervision of the construction site based on the different warning data of each area in the construction site, and promptly issue warnings for safety events, effectively improving the safety of construction site construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 The following is an overall flow chart of a construction site safety supervision method proposed in an embodiment of the present invention;

[0050] Figure 2 The module structure diagram of a safety helmet proposed in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0052] The present application embodiment provides a construction site safety supervision method, such as Figure 1 Shown, including:

[0053] S101, acquiring image data of a construction site area, determining a safety supervision data set based on the image data of the construction site area, and determining a construction site safety supervision zone based on the safety supervision data set;

[0054] In some embodiments of the present application, the method of determining a safety supervision data set based on the construction site area image data includes: performing edge detection on the construction site area image data based on the canny edge detection algorithm, and determining the initial safety supervision area based on the edge detection results; using the center point of each initial safety supervision area as a growth seed point, and performing regional growth on the growth seed point based on the regional growing algorithm to obtain a number of safety supervision areas; identifying the area type corresponding to each safety supervision area, obtaining historical safety events of each area type, and determining the safety risk value and event severity value based on the historical safety events of each area type to obtain a safety supervision data set.

[0055] In this embodiment, the construction site image data is segmented based on a region growing algorithm to create several safety supervision regions. The regional types of the safety supervision regions are used to obtain historical safety events at the construction site in the corresponding region types, thereby obtaining the safety risk value and event severity value of the historical safety events and establishing a safety supervision dataset. The safety risk value reflects the probability of a safety event, while the event severity value represents the severity of the safety event. By calculating the average safety risk value and average event severity value of all historical safety events within the corresponding region type, the safety risk value and event severity value of the region type are obtained and a safety supervision dataset is established. Zoning construction sites through construction site safety supervision zoning is conducive to improving the accuracy of safety incident warnings.

[0056] In some embodiments of the present application, the region growing algorithm is used to perform region growing on the growth seed point, including: traversing the growth seed point and recording the positions of the pixel points in the eight-connected region of the growth seed point; traversing the pixel points to be tested in the eight-connected region, calculating the pixel value difference between the pixel points to be tested and the growth seed point, and judging whether the pixel value difference between the pixel points to be tested and the growth seed point is within a preset interval; if the pixel value difference between the pixel points to be tested and the growth seed point is within the preset interval, setting the pixel point to be tested as a new growth seed point; with the new growth seed point as the center, continue to detect new pixel points to be tested until the region can no longer grow, and obtain several safe supervision regions.

[0057] In this embodiment, different construction scenes correspond to different pixel values, and each construction scene is segmented using a region growing algorithm to form a number of safety supervision areas.

[0058] In some embodiments of the present application, the identification of the area type corresponding to each safety supervision area includes: obtaining a construction site area type database, extracting the safety supervision area image and the corresponding area type in the construction site area type database; establishing a training sample set based on the safety supervision area image and the corresponding area type, establishing an initial type recognition model based on the training sample set and training the initial type recognition model to obtain a trained type recognition model; inputting the safety supervision area image of the current construction site into the trained type recognition model to obtain the corresponding area type.

[0059] In this embodiment, the type of the safety supervision area image is identified based on the deep learning neural network model to identify the corresponding area type. The area types specifically include mechanical operation area, material stacking area, office area, and dangerous isolation area.

[0060] In some embodiments of the present application, determining the construction site safety supervision zones based on the safety supervision data set includes: randomly selecting k initial cluster centers of the safety supervision data set, calculating the Euclidean distance between the safety supervision data in the safety supervision data set and the initial cluster centers, and dividing the safety supervision areas into corresponding cluster clusters according to the Euclidean distance between the safety supervision data in the safety supervision data set and the initial cluster centers; calculating the mean of the safety supervision data within each cluster, and recalculating the cluster centers according to the mean of the safety supervision data within each cluster; and repeatedly iterating the above steps until the cluster centers no longer change or the number of iterations reaches a preset maximum number of iterations, thereby obtaining zones corresponding to each safety supervision area.

[0061] In this embodiment, each safety supervision area is allocated to a corresponding construction site safety supervision zone through the safety supervision data set based on the k-means clustering algorithm, which facilitates the subsequent establishment of safety warning levels for the safety supervision zones.

[0062] S102, obtaining historical safety events of each construction site safety supervision zone, performing data mining on the historical safety events of the construction site safety supervision zone, and determining strong association rules for safety warning data of each construction site safety supervision zone based on the data mining results;

[0063] In some embodiments of the present application, the method of determining strong association rules for safety warning data of each construction site safety supervision zone based on data mining results includes: obtaining safety warning data of historical safety events and preprocessing the safety warning data; mining frequent item sets of safety warning data based on the apriori algorithm, and determining strong association rules based on the frequent item sets of safety warning data.

[0064] In some embodiments of the present application, the apriori algorithm is used to mine frequent item sets of security warning data, and strong association rules are determined based on the frequent item sets of the security warning data, including: determining discretized security warning data based on the preprocessed security warning data, setting a minimum support threshold, and mining key warning features with a support greater than or equal to the minimum support threshold based on the security event type of the security warning data; setting a minimum confidence threshold, and mining key warning features with a confidence greater than or equal to the minimum confidence threshold from the key warning features with a support greater than or equal to the minimum support threshold based on the security event type of the security warning data, to obtain strong association rules.

[0065] In this embodiment, the safety warning data specifically includes the personnel density, dangerous behavior density, equipment operation compliance, equipment parameter abnormal values ​​and environmental parameters of the corresponding construction site safety supervision zone when the historical safety incident occurred. The historical safety incidents of the construction site safety supervision zone are mined based on the apriori association rule algorithm, and the strong association rules between the safety warning data and the corresponding safety incident types are fully mined to facilitate the subsequent evaluation of the zone safety warning level.

[0066] S103, obtaining current safety warning data of each construction site safety supervision zone, determining a safety warning level according to the current safety warning data of each construction site safety supervision zone, and performing a construction site safety warning according to the safety warning level.

[0067] In some embodiments of the present application, the safety warning level is determined based on the current safety warning data of each construction site safety supervision zone, including: obtaining the current safety warning data of each construction site safety supervision zone, matching the current safety warning data of each construction site safety supervision zone with the safety warning data in the strong association rule, and obtaining the degree of matching between the current safety warning data of each construction site safety supervision zone and the safety warning data in the strong association rule; screening out the safety event type corresponding to the safety warning data having a matching degree greater than a preset allowable matching threshold, and obtaining the event severity value of the safety event type corresponding to the safety warning data having a matching degree greater than the preset allowable matching threshold; multiplying the event severity value by the matching degree to obtain the safety warning coefficient of the construction site safety supervision zone, and determining the safety warning level based on the safety warning coefficient.

[0068] In this embodiment, the strong association rules of the safety warning data of each construction site safety supervision zone are used to calculate in real time the degree of matching between the current construction site safety supervision zone and the safety warning data in the strong association rules. The higher the degree of matching, the greater the probability of the corresponding safety incident. The construction site safety supervision zones with a higher degree of matching are screened out and the event severity values ​​of the corresponding safety incident types are extracted. The safety warning coefficient is calculated based on the event severity value and the degree of matching, and the safety warning level is set.

[0069] In some embodiments of the present application, the determination of the safety warning level based on the safety warning coefficient includes: determining a preset allowable warning threshold based on the cluster center of each construction site safety supervision zone, and calculating the difference between the safety warning coefficient and the preset allowable warning threshold; judging whether the difference between the safety warning coefficient and the preset allowable warning threshold is greater than a first preset threshold; if the difference between the safety warning coefficient and the preset allowable warning threshold is greater than the first preset threshold, setting the first level as the safety warning level; if the difference between the safety warning coefficient and the preset allowable warning threshold is less than or equal to the first preset threshold, judging whether the difference between the safety warning coefficient and the preset allowable warning threshold is greater than the second preset threshold; if the difference between the safety warning coefficient and the preset allowable warning threshold is greater than the second preset threshold, setting the second level as the safety warning level; if the difference between the safety warning coefficient and the preset allowable warning threshold is less than or equal to the second preset threshold, setting the third level as the safety warning level.

[0070] In this embodiment, a preset permissible warning threshold is determined based on the cluster center of each construction site safety supervision zone based on a preset cluster center-permissible warning threshold mapping table. The safety warning level corresponding to each construction site safety supervision zone is determined based on the difference between the safety warning coefficient and the preset permissible warning threshold. The larger the difference, the higher the corresponding warning level, and the greater the risk of a safety incident in that area. Using the safety warning level, staff are promptly reminded to monitor construction site safety supervision zones, effectively reducing the probability of safety incidents.

[0071] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides a safety helmet, comprising:

[0072] A safety helmet body is provided with a partitioning module, a mining module and a supervision module; the partitioning module is used to obtain image data of the construction site area, determine a safety supervision data set based on the image data of the construction site area, and determine the construction site safety supervision partition based on the safety supervision data set; the mining module is used to obtain historical safety events of each construction site safety supervision partition, perform data mining on the historical safety events of the construction site safety supervision partition, and determine the strong association rules of the safety warning data of each construction site safety supervision partition based on the data mining results; the supervision module is used to obtain current safety warning data of each construction site safety supervision partition, determine the safety warning level based on the current safety warning data of each construction site safety supervision partition, and perform construction site safety warning according to the safety warning level.

[0073] By applying the above technical solutions, the present invention obtains image data of the construction site area, determines a safety supervision data set based on the image data of the construction site area, and determines the construction site safety supervision zone based on the safety supervision data set; obtains historical safety events of each construction site safety supervision zone, performs data mining on the historical safety events of the construction site safety supervision zone, and determines the strong association rules of the safety warning data of each construction site safety supervision zone based on the data mining results; obtains the current safety warning data of each construction site safety supervision zone, determines the safety warning level based on the current safety warning data of each construction site safety supervision zone, and performs construction site safety warning based on the safety warning level. The present invention can perform zoned supervision of the construction site based on the different warning data of each area in the construction site, and promptly issue warnings for safety events, effectively improving the safety of construction site construction.

[0074] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented through hardware or by using software plus the necessary general hardware platform. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) and includes a number of instructions for enabling a computer device (such as a personal computer, a server, or a network device) to execute the methods described in various implementation scenarios of the present invention.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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 do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A construction site safety supervision method, characterized in that: The method comprises: Acquire image data of the construction site area, determine a safety supervision data set based on the image data of the construction site area, and determine the safety supervision zones of the construction site based on the safety supervision data set; Obtain historical safety events of each construction site safety supervision zone, conduct data mining on the historical safety events of the construction site safety supervision zone, and determine the strong association rules of the safety warning data of each construction site safety supervision zone based on the data mining results; Obtain the current safety warning data of each construction site safety supervision zone, determine the safety warning level based on the current safety warning data of each construction site safety supervision zone, and conduct construction site safety warning based on the safety warning level.

2. The construction site safety supervision method according to claim 1, characterized in that: Determining the safety supervision data set based on the construction site area image data includes: Perform edge detection on the construction site image data based on the Canny edge detection algorithm, and determine the initial safety supervision area based on the edge detection results; The center point of each initial safety supervision area is used as the growth seed point, and the growth seed point is regionally grown based on the region growing algorithm to obtain several safety supervision areas; Identify the regional type corresponding to each security supervision area, obtain historical security events of each regional type, determine the security risk value and event severity value based on the historical security events of each regional type, and obtain a security supervision data set.

3. The construction site safety supervision method according to claim 2, characterized in that: The performing region growing on the growth seed points based on the region growing algorithm includes: Traverse the growth seed points and record the locations of the pixels in the eight-connected regions of the growth seed points; Traverse the pixel points to be tested in the eight-connected area, calculate the pixel value difference between the pixel point to be tested and the growth seed point, and determine whether the pixel value difference between the pixel point to be tested and the growth seed point is within a preset interval; If the pixel value difference between the pixel to be measured and the growth seed point is within the preset interval, the pixel to be measured is set as a new growth seed point; With the new growth seed point as the center, continue to detect new pixels to be tested until the area can no longer grow, and obtain several safe supervision areas.

4. The construction site safety supervision method according to claim 2, characterized in that: The identification of the area type corresponding to each security supervision area includes: Obtaining a construction site area type database, extracting safety supervision area images and corresponding area types from the construction site area type database; Establishing a training sample set based on the safety supervision area image and the corresponding area type, establishing an initial type recognition model based on the training sample set, and training the initial type recognition model to obtain a trained type recognition model; The safety supervision area image of the current construction site is input into the trained type recognition model to obtain the corresponding area type.

5. The construction site safety supervision method according to claim 2, characterized in that: Determining the construction site safety supervision zones based on the safety supervision data set includes: Randomly select k initial cluster centers of the safety supervision data set, calculate the Euclidean distance between the safety supervision data in the safety supervision data set and the initial cluster centers, and divide the safety supervision areas into corresponding clusters according to the Euclidean distance between the safety supervision data in the safety supervision data set and the initial cluster centers; Calculate the mean value of the safety supervision data within each cluster, and recalculate the cluster center based on the mean value of the safety supervision data within each cluster; Repeat the above steps until the cluster center no longer changes or the number of iterations reaches the preset maximum number of iterations, and obtain the partitions corresponding to each safety supervision area.

6. The construction site safety supervision method according to claim 1, characterized in that: The strong association rules for safety warning data of each construction site safety supervision zone are determined based on the data mining results, including: Obtain security warning data of historical security events and pre-process the security warning data; Based on the Apriori algorithm, frequent itemsets of security warning data are mined, and strong association rules are determined according to the frequent itemsets of security warning data.

7. The construction site safety supervision method according to claim 6, characterized in that: The method of mining frequent itemsets of security warning data based on the Apriori algorithm and determining strong association rules based on the frequent itemsets of security warning data includes: Determine discretized security warning data based on the preprocessed security warning data, set a minimum support threshold, and mine key warning features with support greater than or equal to the minimum support threshold based on the security event type of the security warning data; A minimum confidence threshold is set, and according to the security event type of the security warning data, key warning features with confidence greater than or equal to the minimum confidence threshold are mined from the key warning features with support greater than or equal to the minimum support threshold to obtain strong association rules.

8. The construction site safety supervision method according to claim 7, characterized in that: Determining the safety warning level based on the current safety warning data of each construction site safety supervision zone includes: Obtain the current safety warning data of each construction site safety supervision zone, match the current safety warning data of each construction site safety supervision zone with the safety warning data in the strong association rule, and obtain the matching degree between the current safety warning data of each construction site safety supervision zone and the safety warning data in the strong association rule; Filter out the security event types corresponding to the security warning data whose matching degree is greater than a preset allowable matching threshold, and obtain the event severity value of the security event type corresponding to the security warning data whose matching degree is greater than the preset allowable matching threshold; Multiply the event severity value by the matching degree to obtain the safety warning coefficient of the construction site safety supervision zone, and determine the safety warning level based on the safety warning coefficient.

9. The construction site safety supervision method according to claim 8, characterized in that: Determining the safety warning level according to the safety warning coefficient includes: Determine the preset allowable warning threshold based on the cluster center of each construction site safety supervision zone, and calculate the difference between the safety warning coefficient and the preset allowable warning threshold; Determine whether the difference between the safety warning coefficient and the preset allowable warning threshold is greater than a first preset threshold, and if the difference between the safety warning coefficient and the preset allowable warning threshold is greater than the first preset threshold, set the first level as the safety warning level; If the difference between the safety warning coefficient and the preset allowable warning threshold is less than or equal to the first preset threshold, then determining whether the difference between the safety warning coefficient and the preset allowable warning threshold is greater than a second preset threshold; If the difference between the safety warning coefficient and the preset allowable warning threshold is greater than the second preset threshold, the second level is set as the safety warning level; If the difference between the safety warning coefficient and the preset allowable warning threshold is less than or equal to the second preset threshold, the third level is set as the safety warning level.

10. A safety helmet, characterized in that: include: A safety helmet body, wherein the safety helmet body is provided with a partition module, an excavation module and a supervision module; The partitioning module is used to obtain the construction site area image data, determine the safety supervision data set according to the construction site area image data, and determine the construction site safety supervision partition according to the safety supervision data set; The mining module is used to obtain historical safety events of each construction site safety supervision zone, perform data mining on the historical safety events of the construction site safety supervision zone, and determine strong association rules for safety warning data of each construction site safety supervision zone based on the data mining results; The supervision module is used to obtain current safety warning data of each construction site safety supervision zone, determine the safety warning level according to the current safety warning data of each construction site safety supervision zone, and perform construction site safety warning according to the safety warning level.

Images