Risk identification system, engineering safety management platform and terminal equipment

By using image acquisition and analysis modules in the risk identification system at the construction site to identify and mark violation information, the problem of difficult to identify safety hazards at the construction site is solved, and the construction safety is improved.

CN120071015APending Publication Date: 2025-05-30CHINA TOBACCO GUANGDONG IND
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510242234.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-03
Publication Date
2025-05-30

AI Technical Summary

Technical Problem

During the construction process, it is difficult for the existing technology to fully and in real time to identify and manage safety hazards at the construction site, resulting in the occurrence of safety accidents.

Method used

It provides a risk identification system, including an image acquisition module, a construction site situation analysis module and an violation labeling module. By analyzing the construction site images, identifying violation information and marking the type of violation, and then determining the risk category and issuing an alarm.

Benefits of technology

It realizes timely and accurate identification of hidden dangers on the construction site, reduces the risk of accidents and improves construction safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120071015A_ABST
    Figure CN120071015A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of engineering management, and discloses a risk identification system, an engineering safety management platform and terminal equipment, and the risk identification system comprises an image collection module which is used for receiving a construction site image collected by image collection equipment; the construction site condition analysis module is used for performing analysis according to the construction site image to obtain violation information; wherein the violation information comprises behavior violation information, protection equipment violation information, field environment violation information and project permission violation information; and the violation marking module is used for carrying out violation type marking on the corresponding construction site image according to the violation information and determining a risk type according to the violation information. According to the method, the hidden danger problem of the construction site can be timely and accurately obtained, so that the occurrence of accidents is reduced, and the construction safety is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the technical field of project management, and particularly to a risk identification system, an engineering safety management platform, and a terminal device. Background Art

[0002] With the development of the engineering industry, modern construction projects usually involve complex structural designs and high-precision work requirements. To ensure construction quality and safety, construction specifications and technical standards have been widely applied. However, during the actual construction process, due to the influence of various factors, there are still some potential safety hazards. For example, workers not wearing personal protective equipment according to the specifications, improper management of equipment and materials at the construction site, or construction methods not meeting safety standards, etc., all of which may lead to safety accidents. Although existing construction safety management measures have achieved certain results, they still face many challenges in actual operation. Therefore, it is crucial to identify hazards during the construction process. Summary of the Invention

[0003] In view of this, the embodiments of this application provide a risk identification system, an engineering safety management platform, and a terminal device, which can timely and accurately obtain potential problems at the construction site, thereby reducing the occurrence of accidents and improving construction safety.

[0004] In a first aspect, the embodiments of this application provide a risk identification system, including: an image acquisition module, a construction site situation analysis module, and a violation annotation module;

[0005] The image acquisition module is configured to receive construction site images collected by an image acquisition device;

[0006] The construction site situation analysis module is configured to analyze based on the construction site images to obtain violation information; wherein, the violation information includes behavior violation information, protective equipment violation information, on-site environment violation information, and project permission violation information;

[0007] The violation annotation module is configured to perform violation type annotation on the corresponding construction site images according to the violation information, and determine the risk category according to the violation information.

[0008] In some embodiments, the construction site situation analysis module includes a construction site situation analysis unit and a violation analysis unit; wherein, a safety specification knowledge graph of each project node is stored in the violation analysis unit;

[0009] The construction site situation analysis unit is configured to analyze the people, protective equipment, and on-site environment included in the construction site images respectively based on the construction site images to obtain behavior information, protective equipment information, and environment information;

[0010] The violation analysis unit is configured to determine the violation information according to the behavior information, the protection device information, and the environmental information in combination with the safety specification knowledge graph.

[0011] In some embodiments, the construction site images include color images and depth images; the construction site situation analysis unit includes a human behavior analysis subunit, a protection device analysis subunit, and a site environment analysis subunit;

[0012] The human behavior analysis subunit is configured to analyze the human body key points according to the color image to obtain the posture and actions of the current person;

[0013] The protection device analysis subunit is configured to detect the protection device worn by the person and the wearing state of the corresponding protection device according to the color image;

[0014] The site environment analysis subunit is configured to analyze according to the depth image and the color image to obtain air environment information and material stacking information.

[0015] In some embodiments, the violation analysis unit includes a human violation analysis subunit, a protection device violation subunit, and a site environment violation subunit;

[0016] The human violation analysis subunit is configured to determine the behavior violation information according to the posture and actions of the current person in combination with the safety specification knowledge graph corresponding to the current project node;

[0017] The protection device violation subunit is configured to determine the protection device violation information according to the protection device worn by the person and the wearing state of the corresponding protection device in combination with the safety specification knowledge graph corresponding to the current project node;

[0018] The site environment violation subunit is configured to determine the site environment violation information according to the material stacking information in combination with the safety specification knowledge graph corresponding to the current project node.

[0019] In some embodiments, the image acquisition device includes a mobile image acquisition device and a fixed image acquisition device;

[0020] The mobile image acquisition device is a handheld device with a built-in depth camera;

[0021] The fixed image acquisition device is a depth camera installed at the construction site.

[0022] In some embodiments, the construction site situation analysis unit further includes a project permission analysis subunit; the violation analysis unit further includes a project permission violation subunit;

[0023] The mobile image acquisition device is further configured to transmit the positioning information and shooting time information of the mobile image acquisition device to the construction site situation analysis module;

[0024] The fixed image acquisition device is further configured to transmit the number and shooting time information of the fixed image acquisition device to the construction site situation analysis module;

[0025] The project authority analysis subunit is configured to analyze based on the construction site images to obtain the person ID and materials at the current construction site;

[0026] The project authority analysis subunit is further configured to determine the positioning information according to the number of the fixed image acquisition device;

[0027] The project authority violation subunit is configured to determine the project authority violation information according to the positioning information, the shooting time information, the ID of the person, and the materials, in combination with the project implementation rules of the current project node.

[0028] In some embodiments, the violation annotation module includes an image annotation unit, a risk determination unit, and an alarm unit;

[0029] The image annotation unit is configured to annotate the current construction site image according to the violation information determined in each construction site image;

[0030] The risk determination unit is configured to determine the risk category according to all the violation information determined in a preset time in the same area;

[0031] The alarm unit is configured to perform corresponding alarm indications according to the risk category.

[0032] In some embodiments, the risk determination unit is further configured to determine the risk category according to all the violation information determined in a preset time in the same area, in combination with the air environment information.

[0033] In a second aspect, an embodiment of the present application provides an engineering safety management platform, and the engineering safety management platform includes the above-mentioned risk identification system.

[0034] In a third aspect, an embodiment of the present application provides a terminal device, and the terminal device includes a processor and a memory. The memory stores a computer program, and the processor is configured to execute the computer program to run the above-mentioned risk identification system, or execute the computer program to run the module functions in the above-mentioned engineering safety management platform.

[0035] The embodiments of the present application have the following beneficial effects:

[0036] This application obtains construction site images through an image acquisition module, then processes and analyzes the acquired construction site images through a construction site situation analysis module to obtain violation information. After obtaining the violation information, the corresponding parts of the violations in the construction site images are marked according to the violation types through a violation marking module, so as to standardize and manage the violation behaviors based on the marked construction site images. In addition, this application can also give an alarm according to the violation situation. Through this risk identification system, this application can timely and accurately obtain the potential problems at the construction site, thereby reducing the occurrence of accidents and improving construction safety. Brief Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions of the embodiments of this application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application, and therefore should not be regarded as a limitation of the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0038] Figure 1 Shows a schematic structural diagram of the project safety management platform according to an embodiment of this application;

[0039] Figure 2 Shows a schematic diagram of the service application interface according to an embodiment of this application;

[0040] Figure 3 Shows a partial interface schematic diagram of the project management module according to an embodiment of this application;

[0041] Figure 4 Shows a partial interface schematic diagram of the log management module according to an embodiment of this application;

[0042] Figure 5 Shows a partial interface schematic diagram of the intelligent search module according to an embodiment of this application;

[0043] Figure 6 Shows a schematic structural diagram of the risk identification system according to an embodiment of this application;

[0044] Figure 7 Shows a schematic structural diagram of the construction site situation analysis module according to an embodiment of this application;

[0045] Figure 8 Shows a schematic structural diagram of the violation marking module according to an embodiment of this application.

[0046] Main Element Symbol Description:

[0047] 1000 - Engineering Safety Management Platform; 100 - Risk Identification System; 200 - Project Management Module; 300 - Log Management Module; 400 - Intelligent Search Module; 500 - Learning Module; 600 - User Management Module; 700 - Task Reminder Module; 110 - Image Acquisition Module; 120 - Construction Site Situation Analysis Module; 130 - Violation Marking Module; 121 - Construction Site Situation Analysis Unit; 122 - Violation Analysis Unit; 1211 - Human Behavior Analysis Sub - unit; 1212 - Protective Equipment Analysis Sub - unit; 1213 - On - site Environment Analysis Sub - unit; 1221 - Human Violation Analysis Sub - unit; 1222 - Protective Equipment Violation Sub - unit; 1223 - On - site Environment Violation Sub - unit; 131 - Image Marking Unit; 132 - Risk Determination Unit; 133 - Alarm Unit. Detailed Implementation Manner

[0048] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0049] Generally, the components of the embodiments of the present application described and illustrated in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application claimed, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0050] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items. In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0051] Unless otherwise defined, all terms (including technical terms and scientific terms) used here have the same meaning as those commonly understood by those of ordinary skill in the art to which the various embodiments of the present application belong. The terms (such as those defined in a commonly used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or being overly formal, unless clearly defined in the various embodiments of the present application.

[0052] The following will, in conjunction with the accompanying drawings, elaborate on some embodiments of the present application. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0053] In the prior art, potential safety hazards during the construction process are usually detected through manual inspections. There are mainly the following problems with personnel inspections: First, due to limited inspectors, comprehensive and real-time inspections cannot be achieved. Second, personnel inspections are somewhat subjective. Third, personnel inspections are inefficient and prone to omissions. Based on the above problems, the present application proposes a risk identification system, an engineering safety management platform, and a terminal device to be able to timely and accurately obtain risk problems at the construction site, thereby reducing the occurrence of accidents and improving construction safety.

[0054] The following will be combined with Figure 1 First, the engineering safety management platform 1000 of the present application will be described.

[0055] The engineering safety management platform 1000 not only includes the risk identification system 100 in the present application, but also includes, but is not limited to, a project management module 200, a log management module 300, an intelligent search module 400, a learning module 500, a user management module 600, a task reminder module 700, etc.;

[0056] Among them, the project management module 200 is used for the creation of construction projects, querying the progress of construction projects, changes to construction projects, etc.; for the creation of construction projects, it is usually when there is a new project that the project is created. The information that needs to be input during creation includes, but is not limited to, the project name, project introduction, project implementation time, and the overall person in charge of the project; in addition, after the project is created, the information of each project node in the project can also be created. For example, a certain project includes project node A, project node B, project node C, project node E, etc. When creating the current project node, the construction type of the project node, the node construction personnel, the node person in charge, the node construction time, etc. need to be input.

[0057] The project management module 200 also includes a business application unit. This business application unit is used to first apply for filing through the business application unit before executing the construction tasks of a certain project, so as to more clearly determine the executors of each construction task for each project node. When applying for business, the information that needs to be input includes, but is not limited to, the application type, operation time, operation personnel, etc. For example Figure 2 As shown, if the construction task applied for during business application is a hazardous operation (such as hot work, lifting operation, high-altitude operation, confined space operation, or cable operation, etc.), then the platform can send the construction precautions for the relevant hazardous operation to the platform accounts of the relevant operation personnel to remind the relevant operation personnel to pay attention to safety during construction.

[0058] For example Figure 3As shown, the project management module 200 is also used for authorized users to query project materials corresponding to a project, such as project construction drawings, project progress, etc.

[0059] Such as Figure 4 As shown, the log management module 300 is used for the owner (principal), supervisor, and construction personnel to publish the work conditions of the day. It can be published in the form of text, pictures, and videos. On the one hand, this facilitates the parties to summarize the work. On the other hand, they can also see the work conditions of others. In addition, for the log information, others can continue to perform operations such as commenting and liking. In this way, the safety protection situation of the construction can be improved by extracting the log information and the corresponding comment information later. In addition, the construction methods can be learned from each other to promote the development of the work.

[0060] Such as Figure 5 As shown, the intelligent search module 400 is used for information query. For example, it can query construction-related information, project information, personnel information, etc. As Figure 5 shown, when the construction personnel are performing a task of a certain edge protection, they can query the relevant construction content of the edge protection (including but not limited to various construction techniques and construction requirements related to the edge protection) through the intelligent search module 400. The intelligent search module 400 can better help the construction personnel query professional construction knowledge.

[0061] The learning module 500 is mainly used to display some information, safety education information, etc.

[0062] The user management module 600 is mainly used to manage user information, including user basic information, user permission information, etc.

[0063] The task reminder module 700 is used to send a reminder to the corresponding construction personnel according to the project node information in the project management module 200 before the construction personnel need to execute a certain task, so as to prevent the construction personnel from missing a certain task and causing the subsequent tasks to not be carried out normally.

[0064] When applying the risk identification system 100 or the engineering safety management platform 1000 in this application, it can be used with a mobile terminal as the carrier. The risk identification system 100 or the engineering safety management platform 1000 can be used in the form of a small program or in the form of an APP.

[0065] The following will illustrate the risk identification system 100 in combination with some specific embodiments.

[0066] Figure 6A schematic structural diagram of a risk identification system 100 according to an embodiment of the present application is shown. Exemplarily, the risk identification system 100 includes: an image acquisition module 110, a construction site condition analysis module 120, and a violation annotation module 130.

[0067] The image acquisition module 110 is configured to receive construction site images acquired by an image acquisition device. The images in this embodiment include pictures and / or videos.

[0068] The image acquisition device includes a mobile image acquisition device and a fixed image acquisition device. The mobile image acquisition device is a handheld device with a built-in depth camera; for example, it can be a mobile phone with a built-in depth camera, an ipad with a built-in depth camera, etc. The fixed image acquisition device is a depth camera installed at a fixed position on the construction site, that is, a camera is installed at a fixed position on the construction site, and a shooting frequency is set for each camera, such as shooting once every 10 minutes, or shooting once every 20 minutes, or shooting once every 10 seconds. The interval time can be set by itself and is not limited here. The interval shooting times of different fixed cameras can be different. For example, in a construction site with a higher risk level, the shooting frequency can be higher, and in a construction site with a lower risk level, the shooting frequency can be set lower. If pictures are taken, taking a picture once does not only mean taking one picture, but it can be taking multiple consecutive frames of pictures.

[0069] In this embodiment, the construction site images can be acquired by a camera set at a fixed position on the construction site according to a preset shooting frequency; for the mobile image acquisition device, it can be images of the construction site taken by construction site inspectors, construction workers, or accompanying construction personnel, images of construction workers during construction, etc. By combining the use of the mobile image acquisition device and the fixed image acquisition device in this embodiment, the image acquisition during construction can be realized, and the image acquisition when not under construction can also be realized, that is, the image acquisition of the construction site is made more comprehensive.

[0070] In this embodiment, a depth camera is adopted, which can not only acquire color images but also acquire depth images. It can be understood that it can not only realize the function of an ordinary camera to shoot color images, but also obtain the point cloud data of the construction site materials, and then determine information such as the height, width, and length of the materials according to the point cloud data of the materials, so as to determine the state of the materials later (such as whether it is tilted, whether it has fallen, etc.).

[0071] The construction site condition analysis module 120 is configured to analyze the construction site images to obtain violation information.

[0072] In this embodiment, the land supply situation analysis module analyzes the land supply site images collected by the image acquisition module 110 to obtain behavior violation information, protection equipment violation information, on-site environment violation information, and project permission violation information, so as to prepare for subsequent identification of violation information.

[0073] Exemplarily, as Figure 7 shown, the construction site situation analysis module 120 includes a construction site situation analysis unit 121 and a violation analysis unit 122; among them, a safety specification knowledge graph of each project node is stored in the violation analysis unit 122.

[0074] The construction site situation analysis unit 121 is used to analyze the people, protection equipment, and on-site environment included in the construction site image according to the construction site image, so as to obtain behavior information, protection equipment information, and environment information.

[0075] Among them, the behavior information includes the person ID involved in the image, the posture and action information of each person; the protection equipment information refers to the status of the personal protection equipment (PPE) worn by the person; the environment information refers to the air environment information of the construction site (such as dust situation, rain situation, haze situation, etc.) and the material stacking information (that is, the stacking information of the tools or construction raw materials used in the construction, such as the placement information of the scaffolding, the stacking information of lime, etc.).

[0076] In some embodiments, as Figure 7 shown, the construction site situation analysis unit 121 includes a person behavior analysis subunit 1211, a protection equipment analysis subunit 1212, and an on-site environment analysis subunit 1213.

[0077] The person behavior analysis subunit 1211 is used to analyze the human body key points according to the color image to obtain the current posture and action of the person.

[0078] Exemplarily, a 3D skeleton tracking algorithm combined with 17 key points of the human body can be used to analyze the posture and action of the person. Among them, the 3D skeleton tracking algorithm is a technology for capturing and tracking human motion. It reconstructs the three-dimensional skeleton of the human body by identifying and tracking multiple key points (bone nodes) in a video or image sequence, so as to achieve the purpose of accurately analyzing the human body posture. Usually, these key points include the key points in the head area, upper limb area, and lower limb area of the body.

[0079] Among them, the 17 key points include 5 key points in the head area (nose, left eye, right eye, left ear, right ear), 6 key points in the upper limb area (left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist), and 6 key points in the lower limb area (left hip, right hip, left knee, right knee, left ankle, right ankle).

[0080] After collecting multiple consecutive construction site images through the image acquisition module 110, a human keypoint detection model, such as OpenPose, AlphaPose, or HRNet, etc., is applied to each image to locate the positions of the keypoints in the image. These models can be deep learning-based methods that can output the positions of each keypoint in the image coordinate system. Then, according to the detected keypoint positions, they are connected according to the human anatomical structure to form a skeleton model. For example, the line between the left shoulder and the right shoulder represents a part of the spine, while the line between the left shoulder and the left elbow represents the upper arm. Furthermore, the two-dimensional skeleton model is converted into a representation in three-dimensional space. The purpose of this step is to accurately represent the relative positions and orientations of various parts of the human body in three-dimensional space. Finally, by analyzing the reconstructed 3D skeleton, human pose information can be obtained, such as joint angles, bending, climbing, climbing, and limb movement trajectories, etc. By combining the analysis of the human pose with the behavior violation information obtained by the subsequent human violation analysis subunit 1221, the system can achieve 3D skeleton tracking and trajectory prediction, thereby effectively identifying and warning of behavior risks on the construction site. This not only improves the safety management level of the construction site but also can timely discover potential safety hazards and ensure the safety of workers' lives.

[0081] The protection device analysis subunit 1212 is used to detect the protection device worn by the person and the wearing state corresponding to the protection device according to the color image.

[0082] Exemplarily, the protection device analysis subunit 1212 is mainly used to analyze the personal protection devices worn by construction workers, and its personal protection devices include but are not limited to safety helmets, reflective vests, safety shoes, gloves, and safety belts, etc.

[0083] When analyzing and identifying personal protective equipment, target detection is first carried out. The purpose of target detection is to determine the body parts where each personal protective equipment should be worn. For example, for a safety helmet, the human head area needs to be detected; for a reflective vest, the upper body area of the human body needs to be detected; for safety shoes, the foot area needs to be detected, etc. For target area detection, models such as YOLO, SSD, and Faster R-CNN can be used. After determining the detection area, key point detection is carried out, which is mainly to identify the key point positions of personal protective equipment. For example, for a safety helmet, the center position at the top of the safety helmet needs to be detected to ensure that the safety helmet is above the head; for a reflective vest, the boundary position of the reflective vest needs to be detected to ensure that the reflective vest covers most of the upper body; for gloves, the position of the gloves needs to be detected to ensure that the gloves are worn on the hands, etc. Finally, compliance judgment is carried out, such as checking whether the safety helmet is above the head, whether the reflective vest covers the main part of the body, whether the safety shoes are on the feet, whether the gloves are worn on the hands, whether the safety belt is correctly fastened, etc. Through the identification and analysis of personal protective equipment, combined with the subsequent protective equipment violation information obtained through the protective equipment violation subunit 1222, the system can achieve a five-level compliance check on workers' wearing of PPE and verification of the wearing status of safety belts, thus effectively improving the safety management of the construction site. This not only helps to ensure that workers comply with safety regulations, but also can timely detect and correct non-standard behaviors, protecting the lives of workers.

[0084] The on-site environment analysis subunit 1213 is used to analyze based on the depth image and the color image to obtain air environment information and material stacking information.

[0085] Exemplarily, the on-site environment analysis subunit 1213 can analyze the obtained color image to obtain the current environmental state, such as rain conditions, haze conditions, etc.

[0086] For the acquisition of material stacking information, in this embodiment, it can be obtained through the material stack quantification method. Material stack quantification refers to measuring and calculating the specific dimensions and positions of material stacks at the construction site through technical means for better management and planning. The point cloud data obtained from the depth image is preprocessed (including but not limited to removing noise and invalid points), and then the material stack is separated from other environments using a point cloud segmentation algorithm; then three-dimensional geometric calculation algorithms (such as the minimum bounding box algorithm) are used to calculate the size parameters such as the length, width, and height of the material stack, and the centroid position of the material stack, that is, the mass center of the material stack. Through the acquisition of material stacking information in this embodiment, combined with the subsequent on-site environment violation information obtained through the on-site environment violation subunit 1223, the system can achieve accurate measurement and compliance determination of material stacks at the construction site, thus effectively improving the management level of the construction site. This not only helps to ensure that material stacking complies with the specifications, but also can timely detect and correct non-standard behaviors, ensuring construction safety.

[0087] The violation analysis unit 122 is configured to determine the violation information according to the behavior information, the protection device information, the environmental information, and in combination with the safety specification knowledge graph.

[0088] Among them, since the construction specification requirements for each construction project node may be different, a safety specification knowledge graph can be constructed for each project node. Each node in the safety specification knowledge graph represents a specific specification or standard, such as the wearing requirements of safety helmets, the setting standards of guardrails, the regulations for material stacking, etc. It can be understood that each node not only includes basic requirements but may also include specific details and standards. For example, the color, material, and position of the reflective strips of the safety helmet.

[0089] In some embodiments, as Figure 7 shown, the violation analysis unit 122 includes a personnel violation analysis subunit 1221, a protection device violation subunit 1222, and a site environment violation subunit 1223.

[0090] The personnel violation analysis subunit 1221 is configured to determine the behavior violation information according to the posture and actions of the current personnel and in combination with the safety specification knowledge graph corresponding to the current project node. It can be understood that after obtaining the posture information of the personnel through the personnel behavior analysis subunit 1211 and determining the corresponding safety specification knowledge graph according to the project node where the task is currently located, and then combining the posture information and the safety specification knowledge graph of the current project node, the behavior violation information can be determined, such as whether entering a dangerous area, whether operating without following the correct actions, etc.

[0091] The protection device violation subunit 1222 is configured to determine the protection device violation information according to the protection device worn by the personnel and the wearing state of the corresponding protection device and in combination with the safety specification knowledge graph corresponding to the current project node. It can be understood that after obtaining the personal protection device worn by the construction personnel and the wearing state through the protection device analysis subunit 1212 and determining the corresponding safety specification knowledge graph according to the project node where the construction task is currently located, and then combining the worn personal protection device and the wearing state and the safety specification knowledge graph of the current project node, the protection device violation information can be determined, such as whether all personal protection devices are worn and whether the wearing method is correct, etc.

[0092] The on-site environmental violation subunit 1223 is configured to determine the on-site environmental violation information according to the material stacking information and in combination with the safety specification knowledge graph corresponding to the current project node. It can be understood that after the air environmental information and the material stacking information are obtained through the on-site environmental analysis subunit 1213, and the safety specification knowledge graph corresponding to the current project node of the construction task is determined, and then in combination with the air environmental information, the material stacking information, and the safety specification knowledge graph of the current project node, the on-site environmental violation information can be determined, such as the materials not being placed according to the correct specifications, or non-damp materials being placed outside on rainy days, etc.

[0093] In some embodiments, the construction site condition analysis unit 121 further includes a project authority analysis subunit; the violation analysis unit 122 further includes a project authority violation subunit; when the mobile image acquisition device transmits the construction site image to the construction site condition analysis module 120, it simultaneously transmits the positioning information and the shooting time information of the mobile image acquisition device to the construction site condition analysis module 120; when the fixed image acquisition device transmits the construction site image to the construction site condition analysis module 120, it simultaneously transmits the number and the shooting time information of the fixed image acquisition device to the construction site condition analysis module 120; the project authority analysis subunit is configured to analyze the construction site image to obtain the person ID and materials at the current construction site; the project authority analysis subunit is further configured to determine the positioning information according to the number of the fixed image acquisition device; the project authority violation subunit is configured to determine the project authority violation information according to the positioning information, the shooting time information, the ID of the person, and the materials, in combination with the project implementation rules of the current project node.

[0094] It can be understood that the project permission analysis subunit is used to obtain the person ID and materials at the current construction site based on the construction site images. Since the project nodes are determined, the construction personnel required for each project node and the personnel prohibited from construction are determined at the time of project creation. Moreover, the materials required for each construction node and the materials that cannot appear at the current construction node (such as due to construction conditions, some materials may pose risks) are also preset in advance. Additionally, at some special construction sites, there are restrictions on the placement of some materials and personnel. And due to environmental impacts, some materials may not be suitable for placement at the current construction site at some times. All these pieces of information are set in the implementation rules. Therefore, in this embodiment, first, the project permission analysis subunit identifies the person ID and materials at the current construction site, and then the project permission violation subunit determines the project permission violation information based on the positioning information, the shooting time information, the person's ID, and the materials, in combination with the project implementation rules of the current project node. This can prevent construction personnel from randomly carrying out construction (if personnel unfamiliar with the project node carry out construction, safety accidents are likely to occur), and can also avoid safety accidents caused by materials not being placed as required.

[0095] The violation annotation module 130 is used to determine the violation type according to the violation information, and perform violation type annotation on the processed construction site image corresponding to the current violation information according to the determined violation type, and issue an alarm message.

[0096] Exemplarily, as Figure 8 shown, the violation annotation module 130 includes an image annotation unit 131, a risk determination unit 132, and an alarm unit 133.

[0097] The image annotation unit 131 is used to annotate the current construction site image according to the violation information determined in each construction site image. For the identified violation information, it must be annotated on the corresponding image. When annotating, the boundaries of the parts involved in the violation can be eroded / dilated, and then the corresponding violation situation can be marked. All violation situations are marked, so that subsequent statistical analysis can be carried out according to the marked situations to see which violations are more common, and corresponding measures can be taken to avoid the occurrence of such violations and improve the safety of construction.

[0098] The risk determination unit 132 is used to determine the risk category according to all the violation information determined in a preset time in the same area.

[0099] Among them, the risk categories can be predefined, and each risk category corresponds to one type of violation information or a combination of multiple types of violation information. Therefore, after obtaining the violation information at the current construction location, the risk category can be determined based on this violation information. Since each image corresponds to a shooting location and time, the risk determination unit 132 can determine the risk category based on all the images at each location within a preset time.

[0100] The alarm unit 133 is configured to give corresponding alarm indications according to the risk category.

[0101] After the risk determination unit 132 determines the risk category, the alarm unit 133 can give corresponding alarm indications according to the risk category. In this embodiment, the alarm indication can be an alarm reminder issued, or an operation of remote control, such as the alarm indication can be an audible and visual prompt, or an operation to remotely control the device to pause, etc. For example, if the risk category is that construction workers do not wear personal protective equipment correctly but are close to the energized area, then the energized device can be remotely controlled to cut off the power at this time, or if construction workers enter the site where materials are dumped but do not wear safety helmets, a red alarm can be triggered, or when working at height without wearing a safety belt, the operation authority of the tower crane can be remotely controlled to be restricted, etc.

[0102] In some embodiments, the risk determination unit 132 is further configured to determine the risk category based on all the determined violation information in the same area within a preset time and in combination with the air environment information.

[0103] In this embodiment, the risk categories are also predefined. However, when defining the risk categories, the air environment information is added, that is, when defining the risk categories, it is necessary to determine them simultaneously based on the air environment information in combination with the violation information. Since the degree of danger during construction will increase if the air environment is poor, adding the air environment information to the determination of the risk category in this embodiment will be more comprehensive.

[0104] In addition, in order to synchronize the device time used at the construction site, an NTP server can be deployed in this embodiment: that is, one or more NTP servers are deployed in the network, and these servers are responsible for providing accurate time. All devices participating in synchronization (such as cameras, mobile devices used for taking images) need to be configured as NTP clients and regularly obtain time synchronization signals from the NTP server. This can enable the system to more accurately understand multi-source data, thereby improving the reliability and accuracy of the construction site risk identification system 100.

[0105] In this embodiment, the construction site image is acquired by the image acquisition module 110, and then the acquired construction site image is processed and analyzed by the construction site situation analysis module 120 to obtain violation information. After obtaining the violation information, the corresponding parts of the violation in the construction site image are marked according to the violation type by the violation marking module 130, so as to standardize and manage the violation behavior according to the marked construction site image. In addition, this application can also give an alarm according to the violation situation. Through this risk identification system 100, this application can timely and accurately obtain the potential problems at the construction site, thereby reducing the occurrence of accidents and improving construction safety.

[0106] This application also provides a terminal device. Exemplarily, the terminal device includes a processor and a memory. Among them, the memory stores a computer program, and the processor runs the computer program to make the terminal device run the above-mentioned risk identification system 100 or the project safety management platform 1000.

[0107] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0108] The memory can be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. Among them, the memory is used to store the computer program, and after receiving the execution instruction, the processor can execute the computer program accordingly.

[0109] The present application also provides a computer-readable storage medium for storing the computer program used in the above terminal device. For example, the computer-readable storage medium may include, but is not limited to: various media such as USB flash drives, external hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0110] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and the module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0111] In addition, in each embodiment of the present application, the various functional modules or units may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0112] If the above functions are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0113] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application.

Claims

1. A risk identification system, characterized in that: include: Image acquisition module, construction site situation analysis module and violation marking module; The image acquisition module is used to receive the construction site image acquired by the image acquisition device; The construction site situation analysis module is used to analyze the construction site image to obtain violation information; wherein the violation information includes behavior violation information, protective equipment violation information, site environment violation information and project authority violation information; The violation marking module is used to mark the violation type corresponding to the construction site image according to the violation information, and determine the risk category according to the violation information.

2. The risk identification system according to claim 1, characterized in that: The construction site situation analysis module includes a construction site situation analysis unit and a violation analysis unit; wherein the violation analysis unit stores a safety specification knowledge graph of each project node; The construction site situation analysis unit is used to analyze the people, protective equipment and site environment contained in the construction site image respectively according to the construction site image to obtain behavior information, protective equipment information and environment information; The violation analysis unit is used to determine the violation information based on the behavior information, the protective equipment information and the environmental information in combination with the safety specification knowledge graph.

3. The risk identification system according to claim 2, characterized in that: The construction site image includes a color image and a depth image; the construction site situation analysis unit includes a character behavior analysis subunit, a protective equipment analysis subunit and a site environment analysis subunit; The character behavior analysis subunit is used to analyze key points of the human body according to the color image to obtain the current posture and action of the character; The protective equipment analysis subunit is used to detect the protective equipment worn by the person and the wearing status of the protective equipment according to the color image; The on-site environment analysis subunit is used to perform analysis based on the depth image and the color image to obtain air environment information and material stacking information.

4. The risk identification system according to claim 3, characterized in that: The violation analysis unit includes a person violation analysis subunit, a protective equipment violation subunit and a site environment violation subunit; The character violation analysis subunit is used to determine the behavior violation information according to the current posture and action of the character in combination with the safety specification knowledge graph corresponding to the current project node; The protective equipment violation subunit is used to determine the protective equipment violation information according to the protective equipment worn by the person and the wearing status of the protective equipment, combined with the safety specification knowledge graph corresponding to the current project node; The on-site environmental violation sub-unit is used to determine the on-site environmental violation information based on the material stacking information and the safety specification knowledge graph corresponding to the current project node.

5. The risk identification system according to claim 2, characterized in that: The image acquisition device includes a mobile image acquisition device and a fixed image acquisition device; The mobile image acquisition device is a handheld device with a built-in depth camera; The fixed image acquisition device is a depth camera installed on the construction site.

6. The risk identification system according to claim 3, characterized in that: The construction site situation analysis unit further includes a project authority analysis subunit; the violation analysis unit further includes a project authority violation subunit; The mobile image acquisition device is further used to transmit the positioning information and shooting time information of the mobile image acquisition device to the construction site situation analysis module; The fixed image acquisition device is further used to transmit the serial number and shooting time information of the fixed image acquisition device to the construction site situation analysis module; The project authority analysis subunit is used to analyze the construction site image to obtain the person ID and materials at the current construction site; The project authority analysis subunit is further used to determine the positioning information according to the serial number of the fixed image acquisition device; The project authority violation subunit is used to determine the project authority violation information based on the positioning information, the shooting time information, the person's ID and the material, combined with the project implementation rules of the current project node.

7. The risk identification system according to claim 3, characterized in that: The violation labeling module includes an image labeling unit, a risk determination unit and an alarm unit; The image annotation unit is used to annotate the current construction site image according to the violation information determined in each construction site image; The risk determination unit is used to determine the risk category according to all the violation information determined in the same area within a preset time; The alarm unit is used to make corresponding alarm indications according to the risk category.

8. The risk identification system according to claim 7, characterized in that: The risk determination unit is further used to determine the risk category based on all the violation information determined in the same area within a preset time in combination with the air environment information.

9. An engineering safety management platform, characterized in that: The engineering safety management platform includes a risk identification system as described in any one of claims 1-8.

10. A terminal device, characterized in that: The terminal device includes a processor and a memory, the memory stores a computer program, and the processor is used to execute the computer program to run the risk identification system described in any one of claims 1 to 8, or to run the computer program to implement the module function in the engineering safety management platform described in claim 9.