Construction risk early warning method, device, equipment, storage medium and product

Abstract

The invention discloses a construction risk early warning method and device, equipment, a storage medium and a product, and relates to the technical field of the Internet of Things, the construction risk early warning method comprises the following steps: obtaining inspection image data of each engineering area, the inspection image data being obtained after an unmanned aerial vehicle inspects the engineering area according to a preset inspection route; and inputting the inspection image data to a preset risk prediction model, and based on the preset risk prediction model, performing prediction processing on the inspection image data to obtain a risk prediction result, the risk prediction result being obtained by performing prediction based on a risk logic relationship in different image data. And carrying out risk early warning on each engineering area based on the risk prediction result. The technical effect of comprehensively checking potential safety hazards is achieved.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, and in particular to a construction risk early warning method, device, equipment, storage medium, and computer program product. Background Technology

[0002] During construction, safety hazards often exist, such as workers not wearing proper personal protective equipment (safety helmets, safety belts, etc.) or areas near edges not being fenced off. Currently, AI technology is used to identify typical photos. This method is suitable for spot checks of typical construction sites. It simplifies the use of drones for inspections, collects typical photos, and uses AI to identify them, which can yield some localized safety risk results. However, relying solely on a few typical images cannot truly achieve the goal of comprehensively identifying all safety hazards.

[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a construction risk early warning method, device, equipment, storage medium, and computer program product, which aims to solve the technical problem in related technologies that, while AI technology can be used to identify typical photos and obtain some local slice-like results of safety risks, it is impossible to truly achieve the goal of comprehensively investigating potential safety hazards based on only a portion of typical images.

[0005] To achieve the above objectives, this application proposes a construction risk early warning method, which includes:

[0006] The inspection image data of each engineering area is obtained by the UAV after inspecting the engineering area according to the preset inspection route.

[0007] The inspection image data is input into a preset risk prediction model. Based on the preset risk prediction model, the inspection image data is processed to obtain a risk prediction result. The risk prediction result is obtained based on the risk logic relationship in different image data.

[0008] Based on the risk prediction results, risk warnings are issued for each of the aforementioned engineering areas.

[0009] In one embodiment, before the step of acquiring inspection image data for each engineering area, the method further includes:

[0010] Obtain the engineering architecture for each engineering region;

[0011] Based on the aforementioned engineering architecture, a preset inspection route for the UAV is constructed.

[0012] Based on the preset inspection route and preset inspection plan, the drone is controlled to inspect each engineering area and obtain inspection image data.

[0013] In one embodiment, the step of constructing a preset inspection route for the UAV based on the engineering architecture includes:

[0014] Based on the aforementioned engineering architecture, construct 3D reality models and BIM models for each engineering area;

[0015] By integrating the 3D reality model with the BIM model through a digital twin platform, an engineering digital twin model is obtained.

[0016] Based on the aforementioned engineering digital twin model, a pre-defined inspection route for the UAV is planned.

[0017] In one embodiment, the step of performing predictive processing on the inspection image data based on the preset risk prediction model to obtain a risk prediction result includes:

[0018] Based on the preset risk prediction model, construction objects in the inspection image data are identified;

[0019] Determine the timestamp and spatial location of each construction object;

[0020] Based on the preset risk knowledge base, the timestamp, and the spatial location, the risk logic relationship of each combination of construction objects is analyzed to obtain the construction risk probability.

[0021] Based on the construction risk probability, a risk prediction result is generated.

[0022] In one embodiment, the step of providing risk warnings for each of the engineering areas based on the risk prediction results includes:

[0023] Based on the risk prediction results, the construction objects where risks have occurred are located;

[0024] Risk warnings are issued for the construction object, and the corresponding risk alerts are displayed visually on the user's device.

[0025] In one embodiment, before the step of acquiring inspection image data for each engineering area, the method further includes:

[0026] Based on the preset construction safety specifications, various construction objects are logically combined to obtain multiple construction logical combinations;

[0027] Calculate the probability of risk for each of the aforementioned construction logic combinations;

[0028] A mapping relationship between risk-causing factors and risk probabilities is constructed in each of the aforementioned construction logic combinations, resulting in a preset risk knowledge base that includes construction safety hazard events and risk-causing factors.

[0029] Furthermore, to achieve the above objectives, this application also proposes a construction risk early warning device, which includes:

[0030] The first acquisition module is used to acquire inspection image data of each engineering area. The inspection image data is obtained by the UAV inspecting the engineering area according to the preset inspection route.

[0031] The processing module is used to input the inspection image data into a preset risk prediction model, and perform prediction processing on the inspection image data based on the preset risk prediction model to obtain a risk prediction result. The risk prediction result is obtained based on the risk logical relationship in different image data.

[0032] The risk warning module is used to provide risk warnings for each of the engineering areas based on the risk prediction results.

[0033] In addition, to achieve the above objectives, this application also proposes a construction risk early warning device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the construction risk early warning method as described above.

[0034] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the construction risk warning method described above.

[0035] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the construction risk warning method described above.

[0036] This application proposes a construction risk early warning method, device, equipment, storage medium, and computer program product. This application acquires inspection image data of various engineering areas, uses a preset risk prediction model to predict and process the inspection image data, and obtains risk prediction results. Since the risk prediction results are based on the risk logic relationship in different image data, the risk logic between various images can be determined, rather than simply judging whether there is a risk in an area from one or two photos. Based on the risk prediction results, risk warnings are issued for each engineering area, thereby achieving the goal of comprehensively investigating potential safety hazards. Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating an embodiment of the construction risk early warning method of this application.

[0040] Figure 2 This is a schematic diagram of a three-dimensional real-scene model related to the construction risk early warning method in this application;

[0041] Figure 3 This is a schematic diagram of the BIM model of the project involved in the construction risk early warning method of this application;

[0042] Figure 4 This is a schematic diagram of the digital twin model of the project involved in the construction risk early warning method of this application;

[0043] Figure 5 This is a schematic diagram of the module structure of the construction risk early warning device according to an embodiment of this application;

[0044] Figure 6 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the construction risk early warning method in this application embodiment.

[0045] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0046] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0047] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0048] The main solution in this application embodiment is:

[0049] The inspection image data of each engineering area is obtained by the UAV after inspecting the engineering area according to the preset inspection route.

[0050] The inspection image data is input into a preset risk prediction model. Based on the preset risk prediction model, the inspection image data is processed to obtain a risk prediction result. The risk prediction result is obtained based on the risk logic relationship in different image data.

[0051] Based on the risk prediction results, risk warnings are issued for each of the aforementioned engineering areas.

[0052] Because existing technologies use AI to identify typical photos, this method is suitable for spot-checking safety inspections of typical construction sites. It simplifies the use of drones for inspections, collects typical photos, and performs AI recognition on the photos, which can yield some localized slices of safety risk information. However, it cannot truly achieve the goal of comprehensively identifying all potential safety hazards based on only a few typical images.

[0053] This application proposes a construction risk early warning method, device, equipment, storage medium, and computer program product. This application acquires inspection image data of various engineering areas, uses a preset risk prediction model to predict and process the inspection image data, and obtains risk prediction results. Since the risk prediction results are based on the risk logic relationship in different image data, the risk logic between various images can be determined, rather than simply judging whether there is a risk in an area from one or two photos. Based on the risk prediction results, risk warnings are issued for each engineering area, thereby achieving the goal of comprehensively investigating potential safety hazards.

[0054] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or construction risk early warning device capable of performing the above functions. The following description uses a construction risk early warning device as an example to illustrate this embodiment and the subsequent embodiments.

[0055] Based on this, the embodiments of this application provide a construction risk early warning method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the construction risk early warning method of this application.

[0056] In this embodiment, the construction risk early warning method includes steps S10 to S30:

[0057] Step S10: Obtain inspection image data for each engineering area. The inspection image data is obtained by the UAV inspecting the engineering area according to the preset inspection route.

[0058] It should be noted that the construction area includes multiple areas. For example, when building a bridge, it may extend for hundreds of meters or even several kilometers. When using drones to inspect these construction areas, it is impossible to collect images of all these areas at once. Therefore, it is necessary to divide the entire construction area into multiple engineering areas and then use drones to inspect these areas to obtain the required inspection image data.

[0059] It should be noted that the inspection image data can be images taken by drones at a certain angle. When taking pictures, the drone's shooting route and shooting cycle should be set to ensure that the drone can collect construction image data of the entire area and fully cover all places where risks may occur.

[0060] It should be noted that the preset inspection route is constructed based on the layout of the construction area and is planned before the drone takes pictures of each engineering area. The preset inspection route can be changed at any time according to the user's needs. For example, after a long period of rectification, there are no longer any risky areas in a certain area, so this area can be skipped for a short time and other areas can be selected first.

[0061] It should be noted that, generally speaking, to facilitate AI recognition and analysis of security risks in photos, the pixel resolution of the photos must meet certain standards. Based on the imaging performance of a typical drone camera, each photo typically covers a ground area of ​​approximately 80m x 60m. Considering full coverage requirements, the overlap is generally no less than 20%-30%. Taking a 10-kilometer, six-lane, two-way highway project as an example, the construction site is approximately 10 kilometers long and 100 meters wide. Each scan of the entire site will generate about 350 photos. Three daily inspections (morning, noon, and evening) will generate approximately 1000 photos. For each photo to undergo AI recognition, analysis of security risks, and early warning, it is crucial to ensure that the massive number of security risks identified from these photos are unique, in order to achieve closed-loop management of security risks.

[0062] In one feasible implementation, before step S10 of acquiring inspection image data for each engineering area, the method further includes:

[0063] Obtain the engineering architecture for each engineering region;

[0064] It should be noted that the engineering architecture can be the construction architecture of each engineering area. For example, when building a bridge, the engineering architecture can be the bridge structure, construction scaffold, personnel distribution, etc., or other engineering objects, without any specific limitations.

[0065] Based on the aforementioned engineering architecture, a preset inspection route for the UAV is constructed.

[0066] It should be noted that after obtaining the engineering architecture, the inspection route of the drone is constructed by the distribution of each engineering architecture. Constructing the drone's preset inspection route involves multiple steps, including requirements analysis, environmental assessment, route planning, software development, and testing.

[0067] Based on the preset inspection route and preset inspection plan, the drone is controlled to inspect each engineering area and obtain inspection image data.

[0068] It should be noted that the preset inspection plan can be the cycle and frequency of drone inspections, for example, it can be an inspection once every 1 hour or an inspection once every 2 hours.

[0069] It should be noted that various typical projects are selected, drone inspections are carried out, and photos of various construction conditions are collected. Using the photos collected by drones, an AI recognition training set for various objects within the construction site is gradually accumulated. This training set should cover various objects, and there should be no less than 100 typical photos for each object. These photos together constitute the inspection image data.

[0070] In one feasible implementation, the step of constructing the preset inspection route of the UAV based on the engineering architecture includes:

[0071] Based on the aforementioned engineering architecture, construct 3D reality models and BIM models for each engineering area;

[0072] It should be noted that 3D reality models, such as Figure 2 As shown, the process of building a 3D reality model is as follows:

[0073] Point cloud processing: Import the collected point cloud data of the engineering architecture into professional software such as CloudCompare and Autodesk ReCap for preprocessing such as denoising, stitching, and registration.

[0074] Reality modeling: Using reality modeling software such as ContextCapture and Pix4Dmapper, a 3D reality model is generated based on point clouds or images.

[0075] Enhanced details: The realism of the model is improved by adding texture maps and other methods.

[0076] BIM model such as Figure 3 As shown, the BIM model construction process is as follows:

[0077] Choose the right BIM platform: Select the appropriate BIM software based on project requirements.

[0078] Establishing the basic framework: Start creating the basic structure of the building on the BIM platform based on the design drawings.

[0079] Add component information: Add detailed attribute information for each component, such as material type, size specifications, etc.

[0080] Integrated system information: including the design of electrical, water supply and drainage, HVAC and other systems, and integrated with the main building model.

[0081] By integrating the 3D reality model with the BIM model through a digital twin platform, an engineering digital twin model is obtained.

[0082] It should be noted that digital twin platforms can be Autodesk Forge, Bentley iTwins, Dassault Systèmes 3DEXPERIENCE, etc., and there are no specific limitations.

[0083] It should be noted that the schematic diagram of the engineering digital twin model is as follows: Figure 4 As shown, the process of integrating the 3D reality model with the BIM model can be as follows:

[0084] Convert the 3D reality model and BIM model to a format supported by the platform (such as IFC, OBJ, FBX, etc.), ensuring that the two models use the same coordinate system to ensure that they are correctly aligned in space. Then import the 3D reality model and BIM model into the digital twin platform respectively.

[0085] Adjust the position of the models on the platform to ensure precise alignment in space; establish the relationship between objects in the 3D reality model and corresponding components in the BIM model; integrate the hierarchical structure of the models to ensure the consistency and integrity of information. After completing the above steps, the required engineering digital twin model is obtained.

[0086] Based on the aforementioned engineering digital twin model, a pre-defined inspection route for the UAV is planned.

[0087] It should be noted that by analyzing the layout of buildings and facilities, as well as the surrounding environment, in the engineering digital twin model, key areas requiring focused inspection are identified, such as power lines, pipes, and roofs. Potentially hazardous areas or obstacles are marked to prevent drones from flying in these locations.

[0088] Next, inspection goals are set, defining the specific purpose of each inspection, such as checking equipment status, taking photos and videos, and detecting abnormalities. Based on the inspection goals, the location of each inspection point is marked in the digital twin model, and then a preliminary drone inspection route is planned based on these locations.

[0089] Step S20: Input the inspection image data into a preset risk prediction model, and perform prediction processing on the inspection image data based on the preset risk prediction model to obtain a risk prediction result. The risk prediction result is obtained based on the risk logical relationship in different image data.

[0090] It should be noted that the preset risk prediction model can be a neural network model based on deep learning. By performing image analysis on the inspection image data, it can predict the probability of risk in each image data. In the process of analyzing the image data, it can make predictions based on the risk logic relationship of different image data, and then generate risk prediction results.

[0091] It should be noted that different combinations of construction objects at a construction site can lead to safety risk events. Analyzing only a single construction object is insufficient to determine whether a scene in the image presents a risk. By analyzing potential safety risk events (accidents) under various construction conditions, and identifying objects that can cause such events, these objects become the risk factors. This ultimately forms a database of construction safety risk events and risk factors, establishing logical relationships. For example: ① Object A ∩ Object B = Risk Event I (Logical relationship: The simultaneous existence of Object A and Object B leads to Risk Event I), a large full-span scaffold (Object A), temporarily storing a large amount of steel reinforcement (Object B), will lead to a collapse (Risk Event I); ② Object A - Object B = Risk Event I (Logical relationship: The occurrence of Object A, but the absence of Object B, will lead to Risk Event I), the installation of the bridge cap beam steel cage (Object A), without a perimeter fence (Object B), will lead to a fall from height (Risk Event I). The essence of construction safety hazards is that different combinations of objects at the construction site may lead to a certain safety risk event. At this time, there is a safety hazard, and it is necessary to issue an early warning, point out the risk factors, and propose rectification measures.

[0092] In one feasible implementation, step S20, which involves performing prediction processing on the inspection image data based on the preset risk prediction model to obtain a risk prediction result, includes:

[0093] Based on the preset risk prediction model, construction objects in the inspection image data are identified;

[0094] It should be noted that the objects of construction can be scaffolding, workers, fences, and steel bars, etc., without any specific restrictions.

[0095] Determine the timestamp and spatial location of each construction object;

[0096] It should be noted that by locating each construction object and recording its timestamp and spatial location, consistency between time and space is ensured.

[0097] It should be noted that by establishing the transformation relationship between photo pixel coordinates and the Gaussian Cartesian coordinate system, the spatial location of the construction object is determined, so that each object identified by the AI ​​in the photo can be assigned spatial coordinates, ensuring that each object has a unique spatial location.

[0098] Specifically, the coordinate systems are defined as follows: ① Image space coordinate system s. The origin Os is the projection center, Xs and Ys are parallel to the outer frame of the imaging array and are consistent with the image display and storage direction, Zs is determined according to the right-hand coordinate system, and the camera optical axis is the Zs axis; ② UAV body coordinate system b. The origin Ob is the aircraft's center of mass, Xb points to the right, Yb points forward, and Zb points upward; ③ UAV geographic coordinate system e. The origin Oe is the aircraft's center of mass, Xe points to the east, Ye points to the north, and Ze points to the sky; ④ Gaussian plane rectangular coordinate system g.

[0099] Let the elevation angle of the UAV camera gimbal be α, the azimuth angle be β, the yaw angle be ψ, the pitch angle be θ, and the tilt angle be γ. Based on the coordinate transformation principle, obtain the coordinate transformation matrix between different coordinate systems. Let the target's coordinates in the UAV's geographic coordinate system e be (x... e y e , z e The target's coordinates in the image space coordinate system s are (x...). s y s Let f be the focal length of the camera or video camera. The coordinate transformation relationship between the two can be expressed as:

[0100]

[0101] Let the coordinates of the target in the Gaussian plane rectangular coordinate system g be (x... g y g The coordinates of the UAV in the Gaussian Cartesian coordinate system g are (x...). a y a Let H be the relative height between the UAV and the ground target point. Based on the UAV attitude data, camera attitude data, and intrinsic parameters, the Gaussian Cartesian coordinates of any pixel in the aerial image can be calculated.

[0102]

[0103] Based on the preset risk knowledge base, the timestamp, and the spatial location, the risk logic relationship of each combination of construction objects is analyzed to obtain the construction risk probability.

[0104] It should be noted that by using a pre-set risk knowledge base, the risk logic relationship of the combination of the various construction objects is analyzed to determine whether each construction object in the image has a risk. The timestamp and spatial location are used to ensure consistency between time and space and to avoid inaccurate analysis.

[0105] It should be noted that the construction risk probability is the probability that each construction object will encounter a risk. The construction risk probability can be 0.1, 0.5, etc., and there is no specific limitation.

[0106] Based on the construction risk probability, a risk prediction result is generated.

[0107] It should be noted that by correlating each construction object with its construction risk probability, the corresponding risk prediction results are obtained.

[0108] Step S30: Based on the risk prediction results, conduct risk warnings for each of the engineering areas.

[0109] It should be noted that, based on the risk prediction results, the risks of each engineering area are classified into levels, which can be low, medium, or high. Then, the risks of each area are prioritized according to the risk level, and the technical personnel in each area are notified through early warning.

[0110] In one feasible implementation, step S30, which involves issuing risk warnings for each of the engineering areas based on the risk prediction results, includes:

[0111] Based on the risk prediction results, the construction objects where risks have occurred are located;

[0112] It should be noted that data analysis identifies potential risk factors, such as natural disasters, equipment failures, human error, and specific construction objects that pose risks.

[0113] Risk warnings are issued for the construction object, and the corresponding risk alerts are displayed visually on the user's device.

[0114] It should be noted that providing risk warnings for construction projects and displaying them visually on the user end, which is the equipment where the technical personnel are located, ensures that all technical personnel can be notified in a timely manner, thereby improving the safety and management efficiency of the construction site.

[0115] In one feasible implementation, prior to the step of acquiring inspection image data for each engineering area, the method further includes:

[0116] Based on the preset construction safety specifications, various construction objects are logically combined to obtain multiple construction logical combinations;

[0117] It should be noted that the pre-set construction safety specifications may include the "Technical Specifications for Construction Safety of Highway Engineering" (JTGF9), the "Technical Specifications for Safety of High-Altitude Operations in Building Construction" (JGJ80), and the "General Safety Technical Regulations for Construction of Water Conservancy and Hydropower Projects" (SL398), etc.

[0118] It should be noted that various construction objects are logically combined to obtain multiple construction logical combinations. Based on the prescribed standards, it is determined whether these combined objects pose any risks.

[0119] Calculate the probability of risk for each of the aforementioned construction logic combinations;

[0120] It should be noted that the probability of risk of each combination of construction logic can be determined through model analysis. The essence of construction safety hazards is that different combinations of objects at the construction site may lead to a certain safety risk event. At this time, there is a safety hazard, and an early warning must be issued, the risk factors must be identified, and rectification measures must be proposed.

[0121] A mapping relationship between risk-causing factors and risk probabilities is constructed in each of the aforementioned construction logic combinations, resulting in a preset risk knowledge base that includes construction safety hazard events and risk-causing factors.

[0122] It should be noted that when different objects at the construction site are combined, they may lead to safety risk events. These objects are called risk factors. This results in a database of construction safety risk events and risk factors, which are logically related to each construction object. Each object influences the others and may generate potential risks. The mapping relationship exists between the risk factors and the probability of risk in the logical combination of construction, which can ensure that the two correspond and quickly identify risks.

[0123] This application proposes a construction risk early warning method, device, equipment, storage medium, and computer program product. This application acquires inspection image data of various engineering areas, uses a preset risk prediction model to predict and process the inspection image data, and obtains risk prediction results. Since the risk prediction results are based on the risk logic relationship in different image data, the risk logic between various images can be determined, rather than simply judging whether there is a risk in an area from one or two photos. Based on the risk prediction results, risk warnings are issued for each engineering area, thereby achieving the goal of comprehensively investigating potential safety hazards.

[0124] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the construction risk warning method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0125] This application also provides a construction risk early warning device; please refer to... Figure 5 The construction risk early warning device includes:

[0126] The first acquisition module 10 is used to acquire inspection image data of each engineering area. The inspection image data is obtained by the UAV inspecting the engineering area according to the preset inspection route.

[0127] Processing module 20 is used to input the inspection image data into a preset risk prediction model, and perform prediction processing on the inspection image data based on the preset risk prediction model to obtain a risk prediction result, wherein the risk prediction result is obtained based on the risk logical relationship in different image data.

[0128] The risk warning module 30 is used to provide risk warnings for each of the engineering areas based on the risk prediction results.

[0129] Optionally, the device further includes:

[0130] The second first acquisition module is used to acquire the engineering architecture of each engineering area;

[0131] The first construction module is used to construct the preset inspection route of the UAV based on the engineering architecture.

[0132] The control module is used to control the UAV to inspect various engineering areas based on the preset inspection route and preset inspection plan, and obtain inspection image data.

[0133] Optionally, the first building module includes:

[0134] The construction unit is used to construct 3D reality models and BIM models of each engineering area based on the engineering architecture.

[0135] The fusion unit is used to fuse the three-dimensional real-scene model with the BIM model through a digital twin platform to obtain an engineering digital twin model;

[0136] The planning unit is used to plan the preset inspection route of the UAV based on the engineering digital twin model.

[0137] Optionally, the processing module includes:

[0138] The identification unit is used to identify construction objects in the inspection image data based on the preset risk prediction model.

[0139] A determining unit is used to determine the timestamp and spatial location of each of the construction objects;

[0140] The analysis unit is used to analyze the risk logic relationship of each combination of construction objects based on a preset risk knowledge base, the timestamp, and the spatial location, and to obtain the construction risk probability.

[0141] The generation unit is used to generate risk prediction results based on the construction risk probability.

[0142] Optionally, the risk warning module includes:

[0143] The positioning unit is used to locate the construction object that is at risk based on the risk prediction results;

[0144] The visualization unit is used to provide risk warnings for the construction object and to visualize the risk warnings corresponding to the risk warnings on the user's end.

[0145] Optionally, the device further includes:

[0146] The combination module is used to logically combine various construction objects based on preset construction safety specifications to obtain multiple construction logic combinations;

[0147] The calculation module is used to calculate the probability of danger for each of the aforementioned construction logic combinations;

[0148] The second construction module is used to construct the mapping relationship between risk factors and risk probabilities in each of the construction logic combinations, and to obtain a preset risk knowledge base including construction safety hazard events and risk factors.

[0149] The construction risk early warning device provided in this application, employing the construction risk early warning method in the above embodiments, can solve the technical problem of construction risk early warning. Compared with the prior art, the beneficial effects of the construction risk early warning device provided in this application are the same as those of the construction risk early warning method provided in the above embodiments, and other technical features in the construction risk early warning device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0150] This application provides a construction risk early warning device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the construction risk early warning method in the above embodiment 1.

[0151] The following is for reference. Figure 6 The diagram illustrates a structural schematic suitable for implementing the construction risk early warning device in the embodiments of this application. The construction risk early warning device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6The construction risk early warning device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0152] like Figure 6 As shown, the construction risk early warning device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the construction risk early warning device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the construction risk early warning device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows construction risk early warning devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0153] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0154] The construction risk early warning device provided in this application, employing the construction risk early warning method in the above embodiments, can solve the technical problem of construction risk early warning. Compared with the prior art, the beneficial effects of the construction risk early warning device provided in this application are the same as those of the construction risk early warning method provided in the above embodiments, and other technical features of the construction risk early warning device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0155] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0156] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0157] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the construction risk warning method in the above embodiments.

[0158] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0159] The aforementioned computer-readable storage medium may be included in the construction risk early warning device; or it may exist independently and not be assembled into the construction risk early warning device.

[0160] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the construction risk early warning device, cause the construction risk early warning device to:

[0161] The inspection image data of each engineering area is obtained by the UAV after inspecting the engineering area according to the preset inspection route.

[0162] The inspection image data is input into a preset risk prediction model. Based on the preset risk prediction model, the inspection image data is processed to obtain a risk prediction result. The risk prediction result is obtained based on the risk logic relationship in different image data.

[0163] Based on the risk prediction results, risk warnings are issued for each of the aforementioned engineering areas.

[0164] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0165] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0166] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0167] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described construction risk warning method, thereby solving the technical problem of construction risk warning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the construction risk warning method provided in the above embodiments, and will not be repeated here.

[0168] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the construction risk warning method described above.

[0169] The computer program product provided in this application can solve the technical problem of construction risk early warning. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the construction risk early warning method provided in the above embodiments, and will not be repeated here.

[0170] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A construction risk early warning method, characterized in that: The method comprises: Obtaining inspection image data of each engineering area, wherein the inspection image data is obtained after the UAV inspects the engineering area according to a preset inspection route; Inputting the inspection image data into a preset risk prediction model, and performing prediction processing on the inspection image data based on the preset risk prediction model to obtain a risk prediction result, wherein the risk prediction result is obtained by prediction based on the risk logical relationship in different image data; Based on the risk prediction results, risk warnings are issued for each of the project areas.

2. The method according to claim 1, characterized in that Before the step of acquiring the inspection image data of each engineering area, the method further includes: Get the engineering architecture of each engineering area; Based on the engineering architecture, a preset inspection route of the drone is constructed; Based on the preset inspection route and the preset inspection plan, the drone is controlled to inspect each engineering area to obtain inspection image data.

3. The method according to claim 2, characterized in that The step of constructing a preset inspection route of the drone based on the engineering architecture includes: Based on the engineering framework, construct a three-dimensional real-scene model and a BIM model of each engineering area; The three-dimensional real scene model is integrated with the BIM model through the digital twin platform to obtain a digital twin model of the project; Based on the engineering digital twin model, a preset inspection route for the drone is planned.

4. The method according to claim 1, characterized in that The step of performing prediction processing on the inspection image data based on the preset risk prediction model to obtain a risk prediction result includes: Based on the preset risk prediction model, identifying the construction objects in the inspection image data; Determining the timestamp and spatial location of each of the construction objects; Based on the preset risk knowledge base, the timestamp and the spatial position, the risk logic relationship after each combination of the construction objects is analyzed to obtain the construction risk probability; Based on the construction risk probability, a risk prediction result is generated.

5. The method according to claim 1, characterized in that The step of providing risk warning for each of the project areas based on the risk prediction result comprises: Based on the risk prediction results, locate the construction object with risks; A risk warning is issued for the construction object, and a risk prompt corresponding to the risk warning is visually displayed on the user end.

6. The method according to claim 1, characterized in that Before the step of acquiring the inspection image data of each engineering area, the method further includes: Based on the preset construction safety specifications, each construction object is logically combined to obtain multiple construction logic combinations; Calculating the risk probability of each construction logic combination; A mapping relationship between the risk factors and the risk probability in each of the construction logic combinations is constructed to obtain a preset risk knowledge base including construction safety hazard events and risk factors.

7. A construction risk early warning device, characterized in that: The device comprises: The first acquisition module is used to acquire inspection image data of each engineering area, wherein the inspection image data is obtained after the drone inspects the engineering area according to a preset inspection route; A processing module, used for inputting the inspection image data into a preset risk prediction model, and performing prediction processing on the inspection image data based on the preset risk prediction model to obtain a risk prediction result, wherein the risk prediction result is obtained by prediction based on the risk logical relationship in different image data; The risk warning module is used to issue risk warnings to each of the engineering areas based on the risk prediction results.

8. A construction risk early warning device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the construction risk early warning method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the construction risk early warning method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the construction risk early warning method according to any one of claims 1 to 6 are implemented.

Images