Method and apparatus for evaluating risk of construction field using ai

Abstract

A method and apparatus for evaluating the risk of a construction site using artificial intelligence are disclosed. The disclosed method for evaluating the risk of a construction site comprises the steps of: receiving a bird's-eye view image of the construction site captured by a drone hovering over the construction site; evaluating the risk of the construction site using the bird's-eye view image, weather data and work process data for the construction site; and dividing the bird's-eye view image into a plurality of zones according to the level of the risk.

Description

Technology Field

[0001] The present invention relates to a method and apparatus for evaluating the risk level of a construction site, and more specifically, to a method and apparatus for evaluating the risk level of a construction site using artificial intelligence. Background Technology

[0003] Risks at construction sites can result in casualties and property damage. Therefore, safety management at construction sites is crucial.

[0004] Existing methods for assessing risk at construction sites rely on the experience and knowledge of experts. However, these methods are subjective and may not be able to consider all risk factors.

[0005] With the recent advancement of artificial intelligence technology, methods to evaluate risks at construction sites using AI are being researched and developed.

[0006] Relevant prior art includes Korean registered patents No. 10-2595564, No. 10-2832498, No. 10-2600405, and Korean published patent No. 2024-0092677. The problem to be solved

[0008] The present invention is intended to provide a method and device capable of accurately evaluating the risk level of a construction site using artificial intelligence and drones. means of solving the problem

[0010] According to one embodiment of the present invention for achieving the above-mentioned purpose, a method for evaluating the risk of a construction site is provided, comprising: receiving a bird's-eye view image of the construction site captured by a drone hovering over the construction site; evaluating the risk of the construction site using the bird's-eye view image, weather data and work process data for the construction site; and dividing the bird's-eye view image into a plurality of zones according to the level of the risk.

[0011] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for assessing risk for a construction site is provided, which includes movement information of the drone received from the drone, and weather data.

[0012] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for evaluating the risk of a construction site is provided, comprising the steps of: classifying the class of an object included in the bird's-eye view image using a pre-trained artificial intelligence model; and determining the class used in the current work process among the classes according to the work process data, and evaluating the risk of the object for each class.

[0013] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for evaluating the risk of an object by class is provided, wherein the step of evaluating the risk of an object by class involves considering the current weather conditions to determine an object of a class used in the current work process that has a risk level of the first and second levels, and determining the risk level of an object of the remaining class as the third level, wherein the first level is the level with the maximum risk and the third level is the level with the minimum risk.

[0014] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for assessing the risk of a construction site is provided, wherein the plurality of zones includes first and second zones each containing objects of first and second risk levels, and the size of the first and second zones is determined according to the size of the objects and the speed of movement of the objects at the construction site.

[0015] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for assessing risk for a construction site is provided in which the sizes of the first and second zones are dynamically adjusted according to the current weather conditions.

[0016] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for assessing risk of a construction site is provided, further comprising the steps of: confirming the location of a worker at the construction site; and transmitting an escape message to a worker located in an area where the first and second zones overlap.

[0017] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for assessing the risk of a construction site is provided, wherein the step of transmitting the escape message is when the overlap of the first and second zones is maintained for a preset time or longer, and the size of the overlapped area is greater than or equal to a preset size.

[0018] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for assessing risk for a construction site is provided, wherein the step of transmitting the escape message includes transmitting the escape message including an escape path from the overlapping area, and the escape path is an escape path that does not pass through the overlapping area.

[0019] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for assessing risk of a construction site is provided, further comprising the steps of: dynamically determining the hovering position of the drone according to at least one of the class of objects included in the first and second zones, the location, size, and number of the first and second zones; and transmitting the determined hovering position to the drone.

[0020] In addition, according to one embodiment of the present invention for achieving the above-mentioned purpose, a method for assessing risk for a construction site is provided, wherein the step of dynamically determining the hovering position of the drone is to be close to the first and second zones.

[0021] In addition, according to another embodiment of the present invention for achieving the above-mentioned purpose, a risk assessment device for a construction site is provided, comprising: a communication module that receives a bird's-view image of the construction site captured by a drone hovering over the construction site; a memory; and a processor electrically connected to the memory, wherein the processor evaluates the risk of the construction site using a pre-trained classification model, the bird's-view image, weather data and work process data for the construction site, and divides the bird's-view image into a plurality of zones according to the level of the risk. Effects of the invention

[0023] A drone can generate images containing objects such as heavy equipment located at a construction site without blind spots from above the construction site, and since the class of construction site objects can be accurately classified through an artificial intelligence model, according to one embodiment of the present invention, the accuracy of risk assessment for a construction site can be improved. Brief explanation of the drawing

[0025] FIG. 1 is a drawing illustrating a risk assessment system for a construction site according to an embodiment of the present invention. FIG. 2 is a drawing illustrating a method for assessing risk at a construction site according to an embodiment of the present invention. Specific details for implementing the invention

[0026] The present invention is susceptible to various modifications and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the invention to specific embodiments, and it should be understood that the invention includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. Similar reference numerals have been used for similar components in the description of each drawing.

[0027] Hereinafter, embodiments according to the present invention will be described in detail with reference to the attached drawings.

[0029] FIG. 1 is a drawing illustrating a risk assessment system for a construction site according to an embodiment of the present invention.

[0030] Referring to FIG. 1, a cognitive ability evaluation system according to one embodiment of the present invention includes a drone (110) and a risk evaluation device (120).

[0031] A drone (110) generates a bird's-eye view image of a construction site from above the construction site. The construction site may be a site where various types of construction work are being carried out, such as buildings, bridges, or roads. The drone (110) may generate a bird's-eye view image while hovering above the construction site. The drone (110) may include a camera and an inertial sensor for generating the bird's-eye view image, and the inertial sensor may generate movement information of the drone (110). The drone (110) may fly over the construction site while construction is in progress or may fly over the construction site periodically.

[0032] The risk assessment device (120) includes a communication module (121), a memory (122), and a processor (123) and assesses the risk of a construction site. The processor (123) performs a series of processes for risk assessment, and the risk assessment can be performed periodically.

[0033] The communication module (121) receives a bird's-eye view image of the construction site, which is captured by a drone (110) hovering over the construction site. The communication module (121) may receive the bird's-eye view image from the drone (110) or receive the bird's-eye view image from an image processing device that processes the bird's-eye view image received from the drone (110). Additionally, the communication module (121) may transmit the hovering position of the drone (110) to the drone (110).

[0034] The processor (123) is electrically connected to the memory (122) and evaluates the risk level of the construction site using a bird's-eye view image, weather data for the construction site, and work process data. At this time, the processor (123) can evaluate the risk level using an artificial intelligence model, and the artificial intelligence model is a classification model that can classify objects included in the bird's-eye view image. The processor (123) can evaluate the risk level for each object included in the bird's-eye view image. The weather data can be provided from a server that generates weather information, and the work process data can be input by the manager of the construction site.

[0035] The processor (123) divides the bird's-eye view image into multiple zones according to the level of risk. As an example, the risk level may be divided into first to third levels, where the first level corresponds to a level with maximum risk and the third level corresponds to a level with minimum risk. The second level corresponds to a risk level between the first and third levels. The bird's-eye view image may be divided into zones corresponding to the risk levels of the first and second levels.

[0036] Bird-view images segmented according to risk levels can be provided to construction site managers. Managers can review these bird-view images and take appropriate measures to reduce safety accidents.

[0037] The drone (110) can generate an image containing objects such as heavy equipment located at the construction site without blind spots in the air above the construction site, and since the class of the construction site objects can be accurately classified through an artificial intelligence model, according to one embodiment of the present invention, the accuracy of the risk assessment for the construction site can be improved.

[0039] FIG. 2 is a drawing illustrating a method for assessing risk at a construction site according to an embodiment of the present invention.

[0040] A risk assessment method according to one embodiment of the present invention may be performed on a computing device including memory and a processor, and the aforementioned risk assessment device is an example of such a computing device.

[0041] Referring to FIG. 2, a computing device according to an embodiment of the present invention receives (S210) a bird's-eye view image of a construction site taken by a drone hovering over the construction site. Depending on the embodiment, the computing device can control the hovering position of the drone.

[0042] Then, the computing device evaluates the risk level of the construction site (S220) using a bird's-eye view image, weather data for the construction site, and work process data. The weather data may include movement information of a drone provided by a weather information provider server or received from the drone. Although a drone hovering in the air has little movement, its movement may become severe when the wind speed is strong; therefore, the movement information of the drone can be utilized as weather data.

[0043] The computing device classifies the class of objects included in the bird's-eye view image using an artificial intelligence model pre-trained in step S220. The computing device may utilize various well-known artificial intelligence classification models to classify the object classes and may classify the classes of construction equipment at a construction site. For example, the computing device may classify objects included in the bird's-eye view image into classes such as cranes, excavators, and ready-mix concrete trucks. The artificial intelligence classification model receives the bird's-eye view image as input, detects objects within the bird's-eye view image, and outputs the class of the detected objects.

[0044] Images labeled with cranes, excavators, and ready-mix concrete can be used as training data for an artificial intelligence classification model so that the model can classify objects included in a bird's-eye view image into classes such as cranes, excavators, and ready-mix concrete.

[0045] Then, based on the work process data, the computing device determines the class used in the current work process and evaluates the risk level of the object for each class. If the current work process is concrete pouring, ready-mix concrete can be determined as the class used in the current work process.

[0046] The computing device can determine the risk level of the first and second among the objects of the class used in the current work process, taking into account the current weather conditions, and determine the risk level of the remaining class, that is, objects not used in the current work process, as the third level. Among the objects used in the current work process, the risk level of an object that is heavily affected by the current weather conditions can be determined as the first level, and the risk level of an object that is less affected by the current weather conditions can be determined as the second level. For example, if the objects used in the current work process are a crane and a ready-mix concrete, and the current weather is windy, the risk level of the ready-mix concrete can be determined as the first level, and the risk level of the ready-mix concrete can be determined as the second level.

[0047] Then, the computing device divides the bird's-eye view image into multiple zones (S230) according to the level of risk evaluated in step S220. As in the previously described embodiment, when the risk level is set to a first to third level, the bird's-eye view image may be divided into zones corresponding to each of the first to third levels. That is, the multiple zones include a first zone containing an object with a risk level of 1, a second zone containing an object with a risk level of 2, and the remaining zones excluding the first and second zones may correspond to a zone containing an object with a risk level of 3.

[0048] In this case, the first and second zones may be zones centered around the object and larger than the object, and the sizes of the first and second zones may be determined according to the size of the object and the object's movement speed at the construction site. For example, the sizes of the first and second zones may be determined to be proportional to the size and movement speed of the object. The size of the first zone containing the crane may be larger than the size of the second zone containing the ready-mix concrete, and the size of the second zone containing the ready-mix concrete may be larger than the size of the second zone containing the excavator.

[0049] In addition, the size of Zones 1 and 2 can be dynamically adjusted according to current weather conditions. For example, as wind speed and rainfall increase, the size of Zones 1 and 2 may increase, and conversely, as wind speed and rainfall decrease, the size of Zones 1 and 2 may decrease.

[0050] Meanwhile, a computing device according to one embodiment of the present invention can, depending on the embodiment, identify the location of a worker at a construction site and transmit an escape message to a worker located in an area where the first and second zones overlap. In this case, the escape message can be transmitted to a worker located in the overlapping area when a preset condition is satisfied.

[0051] The computing device can transmit an escape message to a worker when the overlap between the first and second zones is maintained for a preset time or longer and the size of the overlapped area is greater than or equal to a preset size. Since the positions of the first and second zones may vary due to the movement of objects located at the construction site and the overlap between the first and second zones may occur temporarily at this time, the computing device can transmit an escape message to a worker located in the overlapped area when the aforementioned conditions are satisfied.

[0052] The escape message may be transmitted to a mobile terminal carried by the worker and may include an escape path from the overlapping area. Since a safety accident may occur if the worker escapes by passing through the overlapping area, the computing device may provide the worker with an escape path that does not pass through the overlapping area. For example, the escape path may be a path heading in the opposite direction of the overlapping area.

[0053] In addition, the computing device can adjust the hovering position of the drone to increase the accuracy of the risk assessment after the risk level of the construction site has been assessed. The computing device can dynamically determine the hovering position of the drone based on at least one of the class of objects included in the first and second zones, the location, size, and number of the first and second zones, and transmit the determined hovering position to the drone.

[0054] As described above, the drone can generate images containing objects such as heavy equipment located at the construction site without blind spots; however, since errors in object classification may occur due to the distance between the drone and the construction site, the computing device can determine the hovering position of the drone so as to be close to the first and second zones. In this case, if there are multiple first and second zones, the computing device can adjust the hovering position of the drone to a location where the first and second zones are relatively large or where the number of first and second zones is relatively dense, and can adjust the hovering position so that the altitude of the drone is lowered.

[0055] For example, if a construction site is located in the xyz axis space, the position of the drone can be adjusted so that the drone's coordinate values ​​are close to the first and second zones, and since the risk level of the first zone is greater than the risk level of the second zone, the position of the drone can be adjusted so that it is closer to the first zone than to the second zone. Here, the distance between the drone's coordinate values ​​and the first and second zones can correspond to the distance between the drone and the objects included in the first and second zones.

[0057] The technical details described above may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiments, or they may be those known and available to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. Hardware devices may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

[0059] As described above, the present invention has been explained by specific details such as specific components, limited embodiments, and drawings; however, this is provided merely to aid in a more comprehensive understanding of the invention, and the invention is not limited to the above embodiments. A person skilled in the art to which the invention pertains can make various modifications and variations from this description. Therefore, the scope of the invention should not be limited to the described embodiments, and all things equivalent to or having equivalent variations to the claims set forth below, as well as the claims themselves, shall be considered to fall within the scope of the concept of the invention.

Claims

Claim 1 A method for assessing risk for a construction site, performed by a computing device, comprises: receiving a bird's-eye view image of the construction site captured by a drone hovering over the construction site; assessing the risk for the construction site using the bird's-eye view image, weather data and work process data for the construction site; and dividing the bird's-eye view image into a plurality of zones according to the level of risk, wherein the step of assessing the risk for the construction site includes classifying the class of objects included in the bird's-eye view image using a pre-trained artificial intelligence model. The method includes the step of determining a class used in the current work process among the classes according to the above work process data, and evaluating the risk level of the object for each class; the step of evaluating the risk level of the object for each class includes, considering the current weather conditions, determining objects with a risk level of the first and second levels among the objects of the class used in the current work process, and determining the risk level of objects of the remaining classes as the third level; the plurality of zones includes first and second zones containing objects with the risk levels of the first and second levels, respectively; the first level is the level with the maximum risk level; and the third level is the level with the minimum risk level. The weather data includes movement information of the drone received from the drone; the size of the first and second zones is dynamically adjusted according to the current weather conditions; and the method for evaluating the risk level of the construction site includes the step of confirming the location of the worker at the construction site.The method for assessing risk in a construction site further includes the step of transmitting an escape message to a worker located in the area where the first and second zones overlap, when the overlap of the first and second zones is maintained for a preset time or longer and the size of the overlapped area is greater than or equal to a preset size; and further includes the step of dynamically determining the hovering position of the drone according to the class of objects included in the first and second zones, and the location, size, and number of the first and second zones; and the step of transmitting the determined hovering position to the drone; wherein the step of dynamically determining the hovering position of the drone, when there are multiple first and second zones, adjusts the hovering position of the drone to a location where the first and second zones are relatively large and adjusts the hovering position of the drone to a location where the first and second zones are relatively dense. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 A method for assessing risk for a construction site, wherein, in claim 1, the sizes of the first and second zones are determined according to the size of the object and the speed of movement of the object at the construction site. Claim 6 delete Claim 7 delete Claim 8 delete Claim 9 A method for assessing risk for a construction site, wherein the step of transmitting the escape message transmits the escape message including an escape path from the overlapping area, and the escape path is an escape path that does not pass through the overlapping area. Claim 10 delete Claim 11 In claim 1, the step of dynamically determining the hovering position of the drone is a method for assessing risk for a construction site, wherein the hovering position of the drone is determined to be close to the first and second zones. Claim 12 delete

Images