Method, device, and program for providing construction site supervision service based on ai

Abstract

The present invention relates to a method for providing a construction site supervision service based on AI, and the method comprises the steps of: obtaining design plan information; collecting construction site information corresponding to the design plan information; and generating supervision information on the basis of the design plan information and the construction site information. Accordingly, the method can enhance the accuracy and efficiency of supervision at construction sites and reduce maintenance costs or defect occurrence rates by improving quality across all processes of construction work types.

Description

Method, device, and program for providing AI-based construction site supervision services

[0001] The present invention relates to a method, device, and program for providing AI-based construction site supervision services, and more particularly, to a method, device, and program for providing construction site supervision services through comparison of design plans and construction sites based on AI.

[0002] In general, construction projects require a lot of time, manpower, and money, and depending on management, there can be a big difference in the completion rate and cost of the project.

[0003] Construction work requires construction and supervision processes. In accordance with the law, buildings, building facilities, or structures are constructed according to the design drawings. Supervision is performed to check whether the constructed buildings are being constructed properly and to provide guidance and supervision on quality control, construction management, and safety management.

[0004] Here, supervision refers to a third party (e.g., a professional supervision firm) commissioned by the ordering party to supervise the proper execution of contractual matters on behalf of the ordering party. This type of supervision differs from auditing, which focuses on detecting errors in completed activities, in that it targets ongoing processes.

[0005] In the construction industry, supervision is the responsibility of guiding and supervising contractors to ensure compliance with all laws and regulations, including various permits and other related construction-related matters. Therefore, poor supervision can lead to poor construction, which can result in not only property damage but also significant casualties. Consequently, the law strictly and rigorously regulates the supervision system and broadly recognizes the responsibilities of supervisors.

[0006] As construction site collapse accidents have occurred one after another recently, interest in management and supervision functions is growing, with the reasons for 'poor construction' being pointed out not only as mistakes by construction companies, but also as the complete failure of the verification system of the ordering company and the supervision company to catch construction errors in each major process.

[0007] Cases of poor construction are primarily due to inadequate quality control by construction companies, clients, and supervisors. However, the lack of standardization in production and construction quality control at construction sites makes it difficult to ensure the reliability of quality control results. Consequently, when defects occur on-site, the cause of the defects cannot be clearly identified. Furthermore, most construction sites rely on supervisors manually reviewing and inspecting hundreds of paper design drawings and manually completing documentation. Furthermore, cases where design drawings are arbitrarily altered to shorten construction periods are not properly detected during the supervision process, resulting in poor supervision.

[0008] Supervisors must closely monitor the construction process at construction sites. They must ensure that construction is being carried out in accordance with the design documents. Furthermore, they are charged with overseeing and directing quality control, construction management, and safety management, making their work even more crucial. Despite this, construction accidents frequently occur, and the number of accidents caused by poor construction continues unabated.

[0009] Therefore, there is a growing demand in the industry for methods that can improve the accuracy and efficiency of supervision applicable to construction sites. In this regard, Republic of Korea Patent No. 10-2513608 discloses a smart inspection system for quality control in construction projects.

[0010] The present invention has been conceived in response to the aforementioned background technology, and aims to provide a method, device, and program for providing AI-based construction site supervision services.

[0011] The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0012] According to one embodiment of the present invention, which aims to solve the aforementioned problem, a method for providing AI-based construction site supervision services is disclosed. The method may include: a step of acquiring design plan information; a step of collecting construction site information corresponding to the design plan information; and a step of generating supervision information based on the design plan information and the construction site information.

[0013] In an alternative embodiment, the method further includes a step of determining a key supervision area based on the design plan information, and generating the supervision information by assigning a weight to the key supervision area.

[0014] In an alternative embodiment, the step of determining a core supervision area based on the design plan information includes: a step of recognizing a type of a construction object based on the design plan information; and a step of inputting the type of the construction object and the construction site information into a pre-learned core supervision area classification model to recognize a work type corresponding to a core supervision area among a plurality of work types corresponding to the construction object; wherein the core supervision area classification model may be pre-learned to output a work type having a low construction match rate based on learning data in which the pre-collected work types for each type of construction object and the pre-collected construction site information of the construction object are labeled.

[0015] In an alternative embodiment, the step of generating the supervision information may include a step of inputting measurement data included in the construction site information into a pre-trained first neural network model to recognize whether an abnormality exists; a step of inputting image data included in the construction site information into a pre-trained second neural network model to recognize whether an abnormality exists; and a step of generating the supervision information based on whether the abnormality exists.

[0016] In an alternative embodiment, the step of generating the supervision information may include: recognizing a first specific area related to the construction site information; generating a digital twin based on the design plan information, and recognizing a second specific area corresponding to the first specific area in the digital twin; inputting first input information corresponding to the first specific area and second input information corresponding to the second specific area into a pre-trained neural network model to obtain a comparison result; and generating the supervision information based on the comparison result.

[0017] In an alternative embodiment, the step of generating the supervision information may include: generating a first digital twin corresponding to the design plan information; generating a second digital twin corresponding to the construction site information; inputting first input data related to the first digital twin and second input data related to the second digital twin into a pre-trained neural network model to obtain a comparison result; and generating the supervision information based on the comparison result.

[0018] In an alternative embodiment, the method further includes a step of generating optimal construction method information for a remaining construction area; wherein the step of generating optimal construction method information may include a step of generating a first digital twin corresponding to the design plan information; a step of generating a second digital twin corresponding to the construction site information; a step of comparing the first digital twin and the second digital twin to recognize a remaining work area; and a step of inputting the remaining work area into a pre-trained neural network model to obtain the optimal construction method information.

[0019] In an alternative embodiment, the design plan information may include at least one of a process plan, a design drawing, a construction specification, and equipment operation information, and the construction site information may include at least one of measurement data measured by a sensor installed at the construction site, meteorological data acquired by a sensor installed at the construction site, image data acquired by an image capturing device installed at the construction site, and soil property data of the construction site.

[0020] In an alternative embodiment, the method further includes, when the supervision information is generated, issuing a transaction including the supervision information; and transmitting the transaction to at least one node included in a blockchain network to record the transaction in the blockchain network; wherein the supervision information may include at least one of information on construction consistency, information on construction progress, and information on a construction forecast period.

[0021] In an alternative embodiment, the method further includes the steps of recognizing a point in time when a specific work type has been completed based on the construction site information; and generating a construction supervision checklist corresponding to the specific work type based on a plurality of transactions recorded in the blockchain network up to the point in time when the specific work type has been completed; wherein the construction supervision checklist may include information on a step-by-step checklist included in the specific work type.

[0022] According to one embodiment of the present invention for solving the above-described problem, a device is disclosed. The device includes: a memory storing one or more instructions; and a processor executing the one or more instructions stored in the memory, wherein the processor can perform the above-described methods by executing the one or more instructions.

[0023] According to one embodiment of the present invention for solving the above-described problem, a computer program stored in a computer-readable recording medium is disclosed, which is combined with a computer as hardware and can perform the above-described methods.

[0024] Other specific details of the present invention are included in the detailed description and drawings.

[0025] The present invention can improve the accuracy and efficiency of construction site supervision. Furthermore, it can reduce maintenance costs and defect rates by improving quality throughout all construction processes.

[0026] For example, the present invention can improve construction quality and work quality through AI-based analysis of construction-related quality factors measured at construction sites, thereby preventing quality degradation due to inaccurate supervision and accidents due to poor construction.

[0027] In addition, the present invention can reduce the occurrence rate of defects in construction work by enabling immediate response to the event (e.g., abnormal signs) detected during monitoring of a construction site by providing the event to workers, supervisors, and construction companies on site.

[0028] In addition, the present invention enables objective measurement of the quantity of materials used and the construction period in real time through various sensors and video data for each type of work, and can track the cause when a problem occurs later.

[0029] The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0030] FIG. 1 is a diagram illustrating a system according to one embodiment of the present invention.

[0031] Figure 2 is a hardware configuration diagram of a computing device according to one embodiment of the present invention.

[0032] FIGS. 3 to 8 are flowcharts illustrating an example of a method for providing AI-based construction site supervision services according to one embodiment of the present invention.

[0033] FIG. 9 is a schematic diagram illustrating one or more network functions related to one embodiment of the present invention.

[0034] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to facilitate an understanding of the present invention. However, it will be apparent that these embodiments may be practiced without these specific details.

[0035] As used herein, the terms "component," "module," "system," and the like refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or an execution of software. For example, a component may be, but is not limited to, a procedure running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and / or a thread of execution. A component may be localized within a single computer. A component may be distributed between two or more computers. Furthermore, these components may execute from various computer-readable media having various data structures stored therein. Components may communicate via local and / or remote processes, for example, by signals comprising one or more data packets (e.g., data from one component interacting with another component in a local system, a distributed system, and / or data transmitted to another system via a network such as the Internet via signals).

[0036] Furthermore, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from context, "X employs A or B" is intended to mean either of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, "X employs A or B" can apply to any of these cases. Furthermore, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the associated items listed.

[0037] Additionally, the terms "comprises" and / or "comprising" should be understood to imply the presence of the features and / or components in question. However, it should be understood that the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other features, components, and / or groups thereof. Furthermore, unless otherwise specified or clear from the context to refer to the singular form, the singular in the specification and claims should generally be construed to mean "one or more."

[0038] Those skilled in the art should further recognize that the various illustrative logical blocks, components, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, components, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0039] The description of the disclosed embodiments is provided to enable those skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present invention. Therefore, the present invention is not limited to the disclosed embodiments. The present invention is to be construed in the widest scope consistent with the principles and novel features disclosed herein.

[0040] In this specification, the term "computer" refers to any type of hardware device including at least one processor, and may also be understood to encompass software components operating on the hardware device, depending on the embodiment. For example, the term "computer" may be understood to encompass, but is not limited to, smartphones, tablet PCs, desktops, laptops, and all user clients and applications running on each device.

[0041] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0042] Although each step described in this specification is described as being performed by a computer, the subject of each step is not limited thereto, and at least some of each step may be performed by different devices depending on the embodiment.

[0043]

[0044] FIG. 1 is a diagram illustrating a system according to one embodiment of the present invention.

[0045] Referring to FIG. 1, a system according to one embodiment of the present invention may include a computing device (100), a user terminal (200), and an external server (300). The system illustrated in FIG. 1 is according to one embodiment, and its components are not limited to the embodiment illustrated in FIG. 1, and may be added, changed, or deleted as needed.

[0046] In one embodiment, the computing device (100) can provide AI-based construction site supervision services.

[0047] Specifically, the computing device (100) can obtain design plan information. Here, the design plan information can include at least one of a process plan, a design drawing, a specification, and equipment operation information.

[0048] A computing device (100) can collect construction site information corresponding to design plan information. Here, the construction site information may include at least one of measurement data measured by sensors installed at the construction site, meteorological data acquired by sensors installed at the construction site, image data acquired by an image capturing device installed at the construction site, and soil property data of the construction site.

[0049] A computing device (100) can generate supervision information based on design plan information and construction site information. Here, the supervision information may include at least one of information on construction consistency, information on construction progress, and information on the construction forecast period.

[0050] In one embodiment, the computing device (100) can generate supervision information by inputting at least one piece of data included in design plan information and at least one piece of information included in construction site information into a pre-learned AI-based model.

[0051] Therefore, the computing device (100) of the present invention can increase the accuracy and efficiency of supervision of a construction site.

[0052] Hereinafter, an example of a method in which a computing device (100) provides an AI-based construction site supervision service will be described with reference to FIGS. 3 to 8.

[0053] In various embodiments, the computing device (100) may provide web- or application-based services, but is not limited thereto.

[0054] The computing device (100) may include any type of computer system or computer device, such as, but not limited to, a microprocessor, a mainframe computer, a digital processor, a portable device, and a device controller.

[0055] Below, a description of the hardware configuration of the computing device (100) will be provided with reference to FIG. 2.

[0056] Meanwhile, the user terminal (200) may be connected to the computing device (100) via a network (400) and may be a user terminal using the AI-based construction site supervision service provided by the computing device (100). For example, the user terminal (200) may include, but is not limited to, terminals of a construction company, a client, a supervisor, etc.

[0057] Here, the user terminal (200) may include, for example, various types of computer devices. For example, the user terminal (200) may refer to various terminal devices such as a smartphone, tablet PC, desktop, or laptop.

[0058] The user terminal (200) includes a display on at least a portion of the terminal, and may include an operating system for driving an application or extension program-based service provided from the computing device (100). For example, the user terminal (200) may be a smart phone, but is not limited thereto, and the user terminal (200) may include all types of handheld-based wireless communication devices such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminals, smart pads, tablet PCs, etc., as a wireless communication device that ensures portability and mobility.

[0059] An external server (300) can be connected to a computing device (100) via a network (400), and the computing device (100) can transmit and receive various information / data necessary for providing AI-based construction site supervision services, and the computing device (100) can store and manage various information / data generated as it provides AI-based construction site supervision services.

[0060] For example, the external server (300) may be a database server that stores information used in an AI-based construction site supervision service. As another example, the external server (300) may be a server that provides information used in an AI-based construction site supervision service.

[0061] A network (400) may refer to a connection structure that enables information exchange between each node, such as a computing device, multiple terminals, and servers. For example, the network (400) includes a local area network (LAN), a wide area network (WAN), the Internet (WWW), a wired and wireless data communication network, a telephone network, a wired and wireless television communication network, etc.

[0062] Wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, the Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

[0063]

[0064] Figure 2 is a hardware configuration diagram of a computing device according to one embodiment of the present invention.

[0065] Referring to FIG. 2, a computing device (100) according to one embodiment of the present invention may include one or more processors (110), a memory (120) for loading a computer program (151) executed by the processor (110), a bus (130), a communication interface (140), and a storage (150) for storing the computer program (151). Here, only components related to the embodiment of the present invention are illustrated in FIG. 2. Therefore, a person skilled in the art to which the present invention pertains will understand that other general components may be included in addition to the components illustrated in FIG. 2.

[0066] The processor (110) controls the overall operation of each component of the computing device (100). The processor (110) may be configured with one or more cores, and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU) of the computing device. Alternatively, the processor may be configured to include any type of processor well known in the technical field of the present invention.

[0067] Additionally, the processor (110) may perform operations for at least one application or program for executing a method according to embodiments of the present invention, and the computing device (100) may have one or more processors.

[0068] In various embodiments, the processor (110) may further include a Random Access Memory (RAM, not shown) and a Read-Only Memory (ROM, not shown) that temporarily and / or permanently store signals (or data) processed within the processor (110). In addition, the processor (110) may be implemented in the form of a system on chip (SoC) that includes at least one of a graphics processing unit, RAM, and ROM.

[0069] The memory (120) stores various data, commands, and / or information. The memory (120) can load a computer program (151) from the storage (150) to execute methods / operations according to various embodiments of the present invention. When the computer program (151) is loaded into the memory (120), the processor (110) can perform the method / operation by executing one or more instructions constituting the computer program (151). The memory (120) may be implemented as a volatile memory such as RAM, but the technical scope of the present invention is not limited thereto.

[0070] The bus (130) provides a communication function between components of the computing device (100). The bus (130) may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0071] The communication interface (140) supports wired and wireless Internet communication of the computing device (100). Furthermore, the communication interface (140) may support various communication methods other than Internet communication. To this end, the communication interface (140) may be configured to include a communication module well known in the technical field of the present invention. In some embodiments, the communication interface (140) may be omitted.

[0072] Storage (150) can non-temporarily store a computer program (151). When performing a process according to an embodiment of the present invention through a computing device (100), storage (150) can store various information necessary to provide a service or perform an analysis according to the disclosed embodiment.

[0073] Storage (150) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present invention pertains.

[0074] The computer program (151) may include one or more instructions that cause the processor (110) to perform a method / operation according to various embodiments of the present invention when loaded into the memory (120). That is, the processor (110) may perform the method / operation according to various embodiments of the present invention by executing the one or more instructions.

[0075] In one embodiment, the computer program (151) may include one or more instructions for performing various methods associated with various tasks related to learning a neural network model.

[0076] The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in a random access memory (RAM), a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art to which the present invention pertains.

[0077] The components of the present invention may be implemented as a program (or application) and stored on a medium to be executed in conjunction with a computer, which is hardware. The components of the present invention may be implemented as software programs or software elements. Similarly, the embodiments may be implemented in a programming or scripting language such as C, C++, Java, or an assembler, including various algorithms implemented as a combination of data structures, processes, routines, or other programming components. Functional aspects may be implemented as algorithms that are executed on one or more processors.

[0078]

[0079] FIGS. 3 to 8 are flowcharts illustrating an example of a method for providing AI-based construction site supervision services according to one embodiment of the present invention.

[0080] Referring to FIG. 3, a computing device (100) can obtain design plan information (S100). Here, the design plan information may include at least one of a process plan, a design drawing, a construction specification, and equipment operation information.

[0081] For example, the computing device (100) can receive design plan information from a construction company terminal or an ordering company terminal.

[0082] The computing device (100) can collect construction site information corresponding to design plan information (S200). Here, the construction site information may include at least one of measurement data measured by sensors installed at the construction site, meteorological data acquired by sensors installed at the construction site, image data acquired by an image capturing device installed at the construction site, and soil property data of the construction site.

[0083] For example, the computing device (100) may receive construction site information from a worker terminal, a supervisor terminal, a construction company terminal, or a client terminal at the construction site. As another example, the computing device (100) may receive construction site information directly from sensors or video recording devices installed at the construction site.

[0084] A computing device (100) can generate supervision information based on design plan information and construction site information (S300). Here, the supervision information may include at least one of information on construction consistency, information on construction progress, and information on the construction forecast period.

[0085] According to one embodiment, the computing device (100) may determine a core supervision area based on design plan information. Here, the core supervision area is an area related to the safety and completeness of the construction object, and may include a specific type of work of the construction object, at least one step included in a specific type of work, or a specific portion related to at least one step. In this case, the computing device (100) may generate supervision information by assigning weights to the core supervision area in step (S300).

[0086] For example, the computing device (100) can analyze design plan information for a high-rise office building to identify the building's height, materials to be used, expected structural characteristics, etc. Based on the identified information, the computing device (100) can determine key supervision areas that are particularly important in the construction of high-rise buildings. For example, the computing device (100) can determine structural safety, fire prevention systems, elevator installation, etc. as key supervision areas.

[0087] And, when generating surveillance information, the computing device (100) can assign weights to the determined key surveillance areas, for example, assign the highest weight to structural safety, and generate surveillance information that guides special attention to be paid to the corresponding area during the surveillance process.

[0088] According to a specific embodiment, when determining a core supervision area based on design plan information, the computing device (100) may recognize the type of a construction object based on the design plan information. Here, the type of the construction object may mean something that has been pre-classified according to the object's purpose, structure, size, etc. For example, the type of the construction object may include, but is not limited to, residential buildings, commercial buildings, industrial buildings, public facilities, special-purpose buildings (e.g., research institutes, religious facilities, etc.), infrastructure structures, and landscaping facilities.

[0089] When the computing device (100) recognizes the type of a construction object, it inputs the type of the construction object and construction site information into a pre-learned core supervision area classification model, thereby recognizing a work type corresponding to a core supervision area among a plurality of work types corresponding to the construction object. Here, the core supervision area classification model may be pre-learned to output a work type with a low construction consistency based on learning data labeled with the pre-collected work types for each type of construction object and the pre-collected construction site information of the construction object.

[0090] For example, the computing device (100) can recognize that the object under construction is a large shopping mall based on design drawings, project specifications, location information, etc. included in the design plan information. Furthermore, the computing device (100) collects data (i.e., construction site information) in real time from the construction site. This data may include the current progress of the work, the amount of materials used, the deployment of workers, weather conditions, etc.

[0091] Additionally, the computing device (100) can input construction object types (large shopping malls) and construction site information into a core supervision area classification model. This model is trained by labeling construction type data and site information for various types of construction objects, and can be trained to identify construction types with low construction consistency, i.e., construction types that show progress that differs from expectations.

[0092] For example, a key supervision area classification model can identify "structural safety," "electrical and plumbing systems," and "interior finishing work" as key supervision areas for a large shopping mall. Specifically, the model can analyze discrepancies between current and projected progress to classify work items requiring management. For example, it can identify that interior finishing work is running behind schedule and may impact subsequent work.

[0093] The classification results can be delivered to construction managers or supervisors, allowing them to adjust work schedules by allocating more resources to specific work types or to strengthen supervision of specific work types. Through this, the computing device (100) can improve the overall progress of the construction site and ensure efficient work execution.

[0094] In various embodiments, when a key supervision area is determined, the computing device (100) may provide a notification to the supervisor's terminal to intensify supervision activities in that area. Furthermore, the computing device (100) may sequentially guide the supervisor to the current or previous key supervision area and the next key supervision area according to the construction order of the construction site, thereby enhancing the convenience of supervision work.

[0095]

[0096] Referring to FIG. 4, when the computing device (100) generates surveillance information in step (S300), it can perform the following process.

[0097] The computing device (100) can input measurement data included in construction site information into a pre-learned first neural network model to recognize the presence of an abnormality (S311).

[0098] In one embodiment, the computing device (100) may generate first learning data based on measurement data containing previously detected anomalies. For example, the computing device (100) may generate first learning data by labeling measurement data containing previously detected anomalies and design plan information corresponding to the measurement data.

[0099] In addition, the computing device (100) can pre-train a first neural network model that determines whether an abnormality exists in the measurement data based on the first learning data.

[0100] That is, the computing device (100) can input measurement data into the first neural network model to recognize whether an abnormality sign exists at the construction site corresponding to the measurement data.

[0101] The computing device (100) can input image data included in construction site information into a pre-learned second neural network model to recognize the presence of an abnormality (S312).

[0102] In one embodiment, the computing device (100) may generate second learning data based on image data related to previously detected anomalies. For example, the computing device (100) may generate second learning data by labeling image data containing previously detected anomalies and design plan information corresponding to the image data.

[0103] In addition, the computing device (100) can pre-train a second neural network model that determines whether an abnormality exists in the image data based on the second learning data.

[0104] That is, the computing device (100) can input image data into a second neural network model to recognize whether an abnormality exists at a construction site corresponding to the image data.

[0105] The computing device (100) can generate monitoring information based on the presence or absence of abnormal signs in each of the measurement data and image data (S313).

[0106] Specifically, the computing device (100) can generate supervision information including information on the construction consistency of a construction site.

[0107] For example, if the computing device (100) recognizes that there is no abnormality in each of the measurement data and the image data, it may determine that the construction consistency is 1 and generate supervision information including information about this.

[0108] For another example, the computing device (100) may determine that the construction consistency is 0.5 when an abnormality exists in the measurement data and no abnormality exists in the image data, and may generate monitoring information including information about this.

[0109] As another example, the computing device (100) may determine that the construction consistency is 0.5 when there is no abnormality in the measurement data and an abnormality exists in the image data, and may generate monitoring information including information about this.

[0110] As another example, if the computing device (100) recognizes that an abnormality exists in each of the measurement data and the image data, it may determine that the construction consistency is 0 and generate monitoring information including information about this.

[0111] Meanwhile, the computing device (100) can transmit monitoring information to the user terminal (200). In this case, the user can recognize whether the construction is progressing normally or whether a problem has occurred during the construction based on the construction consistency.

[0112]

[0113] Referring to FIG. 5, when the computing device (100) generates surveillance information in step (S300), it can perform the following process.

[0114] The computing device (100) can recognize a first specific area related to construction site information (S321).

[0115] For example, the computing device (100) can recognize a first specific area corresponding to measurement data or image data included in construction site information.

[0116] For example, if the measurement data or image data included in the construction site information is data related to an underground parking lot, the computing device (100) can recognize the first specific area as an underground parking lot.

[0117] The computing device (100) can create a digital twin based on design plan information and recognize a second specific area corresponding to a first specific area in the digital twin (S322).

[0118] In the present invention, a digital twin may mean a virtual digital replica of an actual physical object, process, system, or space.

[0119] For example, in step S322, the computing device (100) may create a digital twin of a completed object using design plan information. Specifically, the computing device (100) may create a digital twin through simulation and 3D modeling based on at least one of a process plan, design drawing, specifications, and equipment operation information included in the design plan information. Furthermore, the computing device (100) may recognize a second specific area corresponding to a first specific area in the completed object.

[0120] For example, if the computing device (100) recognizes the first specific area as an underground parking lot, it can recognize the underground parking lot area (i.e., the second specific area) on the digital twin of the completed object.

[0121] The computing device (100) can input first input information corresponding to a first specific area and second input information corresponding to a second specific area into a pre-trained neural network model to obtain a comparison result (S323). Furthermore, the computing device (100) can generate monitoring information based on the comparison result (S324). Here, the comparison result may include, but is not limited to, a similarity score.

[0122] Here, the first input information is actual construction site information, which may include information about a first specific area of ​​the construction site. For example, the first input information may include, but is not limited to, construction progress, structural characteristics of the site, environmental conditions, and the status of materials and equipment used at the site.

[0123] The second input information is digital twin information, which is data derived from the digital twin created based on the design plan. This information corresponds to a second specific area of ​​the digital twin and can correspond to a first specific area of ​​the actual construction site. For example, the second input information may include, but is not limited to, the expected construction progress, design parameters, and expected material properties.

[0124] In one embodiment, the computing device (100) may pre-train a neural network model that inputs first input information and second input information. The model may be trained to output a comparison result between the first input information and the second input information, and may include a similarity analysis model.

[0125] In one embodiment, the neural network model that receives the first input information and the second input information may be a pre-trained model such that the feature extraction model outputs a similarity score between the features extracted from each of the two input information.

[0126] Specifically, the neural network model can perform learning to optimize the similarity between feature points extracted from each of the two input pieces of information by using input information corresponding to an actual construction site with no abnormalities and input information derived from a digital twin corresponding to the construction site.

[0127] That is, the computing device (100) can input the first input information and the second input information into a pre-trained neural network model to obtain a similarity score between the first input information and the second input information. Then, the computing device (100) can generate supervision information including information on construction consistency and information on construction progress based on the similarity score.

[0128] For example, assuming that the computing device (100) has a design plan in which the basement is a simple flat plate structure (in this case, the slab thickness must be 400 mm or more) and a digital twin is created to include a slab having a thickness of 400 mm, the monitoring information can be created based on the result of comparing the slab thickness of the first column in the first input data photographed or measured underground at the actual construction site with the slab thickness of the second column in the second input data derived from the digital twin.

[0129]

[0130] Referring to FIG. 6, when the computing device (100) generates surveillance information in step (S300), it can perform the following process.

[0131] The computing device (100) can generate a first digital twin corresponding to the design plan information (S331).

[0132] For example, the computing device (100) may create a first digital twin of a completed object using design plan information. For example, the computing device (100) may create the first digital twin through simulation and 3D modeling based on at least one of the process plan, design drawing, specifications, and equipment operation information included in the design plan information.

[0133] The computing device (100) can generate a second digital twin corresponding to construction site information (S332).

[0134] For example, the computing device (100) can use construction site information to create a second digital twin for an object completed to date. For example, the computing device (100) can create a second digital twin through simulation and 3D modeling based on at least one of measurement data, image data, and soil property data included in the construction site information.

[0135] The computing device (100) can input first input data related to the first digital twin and second input data related to the second digital twin into a pre-trained neural network model to obtain comparison results (S333). Furthermore, the computing device (100) can generate monitoring information based on the comparison results (S334). Here, the comparison results may include, but are not limited to, a similarity score.

[0136] In one embodiment, the neural network model that receives the first input data and the second input data may be a pre-trained model that outputs a similarity score between features extracted from each of the two input pieces of information by the feature extraction model.

[0137] Specifically, the neural network model can perform learning to optimize the similarity of feature points extracted from each of the two input pieces of information by using input data derived from a digital twin corresponding to an actual construction site with no abnormalities and input data derived from a digital twin corresponding to the construction site.

[0138] That is, the computing device (100) can input the first input data and the second input data into a pre-trained neural network model to obtain a similarity score of the first input data and the second input data. Then, the computing device (100) can generate supervision information including information on construction consistency and information on construction progress based on the similarity score.

[0139]

[0140] According to various embodiments of the present invention, the computing device (100) can generate optimal construction method information for the remaining construction area.

[0141] Specifically, referring to FIG. 7, when generating optimal construction method information, the computing device (100) can perform the following process.

[0142] The computing device (100) can generate a first digital twin corresponding to the design plan information (S401).

[0143] For example, the computing device (100) may create a first digital twin based on the original design plans of a construction project. This twin may include a 3D model of the building, design specifications, projected material usage, planned work sequences, etc. For example, it may include detailed information on all floors of a proposed high-rise building, the internal structure of each floor, the required amount of rebar and concrete, and the machinery and equipment to be installed.

[0144] The computing device (100) can generate a second digital twin corresponding to construction site information (S402).

[0145] For example, the computing device (100) can generate a second digital twin reflecting the current status of the construction site. This may be based on data collected through sensors installed on-site and drone footage. This data may include information such as the actual progress of the work, the amount of materials used, the impact of weather conditions, and the deployment and activity status of on-site workers. For example, this data may include the current number of floors of the building under construction, the amount of rebar and concrete actually installed, and the causes of work delays.

[0146] The computing device (100) can compare the first digital twin and the second digital twin to recognize the remaining work area (S403).

[0147] Specifically, the computing device (100) can compare and analyze the first digital twin (design plan) and the second digital twin (current construction site status). Here, the analysis may include various factors such as structural consistency, progress status, and material usage.

[0148] For example, while the design plan calls for a ten-story building to be completed, only eight floors may be completed on-site. Furthermore, if the actual amount of rebar used is less or more than planned, the computing device (100) can identify such differences.

[0149] The computing device (100) can accurately identify work areas that have not yet been completed by comparing the first and second digital twins. This can be used as important information for future work planning.

[0150] The computing device (100) can obtain optimal construction method information by inputting the remaining work area into a pre-learned neural network model (S404).

[0151] Specifically, a pre-trained neural network model can be trained to determine the optimal construction method based on data about the remaining work area. This model can be trained by analyzing data such as past similar construction cases, success rates of various construction methods, cost-effectiveness, and time requirements.

[0152] For example, if the remaining work involves structural strengthening, the model can suggest the most appropriate method. This could include specific structural strengthening techniques, material selection, and personnel allocation plans. Furthermore, the model can assess whether this method can optimize time and cost while meeting safety standards.

[0153] The computing device (100) can transmit optimal construction method information obtained from the model to the terminal of a construction site manager or engineer. In this case, the optimal construction method can be applied to the actual construction process, which can contribute to maximizing project efficiency and minimizing budget overruns and delays.

[0154]

[0155] According to various embodiments of the present invention, the computing device (100) can record supervision information on a blockchain network. Furthermore, the computing device (100) can generate a construction supervision checklist based on the supervision information recorded on the blockchain network.

[0156] Specifically, referring to FIG. 8, if the computing device (100) generates monitoring information, it can issue a transaction including the monitoring information (S501). Furthermore, the computing device (100) can transmit the transaction to at least one node included in the blockchain network to record the transaction on the blockchain network (S502). Here, the transaction may include, but is not limited to, details of the monitoring information, the date, the signature of the relevant person in charge, etc.

[0157] Specifically, the computing device (100) may generate a transaction including the monitoring information as it generates the monitoring information. Furthermore, the computing device (100) may transmit the transaction to multiple nodes (e.g., a user terminal (200) and an external server (300), etc.). In this case, each of the multiple nodes receiving the transaction may verify the transaction through a consensus algorithm. Furthermore, each of the multiple nodes may generate a block and record the transaction in the block if the transaction is verified. Here, the block may refer to a block recorded in a blockchain network.

[0158] The computing device (100) can recognize the completion point of a specific work type based on the construction site information acquired in step (S200) (S503). Furthermore, the computing device (100) can generate a construction supervision checklist corresponding to a specific work type based on multiple transactions recorded on the blockchain network up to the point of completion of the specific work type (S504). Here, the construction supervision checklist may include information on a step-by-step checklist included in the specific work type.

[0159] For example, when the completion time of a building's reinforcing work is confirmed, the computing device (100) can recognize this and process the corresponding information. Furthermore, the computing device (100) can generate a construction supervision checklist that includes the completion level of each stage of reinforcing work, quality inspection results, and compliance with safety standards.

[0160] Therefore, the computing device (100) of the present invention can efficiently manage construction site supervision information and transparently and reliably record project progress. In particular, the use of blockchain technology of the present invention can ensure the integrity of supervision information and provide accurate, real-time information to project managers and stakeholders.

[0161]

[0162] FIG. 9 is a schematic diagram illustrating one or more network functions related to one embodiment of the present invention.

[0163] Throughout this specification, the terms "artificial intelligence model," "neural network model," "neural network," "network function," and "neural network" may be used interchangeably. A neural network may be composed of a set of interconnected computational units, generally referred to as "nodes." These "nodes" may also be referred to as "neurons."

[0164] A deep neural network (DNN) can refer to a neural network that includes multiple hidden layers in addition to input and output layers. Using a deep neural network, one can identify latent structures in data. That is, one can identify latent structures in photos, text, videos, voices, and music (e.g., what objects are in a photo, what the content and emotion of a text are, what the content and emotion of a voice are, etc.). A deep neural network can include a convolutional neural network (CNN), a recurrent neural network (RNN), an autoencoder, a generative adversarial network (GAN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, and the like. The description of the above-described deep neural network is merely an example, and the present invention is not limited thereto.

[0165] Neural networks can be trained using at least one of supervised learning, unsupervised learning, and semi-supervised learning. The goal of neural network training is to minimize output errors. Training involves repeatedly inputting training data into the neural network, calculating the neural network output and target error for the training data, and backpropagating the neural network error from the output layer to the input layer to update the weights of each node in the neural network in a direction that reduces the error. Supervised learning uses training data with the correct answer labeled for each training data (i.e., labeled training data). Unsupervised learning, on the other hand, may not have the correct answer labeled for each training data. For example, in the case of supervised learning for data classification, the training data may be data in which each training data category is labeled. Labeled training data is input to a neural network, and an error can be calculated by comparing the output (categories) of the neural network with the labels of the training data. For example, in unsupervised learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the backward direction (i.e., from the output layer to the input layer) in the neural network, and the connection weights of each node in each layer of the neural network can be updated through backpropagation. The amount of change in the connection weights of each updated node can be determined by the learning rate. The neural network's calculation of the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the neural network's learning cycle.For example, in the early stages of training a neural network, a high learning rate can be used to quickly allow the neural network to achieve a certain level of performance, thereby improving efficiency, while in the later stages of training, a low learning rate can be used to improve accuracy.

[0166] In neural network training, training data can typically be a subset of real-world data (i.e., the data to be processed using the trained neural network). Therefore, there can be a learning cycle where errors on the training data decrease but errors on the real-world data increase. Overfitting is a phenomenon where excessive training on the training data leads to increased errors on the real-world data. For example, a neural network trained on yellow cats may fail to recognize cats when shown non-yellow colors, a type of overfitting. Overfitting can increase errors in machine learning algorithms. Various optimization methods can be used to prevent overfitting. Methods such as increasing the training data, regularization, and dropout, which omits some nodes from the network during the training process, can be applied.

[0167] The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in a random access memory (RAM), a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art to which the present invention pertains.

[0168] The components of the present invention may be implemented as programs (or applications) and stored on a medium to be executed in conjunction with a computer, which is hardware. The components of the present invention may be implemented as software programs or software elements. Similarly, the embodiments may be implemented in a programming or scripting language such as C, C++, Java, or an assembler, including various algorithms implemented as a combination of data structures, processes, routines, or other programming components. Functional aspects may be implemented as algorithms that are executed on one or more processors.

[0169] Those skilled in the art will appreciate that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, various forms of programs or design code (referred to herein, for convenience, as “software”), or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

[0170] The various embodiments presented herein can be implemented as a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" includes a computer program, carrier, or media accessible from any computer-readable device. For example, computer-readable media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Furthermore, the various storage media presented herein include one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" includes, but is not limited to, wireless channels and various other media capable of storing, retaining, and / or carrying instructions and / or data.

[0171] It should be understood that the specific order or hierarchy of steps in the presented processes is merely an example of exemplary approaches. It should be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present invention based on design priorities. The appended method claims provide elements of various steps in a sample order, but are not intended to be limited to the specific order or hierarchy presented.

[0172]

[0173] While the embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will appreciate that the present invention can be implemented in other specific forms without altering the technical concept or essential features thereof. Therefore, the embodiments described above should be understood to be illustrative in all respects and not restrictive.

Claims

1. A method performed by a computing device including at least one processor, Step of obtaining design plan information; A step of collecting construction site information corresponding to the above design plan information; and A step of generating supervision information based on the above design plan information and the above construction site information; Including, Method for providing AI-based construction site supervision services.

2. In paragraph 1, The above method, A step of determining a key supervision area based on the above design plan information; Including more, Generating the above surveillance information by assigning weights to the above key surveillance areas, Method for providing AI-based construction site supervision services.

3. In paragraph 2, Based on the above design plan information, the step of determining the key supervision area is: A step of recognizing the type of a construction object based on the above design plan information; and A step of inputting the type of the construction object and the construction site information into a pre-learned core supervision area classification model to recognize a work type corresponding to a core supervision area among a plurality of work types corresponding to the construction object; Including, The above core supervision area classification model is: Based on the learning data labeled with the types of construction work for the pre-collected construction objects and the construction site information of the pre-collected construction objects, the work type with low construction match rate is pre-learned. Method for providing AI-based construction site supervision services.

4. In paragraph 1, The steps for generating the above surveillance information are: A step of inputting measurement data included in the above construction site information into a pre-learned first neural network model to recognize whether there is an abnormality; A step of inputting image data included in the above construction site information into a pre-learned second neural network model to recognize whether there is an abnormality; and A step of generating the above surveillance information based on the presence or absence of the above abnormal symptoms; Including, Method for providing AI-based construction site supervision services.

5. In paragraph 1, The steps for generating the above surveillance information are: A step of recognizing a first specific area related to the above construction site information; A step of creating a digital twin based on the above design plan information and recognizing a second specific area corresponding to the first specific area in the digital twin; A step of inputting first input information corresponding to the first specific area and second input information corresponding to the second specific area into a pre-learned neural network model to obtain a comparison result; and A step of generating the above-mentioned supervision information based on the above-mentioned comparison results; Including, Method for providing AI-based construction site supervision services.

6. In paragraph 1, The steps for generating the above surveillance information are: A step of generating a first digital twin corresponding to the above design plan information; A step of creating a second digital twin corresponding to the above construction site information; A step of inputting each of the first input data related to the first digital twin and the second input data related to the second digital twin into a pre-trained neural network model to obtain a comparison result; and A step of generating the above-mentioned supervision information based on the above-mentioned comparison results; Including, Method for providing AI-based construction site supervision services.

7. In paragraph 1, The above method, A step for generating optimal construction method information for the remaining construction area; Including more, The step of generating the above optimal construction method information is: A step of generating a first digital twin corresponding to the above design plan information; A step of creating a second digital twin corresponding to the above construction site information; A step of recognizing a remaining work area by comparing the first digital twin and the second digital twin; and A step of obtaining the optimal construction method information by inputting the remaining work area into a pre-learned neural network model; Including, Method for providing AI-based construction site supervision services.

8. In paragraph 1, The above design plan information is, Contains at least one of the following: process plan, design drawing, specifications, and equipment operation information; The above construction site information is, Including at least one of measurement data measured by a sensor installed at a construction site, weather data acquired by a sensor installed at the construction site, image data acquired by an image capturing device installed at the construction site, and soil property data of the construction site. Method for providing AI-based construction site supervision services.

9. In paragraph 1, The above method, When the above surveillance information is generated, a step of issuing a transaction including the above surveillance information; and A step of transmitting the transaction to at least one node included in the blockchain network to record the transaction in the blockchain network; Including more, The above surveillance information is, Containing at least one of information on construction consistency, information on construction progress, and information on the estimated construction period; Method for providing AI-based construction site supervision services.

10. In paragraph 9, The above method, A step of recognizing the time at which a specific type of work is completed based on the above construction site information; and A step of generating a construction supervision checklist corresponding to the specific work type based on multiple transactions recorded in the blockchain network until the specific work type is completed; Including more, The above construction supervision checklist is: Contains information on the step-by-step checklist included in the above specific work type; Method for providing AI-based construction site supervision services.

11. Memory for storing one or more instructions; and A processor that executes one or more instructions stored in said memory. Including, The above processor executes one or more of the above instructions, A device performing the method of claim 1.

12. A computer program stored on a computer-readable recording medium that is combined with a computer, which is hardware, to perform the method of claim 1.

Images