KR20200094897A - Apparatus and method for providing diagnostic report on building defect - Google Patents

Abstract

The present disclosure provides a computing device for providing a diagnostic report on building defect. According to the present disclosure, the system comprises: a diagnosis request module configured to receive a first request for diagnosing defects in the building from a user terminal, and transmit a second request for diagnosing defects in the building to an inspector terminal; an information registration module configured to receive first building defect diagnosis information and building diagnosis information from the inspector terminal in response to the second request; a defect diagnosis report generation module configured to automatically generate a defect diagnosis report for the building using the first building defect diagnosis information; and an output module configured to provide a defect diagnosis report for the building to the user terminal.

Description

Apparatus and method for providing a building defect diagnosis report {APPARATUS AND METHOD FOR PROVIDING DIAGNOSTIC REPORT ON BUILDING DEFECT}

The present disclosure relates to an apparatus and method for providing a defect diagnosis report of a building, and more specifically, the construction building planned to be occupied was properly constructed based on the constructed part or design drawing unlike the design drawing. Regarding the device and method for automatically creating and providing a defect diagnosis report for the building by analyzing the defect inspection result through artificial intelligence and performing defect inspection of the building, such as the part that caused safety, functional and/or aesthetics after the inspection. will be.

A general defect is a condition in which the manufactured product does not have the quality or performance that it should have in general, that is, when a part or all of the structure is collapsed, or cracks or defects occur due to construction errors, resulting in obstacles to the safety, function, and aesthetics of the building. This refers to the case where there has been a problem, but recently, disputes over defects in buildings such as apartments, officetels, and apartment houses have continued. Usually, defect extraction companies diagnose and inspect building defects. Building defect collection companies perform a building inspection after tenants move in. If a defect is found by defect inspection after the tenant moves in, a defect lawsuit can be conducted so that the damaged tenant can receive compensation.

However, these existing methods of defect extraction companies have the problem of having to review defects after moving in, and it takes too long to win a defect lawsuit, and even if they win a defect lawsuit, the use of compensation for the tenant There is a problem that it is used as an expense for the benefit of the whole building, not for the purpose. In order to solve this problem, it is necessary to provide a defect diagnosis report for a building that can be prevented in advance so that the potential tenant checks for defects before moving in, repairs, and compensates, so that damage does not occur after moving in.

Embodiments disclosed in the present specification are intended to provide an apparatus and method for providing a building defect diagnosis report capable of receiving objective defect determination information before a prospective occupant moves in by providing a building defect diagnosis report to a user. .

A computing device that provides a building defect diagnosis report according to an embodiment of the present disclosure receives a first request for diagnosing defects in a building from a user terminal and transmits a second request for diagnosing defects in the building to an inspector terminal. In response to the second request, a diagnosis request module configured to perform, an information registration module configured to receive first building defect diagnosis information and building diagnosis information from the inspector terminal, and a defect diagnosis report for the building using the first building defect diagnosis information. It may include a defect diagnosis report generation module configured to automatically generate, and an output module configured to provide a defect diagnosis report for a building to a user terminal.

In addition, a method for providing a defect diagnosis report of a building by a computing device according to an embodiment of the present disclosure includes receiving a first request for diagnosing a defect in the building from a user terminal, and receiving a defect in the building with an inspector terminal. Transmitting a second request for diagnosing a second request, receiving first building defect diagnosis information and building diagnosis information from the inspector terminal in response to the second request, and diagnosing a building defect using the first building defect diagnosis information It may include automatically generating a report and providing a defect diagnosis report for the building to a user terminal.

According to various embodiments of the present disclosure, defects on a building are checked, repaired, and compensated for a building prior to the occupant's occupancy to prevent damage after occupancy.

The effects of the present disclosure 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 of the claims.

Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, where like reference numerals denote like elements, but are not limited thereto.
1 is an exemplary diagram of a system for inputting a defect diagnosis request and information in a building using a user terminal according to an embodiment of the present disclosure.
2 is a schematic diagram of a computing device for providing a defect diagnosis report for a building according to an embodiment of the present disclosure.
3 is a schematic diagram of a server device according to an embodiment of the present disclosure.
4 illustrates an example of basic building information held in a building basic information DB according to an embodiment of the present disclosure.
5 illustrates an example of building diagnosis information held in a building diagnosis information DB according to an embodiment of the present disclosure.
6 shows an example of building defect diagnosis information held in a building defect diagnosis information DB according to an embodiment of the present disclosure.
7 is a flowchart illustrating a method of providing a defect diagnosis report for a building according to an exemplary embodiment of the present disclosure.
8 is a structural diagram illustrating an artificial neural network for extracting defect diagnosis information of a building according to an embodiment of the present disclosure.
9 is a structural diagram illustrating an artificial neural network that automatically generates a defect diagnosis report for a building according to an embodiment of the present disclosure.
FIG. 10 is an exemplary diagram showing a list of inspection of a defect diagnosis report of a building according to an embodiment of the present disclosure.
11 is an exemplary view showing a photographic site of a finished defect of a defect diagnosis report of a building according to an embodiment of the present disclosure.
12 is an exemplary view showing a thermal imaging camera photographing report of a defect diagnosis report of a building according to an embodiment of the present disclosure.
13 is an exemplary view showing a reinforcing bar survey report of a defect diagnosis report of a building according to an embodiment of the present disclosure.

Hereinafter, with reference to the accompanying drawings, specific details for the practice of the present disclosure will be described in detail. However, in the following description, when there is a risk of unnecessarily obscuring the subject matter of the present disclosure, detailed descriptions of well-known functions or configurations will be omitted.

In the accompanying drawings, identical or corresponding elements are given the same reference numerals. In addition, in the following description of the embodiments, it may be omitted to describe the same or corresponding elements overlapping. However, even if description of a component is omitted, it is not intended that such component is not included in any embodiment.

A method of providing a defect diagnosis report for a building according to an embodiment of the present disclosure may analyze defect diagnosis information in a building received from an inspector terminal and generate a defect diagnosis report for the building. For example, this method uses at least one of supervised learning, unsupervised learning, and semi-supervised learning, which are one of artificial intelligence (machine learning) methods, Building defect diagnosis reports can be provided.

1 is an exemplary diagram of an interface for inputting a defect diagnosis request and information in a building using a user terminal 110 according to an embodiment of the present disclosure. Through an interface of the user terminal 110 (eg, a touch display, a keyboard, a mouse, a touch pen, or a stylus, a microphone, a motion recognition sensor, etc.), a user may input a request for defect diagnosis and occupancy information in a building. A user can apply for a defect diagnosis service by clicking the defect diagnosis service request button to diagnose a defect in a building to be occupied and inputting the occupancy information. The occupancy information input may include information such as an address of a building to be occupied, an occupied date of a prospective occupant, and a desired date for inspection.

In one embodiment, the user may click a defect diagnosis service request button on the defect diagnosis service request screen 120 of the user terminal 110 in order to request a defect diagnosis service. When the user clicks the defect diagnosis service request button, the screen of the user terminal is changed to the occupancy information input screen 130, and the occupant information such as the address of the building to be occupied, the occupant expected date of the occupant, and the inspection desired date can be entered. have. For example, if a user enters XX-gu ㅇㅇ-dong, OOO city on February 5, 2019 on the occupancy information input screen 130 using the user terminal 110 and clicks the submit button for a defect diagnosis service, a defect in the building The diagnosis request can be completed. In response to such a defect diagnosis request, a defect diagnosis report may be automatically generated. The configuration of the automatic generation of the defect diagnosis report will be described in detail with reference to FIGS. 2 to 13 below.

2 is a schematic diagram of a computing device for providing a defect diagnosis report for a building according to an embodiment of the present disclosure. In this embodiment, the computing device may be the server device 220, but is not limited thereto, and may be an arbitrary computing device such as a client device. The system shown in FIG. 2 may request the server device 220 to provide a building defect diagnosis report based on a defect diagnosis request in the building input by the user from the user terminal 110. Here, the user terminal 110 may receive information about occupancy of a building and may be an appropriate computing device having a user interface. The inspector terminal 240 receives defect information (for example, information on the defect location, defect details, etc.) in the building that the inspector diagnosed using the measuring equipment, and the server device 220 through the communication network 210 ), and can be any suitable computing device with a user interface.

For example, the interface of the user terminal 110 and/or the inspector terminal 240 may include one or more of a touch display, a keyboard, a mouse, a touch pen or a stylus, a microphone, and a motion recognition sensor, but are limited thereto. no. Meanwhile, the user terminal 110 and/or the inspector terminal 240 may be any one of a personal computer, a smart phone, and a tablet computer, but is not limited thereto.

When the server device 220 receives the user's request for defect diagnosis, through the communication network 210, the server device 220 may receive information on the building that the user intends to occupy from the construction company server 230 and store it in the database. The server device 220 can read the defect information of the building that the user is going to occupy, and learn the artificial neural network based on the read information, thereby extracting defects in the building and/or generating a defect diagnosis report of the building. I can. Here, the server device 220 is a computing device capable of communicating with other devices through a wired or wireless network, and may use one of a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), and the like. It may be a computing device capable of performing an arithmetic operation by using, but is not limited thereto. The server device 220 may provide the generated building defect diagnosis report to the user terminal 110 through the communication network 210, and sort the generated building defect diagnosis report by contractor and user to Can be saved.

3 is a schematic diagram of a server device according to an embodiment of the present disclosure. Hereinafter, the components of the server device 220 will be described in more detail. As illustrated in FIG. 3, the server device 220 may include a communication module 310, a processor 320, and a database 340. The processor 320 may include a diagnosis request module 322, an information registration module 324, an extraction module 326, a defect diagnosis report generation module 328, an output module 330, and a database 340 May include building basic information DB 342, building diagnosis information DB 344, and building defect diagnosis information DB 346. The server device 220 shown in FIG. 2 may include functions or components of the server device 220 shown in FIG. 3. In addition, among the functions or components of the server device 220, for components having the same member numbers or names as described in FIG. 2 described above, detailed descriptions may be omitted to avoid repetition, and changes Or, you can only explain additional parts.

The database 340 includes the building type, construction list, building location, area, construction projected design, etc., classified and stored, and the building basic information DB 342, the actual construction design of the actually constructed building, rebar exploration real photos, rebar exploration Building diagnosis information DB (344) that stores the results, real photos of thermal images, and results of thermal imaging cameras are classified and stored, details of defects diagnosed by the inspector, the details of defects of the building diagnosed by the inspector, list of existing constructions of the building, and actual construction A building defect diagnosis information DB 346 in which a list, a missing construction list, and defect details are classified and stored may be included. When receiving the user's request for defect diagnosis, the server device 220 may receive information on a building that the user is expected to occupy from the construction company server 230 through the communication network 210 and store the information in the building basic information DB, respectively.

In one embodiment, the server device 220, in the building basic information DB 342, the building diagnosis information DB 344, the building defect diagnosis information DB 346, the basic information of the building, the diagnosis information of the building, the defect of the building Diagnostic information can be read. In addition, the building diagnosis information DB 344 may output defect information of a building diagnosed by an inspector. Based on the diagnosis information of the building, the server device 220 uses at least one of, for example, supervised learning, unsupervised learning, and semi-supervised learning. One can be used to extract defect information other than the defect information of the building diagnosed by the inspector, and generate a defect diagnosis report of the building.

The server device 220 may provide the generated building defect diagnosis report to the user terminal 110 through the communication network 210, and sort the generated building defect diagnosis report by contractor and/or user. Building defect diagnosis information can be stored in DB. In FIG. 3, the database 340 is shown to be included in the server device 220, but is not limited thereto. According to embodiments, the database exists separately outside the server device 220 to be connected to the communication network 210. May be.

The communication module 310 may receive a building defect diagnosis request from the user terminal 110, and transmit the building defect diagnosis report output by the output module 330 to the user terminal 110 in response to the request. I can. The request for defect diagnosis of a building may include an address of a building to be occupied, an expected date of occupancy of the occupant, and a date desired for inspection, input through the user terminal 110. The communication module 310 may transmit a building defect diagnosis request including such user input information to the processor 320.

According to an embodiment, a user may request a defect diagnosis of a building by inputting user information through the user terminal 110. For example, after the user clicks the "defect diagnosis service request button" using the user terminal 110, enters ㅇㅇ-dong, XX-gu, OOO city, February 5, 2019, and "submits an application for defect diagnosis service" When a request for defect diagnosis of a building is requested by clicking a button, the communication module 310 is provided with the address of the user, the expected date of occupancy, and the date desired for inspection (for example, "OOO City XX-gu ㅇㅇ-dong", "February 5, 2019. Day", "January 7, 2019") may be transmitted to the processor 320 of the server device 220.

The diagnosis request module 322 may receive a first request for diagnosing defects in the building from the user terminal, and transmit a second request for diagnosing defects in the building to the inspector terminal 240. When the user inputs a first request for diagnosing defects in the building to the user terminal 110, the diagnosis request module 322 may transmit a second request for diagnosing defects in the building to the inspector terminal 240. Upon receiving the second request, the inspector terminal 240 may receive occupancy information such as an address of a building to be occupied, an occupied date of a prospective occupant, and a desired inspection date inputted by the user through the user terminal 110. The inspector can accept the request for defect diagnosis if it is possible to check the defect of the building on the desired inspection date entered by the user. If the defect inspection of the building is not possible on the desired inspection date, the inspector can propose another date to the user. The user terminal 110 and the inspector terminal 240 may adjust the inspection date through the diagnosis request module 322, and when the inspection date adjustment is completed, the inspector uses the inspector terminal 240 to set the inspection date to the user terminal ( 110) and finally accept the defect diagnosis request.

In one embodiment, the user clicks the defect diagnosis service request button on the defect diagnosis service application screen 120 of the user terminal 110, and the address of the building to be occupied on the occupancy information input screen 130, and the occupant expected date of occupancy , If you enter the desired date of inspection (for example, "OOO City XX ward ㅇㅇ-dong", "February 5, 2019", "January 7, 2019"), the inspector can use the diagnosis request module 322 Information input by the user may be received by the inspector terminal 240. The inspector can accept the request for defect diagnosis if it is possible to inspect the defect of the building on the inspection date entered by the user (for example, "January 7, 2019"). If the defect inspection of the building is not possible on the desired inspection date Other dates ("January 8, 2019", "January 10, 2019"...) can be suggested to the user. The user selects the date on which defect diagnosis is possible among the inspection dates suggested by the inspector through the user terminal and transmits it to the inspector terminal, and the inspector who receives the inspection date selected by the user transmits the final inspection date to the user terminal to finally diagnose the defect. You can accept your request.

The information registration module 324 may be configured to receive defect information on the building from the inspector terminal that has received the second request. Here, the defect information received from the inspector terminal about the building diagnosed by the inspector may be referred to as first building defect diagnosis information. According to an embodiment, the information registration module 324 may receive information that the inspector who has received the user's request for defect inspection visits the user's building to be occupied and diagnosed using specialized equipment. The inspector can diagnose the building and generate building diagnosis information, and can generate the first building defect diagnosis information for generating the defect diagnosis report by separately marking and recording the part where the defect occurred while diagnosing the building. In this case, the building diagnosis information may include information that can be collected using specialized equipment such as a real photo of rebar exploration and a real photo of thermal image. The first building defect diagnosis information may include information such as a list of missing constructions, differences from actual design drawings, and defect details. The first building defect diagnosis information collected by the inspector may be stored in the building defect diagnosis information DB. In this case, the picture taken for defect diagnosis may be stored together with a timestamp so that manipulation is impossible. For example, a time stamp can be recorded on the screen in the form of year, month, day, hour, minute, and second in a picture taken for defect diagnosis, so that it can be stored in the building diagnosis information DB so that it cannot be arbitrarily changed.

In one embodiment, the information registration module 324 includes building diagnosis information diagnosed using specialized equipment by an inspector visiting a building to be occupied by the user, and first building defect diagnosis information, which is details of defects of the building directly diagnosed by the inspector. Can receive. Specialized equipment includes digital thermometer, roughness meter, rebound hardness meter, ultrasonic measuring device, combustion efficiency meter, tile drawing meter, film thickness meter, line laser level, humidity meter, noise meter, concrete cover meter, leakage current meter, crack width It may include at least one of a measuring microscope, a wood moisture content meter, a laser distance meter, and an odor meter, but is not limited thereto. The inspector uses specialized equipment to mark the defective part by defect grade (for example, red sticker, yellow sticker, green sticker), and associates the mark with the defect details and detailed location to generate a defect diagnosis report. 1 Building defect diagnosis information can be generated. The collected first building defect diagnosis information may be stored in the building defect diagnosis information DB. For example, when the information registration module 324 stores the first building defect diagnosis information for generating a defect diagnosis report in the building defect diagnosis information DB, for example, a picture of a space taken with a thermal imaging camera and defect details Items (ex. gap between insulation material and double-glazed window, lack of filling urethane foam), detailed location, repair plan and countermeasure can be related and stored. At this time, the information registration module 324 stores the photograph taken for defect diagnosis and a timestamp (for example, "2018.10.03 13:24:15") together in the building diagnosis information DB, in the building diagnosis information DB. It can be set to make it impossible to change the stored information.

In another embodiment, the inspector may generate the first building defect diagnosis information based on basic information of a building, such as a construction projected plan, a construction list, and a reference real picture stored in the building basic information DB. For example, the inspector compares the standard real photo, which is the information of the building that has completed normal construction, stored in the basic building information DB and the information of the building to find the part where the defect has occurred, or compares the expected construction plan and the actually constructed design. By comparison, you can find the incorrectly constructed part.

The extraction module 326 receives the building diagnosis information and the first building defect diagnosis information generated from the information registration module 324, and the received building diagnosis information, the first building defect diagnosis information, and the building stored in the building basic information DB It can be configured to extract defects for buildings from basic information. Here, the defect for the building extracted through the extraction module may be referred to as second building defect diagnosis information. According to an embodiment, the extraction module 324 includes building diagnosis information diagnosed using specialized equipment by an inspector visiting a building to be occupied by the user, and first building defect diagnosis information, which is details of defects of the building directly diagnosed by the inspector. , By using the building basic information stored in the building basic information DB, defects for the building can be extracted. At this time, the building diagnosis information may refer to information that can be collected using specialized equipment such as real rebar exploration photos and thermal images.

The first building defect diagnosis information, the building diagnosis information, and the building basic information stored in the building basic information DB generated by the information registration module 324 are input to the input floor of the artificial neural network to extract the second building defect diagnosis information. Can be created. For example, the artificial neural network may extract the second building defect diagnosis information through at least one of supervised learning, unsupervised learning, and semi-supervised learning. Analyzes the first building defect diagnosis information, building diagnosis information, and building basic information stored in the building basic information DB, collected and/or generated by the inspector using an artificial neural network-based learning method, and based on this, the second building defect diagnosis information Can be extracted. The input variable input to the input floor of the artificial neural network may be a vector representing first building defect diagnosis information, building diagnosis information, and building basic information. For example, categories of first building defect diagnosis information, building diagnosis information, and building basic information may each be configured as one vector element. On the other hand, the output variable output from the output layer of the artificial neural network, according to an embodiment, such as the location of the defect analyzed by the extraction module 326, reinforcement analysis analysis, thermal image analysis, defect details, repair method, etc. It can be the second building defect diagnosis information. The extraction module 326 may train an artificial neural network using these input and output variables.

According to an embodiment, a list of missing constructions, differences between actual design drawings, first building defect diagnosis information including defect details, building diagnosis information generated by an inspector while diagnosing a building, and a building stored in the building diagnosis information DB Second building defect diagnosis information may be extracted for each item by using the basic information.

The defect diagnosis report generation module 328 may be configured to automatically generate a defect diagnosis report for a building by using the first building defect diagnosis information received by the information registration module 324. According to another embodiment, the defect diagnosis report generation module 328 receives the second defect diagnosis information extracted by the extraction module 326, and uses the received second defect diagnosis information to provide a defect diagnosis report for a building. Can be configured to automatically generate

According to an embodiment, the defect diagnosis report generation module 328 inputs at least one of the received first building defect diagnosis information and the second building defect diagnosis information to the input floor of the artificial neural network to automatically generate a defect diagnosis report of the building. You can create artificial neural networks that generate them. For example, similar to the extraction module 326, the artificial neural network diagnoses building defects through at least one of supervised learning, unsupervised learning, and semi-supervised learning. Reports can be automatically generated. Analyzes the first building defect diagnosis information received by the information registration module 324 and the second building defect diagnosis information output from the extraction module 326 using an artificial neural network-based learning method, and diagnoses building defects based on this Reports can be generated. The input variable input to the input floor of the artificial neural network will be a vector representing at least one of the first building defect diagnosis information received by the information registration module 324 and the second building defect diagnosis information output from the extraction module 326. I can. For example, the categories of the first building defect diagnosis information and the second building defect diagnosis information may each be configured as one vector data element. Meanwhile, the output variable output from the output layer of the artificial neural network may be a vector representing information on generation of a defect diagnosis report generated by the defect diagnosis report generation module 328 according to an embodiment. The defect diagnosis report generation module 328 may train the artificial neural network using these input variables and output variables. In FIG. 3, the extraction module 326 and the defect diagnosis report generation module 328 are implemented as separate modules, but the defect diagnosis report generation module 328 may be configured to include the extraction module 326. In addition, in Figure 3, the extraction module 326 discloses a configuration using an artificial neural network different from the artificial neural network used in the diagnostic report generation module 328, but is not limited thereto, and the extraction module 326 and the diagnostic report generation The module 328 may be configured to perform learning and inference tasks using the same artificial neural network.

According to an embodiment, the first building defect diagnosis information and the second building defect diagnosis information may be configured and output according to a building defect diagnosis report form. For example, a report on a defect inspection list for closing defects can display the details of defects, detailed locations, and grades of defects, which summarize the contents of all defects in the building. Photos, etc. can be displayed, and outside temperature, indoor temperature, relative humidity, thermal imaging photos, real photos, location of drawings, defect details, etc. can be displayed in the thermal imaging report, and the location of the drawings in the rebar exploration report. , Inspection photos, rebar exploration status map, defect details, etc. can be displayed.

The output module 330 may be configured to output a defect diagnosis report of a building generated by the defect diagnosis report generation module 328. Here, the defect diagnosis report of the building may be provided to and outputted to the user terminal 110, and the content of the report includes an inspector's opinion on defects, a picture taken by defect item, time information about the picture taken, and details of defects. The same information may be included and output, but is not limited thereto.

4 illustrates an example of basic building information held in a building basic information DB according to an embodiment of the present disclosure. The building basic information DB may include input information input through the user terminal 110 and may include basic information of a building. The basic building information may include a building type, a construction list, a building location, an area, an expected construction plan, and a reference real picture. In addition, the basic information of the building may be information of a building to which the user is expected to move in, provided from the contractor server 230. The standard real photo may refer to a photo representing information taken by a thermal imaging camera and rebar exploration information that was normally constructed.The standard real photo is a photo collected by an inspector while diagnosing defects in several buildings, or a contractor server and/or server It may include photos received from the device.

5 illustrates an example of building diagnosis information held in a building diagnosis information DB according to an embodiment of the present disclosure. The building diagnosis information may include the building diagnosis information collected by the inspector while diagnosing the building. The building diagnosis information may include an actual construction plan, a rebar exploration real picture, a rebar exploration result, a thermal image real picture, and a thermal imaging camera photographing result. In the reinforcing bar survey result and the thermal imaging result, the inspector's diagnosis opinion (ex. reason for defect, repair plan, and countermeasure) can be associated and stored. At this time, the rebar exploration result and thermal imaging result are the buildings diagnosed by the inspector. It can be classified into defect details and stored in the building diagnosis information DB. The building diagnosis information may be stored such that a timestamp for a photographed picture is stored together and manipulation is impossible. For example, a timestamp is recorded on the screen in the form of year, month, day, hour, minute, and second in a picture taken for defect diagnosis of a building, so that it cannot be arbitrarily changed, it is stored together in the building diagnosis information DB. The information stored in the diagnostic information DB can be set to be impossible to change arbitrarily. The building diagnosis information stored in the building diagnosis information DB may be input to the input floor of the artificial neural network by the extraction module 326 to extract defect diagnosis information.

6 shows an example of building defect diagnosis information held in a building defect diagnosis information DB according to an embodiment of the present disclosure. The building defect diagnosis information may include details of defects found by the inspector while diagnosing the building and/or defect diagnosis information extracted by the extraction module 326. Building defect diagnosis information may include existing construction list, actual construction list, missing construction list, and defect details. The building defect diagnosis information may be input to the input floor of the artificial neural network by the defect diagnosis report generation module 328 to generate a building defect diagnosis report.

7 is a flowchart illustrating a method of providing a defect diagnosis report for a building according to an exemplary embodiment of the present disclosure. The method of providing a building defect diagnosis report may be initiated with a step (S710) of receiving a first request for diagnosing defects in the building from a user terminal and transmitting a second request for diagnosing defects in the building to an inspector terminal. have. The diagnosis request module 322 may receive a defect diagnosis request in a building input by a user from a user terminal, and may transmit a defect diagnosis request in the building to the inspector terminal 240. The received and transmitted defect diagnosis request information in the building can be stored in a database for each user. Here, the defect diagnosis request in the building may include an address of a building to be occupied, an expected occupancy date of a occupant, a desired inspection date, and the like. In one example, referring to FIG. 3, the communication module 310 may receive a request for diagnosis of defects in a building from the user terminal 110. For example, when the user inputs occupancy information using the user terminal 110 and requests for defect diagnosis in the building, the communication module 310 transmits the user's input to the processor 320 of the server device 220 Can be transferred to.

After transmitting the second request, in response to the second request, defect diagnosis information of the building may be received from the inspector terminal (S720). The information registration module 324 may receive building diagnosis information diagnosed by the inspector using specialized equipment and first building defect diagnosis information, which is defect information for the building diagnosed by the inspector. The inspector can diagnose the building and generate building diagnosis information, and can generate the first building defect diagnosis information for generating the defect diagnosis report by separately marking and recording the part where the defect occurred while diagnosing the building. The first building defect diagnosis information may include information such as a defect detail missing construction list, a difference from an actual design drawing, and defect details.

The extraction module 326 receives the building diagnosis information and the first building defect diagnosis information generated from the information registration module 324, and the received building diagnosis information, the first building defect diagnosis information, and the building stored in the building basic information DB It can be configured to extract defects for buildings from basic information. Here, the extracted defect on the building may be referred to as second building defect diagnosis information. In one embodiment, the information registration module 322, the inspector visits the user's planned occupancy building and diagnoses building diagnosis information using specialized equipment and first building defect diagnosis information, which is details of defects of the building directly diagnosed by the inspector. Can receive. Specialized equipment includes digital thermometer, roughness meter, rebound hardness meter, ultrasonic measuring device, combustion efficiency meter, tile drawing meter, film thickness meter, line laser level, humidity meter, noise meter, concrete cover meter, leakage current meter, crack width It may include at least one of a measuring microscope, a wood moisture content meter, a laser distance meter, and an odor meter, but is not limited thereto. The inspector uses specialized equipment to mark the defective part by defect grade (for example, red sticker, yellow sticker, green sticker), and associates the mark with the defect details and detailed location to generate a defect diagnosis report. 1 Building defect diagnosis information can be generated. The collected first building defect diagnosis information may be stored in a building defect diagnosis information DB. According to another embodiment, the extraction module 324 includes diagnosis information diagnosed using specialized equipment by an inspector visiting a building to be occupied by the user and first building defect diagnosis information, which is details of defects of the building directly diagnosed by the inspector. Using this, it is possible to generate second building defect diagnosis information that extracts defects on the building. At this time, the building diagnosis information may refer to information that can be collected using specialized equipment such as real rebar exploration photos and thermal images.

Thereafter, a defect diagnosis report for the building may be automatically generated by using the defect diagnosis information of the building (S730). In the defect diagnosis report generation module 328, the first building defect diagnosis information and the second building defect diagnosis information generated and extracted by the information registration module 324 and the extraction module 326 are input to the input floor of the artificial neural network, You can create an artificial neural network that generates a defect diagnosis report. For example, the artificial neural network may generate a defect diagnosis report of a building through at least one of supervised learning, unsupervised learning, and semi-supervised learning. Analyzes the first building defect diagnosis information received by the information registration module 324 and the second building defect diagnosis information output from the extraction module 326 using an artificial neural network-based learning method, and diagnoses building defects based on this Reports can be generated. The input variable input to the input floor of the artificial neural network may be a vector representing the first building defect diagnosis information received by the information registration module 324 and the second building defect diagnosis information output from the extraction module 326. For example, the categories of the first building defect diagnosis information and the second building defect diagnosis information may each be configured as one vector data element. Meanwhile, the output variable output from the output layer of the artificial neural network may be a vector representing information on generation of a defect diagnosis report generated by the defect diagnosis report generation module 328 according to an embodiment. The defect diagnosis report generation module 328 may automatically generate a defect diagnosis report for a building by learning an artificial neural network using these input variables and output variables.

A defect diagnosis report for the building may be provided to the user terminal 110 (S740). The defect diagnosis report of the building generated by the defect diagnosis report generation module 328 may be output to the user terminal 110 for each report, and the contents of the report include an inspector's opinion on defects, a picture taken by defect item, and a photographed picture. Information, such as time information and defect details, may be included and output.

8 is a structural diagram showing an artificial neural network for extracting defect diagnosis information of a building according to an embodiment of the present disclosure, and FIG. 9 is a diagram illustrating an artificial neural network for automatically generating a defect diagnosis report of a building according to an embodiment of the present disclosure. It is a structural diagram shown. The artificial neural networks 800 and 900 are a statistical learning algorithm implemented based on the structure of a biological neural network or a structure that executes the algorithm in machine learning technology and cognitive science. In other words, in the artificial neural network (800, 900), as in the biological neural network, the nodes, which are artificial neurons that form a network by combining synapses, repeatedly adjust the weight of the synapse, and correct output and inference corresponding to a specific input. By learning so that the error between the outputs is reduced, a machine learning model with problem solving ability is represented.

In general, an artificial neural network is implemented as a multilayer perceptron (MLP) composed of multilayer nodes and their connections. The artificial neural networks 800 and 900 according to the present embodiment may be implemented using one of various artificial neural network structures including MLP. 8 and 9, the artificial neural networks 800 and 900 are input layers 820 and 920 that receive input signals or data 810, 812, and 814 from the outside, and an output corresponding to the input data. It is located between the output layers 840 and 940 that output signals or data (850, 852, 854, 856, 858, 960), the input layers 820 and 920 and the output layers 840 and 940, and the input layers 820 and 920 ), which extracts a characteristic and transmits it to the output layers 840 and 940, and includes n hidden layers 830_1 to 830_n and 930_1 to 930_n. Here, the output layers 840 and 940 receive signals from the hidden layers 830_1 to 830_n and 930_1 to 930_n and output them to the outside.

In general, the learning methods of the artificial neural networks 800 and 900 include a supervised learning method that learns to be optimized to solve a problem by inputting a teacher signal (correct answer), and an unsupervised learning method that does not require a teacher signal. There is an unsupervised learning method, and a semi-supervised learning method that uses supervised and unsupervised learning together. The system for extracting defect diagnosis information of a building using an artificial neural network shown in FIG. 8 is a supervised learning method, an unsupervised learning method, and a semi-supervised learning method to extract the building defect diagnosis information. Semi-supervised Learning) method, using at least one of the first building defect diagnosis information, building diagnosis information, and building basic information to determine the location of the defect, details of the defect, repair method, rebar exploration analysis, thermal image An artificial neural network 800 that provides second building defect diagnosis information such as an analysis diagram may be trained. The learned artificial neural network 800 may provide defect diagnosis information in the building in response to the user's request for diagnosis of defects in the building.

According to an embodiment, as shown in FIG. 8, the input variable of the artificial neural network 800 capable of extracting the defect diagnosis information of the building is the first building defect diagnosis collected by the inspector in the information registration module 324 The first building defect diagnosis information vector 810, the building diagnosis information vector 812, and the building basic information vector 814, in which categories of information, building diagnosis information, and building basic information are each composed of one vector data element. have.

For example, suppose that when the inspector executes a diagnosis on a building for which the user requested the defect diagnosis through the user terminal 110, a defect of "bedroom 1-molding contamination" is found. At this time, if you want to extract the defects of the building, assign a value of 1 to elements such as the first building defect diagnosis information, building diagnosis information, and basic building information such as "bedroom 1-molding pollution" found by the inspector, and the remaining elements Fields can be assigned a value of 0.

On the other hand, the output variable output from the output layer 840 of the artificial neural network 800 represents the location of the defect extracted by the extraction module 326, details of the defect, the repair method, rebar exploration analysis diagram, and thermal image analysis diagram. It can be a vector. According to an embodiment, the output variable is a defect position vector 850, a defect detail vector 852, a complement method vector 854, a rebar exploration analysis vector 856, and a thermal image analysis vector 858. It can be composed of. This output variable may be recognized as the second building defect diagnosis information and may act as an input variable of the artificial neural network 900 capable of generating the defect diagnosis report shown in FIG. 9. In the present disclosure, the input variables and output variables of the artificial neural network 800 may not be limited to the types described above.

In this way, a plurality of output variables corresponding to a plurality of input variables are matched with the input layer 820 and the output layer 840 of the artificial neural network 800, respectively, and the input layer 820, the hidden layers 830_1 to 830_n, and the output layer ( By adjusting the synaptic values between nodes included in 840), it is possible to learn to infer a correct output corresponding to a specific input. Through this learning process, the characteristics hidden in the input variable of the artificial neural network 800 can be identified, and the error between the output variable calculated based on the input variable and the target output is reduced. You can adjust the synaptic value (or weight). Using the artificial neural network 800 learned in this way, the second building defect diagnosis information such as the location of the defect, details of the defect, a repair method, a rebar exploration analysis diagram, and a thermal image analysis diagram may be extracted.

On the other hand, the system for generating a defect diagnosis report using the artificial neural network shown in FIG. 9 is a supervised learning method, an unsupervised learning method, and a semi-supervised learning method to generate a defect diagnosis report. -supervised Learning) method, it is possible to learn the artificial neural network 900 that provides a defect diagnosis report of a building by using the first building defect diagnosis information and the second building defect diagnosis information. The learned artificial neural network 900 may provide a defect diagnosis report in the building in response to the user's request for defect diagnosis in the building.

According to an embodiment, as shown in FIG. 9, the input variable of the artificial neural network 900 is the first building defect diagnosis information generated by the information registration module 324 and the second building extracted from the extraction module 326. A first building defect diagnosis information vector 910 and a second building defect diagnosis information vector 912, each of which categories of defect diagnosis information are composed of one vector data element, may be included.

For example, it is assumed that when the inspector executes the diagnosis of the building for which the user requested the defect diagnosis through the user terminal 110, a defect called “kitchen-sink top scratch” is found. At this time, the defect information of the building found by the inspector may be recognized as the first building defect diagnosis information, such as the location of the defect extracted by the extraction module 326, details of the defect, the repair method, rebar exploration analysis, and thermal image analysis. The information may be recognized as second building defect diagnosis information. In order to provide a defect diagnosis report in a building, a value of 1 may be assigned to elements such as the first building defect diagnosis information and the second building defect diagnosis information, and a value of 0 may be assigned to the elements of the remaining guides.

Meanwhile, the output variable output from the output layer 940 of the artificial neural network 900 may be a vector representing the defect diagnosis report generated by the defect diagnosis report generation module 328. According to an embodiment, the output variable may be composed of a defect diagnosis report vector 950. In the present disclosure, the input variable and the output variable of the artificial neural network 900 may not be limited to the types described above.

In this way, the input layer 920 and the output layer 940 of the artificial neural network 900 are matched with a plurality of output variables corresponding to a plurality of input variables, respectively, and the input layer 920, the hidden layers 930_1 to 930_n, and the output layer By adjusting the synaptic value between nodes included in 940, it is possible to learn to infer a correct output corresponding to a specific input. Through this learning process, the characteristics hidden in the input variable of the artificial neural network 900 can be identified, and the error between the output variable calculated based on the input variable and the target output is reduced. You can adjust the synaptic value (or weight). Using the artificial neural network 900 learned in this way, a defect diagnosis report in the building may be extracted.

FIG. 10 is an exemplary diagram showing a list of inspection of a defect diagnosis report of a building according to an embodiment of the present disclosure. The deadline inspection list 1000 may include first building defect diagnosis information extracted from the extraction module 326 and the first building defect diagnosis information that the inspector visits to the user's scheduled occupancy building and diagnosed using specialized equipment. . At this time, the detailed location where the defect has occurred, the details of the defect, and the indication for each level of the defect may be displayed and output.

According to an embodiment, when the inspector performs a defect diagnosis on the front door, if it is considered that the defect degree of the front door is high, the defect grade is determined as the first grade, and then a red sticker may be attached. At this time, the final defect score in the building can be derived by collecting the defect and the defect grade.

11 is an exemplary view showing a photographic site of a finished defect of a defect diagnosis report of a building according to an embodiment of the present disclosure. The deadline photo mount 1100 may output an inspection photo corresponding to the defect output from the deadline inspection list 1000 and detailed contents. The finished photo site 1100 may be provided to the contractor, and the contractor may provide the user with a scheduled repair date, a repair completion date, a repair method, and a repair completion picture for the defect.

12 is an exemplary view showing a thermal imaging camera photographing report of a defect diagnosis report of a building according to an embodiment of the present disclosure. The thermal imaging camera photographing report 1200 may be output including a thermal photographing photograph, a real photograph, a drawing position, a detailed position, and defect details. For example, if the "Corner of the Living Room" was photographed with a thermal imaging camera, a photo of the thermal image of the "Corner of the Living Room", and a real photo, location in the drawing, detailed location, and defect details can be printed together. have.

13 is an exemplary view showing a reinforcing bar survey report of a defect diagnosis report of a building according to an embodiment of the present disclosure. The reinforcing bar exploration report 1300 may be output, including an inspection photo of the location where the reinforcing bar exploration was performed, the location in the drawing, a reinforcing bar exploration status diagram, details of defects, and repair plans and countermeasures.

In general, the system for outputting a list of properties in which false properties have been inspected as described in the present specification includes a wireless telephone, a cellular telephone, a laptop computer, a wireless multimedia device, a wireless communication PC (personal computer) card, a PDA, an external modem or an internal modem. , A device that communicates over a wireless channel, and the like. The device includes an access terminal (AT), an access unit, a subscriber unit, a mobile station, a mobile device, a mobile unit, a mobile phone, a mobile, a remote station, a remote terminal, a remote unit, a user device, a user equipment, It may have various names, such as handheld devices. Any device described herein may have a memory to store instructions and data, as well as hardware, software, firmware, or combinations thereof.

The techniques described herein may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented in electronic hardware, computer software, or combinations 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 on 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, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

In a hardware implementation, the processing units used to perform the techniques include one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs). ), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described herein. , Computer, or a combination thereof.

Accordingly, various exemplary logic blocks, modules, and circuits described in connection with the disclosure herein include general purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, Alternatively, it may be implemented or performed in any combination of those designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, eg, a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in connection with the DSP core, or any other such configuration.

In firmware and/or software implementation, the techniques include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), PROM ( on computer-readable media such as programmable read-only memory), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage device, etc. It can also be implemented as stored instructions. The instructions may be executable by one or more processors, and may cause the processor(s) to perform certain aspects of the functionality described herein.

When implemented in software, the functions may be stored on a computer-readable medium as one or more instructions or codes or transmitted through a computer-readable medium. Computer-readable media includes both computer storage media and communication media, including any medium that facilitates transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a computer. By way of non-limiting example, such computer-readable medium may contain RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or desired program code in the form of instructions or data structures. It may include any other media that may be used for transfer or storage to and accessible by a computer. Also, any connection is properly termed a computer-readable medium.

For example, if the software is transmitted from a website, server, or other remote source using wireless technologies such as coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or infrared, wireless, and microwave, coaxial cable , Fiber optic cable, twisted pair, digital subscriber line, or wireless technologies such as infrared, wireless, and microwave are included within the definition of the medium. As used herein, disks and disks include CDs, laser disks, optical disks, digital versatile disks (DVDs), floppy disks, and Blu-ray disks, where disks are usually The data is reproduced magnetically, while the discs reproduce the data optically using a laser. Combinations of the above should also be included within the scope of computer-readable media.

The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other type of storage medium known in the art. An exemplary storage medium can be coupled to a processor such that the processor can read information from or write information to the storage medium. Alternatively, the storage medium may be integrated into the processor. The processor and storage medium may also reside within the ASIC. The ASIC may exist in the user terminal. Alternatively, the processor and storage medium may exist as separate components in the user terminal.

The preceding description of the present disclosure is provided to enable those skilled in the art to make or use the present disclosure. Various modifications of the present disclosure will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to various modifications without departing from the spirit or scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the examples described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Although exemplary implementations may refer to utilizing aspects of the presently disclosed subject matter in the context of one or more standalone computer systems, the subject matter is not so limited, but rather is associated with any computing environment such as a network or distributed computing environment. It can also be implemented. Furthermore, aspects of the presently disclosed subject matter may be implemented in or across multiple processing chips or devices, and storage may be similarly affected across multiple devices. Such devices may include PCs, network servers, and handheld devices.

Although the subject matter has been described in language specific to structural features and/or methodological actions, it will be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and acts described above are described as an exemplary form of implementing the claims.

Although the method mentioned in this specification has been described through specific embodiments, it is possible to implement it as a computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices that store data that can be read by a computer system. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tapes, floppy disks, and optical data storage devices. In addition, the computer-readable recording medium can be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion. In addition, functional programs, codes, and code segments for implementing the embodiments can be easily inferred by programmers in the technical field to which the present invention belongs.

In the present specification, the present disclosure has been described with reference to some embodiments, but it should be understood that various modifications and changes may be made without departing from the scope of the present disclosure as understood by those skilled in the art to which the present invention belongs. something to do. In addition, such modifications and variations should be considered within the scope of the claims appended hereto.

110: user terminal 120: defect diagnosis service application screen
130: occupancy information input screen 210: communication network
220: server device 230: contractor server
240: inspector terminal 310: communication module
320: processor 322: diagnostic request module
324: information registration module 326: extraction module
328: fault diagnosis report generation module 330: output module
340: database 342: building basic information DB
344: Building diagnosis information DB 346: Building defect diagnosis information DB
800, 900: artificial neural network 810: first building defect diagnosis information vector
812: building diagnostic information vector 814: building basic information vector
820, 920: input layer
830_1 to 830_n, 930_1 to 930_n: hidden layer
840, 940: output layer 850: position vector of the defect
852: Let's detail vector 854: Conservative method vector
856: rebar exploration analysis diagram vector 858: thermal image analysis diagram vector
910: first building defect diagnosis information vector
912: second building defect diagnosis information vector
950: defect diagnostic report vector 1000: deadline checklist
1100: Let's close photo site 1200: Thermal imaging camera shooting report
1300: Rebar Exploration Report

Claims (10)

In a computing device that provides a building defect diagnosis report,
A diagnosis request module, configured to receive a first request for diagnosing a fault in the building from a user terminal, and transmit a second request for diagnosing a defect in the building to an inspector terminal;
An information registration module configured to receive first building defect diagnosis information and building diagnosis information from the inspector terminal in response to the second request;
A defect diagnosis report generation module configured to automatically generate a defect diagnosis report for the building using the first building defect diagnosis information; And
Output module configured to provide a defect diagnosis report for the building to the user terminal
Computing device comprising a.
The method of claim 1,
The computing device further comprising an extraction module configured to extract a defect for the building from the first building defect diagnosis information, the building diagnosis information, and the building basic information.
According to claim 2,
The extraction module,
Computing further configured to input the first building defect diagnosis information, the building diagnosis information, and the building basic information into an input floor of the learned artificial neural network to extract second building defect diagnosis information including the extracted defects for the building. Device.
The method of claim 1,
The first building defect diagnosis information,
Computing device that contains at least one of a list of missing constructions, differences from actual blueprints, and defect details.
The method of claim 3,
The defect diagnosis report generation module,
A computing device configured to automatically generate the defect diagnosis report by inputting at least one diagnosis information of the first building defect diagnosis information and the second building defect diagnosis information into an input floor of an artificial neural network.
The method of claim 1,
Further comprising a database configured to store a plurality of building basic information, a plurality of building diagnosis information, and a plurality of building defect diagnosis information,
The plurality of building basic information,
Includes at least one of a building type, a construction list, a building location, an area, and an expected construction plan of the building,
The plurality of building diagnosis information,
Including at least one of location information of the building, a picture taken for each predetermined defect item, time information for the taken picture, and defect details,
The plurality of building defect diagnosis information,
Including at least one of the existing construction list, the actual construction list, the missing construction list, and defect details of the building,
Computing device.
In a method for providing a defect diagnosis report of a building by a computing device,
Receiving a first request for diagnosing defects in the building from a user terminal, and transmitting a second request for diagnosing defects in the building to an inspector terminal;
Receiving first building defect diagnosis information and building diagnosis information from the inspector terminal in response to the second request;
Automatically generating a defect diagnosis report for the building by using the first building defect diagnosis information;
Including the step of providing a defect diagnosis report for the building to a user terminal,
How to provide a building defect diagnosis report.
The method of claim 7,
The method of providing a building defect diagnosis report further comprising the step of extracting a defect for the building from the defect diagnosis information of the first building, the building diagnosis information, and the basic building information.
The method of claim 8,
The step of extracting the defect for the building,
And extracting second building defect diagnosis information including the extracted defects for the building by inputting the first building defect diagnosis information, the building diagnosis information, and the building basic information into an input floor of the learned artificial neural network. , How to provide a building's defect diagnosis report
A computer-readable storage medium in which a program including instructions for performing each step according to the method of providing a defect diagnosis report of any one of claims 7 to 9 is recorded.

Images