Computer program, information processor and information processing method

Abstract

To provide a computer program, an information processor, and an information processing method that enable accurate and easy acquisition of information on the conformance of an architectural structure.SOLUTION: A computer program makes a computer execute processes for obtaining nonconformance specific information that specifies a nonconforming point in an architectural structure that do not conform to the regulations, and outputting conformance information on the conformance of the architectural structure at a given implementation time based on the obtained non-conformance specific information and the first model using regulations for multiple architectural structures at different implementation times.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The present disclosure relates to a computer program, an information processing device, and an information processing method. [Background technology]

[0002] Patent Document 1 discloses a computer program that uses a learning model for fixed asset valuation, thereby making it possible to automatically and accurately obtain data necessary for calculating fixed asset valuation. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Application No. 2022-78745 Summary of the Invention [Problem to be solved by the invention]

[0004] There are cases where it becomes necessary to check whether a specific building, such as a building you own or a building you live in, complies with the current building regulations, and if it does not, whether it complies with the regulations at the time the building was enacted. However, because the amount of building regulations is enormous, such an investigation is not easy and takes time.

[0005] The present disclosure has been made in consideration of the above circumstances, and aims to provide a computer program, an information processing device, and an information processing method that can accurately and easily obtain information regarding the suitability of a building. [Means for solving the problem]

[0006] The computer program disclosed herein acquires non-compliance identification information that identifies non-compliant parts of a building that do not comply with regulations, and causes a computer to execute a process of outputting compliance information regarding the compliance of the building at a specified implementation date based on the acquired non-compliance identification information and a first model that uses regulations for multiple buildings with different implementation dates.

[0007] The information processing device of the present disclosure includes a control unit, which acquires non-compliance identification information that identifies non-compliant parts of a building that do not comply with regulations, and outputs compliance information regarding the compliance of the building at a specified implementation date based on the acquired non-compliance identification information and a first model that uses regulations for multiple buildings with different implementation dates.

[0008] The information processing method disclosed herein involves a computer executing a process to acquire non-compliance identification information that identifies non-compliant parts of a building that do not comply with regulations, and output compliance information regarding the compliance of the building at a specified implementation date based on the acquired non-compliance identification information and a first model that uses regulations for multiple buildings with different implementation dates. Effect of the Invention

[0009] According to the present invention, a computer program, an information processing device, and an information processing method are provided that can accurately and easily obtain information on the suitability of a building. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is an explanatory diagram conceptually illustrating an embodiment according to the present disclosure. [Diagram 2] 1 is a functional block diagram showing an example of the configuration of a compatibility determination device according to a first embodiment. [Diagram 3] 2 is a functional block diagram showing a configuration example of a server device according to the first embodiment. FIG. [Figure 4] 11 is a flowchart illustrating the processing of a first function that outputs nonconformity identifying information for drawing data from a user. [Diagram 5]10 is an illustrative diagram showing an example of non-conformity specific information displayed on a display unit of the conformity determination device; FIG. [Figure 6] FIG. 13 is an explanatory diagram conceptually illustrating generation of a prompt. [Figure 7] 13 is a flowchart illustrating the processing of a second function of outputting compatibility information for drawing data from a user. [Figure 8] FIG. 13 is an explanatory diagram conceptually illustrating generation of a prompt. [Figure 9] 11 is an illustrative diagram showing an example in which non-conformity specific information is displayed on a display unit of the conformity determination device; FIG. [Figure 10] 11 is a flowchart illustrating a process of outputting a report on non-conformance points in drawing data from a user. [Figure 11] FIG. 13 is an explanatory diagram conceptually illustrating the generation of a prompt for creating a report. [Figure 12] FIG. 13 is an explanatory diagram conceptually illustrating a report output by a language model. [Figure 13] 13 is a flowchart illustrating a report editing process according to the second embodiment. [Figure 14] 11 is a flowchart illustrating a process for outputting a report including compatibility information for drawing data from a user. [Figure 15] FIG. 13 is an explanatory diagram conceptually illustrating the generation of a prompt for creating a report. [Figure 16] FIG. 13 is an explanatory diagram conceptually illustrating a report output by a language model. [Figure 17] 13 is a flowchart illustrating a process for outputting a future scenario of a building related to drawing data based on suitability information for the drawing data from a user. [Figure 18] FIG. 13 is an explanatory diagram conceptually showing the generation of a prompt for creating a scenario. [Figure 19] FIG. 13 is an explanatory diagram conceptually illustrating a scenario output by a language model. [Figure 20] FIG. 13 is a functional block diagram showing a configuration example of a server device according to a fifth embodiment. [Figure 21] 11 is a flowchart illustrating an example in which the server device outputs an estimate of repair costs when a non-conforming portion in drawing data from a user is repaired to make it conforming. [Figure 22] FIG. 13 is an explanatory diagram conceptually illustrating the generation of a prompt for creating a quote. [Diagram 23] FIG. 13 is an explanatory diagram conceptually illustrating an estimate output by a language model. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the drawings showing embodiments thereof.

[0012] (Embodiment 1) FIG. 1 is an explanatory diagram conceptually illustrating an embodiment according to the present disclosure. In this embodiment, reference numeral 10 denotes a compatibility determination device, and reference numeral 20 denotes a server device (information processing device). The compatibility determination device 10 is connected to the server device 20 via a network N including a wireless LAN (Local Area Network) and the Internet. The server device 20 is, for example, a server computer, a personal computer, or a quantum computer.

[0013] The conformity determination device 10 is, for example, a personal computer, and outputs nonconformity identification information that identifies parts that do not conform to current regulations regarding buildings (nonconforming parts) (hereinafter, first function). Furthermore, when a nonconforming part is identified, the conformity determination device 10 outputs conformity information indicating whether or not the nonconforming part conforms to regulations related to a specified enforcement date in the past (hereinafter, second function). Here, regulations regarding buildings include, for example, the Building Standards Act, the Barrier-Free Act, the Energy Conservation Act, etc. The following description will be given taking the Building Standards Act as an example.

[0014] In executing the first function, the conformity determination device 10 acquires, for example, design drawings (CAD data, PDF data), photographic data, and the like (hereinafter referred to as drawing data) from a user, and transmits the acquired drawing data to the server device 20. The server device 20 transmits nonconformity identification information that identifies nonconformity points that do not conform to the current Building Standards Act for the transmitted drawing data to the conformity determination device 10. The conformity determination device 10 outputs the nonconformity identification information for the drawing data acquired from the user based on the transmitted nonconformity identification information.

[0015] In executing the second function, as described above, the server device 20 outputs conformity information for non-compliant parts that do not conform to the current Building Standards Act in the drawing data acquired from the user via the conformity determination device 10, based on the Building Standards Act of a specified past enforcement date. In the second function, the server device 20 outputs conformity information, for example, based on the Building Standards Act of the time of construction of the building related to the drawing data acquired from the user.

[0016] FIG. 2 is a functional block diagram showing an example of the configuration of the compatibility determination device 10 according to the first embodiment. The compatibility determination device 10 includes a control unit 11, a storage unit 12, an output unit 13, an input unit 14, a communication unit 15, a reading unit 16, and a display unit 17. Each component is connected via a bus.

[0017] The control unit 11 includes one or more arithmetic processing devices such as a CPU, an MPU (Micro-Processing Unit), a GPU (Graphics Processing Unit), etc., and performs various information processing, control processing, etc. related to the compatibility judgment device 10 by reading and executing a control program P described below that is stored in the memory unit 12 using built-in memories such as a ROM (Read Only Memory) or RAM (Random Access Memory), a clock, a counter, etc.

[0018] The storage unit 12 includes a non-volatile memory such as a hard disk, a flash memory, or an SSD. The storage unit 12 stores various computer programs and data referenced by the control unit 11. The storage unit 12 stores a control program P for causing a computer to execute processing related to the output of non-conformity identification information. The storage unit 12 also temporarily stores data and the like required for the control unit 11 to execute arithmetic processing.

[0019] The output unit 13 displays the information to be displayed to the user on the display unit 17, or outputs it by printing it on a recording medium such as paper via a printing mechanism (not shown) provided in the conformity determination device 10. For example, the output unit 13 displays the nonconformity specification information for the acquired drawing data on the display unit 17, or prints it on paper.

[0020] The input unit 14 is an interface that accepts input from a user. The input unit 14 includes, for example, a keyboard, a mouse, a touch panel device with a built-in display, a scanner, etc. For example, the input unit 14 accepts input of drawing data from the user.

[0021] The communication unit 15 performs data communication with the server device 20, for example, via a wireless LAN and the Internet. For example, the communication unit 15 transmits drawing data input by a user to the server device 20, and receives nonconformity identification information from the server device 20.

[0022] The reading unit 16 reads a portable storage medium 200a including a CD (Compact Disc)-ROM or a DVD (Digital Versatile Disc)-ROM. The control unit 11 may read the control program P from the portable storage medium 200a via the reading unit 16 and store it in the storage unit 12. The control unit 11 may also download the control program P from another computer via a network N or the like and store it in the storage unit 12. Furthermore, the control unit 11 may read the control program P from the semiconductor memory 200b.

[0023] The display unit 17 is a liquid crystal display, an organic EL (electroluminescence) display, or the like, and displays various information according to instructions from the control unit 11. For example, the display unit 17 displays the non-conformity specifying information as described above.

[0024] FIG. 3 is a functional block diagram showing an example of the configuration of the server device 20 according to the first embodiment. The server device 20 according to the first embodiment includes a control unit 21, a storage unit 22, a communication unit 23, a reading unit 24, and a large-capacity storage unit 25. Each component is connected via a bus.

[0025] The control unit 21 includes an arithmetic processing unit such as a CPU, an MPU, a GPU, etc., and performs various information processing, control processing, etc. related to the server device 20 by reading and executing the control program P2 stored in the storage unit 22. The control program P2 can be deployed so as to be executed on a single computer, or on one site, or distributed across multiple sites and on multiple computers interconnected by a communication network. In this embodiment, the control unit 21 is described as being a single processor, but it may also be a multiprocessor.

[0026] The storage unit 22 includes memory elements such as RAM and ROM, and stores the control program P2 or data required for the control unit 21 to execute processing. The storage unit 22 also temporarily stores data required for the control unit 21 to execute arithmetic processing. The storage unit 22 also stores text data for each violation related to the annotation described below.

[0027] The communication unit 23 performs data communication with the conformity determination device 10, for example, via a wireless LAN and the Internet. For example, the communication unit 23 transmits to the conformity determination device 10 nonconformity identification information for the drawing data from the user.

[0028] The reading unit 24 reads the portable storage medium 200a including a CD-ROM or a DVD-ROM. The control unit 21 may read the control program P2 from the portable storage medium 200a via the reading unit 24 and store it in the mass storage unit 25. The control unit 21 may also download the control program P2 from another computer via the network N or the like and store it in the mass storage unit 25. Furthermore, the control unit 21 may read the control program P2 from the semiconductor memory 200b.

[0029] The mass storage unit 25 includes a recording medium such as a hard disk drive (HDD), a solid state drive (SSD), etc. The mass storage unit 25 stores a regulation database (DB) 251, a language model 252, a non-conforming part model 258, and training data 259.

[0030] The regulations DB 251 stores a plurality of regulations (Building Standards Acts) relating to buildings that were enacted at different times. Civil Code may also be stored in the regulations DB 251. The regulations DB 251 stores the provisions (text data) of each Building Standards Act in association with the date of enactment. When the Building Standards Act is amended, new regulations are acquired via the reading unit 24 or the communication unit 23, and the regulations DB 251 is updated.

[0031] The non-conforming part model 258 is a trained learning model generated by machine learning. The non-conforming part model 258 uses semantic segmentation on the drawing data sent from the conformity determination device 10 to identify non-conforming parts in the drawing data that are in conformity with the current Building Standards Act, and outputs non-conformity identification information.

[0032] In detail, when drawing data is input, the non-compliant part model 258 recognizes objects (here, compliant and non-compliant architectural components under the current Building Standards Act) included in the drawing data, classifies each pixel of the input drawing data into compliant and non-compliant architectural components, and outputs label drawing data (hereinafter, non-compliance specific information) in which a label indicating a violation, which will be described later, is associated with the non-compliant architectural components. Here, architectural components are parts that make up a building, such as rooms, roofs, exterior walls, interior walls, fittings (windows, doors, etc.), floors, finishing materials, etc., and architectural components that are non-compliant under the current Building Standards Act correspond to non-compliant parts.

[0033] Any type of neural network may be used to configure the nonconforming part model 258. The nonconforming part model 258 is a learning model such as a Convolutional Neural Network (CNN), and may be configured with, for example, a U-Net, a Fully Convolutional Network (FCN), or a SegNet. The nonconforming part model 258 may also be a learning model such as a Recurrent Neural Network (RNN), a Transformer, or a GPT.

[0034] The non-conformity part model 258 has an input layer, an intermediate layer, and an output layer (not shown), and drawing data from a user is input to the input layer. The intermediate layer has a convolution layer, a pooling layer, and a deconvolution layer. The drawing data input to the intermediate layer via the input layer is filtered in the convolution layer to extract image features and generate a feature map, and the generated feature map is compressed in the pooling layer. The deconvolution layer expands (maps) the feature map generated by the convolution layer and the pooling layer to the original image size. The deconvolution layer identifies which object exists in which position in the image on a pixel-by-pixel basis based on the features extracted in the convolution layer, and outputs label drawing data that identifies the object (non-conformity part).

[0035] The training data 259 stores training data for generating the non-conforming part model 258 by machine learning an unlearned learning model. For example, the training data 259 stores a training data set in which training sample drawing data and correct label drawing data that is labeled to identify an object (non-conforming part) to be determined in the sample drawing data are associated with each other. The correct label drawing data is annotated with the class name (architectural component) of each object (non-conforming part) and information (e.g., a mark) indicating a violation of the current Building Standards Act in each non-conforming part. For example, in the correct label drawing data, a different mark is attached to each non-conforming part (architectural component) according to the violation.

[0036] Specifically, a different mark is used to annotate the violation, such as a circle mark for a window size less than the current regulations, a square mark for a wall thickness less than the current regulations, a star mark for a building coverage ratio less than the current regulations, etc. A plurality of such training datasets are stored in the training data 259, and a unique ID of the training dataset is stored to identify each training dataset.

[0037] The process of generating the nonconforming part model 258 by performing machine learning will be described. The nonconforming part model 258 is trained to output correct label drawing data when sample drawing data is input. The control unit 21 of the server device 20 acquires a plurality of training data sets from the training data 259. The control unit 21 sequentially inputs the sample drawing data to the nonconforming part model 258, and sequentially outputs label drawing data marked according to the violation for each building component related to the nonconforming part. Specifically, the nonconforming part model 258 performs calculations in the intermediate layer based on the input sample drawing data, and outputs label drawing data marked with a violation for each classified nonconforming part. Then, the nonconforming part model 258 compares the output label drawing data with the correct label drawing data corresponding to the input sample drawing data, and optimizes parameters such as weights (coupling coefficients) between nodes so that the two are similar. In this way, the nonconforming part model 258 is generated, and the generated nonconforming part model 258 is stored in the large-capacity storage unit 25.

[0038] The language model 252 is a trained language model, and examples of the language model 252 that can be used include Bidirectional Encoder Representations from Transformers (BERT), Transformer, Generative Pre-trained Transformer (GPT)-3, GPT-4, Large Language Model Meta AI (LLaMA), and Pathways Language Model (PaLM) 2. The above model is a general-purpose natural language processing model constructed by performing unsupervised pre-training using a large-scale set of sentences.

[0039] The language model 252 receives a prompt input and outputs the conformity information. The prompt includes the nonconformity specification information output from the nonconformity part model 258 and regulation specification information specifying the Building Standards Act on a specified enforcement date. The conformity information also includes an answer corresponding to the prompt and a provision on which the answer is based. The enforcement date of the regulation related to the regulation specification information is input by the user via the conformity determination device 10, for example.

[0040] FIG. 4 is a flowchart illustrating the process of the first function of outputting non-conformity identifying information for drawing data from a user.

[0041] The input unit 14 of the compatibility determination device 10 receives input of drawing data from a user (step S101). Such drawing data may be electronic data or may be scan data obtained by scanning a drawing on a paper medium using a scanner (input unit 14).

[0042] When the input unit 14 accepts input of drawing data from a user, the communication unit 15 transmits the drawing data accepted from the user to the server device 20 via the network N (step S102), and the communication unit 23 of the server device 20 receives the drawing data (step S201).

[0043] When the drawing data is received, the control unit 21 of the server device 20 inputs the received drawing data to the nonconformity part model 258 (step S202). When the drawing data is input, the nonconformity part model 258 recognizes objects included in the drawing data, classifies the nonconformity parts, and outputs label drawing data (nonconformity identification information) in which a different label is attached according to the violation for each building component related to the nonconformity part, and the control unit 21 acquires the nonconformity identification information (step S203).

[0044] In this way, the control unit 21, which has acquired the non-conformity identification information from the non-conformity area model 258, generates the non-conformity identification information in text format, for example, based on the contents stored in the memory unit 22 and the acquired non-conformity identification information (label image data) (step S204). That is, the control unit 21 generates non-conformity specifying information in text format based on non-conformity specifying information in image format, which indicates non-conformity points (architectural components) on the drawing by marking them according to the violations.

[0045] Specifically, the control unit 21 generates non-conformity specific information in text format by reading the text for each violation to be annotated from the storage unit 22. For example, for a circle on the drawing, a text stating "The window size is below the current regulations" is generated, for a square, a text stating "The wall thickness is below the current regulations" is generated, and for a star, a text stating "The building coverage ratio is below the current regulations" is generated. Hereinafter, the image-format non-conformity specific information and the text-format non-conformity specific information will be collectively referred to as simply non-conformity specific information.

[0046] As described above, when the control unit 21 acquires non-conformity identification information in image format and generates non-conformity identification information in text format, the communication unit 23 transmits the non-conformity identification information to the conformity judgment device 10 via the network N (step S205), and the communication unit 15 of the conformity judgment device 10 receives the non-conformity identification information (step S103).

[0047] When the nonconformity specific information is received from the server device 20, the output unit 13 of the conformity judgment device 10 displays the received nonconformity specific information on the display unit 17 or outputs it by printing it on a paper medium (step S104).

[0048] FIG. 5 is an illustrative diagram showing an example of the non-conformity specifying information displayed on the display unit 17 of the conformity determining device 10. As shown in FIG. As shown in Fig. 5, the display unit 17 of the conformity determination device 10 displays nonconformity specific information in text format together with image-format nonconformity specific information in which a mark M is attached according to the violation for each architectural component corresponding to a nonconformity on the drawing related to the drawing data from the user. Therefore, the user can grasp the nonconformity at a glance.

[0049] In the above, the non-conforming part model 258 is described as a learning model of CNN, but the present invention is not limited to this, and may be a language model of GPT. In this case, the non-conforming part model 258 is a general-purpose natural language processing model constructed by performing unsupervised pre-learning using a large-scale text group, and outputs non-conforming specific information in text format. In addition, the non-conforming part model 258 may be a visual language model such as Flamingo by Google (registered trademark).

[0050] Specifically, the control unit 21 of the server device 20 generates a prompt requesting the user to identify non-compliant areas in the received drawing data based on the current Building Standards Act, and inputs the prompt into the non-compliant area model 258 together with the received drawing data.

[0051] FIG. 6 is an explanatory diagram conceptually showing the generation of a prompt. For example, the control unit 21 generates a first prompt saying, "Please answer whether there are any non-compliant parts in the attached drawing data that do not comply with the regulations based on the current Building Standards Act below." At this time, such a prompt includes a regulation-specific item that specifies the current Building Standards Act, as shown in Fig. 6. Specifically, the regulation-specific item is link information to the current Building Standards Act (Reiwa☆ revised Building Standards Act) in the regulations DB 251.

[0052] When the prompt is input, the non-compliant part model 258 acquires the current building code from the regulation DB 251 based on the regulation-specific items in the prompt. The non-compliant part model 258 identifies the non-compliant part in the input drawing data based on the prompt and the acquired current building code.

[0053] The non-conforming area model 258 recognizes the drawing symbols, directional symbols, dimensions, etc. in the drawing data, thereby recognizing the architectural components and the sizes of the architectural components, identifies the non-conforming areas under the current Building Standards Act, and outputs non-conforming area information in text format.

[0054] For example, the non-compliant part model 258 outputs non-compliant specific information in text format for the input drawing data, such as "The building coverage ratio of a two-story house in a quasi-urban planning area is 30%, which exceeds the current regulations" (first non-compliant specific information), "The size of the window in the south-facing room is 1.5 square meters, which is less than the current regulations" (second non-compliant specific information). Such non-compliant specific information includes the reason why the part is judged to be non-compliant in addition to identifying the non-compliant part.

[0055] In the above, the non-compliant part model 258 outputs non-compliance specific information based on the current Building Standards Act, but the present invention is not limited to this. The user may select a standard law or enforcement date for the output of the non-compliant part, and the non-compliant part model 258 may output non-compliance specific information using the selected law or enforcement date.

[0056] FIG. 7 is a flowchart illustrating the process of the second function of outputting compatibility information for drawing data from a user. For the sake of convenience, in the following explanation, it is assumed that the nonconformity area model 258 is a GPT language model, and that, as the nonconformity identification information, text data of the first nonconformity identification information or the second nonconformity identification information is output for the input drawing data, as described above.

[0057] The input unit 14 of the conformity determination device 10 accepts input of drawing data and enforcement time information from a user (step S301). The drawing data may be electronic data or scanned data of the drawing. The enforcement time information is information for identifying the Building Standards Act used when executing the second function, and may be, for example, the construction date of the building related to the drawing data obtained from the user. The user inputs the enforcement time information (text data) via the input unit 14.

[0058] In this embodiment, as described above, the case where the execution time information is input in text form is taken as an example, but is not limited to this. For example, instead of inputting the execution time information, the text data of the execution time information may be obtained from the drawing data using OCR (Optical Character Recognition).

[0059] When the input unit 14 accepts input of drawing data and implementation time information from a user, the communication unit 15 transmits the accepted drawing data and implementation time information to the server device 20 via the network N (step S302), and the communication unit 23 of the server device 20 receives the drawing data and implementation time information (step S401).

[0060] The subsequent processing in steps S402 to S403 in FIG. 7 is the same as the processing in steps S202 to S203 in FIG. 4, and detailed description thereof will be omitted.

[0061] When non-conformity identification information is acquired, the control unit 21 of the server device 20 generates a prompt including regulation specific information that identifies the Building Standards Act to be used to output the acquired non-conformity identification information and the conformity information related to the second function (step S404).

[0062] The control unit 21 generates a regulation-specific item based on the enforcement time information from the user. For example, when the enforcement time information is the construction date of a building related to the drawing data acquired from the user, the control unit 21 generates a prompt including a regulation-specific item that identifies the building standards law in force at the time of the construction date of the building.

[0063] FIG. 8 is an explanatory diagram conceptually showing the generation of a prompt. For example, the control unit 21 generates a first prompt for the first non-conformity specific information (FIG. 8A) saying, "The building coverage ratio of a two-story house in a quasi-urban planning area is 30%, which exceeds the current regulations. Please refer to the historical article data below and answer whether it conforms or not." At this time, the first prompt includes a regulation specific item that specifies the past Building Standards Act, as shown in FIG. 8A. Specifically, the regulation specific item is link information to the past Building Standards Act (the Building Standards Act revised in 2008) in the regulations DB 251. Furthermore, the control unit 21 generates a second prompt for the second non-conformity specific information (FIG. 8B) saying, "The size of the window in the south-facing room is 1.5 square meters, which is less than the current regulation. Please refer to the historical article data below and reply whether it conforms or not." At this time, the second prompt includes a regulation specific item that specifies the past Building Standards Act, as shown in FIG. 8B.

[0064] Control unit 21 inputs the generated first prompt or second prompt to language model 252 (step S405).

[0065] The language model 252 to which the first or second prompt has been input acquires past building standards laws to be used for outputting conformity information from the regulations DB 251 based on the regulation specific items in the first or second prompt. The language model 252 outputs conformity information based on the first or second prompt and the acquired past building standards laws. As a result, the control unit 21 acquires the conformity information (step S406).

[0066] For example, when a first prompt is input, the language model 252 outputs the first conformity information, such as, "The building coverage ratio of a two-story house in a quasi-urban planning area being 30% exceeds the current regulations and is non-compliant with the Building Standards Act revised in 2008. Basis provision: Building Standards Act revised in 2008, Article N, Clause M...."

[0067] For example, when a second prompt is input, language model 252 outputs the second conformity information, such as, "The size of the window in the south-facing room is 1.5 square meters, which is below the current regulations but complies with the revised Building Standards Act of 2017 △. Basis article: Article Z of the revised Building Standards Act of 2017 △."

[0068] As described above, when the control unit 21 acquires the compatibility information, the communication unit 23 transmits the acquired compatibility information to the compatibility determination device 10 via the network N (step S407). The communication unit 15 of the compatibility determination device 10 receives the compatibility information from the server device 20 (step S303).

[0069] When the compatibility information is received from the server device 20, the output unit 13 of the compatibility determination device 10 displays the received compatibility information on the display unit 17 or outputs it by printing it on a paper medium (step S304).

[0070] In this embodiment, as described above, the user can obtain non-conformity specific information for the drawing data (first function) simply by inputting drawing data into the conformity determination device 10, and can obtain conformity information including the basis clause for the drawing data (second function) simply by inputting drawing data and execution time information into the conformity determination device 10. Therefore, the conformity of a building can be confirmed accurately and easily.

[0071] In the above, the server device 20 is described as having the regulations DB 251, the language model 252, and the language model 252 as an example, but is not limited to this. The conformity determination device 10 may be configured to have the regulations DB 251, the language model 252, and the language model 252.

[0072] In the above, an example has been described in which the language model 252 refers to past building standards laws through prompts, but the present invention is not limited to this. The language model 252 may learn in advance, for example, a plurality of building standards laws that were enacted at different times. The control unit 21 may fine-tune the language model 252 by using a training data set that includes non-conformity specification information and conformity information. The language model 252 may be provided in an external server (not shown).

[0073] In the above, the case where the language model 252 acquires a past building standard law from the regulations DB 251 based on the regulation specific matters included in the prompt has been described as an example, but the present invention is not limited to this. The control unit 21 may be configured to acquire the past building standard law related to the prompt from the regulations DB 251 together with the prompt, and input the same to the language model 252.

[0074] In the above, an example has been given of a case where, when non-compliance identification information is output from the non-compliance area model 258, the control unit 21 creates a prompt based on the output non-compliance identification information and legal specific matters based on enforcement information from the user, but this is not limited to this.

[0075] For example, when non-conformity identification information is output from the non-conformity part model 258, the control unit 21 of the server device 20 uses the non-conformity identification information as a key to collect information related to the non-conformity identification information. For example, the control unit 21 searches Q&A information stored in the device itself to collect information related to the non-conformity identification information, and also crawls through the network N to collect information related to the non-conformity identification information from a website. The control unit 21 may be configured to input the information related to the non-conformity identification information collected in this manner, together with the non-conformity identification information and a prompt including execution time information from the user, into the language model 252, thereby acquiring conformity information.

[0076] In the above, a case has been described in which drawing data is input by the user via the compatibility determination device 10, and a prompt is generated using the nonconformity identification information output by the nonconformity part model 258, but the present invention is not limited to this. A configuration may also be adopted in which the user directly inputs information equivalent to the nonconformity identification information via the input unit 14 of the compatibility determination device 10, and the control unit 21 of the server device 20 creates a prompt using the input information.

[0077] Furthermore, in the above description, an example has been given in which the output of the nonconformity identification information related to the first function is performed by the nonconformity part model 258, and the output of the compatibility information related to the second function is performed by the language model 252 using the nonconformity identification information output by the nonconformity part model 258, but the present invention is not limited to this. The language model 252 may be configured to be able to execute both the output of the nonconformity identification information related to the first function and the output of the compatibility information related to the second function.

[0078] In the above, the compatibility determination device 10 and the server device 20 are provided separately, but the present invention is not limited to this. The compatibility determination device 10 and the server device 20 may be integrated.

[0079] (Modification) In the above, an example has been described in which the non-conformity specific information relating to the first function is output in text format or image format (marking on a drawing), but the present invention is not limited to this.

[0080] FIG. 9 is an illustrative diagram showing an example of the non-conformity specification information displayed on the display unit 17 of the conformity determination device 10. As shown in FIG. 9, in the drawing data input by the user, the nonconformity identification information in which a mark M is added to a nonconformity part that does not comply with the current Building Standards Act by the nonconformity part model 258 is displayed on the display unit 17. At this time, the mark M is provided to be selectable. When any mark M is selected by the user, the nonconformity identification information in text format related to the selected mark M is displayed on the display unit 17.

[0081] For example, when a user selects any of the marks M on the drawing displayed on the display unit 17 by appropriately operating the mouse (input unit 14), the control unit 11 accepts this as an instruction to display the non-conformity specific information of the mark M in text format, and the output unit 13 pops up the non-conformity specific information in text format on the display unit 17 as shown in Figure 9.

[0082] (Embodiment 2) The conformity judgment device 10 of the second embodiment is, for example, a personal computer, which identifies non-compliant parts of the drawing data that do not comply with current regulations, and outputs a report (second report) to the user based on the identified non-compliant parts (non-conformity identification information).

[0083] The compatibility determination device 10 according to the second embodiment, like the first embodiment, includes a control unit 11, a storage unit 12, an output unit 13, an input unit 14, a communication unit 15, a reading unit 16, and a display unit 17. These components have already been described, and detailed description thereof will be omitted.

[0084] The server device 20 according to the second embodiment includes, as in the first embodiment, a control unit 21, a storage unit 22, a communication unit 23, a reading unit 24, and a large-capacity storage unit 25, and the large-capacity storage unit 25 stores a regulations DB 251, a non-conforming part model 258, a language model 252, and training data 259 (see FIG. 3). These components have already been described, and detailed description thereof will be omitted.

[0085] FIG. 10 is a flowchart for explaining a process for outputting a report on non-conformances in drawing data from a user.

[0086] The input unit 14 of the compatibility determination device 10 receives input of drawing data from a user (step S501). Such drawing data may be electronic data or scanned data of the drawing.

[0087] When the input unit 14 accepts input of drawing data from a user, the communication unit 15 transmits the accepted drawing data to the server device 20 via the network N (step S502), and the communication unit 23 of the server device 20 receives the drawing data (step S601).

[0088] The subsequent processing in steps S602 to S603 in FIG. 10 is the same as the processing in steps S202 to S203 in FIG. 4, and detailed description thereof will be omitted.

[0089] Also, in step S603, the following non-compliance specific information is acquired: "The building coverage ratio of a two-story house in a quasi-urban planning area is 30%, which exceeds the current regulations" (first non-compliance specific information), and "The size of the window in room 1 of the house is 1.5 square meters, which is below the current regulations" (second non-compliance specific information).

[0090] When the nonconformity specifying information is acquired, the control unit 21 of the server device 20 generates a prompt for creating a report including the acquired first and second nonconformity specifying information (step S604).

[0091] FIG. 11 is an explanatory diagram conceptually showing the generation of a prompt for creating a report. For example, the control unit 21 generates a prompt saying, "Please create a report citing the provisions of the current Building Standards Act that the building related to the attached drawing is incompatible with the current Building Standards Act in that the building coverage ratio of a two-story house in a quasi-urban planning area is 30% and the size of the window in the house is 1.5 square meters." At this time, the prompt includes a regulation-specific item (link information, etc.) that specifies the current Building Standards Act in the regulations DB251.

[0092] The control unit 21 inputs the generated prompt to the language model 252 together with the drawing data from the user (step S605).

[0093] The language model 252 to which the prompt is input acquires the current building code from the laws and regulations DB 251 based on the law-specific items in the prompt. The language model 252 generates a report based on the prompt and the acquired current building code. As a result, the control unit 21 acquires the report (step S606).

[0094] FIG. 12 is an explanatory diagram conceptually illustrating a report output by the language model 252. As shown in FIG. For example, a report output from language model 252 displays target drawings based on drawing data from a user, and for each non-compliant part in the target drawing, the reason for the non-compliance and the underlying provision of the current Building Standards Act are displayed.

[0095] As described above, when the control unit 21 acquires a report, the communication unit 23 transmits the acquired report to the compatibility judgment device 10 via the network N (step S607), and the communication unit 15 of the compatibility judgment device 10 receives the report (step S503).

[0096] When the report is received from the server device 20, the output unit 13 of the conformity determining device 10 displays the received report on the display unit 17 or outputs it by printing it on a paper medium (step S504).

[0097] Furthermore, the conformity determination device 10 according to the second embodiment can accept a user's instruction to edit the report displayed on the display unit 17. That is, when the report is displayed on the display unit 17, the user can use the input unit 14 to make corrections to the displayed report. FIG. 13 is a flowchart illustrating a report editing process according to the second embodiment.

[0098] When the report is displayed on the display unit 17 by the output unit 13 (step S701), the user uses the input unit 14 to make corrections to the displayed report as necessary. At this time, the input unit 14 accepts editing information input by the user (step S702). Here, the editing information is, for example, additions and deletions accepted from the user regarding the displayed report. The communication unit 15 transmits the editing information accepted by the input unit 14 to the server device 20 (step S703).

[0099] In the server device 20, when the editing information is received from the compatibility determination device 10, the control unit 21 generates a prompt for re-creating a report reflecting the received editing information, and inputs the received editing information and the original report to the language model 252. The language model 252 re-generates and outputs the report based on the input editing information and the original report, and the control unit 21 acquires the re-generated report (hereinafter referred to as the re-generated report).

[0100] Next, the communication unit 23 transmits the regenerated report (text data) to the conformity determination device 10 via the network N, and the communication unit 15 of the conformity determination device 10 receives the regenerated report (step S704).

[0101] When the regenerated report is received from the server device 20, the output unit 13 of the conformity determining device 10 displays the received regenerated report on the display unit 17 or outputs it by printing it on a paper medium (step S705).

[0102] In this embodiment, as described above, a user can obtain a report including non-conforming parts (non-conforming specific information) and grounds for the drawings by simply inputting the drawing data into the conformity determination device 10. Therefore, the conformity of a building can be confirmed accurately and simply.

[0103] The same parts as those in the first embodiment are given the same reference numerals and detailed explanations are omitted.

[0104] (Embodiment 3) The conformity determination device 10 according to the third embodiment is, for example, a personal computer, which outputs conformity information for drawing data from a user and outputs a report (first report) including the conformity information.

[0105] The compatibility determination device 10 according to the third embodiment includes a control unit 11, a storage unit 12, an output unit 13, an input unit 14, a communication unit 15, a reading unit 16, and a display unit 17, as in the second embodiment (see FIG. 10). These components have already been described, and detailed description thereof will be omitted.

[0106] Also, like in the first embodiment, the server device 20 of the third embodiment includes a control unit 21, a memory unit 22, a communication unit 23, a reading unit 24 and a large-capacity memory unit 25, and the large-capacity memory unit 25 stores a regulations DB 251, a non-compliance part model 258, a language model 252 and training data 259 (see FIG. 3).

[0107] In the third embodiment, as described above, the language model 252 generates a report including conformance information related to the drawing data acquired via the conformance determination device 10. The language model 252 generates the report based on the conformance information, the current Building Standards Act, and the Building Standards Act corresponding to the enforcement information from the user.

[0108] FIG. 14 is a flowchart illustrating a process for outputting a report including compatibility information for drawing data from a user.

[0109] The input unit 14 of the compatibility determination device 10 receives input of drawing data and construction time information from a user (step S801). Such drawing data is electronic data or scanned data of a drawing, and the construction time information is, for example, the construction date of a building related to the drawing data acquired from the user. In addition, the user inputs the construction time information (text data) via the input unit 14.

[0110] When the input unit 14 accepts input of drawing data and implementation time information from a user, the communication unit 15 transmits the accepted drawing data and implementation time information to the server device 20 via the network N (step S802), and the communication unit 23 of the server device 20 receives the drawing data and implementation time information (step S901).

[0111] The subsequent processes up to obtaining the compatibility information in FIG. 14 (steps S902 to S906) are the same as the processes in steps S402 to S406 in FIG. 7, and therefore a detailed description thereof will be omitted.

[0112] Also, in step S906, it is assumed that the conformity information obtained is, "The building coverage ratio of a two-story house in a quasi-urban planning area is 30%, which exceeds the current regulations, but is in conformity with the revised Building Standards Act of 20XX. Basis provision: Revised Building Standards Act of 20XX, Article N, Clause M...".

[0113] In this way, when the compatibility information is acquired, the control unit 21 of the server device 20 generates a prompt for creating a report including the acquired compatibility information (step S907).

[0114] FIG. 15 is an explanatory diagram conceptually showing the generation of a prompt for creating a report. For example, the control unit 21 generates a prompt saying, "Please create a report stating that the building related to the attached drawing is non-compliant with the current Building Standards Act because the building coverage ratio of a two-story house in a quasi-urban planning area is 30%, but is compliant with the Building Standards Act revised in 2008, citing the provisions of the current Building Standards Act and the Building Standards Act revised in 2008." At this time, the prompt includes information such as a link to the legal regulations DB 251, which specifies the current Building Standards Act and the Building Standards Act corresponding to the enforcement information from the user.

[0115] Control unit 21 inputs the generated prompt to language model 252 together with the drawing data from the user (step S908). The language model 252 to which the prompt is input acquires the current Building Standards Act and the Building Standards Act corresponding to the enforcement information, i.e., the above-mentioned Building Standards Act revised in 2008, from the laws and regulations DB 251 based on the law-specific items in the prompt. The language model 252 generates a report based on the prompt and the acquired current Building Standards Act and Building Standards Act revised in 2008. As a result, the control unit 21 acquires the report (step S909).

[0116] FIG. 16 is an explanatory diagram conceptually illustrating a report output by the language model 252. As shown in FIG. For example, the report output from language model 252 displays a target drawing based on drawing data provided by a user, and indicates that the building related to the drawing data is non-compliant under the current Building Standards Act (Reiwa★ revised Building Standards Act), but is compliant under the Heisei XX revised Building Standards Act, along with the supporting provisions of the current Building Standards Act and the Heisei XX revised Building Standards Act.

[0117] As described above, when the control unit 21 acquires a report, the communication unit 23 transmits the acquired report to the compatibility judgment device 10 via the network N (step S910), and the communication unit 15 of the compatibility judgment device 10 receives the report (step S803).

[0118] When the report is received from the server device 20, the output unit 13 of the conformity determining device 10 displays the received report on the display unit 17 or outputs it by printing it on a paper medium (step S804).

[0119] In this embodiment, as described above, a user can obtain a report including conformity information and basis clauses related to the drawing data by simply inputting the drawing data and construction time information into the conformity determination device 10. Therefore, the conformity of a building can be confirmed accurately and simply.

[0120] The invention according to the third embodiment is not limited to the above description. The third embodiment may also be configured to allow the user to edit the report, as in the second embodiment. That is, when a report including compatibility information is displayed on the display unit 17, the input unit 14 may receive editing information from the user via the input unit 14, and the language model 252 of the server device 20 may regenerate the report reflecting the editing information.

[0121] In the above, the case where the report contains only the conformance information acquired in step S906 in Fig. 14 has been described as an example, but the present invention is not limited to this. In addition to the conformance information, the nonconformity specification information acquired in step S903 (see Fig. 12) may be included.

[0122] The same parts as those in the first embodiment are given the same reference numerals and detailed explanations are omitted.

[0123] (Embodiment 4) The conformity judgment device 10 of the fourth embodiment is, for example, a personal computer, and outputs future scenarios, such as what would happen if non-conforming parts of the building related to the drawing data from the user were left unattended or if corrective measures were taken, for example.

[0124] The compatibility determination device 10 according to the fourth embodiment includes a control unit 11, a storage unit 12, an output unit 13, an input unit 14, a communication unit 15, a reading unit 16, and a display unit 17, similar to the first embodiment (see FIG. 2). These components have already been described, and detailed description thereof will be omitted.

[0125] Also, like in the first embodiment, the server device 20 of the fourth embodiment includes a control unit 21, a memory unit 22, a communication unit 23, a reading unit 24 and a large-capacity memory unit 25, and the large-capacity memory unit 25 stores a regulations DB 251, a non-compliance part model 258, a language model 252 and training data 259 (see FIG. 3).

[0126] In the fourth embodiment, as described above, the language model 252 generates a scenario in the case where non-compliant parts of a building related to the drawing data acquired via the conformity determination device 10 are left as they are, or where countermeasures are taken. The language model 252 generates the scenario based on the conformity information, the current Building Standards Act, and the Building Standards Act corresponding to the enforcement information from the user, from the intent and opposing interpretation of such laws and regulations.

[0127] For the sake of convenience, the following description will be given by taking as an example a case in which the language model 252 generates a scenario in which non-compliant parts of a building are left unattended in relation to drawing data received from a user.

[0128] FIG. 17 is a flowchart illustrating a process for outputting a future scenario of a building related to drawing data, based on suitability information for the drawing data from a user.

[0129] The input unit 14 of the compatibility determination device 10 accepts input of drawing data and implementation time information from a user (step S1001). The user inputs the implementation time information (text data) via the input unit 14.

[0130] When the input unit 14 accepts input of drawing data and implementation time information from a user, the communication unit 15 transmits the accepted drawing data and implementation time information to the server device 20 via the network N (step S1002), and the communication unit 23 of the server device 20 receives the drawing data and implementation time information (step S1101).

[0131] The subsequent processes up to obtaining the compatibility information in FIG. 17 (steps S1102 to S1106) are the same as the processes in steps S402 to S406 in FIG. 7, and therefore a detailed description thereof will be omitted.

[0132] Hereinafter, in step S1106, it is assumed that the first conformity information is obtained, which states, "The building coverage ratio of a two-story house in a quasi-urban planning area being 30% exceeds the current regulations and is non-compliant under the Building Standards Act revised in 20XX. Basis provision: Building Standards Act revised in 20XX, Article N, Clause M...", or the second conformity information is obtained, which states, "The size of the windows in the rooms of the house being 1.5 square meters is below the current regulations but is compliant under the Building Standards Act revised in 20XX. Basis provision: Building Standards Act revised in 20XX, Article Z...".

[0133] When the first and second compatibility information are acquired, the control unit 21 of the server device 20 generates a prompt for future scenario creation for the building related to the drawing data from the user based on the acquired first and second compatibility information (step S1107).

[0134] FIG. 18 is an explanatory diagram conceptually showing the generation of a prompt for creating a scenario. For example, the control unit 21 generates a prompt for the first compliance information as shown in FIG. 18A , stating, "In terms of the building, the building coverage ratio of a two-story house in a quasi-urban planning area is 30%, which exceeds the current regulations and is also non-compliant under the revised regulations of 2008. In light of the current Building Standards Act and the revised Building Standards Act of 2008, please create a future scenario regarding legal risks based on the intent of the Building Standards Act and its opposite interpretation." In addition, for example, the control unit 21 generates a prompt for the second compliance information as shown in FIG. 18B , stating, "In a building, the size of a window in a room in a house is 1.5 square meters, which is below the current regulations but complies with the revised regulations of 2018 △. In light of the current Building Standards Act and the revised Building Standards Act of 2018 △, please create a future scenario regarding safety risks based on the intent and opposite interpretation of the Building Standards Act." At this time, the prompt includes a regulation specification item (such as link information) that specifies the current building standard law in the regulation DB 251 and the building standard law corresponding to the enforcement time information from the user.

[0135] That is, the prompts for scenario creation include the textual interpretation and logical interpretation of the law as guidelines for scenario creation. Textual interpretation is a method of interpretation that faithfully grasps the words and sentences of the provisions, and logical interpretation is a method of interpretation that not only interprets the law grammatically but also places importance on the history, meaning, and purpose of the enactment of the law. Logical interpretation includes opposite interpretation, analogical interpretation, obvious interpretation, narrow interpretation, broad interpretation, and modified interpretation. Although the opposite interpretation has been described above as an example of logical interpretation, it is not limited to this, and any of opposite interpretation, analogical interpretation, obvious interpretation, narrow interpretation, broad interpretation, and modified interpretation may be included, or all of them may be included.

[0136] In addition, an adverse interpretation is an interpretation method that applies only to what is written in the law and does not apply to what is not written in the law, even if it is similar. In addition, an analogical interpretation is an interpretation method that applies the law that stipulates similar matters to matters not written in the law. In addition, of course interpretation is an interpretation method that considers the history, meaning, and purpose of the enactment of the law and naturally applies it in the same way as similar matters, even if it is not written in the law. In addition, a narrow interpretation is an interpretation method that interprets the meaning narrower than the normal meaning when it is not appropriate to apply the broad wording as it is, considering the history, meaning, and purpose of the enactment of the law. In addition, an expansive interpretation is an interpretation method that interprets the meaning broader than the normal meaning when it is not appropriate to apply the narrow wording as it is, considering the history, meaning, and purpose of the enactment of the law. And a modified interpretation is an interpretation method that changes the wording when the wording of the law is incorrect and the wording used is contrary to the inherent principle.

[0137] Control unit 21 inputs the generated prompt to language model 252 (step S1108). The language model 252 to which the prompt is input acquires the current Building Standards Act and the Building Standards Act corresponding to the enforcement information, i.e., the Building Standards Act revised in 2008, from the laws and regulations DB 251 based on the law-specific items in the prompt, and generates a scenario based on the intent and opposite interpretation of the acquired current Building Standards Act and the Building Standards Act revised in 2008. In this way, the control unit 21 acquires the scenario (step S1109).

[0138] As described above, the language model 252 outputs a scenario when a non-compliant part in a building related to drawing data from a user is left unattended based on a prompt (compliance information). Such a scenario includes, for example, a legal risk scenario or a safety risk scenario. For example, a legal risk scenario indicates the penalties and the degree of trust that will be lost due to leaving a non-compliant part unattended, and a safety risk scenario indicates the degree to which safety will be threatened due to leaving the non-compliant part unattended or incompletely addressed.

[0139] FIG. 19 is an explanatory diagram conceptually illustrating a scenario output by the language model 252. As shown in FIG. For example, a scenario output from language model 252 corresponding to the first consistency information indicates a legal risk scenario for the building related to the input drawing data, and a scenario output from language model 252 corresponding to the second consistency information also indicates a safety risk scenario for the building related to the input drawing data.

[0140] As a specific example, for example, a scenario output from the language model 252 corresponding to the first consistency information shows a legal risk scenario of "There is a risk of being fined up to 1 million yen or imprisoned for up to △ years" based on the penalty provisions in the provisions of the relevant law, as shown in Fig. 19A. Also, a scenario output from the language model 252 corresponding to the second consistency information shows a safety risk scenario of "There is a possibility of hindering evacuation in the event of a fire" based on the intent and opposite interpretation of the law, as shown in Fig. 19B.

[0141] As described above, when the control unit 21 acquires a scenario, the communication unit 23 transmits the acquired scenario to the compatibility judgment device 10 via the network N (step S1110), and the communication unit 15 of the compatibility judgment device 10 receives the scenario (step S1003).

[0142] When the scenario is received from the server device 20, the output unit 13 of the compatibility determination device 10 displays the received scenario on the display unit 17 or outputs it by printing it on a paper medium (step S1004).

[0143] In this embodiment, as described above, the user can obtain a future scenario in the case where a non-compliant part of a building related to the drawing data is left unattended, simply by inputting drawing data and construction time information into the conformity determination device 10. Therefore, when a non-compliant part exists in a building, the user can quickly consider how to deal with it.

[0144] In the above, an example has been described in which a safety risk scenario is presented based on the intent of the regulation and its opposite interpretation, but the present invention is not limited to this. For example, a database of past accidents and incidents may be provided in the server device 20, and the safety risk scenario may be presented by referring to past accidents and incidents in addition to the opposite interpretation of the intent of the regulation.

[0145] Also, instead of using a DB for accidents and incidents, the server device 20 may be configured to crawl and collect information on accidents and incidents from websites.

[0146] The same parts as those in the first embodiment are given the same reference numerals and detailed explanations are omitted.

[0147] (Embodiment 5) As in the fourth embodiment, the conformity determination device 10 according to the fifth embodiment acquires drawing data from a user and transmits it to the server device 20, the server device 20 identifies non-conforming parts in the transmitted drawing data, outputs the cost (estimate) of taking measures to make the non-conforming parts conforming, and transmits information representing the estimate to the conformity determination device 10. The conformity determination device 10 outputs the transmitted estimate information.

[0148] The compatibility determination device 10 according to the fifth embodiment includes a control unit 11, a storage unit 12, an output unit 13, an input unit 14, a communication unit 15, a reading unit 16, and a display unit 17, similar to the first embodiment (see FIG. 2). These components have already been described, and detailed description thereof will be omitted.

[0149] FIG. 20 is a functional block diagram showing an example of the configuration of the server device 20 according to the fifth embodiment. The server device 20 of embodiment 5, like embodiment 1, is equipped with a control unit 21, a memory unit 22, a communication unit 23, a reading unit 24 and a large-capacity memory unit 25, and the large-capacity memory unit 25 stores a regulations DB 251, a non-compliant part model 258, a language model 252 and training data 259.

[0150] In the fifth embodiment, the language model 252 identifies the building materials, size, etc. of the parts to be repaired (non-conforming parts) based on the non-conformity identification information that identifies the non-conforming parts in the drawing data sent from the conformity judgment device 10, and outputs an estimate of the cost (repair cost) of carrying out repairs, which are countermeasures to make such non-conforming parts conform. That is, when the language model 252 receives the non-conformity identification information and the average unit price information of the building materials, it outputs an estimate of the repair cost.

[0151] Furthermore, the mass storage unit 25 of the server device 20 according to the fifth embodiment stores a construction material unit price DB260. The construction material unit price DB260 stores average unit price information of construction materials. Specifically, the construction material unit price DB260 stores the unit price of each of the building materials used in the architectural components that make up a building, such as roofs, exterior walls, interior walls, fittings (windows, doors, etc.), floors, and finishing materials. For example, the construction material unit price DB260 stores the average unit price by material, size, or grade for each construction material. In addition, the construction material unit price DB260 stores average labor cost information for each type of repair work, such as painting, floor replacement, etc.

[0152] FIG. 21 is a flowchart for explaining an example in which the server device 20 outputs an estimate of repair costs when non-conforming parts in drawing data from a user are repaired to make them conforming.

[0153] The process of steps S1201 to S1202 in which the conformity determination device 10 accepts drawing data from a user and transmits it to the server device 20 is the same as the process of steps S101 to S102 in Fig. 4 of the first embodiment, and detailed explanations will be omitted. Also, the process of steps S1301 to S1303 in which the server device 20 receives drawing data and acquires nonconformity identification information is the same as the process of steps S201 to S203 in Fig. 4 of the first embodiment, and detailed explanations will be omitted.

[0154] In the following, it is assumed that in step S1303, the non-compliance part model 258 outputs non-compliance identification information indicating that "the size of the window in the room of the house is 1.5 square meters, which is less than the current regulations."

[0155] In this manner, when nonconformity identification information is acquired, the control unit 21 of the server device 20 generates a prompt for creating an estimate of the cost of repairs to bring the nonconformity parts related to the acquired nonconformity identification information into conformity (step S1304).

[0156] FIG. 22 is an explanatory diagram conceptually illustrating the generation of a prompt for creating a quote. For example, the control unit 21 generates a prompt saying, "In the attached drawing, the size of the window in the room of the house is 1.5 square meters, which is not compliant with the current Building Standards Act. Please calculate the estimate of the cost of repairing the window size so that it conforms to the current Building Standards Act, by referring to the average unit price information of building materials and average labor cost information below." At this time, the prompt includes link information of the regulations DB251 to the current Building Standards Act, and link information of the average unit price information of building materials and average labor cost information of the building material unit price DB260.

[0157] The control unit 21 inputs the generated prompt and the drawing data from the user to the language model 252 (step S1305). The language model 252, to which the prompt and drawing data have been input, retrieves the current building code law from the regulations DB 251, retrieves average unit price information for building materials and average labor cost information from the building material unit price DB 260, and generates an estimate based on the drawing data, the current building code law, and the average unit price information for building materials and average labor cost information.

[0158] For example, the language model 252 identifies the object of repair based on the nonconformity identification information, identifies the building components corresponding to the object of repair by recognizing the drawing symbols, dimensions, etc. in the drawing data, identifies the building materials and sizes required for the repair, etc., and outputs an estimate of the repair cost by referring to the average unit price information of the building materials and the average labor cost information. In this way, the control unit 21 obtains the estimate (step S1306).

[0159] In this embodiment, the "window" is determined to be the target of repair based on the non-conformity specifications, and the language model 252 identifies the window corresponding to the target of repair by recognizing drawing symbols, dimensions, etc. in the drawing data, and also identifies the building materials and size, etc. required for the repair. It obtains the size of the window required for repair based on the current Building Standards Act, and outputs an estimate of the repair costs by referring to the average unit price information of the building materials and average labor cost information.

[0160] FIG. 23 is an explanatory diagram conceptually illustrating an estimate output by the language model 252. As shown in FIG. For example, the estimate output from language model 252 shows details of the building related to the input drawing data, including the repair targets (non-conforming areas), dimensions, materials, unit prices, etc. of the repair targets, and a total based on such details.

[0161] As described above, when the control unit 21 obtains an estimate, the communication unit 23 transmits the obtained estimate to the compatibility judgment device 10 via the network N (step S1307), and the communication unit 15 of the compatibility judgment device 10 receives the estimate (step S1203).

[0162] When the estimate is received from the server device 20, the output unit 13 of the suitability determination device 10 displays the received estimate on the display unit 17 or outputs it by printing it on a paper medium (step S1204).

[0163] In this embodiment, as described above, the user can obtain an estimate of the cost (repair cost) of repairing non-compliant parts in the drawing data to make them conforming simply by inputting the drawing data into the conformity determination device 10. This makes it easier for the user to consider how to deal with the presence of non-compliant parts in a building.

[0164] The same parts as those in the first embodiment are given the same reference numerals and detailed explanations are omitted.

[0165] The technical features (constituent elements) described in the first to fifth embodiments can be combined with each other, and by combining them, new technical features can be arrived at. The embodiments disclosed herein are illustrative in all respects and should not be considered as limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the scope and meaning equivalent to the claims.

[0166] The matters described in each embodiment can be combined with each other. In addition, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations regardless of the citation format. Furthermore, the claims use a format in which a claim cites two or more other claims (multiple claim format), but this is not limited to this. The claims may also be written in a format in which a multiple claim cites at least one other multiple claim (multi-multi claim). [Explanation of symbols]

[0167] 10 Compatibility Determination Device 11 Control section 13 Output section 17 Display section 20 Server device (information processing device) 21 Control section 25 Mass storage 251 Law DB 252 Language Model (First Model) 258 Non-conforming part model (2nd model) 259 training data 260 Building material unit price DB N Network P,P2 control program

Claims

1. Obtain non-compliance specific information that identifies non-compliant areas of buildings that do not comply with regulations, Based on the acquired non-conformity specific information and a first model using a plurality of building-related laws and regulations with different enforcement dates, outputting conformity information regarding the conformity of the building at a predetermined enforcement date. A computer program that causes a computer to carry out processing.

2. the first model is a language generation model; obtaining a prompt including the non-conformance specific information; The first model outputs the compliance information based on a database storing the plurality of building codes and a prompt obtained.

2. The computer program product of claim 1.

3. Generate a first report based on the outputted conformance information 2. The computer program product of claim 1.

4. Output a scenario in which the non-conformity is left unchecked 2. The computer program product of claim 1.

5. Output the costs associated with the measures taken to address the non-conformance 2. The computer program product of claim 1.

6. Acquire architectural drawing data, The acquired building drawing data is input to a second model that has been trained to output the non-conformity specific information when the building drawing data is input, and the non-conformity specific information is output.

2. The computer program product of claim 1.

7. Generate a second report based on the output non-conformity identification information 7. A computer program according to claim 6.

8. Based on the output non-conformity identification information, non-conformity areas are marked on the building drawings related to the acquired building drawing data.

7. A computer program according to claim 6.

9. By selecting a mark, information about the non-conformance corresponding to the mark is output.

9. A computer program according to claim 8.

10. Storing newly enacted building regulations in the database 3. A computer program according to claim 2.

11. A control unit is provided, The control unit: Obtain non-compliance specific information that identifies non-compliant areas in buildings that do not comply with regulations, Based on the acquired non-conformity specific information and a first model using a plurality of building-related laws and regulations with different enforcement dates, outputting conformity information regarding the conformity of the building at a predetermined enforcement date. Information processing device.

12. Obtain non-compliance specific information that identifies non-compliant areas in buildings that do not comply with regulations, Based on the acquired non-conformity specific information and a first model using a plurality of building-related laws and regulations with different enforcement dates, outputting conformity information regarding the conformity of the building at a predetermined enforcement date. An information processing method in which processing is performed by a computer.

Images