Information processing device, information processing method, and computer program

Abstract

Based on house plans and information, the system automatically and accurately outputs house valuation-related data. [Solution] The information processing device includes: an evaluation base information acquisition unit that acquires evaluation base building drawings and evaluation base building information, evaluation base building components and evaluation base building equipment provided in the evaluation base building drawings; a boundary identification unit that compares grid lines along building modules based on building drawings and building information with evaluation base building information and identifies evaluation base building components and evaluation base building equipment that meet predetermined conditions as boundary lines constituting the building; a wall identification unit that identifies detailed information of walls based on boundary lines, evaluation base building drawings and evaluation base building information; a room identification unit that identifies detailed information of rooms based on boundary lines, evaluation base building drawings and evaluation base building information; and an output unit that outputs evaluation data necessary for house evaluation based on evaluation base building drawings and evaluation base building information, detailed information of rooms and detailed information of walls.

Description

Technical Field

[0001] The present invention relates to house evaluation, and particularly to an information processing apparatus, an information processing method, and a computer program for calculating data necessary for performing house evaluation calculations based on house drawings.

Background Art

[0002] The method for evaluating a house that serves as the basis for fixed asset tax is a method of evaluating based on the reconstruction price in accordance with the "Fixed Asset (House) Evaluation Standards".

[0003] The Fixed Asset (House) Evaluation Standards are notifications of the Minister of Internal Affairs and Communications based on the Local Tax Law for the purpose of achieving national uniformity in evaluation methods and enabling appropriate and balanced evaluations in each municipality. Specifically, it is a standard that defines the criteria for evaluating the prices, the methods for conducting evaluations, and the procedures for land, houses, and depreciable assets. The reconstruction price method is to obtain the construction cost (reconstruction cost evaluation score) required when constructing the same house as the object of evaluation at the same location at the time of evaluation, and to consider the depreciation (annual depreciation correction rate) due to the wear and tear caused by the passage of years after the construction of the house, and to obtain the value (evaluation amount) of the house. The annual depreciation correction rate represents the depreciation and the like due to the wear and tear caused by the passage of years after the construction of the house, and varies depending on the type and structure, with a lower limit of 0.2.

[0004] Next, the method for calculating the evaluation amount of a house is to attach a reconstruction cost evaluation score to each house, multiply it by the depreciation correction rate according to the annual (wear and tear) situation, and further multiply it by the value per evaluation point considering the price level, design management fees, etc. to obtain the evaluation amount of the target house.

[0005] The house survey assigns reconstruction cost points to each house using a calculation method based on the fixed asset valuation standards, such as by component (exterior finishes such as roofs and exterior walls, interior finishes such as floors, walls, and ceilings, and building equipment). Therefore, newly constructed and extended buildings are surveyed and evaluated individually. Specifically, surveyors visit the site and record the house layout and the type of finish for each room in a report, and then calculate the house valuation based on that. In the actual calculation process, the points assigned to each finish and the amount of that finish used are used to determine the points for each finish, which are then totaled for each component, and finally the reconstruction cost points for each component are summed up to determine the valuation for the entire building. This process of conducting house valuations is largely done manually and is extremely inefficient. Conventionally, as a house valuation calculation processing device that performs house valuation calculations by inputting a floor plan of a house, the inventions described in Patent Documents 1 and 2 below are known, for example.

[0006] The invention described in Patent Document 1 provides a scoring device and scoring method for calculating house evaluations that minimizes the repeated input of scoring items for each house and enables efficient data input by inputting scoring items and their additional conditions, house floor plan data, attribute data such as scoring items and quantities for each part of the house using a reading device, and inputting the area and scoring items of each room area for each room name.

[0007] The invention described in Patent Document 2 provides a house evaluation calculation score addition device and score addition method that minimizes the repeated input operation of house evaluation items for each house, and enables efficient data input, by selecting from multiple types of score pattern files that store different score items and additional conditions for each part of a house, such as finishing data. The invention described in Patent Document 3 provides a house evaluation calculation processing device that reads the score for each part of a house from a score correction pattern file, extracts the additional part from the floor plan data for each part, calculates the quantity necessary for evaluation calculation, stores the associated additional shape data, score, and quantity in a drawing data file, and when calculating the score from the drawing analysis results, reads the score correction for each part of the house again from the score correction pattern file, extracts the corresponding part from the calculation data, applies each correction, and performs score calculation.

[0008] On the other hand, in contrast to the inventions described in Patent Document 1 and Patent Document 2, the information processing device of the present invention reads scoring items for each part of a house, attribute data such as additional conditions and quantities, and house floor plan data from original drawings and current information such as building drawings and building information, and uses a machine learning model to calculate the area and scoring items of each room area for each room name. This eliminates the need to create scoring pattern files in advance and dramatically reduces the time and effort required for repeated scoring item input operations for each house. The functions of the present invention are significantly different from those of Patent Documents 1 and 2. Furthermore, the invention described in the patent document differs from the information processing device of the present invention in that it requires repeated input of scoring items for each part of a house and repeated correction input for each correction item for each scoring item for each part of a house, resulting in a heavy operational burden on the operator and failing to escape operations that lead to human error. [Prior art documents] [Patent Documents]

[0009] [Patent Document 1] Japanese Patent Application Publication No. 05-89142 [Patent Document 2] Patent No. 3177489 [Patent Document 3] Japanese Patent Publication No. 2011-081850 [Overview of the project] [Problems that the invention aims to solve]

[0010] Thus, while conventional house valuation methods allow for some degree of efficient data entry, they still lack an efficient method for handling the repeated data entry tasks for multiple houses.

[0011] This invention has been made in view of the above circumstances, and aims to provide a learning model, a method for generating a learning model, an information processing device, an information processing method, and a computer program that can automatically acquire data necessary for calculating house valuation with high accuracy from house floor plans, finishing schedules, etc., for evaluation items necessary for house valuation. [Means for solving the problem]

[0012] An information processing device according to one aspect of the present invention includes: a reading unit that reads a building drawing comprising at least one of building components and building equipment, and building information which is detailed information relating to the building components and building equipment; a processing unit that performs labeling and coloring on the building components and building equipment contained in the building drawing, and adds processing information to the building information; a training data acquisition unit that acquires as training data a processed building drawing comprising at least one of the processed building components and processed building equipment processed by the processing unit based on the building drawing and building information, and processed building information which is detailed information relating to the processed building components and processed building equipment; and when input data comprising a building drawing and building information is input, it outputs an evaluation base building drawing and evaluation base building information which are the same as the processed building drawing and processed building information, respectively, based on the training data, and further outputs an evaluation base building drawing which are the same as the processed building components and processed building equipment contained in the processed building drawing and evaluation base building equipment, respectively. The system includes: an evaluation base information acquisition unit that inputs building drawings and building information into a learning model that outputs evaluation base building equipment, and acquires evaluation base building drawings and evaluation base building information, as well as evaluation base building components and evaluation base building equipment provided in the evaluation base building drawings; a boundary identification unit that compares grid lines along building modules based on building drawings and building information with evaluation base building information and identifies evaluation base building components and evaluation base building equipment that meet predetermined conditions as boundary lines constituting the building; a wall identification unit that identifies detailed wall information, including wall type and wall size, based on boundary lines, evaluation base building drawings, and evaluation base building information; a room identification unit that identifies detailed room information, including room type and room size, based on boundary lines, evaluation base building drawings, and evaluation base building information; and an output unit that outputs evaluation data necessary for house evaluation based on evaluation building drawings and evaluation base building information, detailed room information acquired by the room identification unit, and detailed wall information acquired by the wall identification unit.

[0013] An information processing method according to one aspect of the present invention includes: a reading step of reading a building drawing comprising at least one of building components and building equipment, and building information which is detailed information relating to the building components and building equipment; a processing step of labeling and coloring the building components and building equipment contained in the building drawing, and adding information relating to the processing to the building information; a training data acquisition step of acquiring a processed building drawing comprising at least one of the processed building components and processed building equipment processed based on the building drawing and building information, and processed building information which is detailed information relating to the processed building components and processed building equipment, as training data; and when input data comprising a building drawing and building information is input, outputting an evaluation base building drawing and evaluation base building information which are identical to the processed building drawing and processed building information, respectively, based on the training data, and further outputting an evaluation base building drawing and evaluation base building information which are identical to the processed building components and processed building equipment contained in the processed building drawing and evaluation base The learning model that outputs basic building equipment includes: an evaluation basic information acquisition step in which building drawings and building information are input, and evaluation basic building drawings and evaluation basic building information, and evaluation basic building components and evaluation basic building equipment provided in the evaluation basic building drawings; a boundary identification step in which grid lines along building modules based on building drawings and building information are compared with evaluation basic building information, and evaluation basic building components and evaluation basic building equipment that meet predetermined conditions are identified as boundary lines constituting the building; a wall identification step in which detailed information about walls, including wall type and wall size, is identified based on the boundary lines and evaluation basic building drawings and evaluation basic building information; a room identification step in which detailed information about rooms, including room type and room size, is identified based on the boundary lines and evaluation basic building drawings and evaluation basic building information; and an output step in which evaluation data necessary for house evaluation is output based on evaluation basic building drawings and evaluation basic building information, detailed room information obtained by the room identification step, and detailed wall information obtained by the wall identification step.

[0014] A computer program according to one aspect of the present invention includes: a reading step of reading a building drawing comprising at least one of building components and building equipment, and building information which is detailed information relating to the building components and building equipment; a processing step of labeling and coloring the building components and building equipment in the building drawing and adding processing information to the building information; a training data acquisition step of acquiring a processed building drawing comprising at least one of the processed building components and processed building equipment processed based on the building drawing and building information, and processed building information which is detailed information relating to the processed building components and processed building equipment, as training data; and a learning model that, when input data comprising a building drawing and building information is input, outputs an evaluation base building drawing and evaluation base building information which are the same as the processed building drawing and processed building information, respectively, based on the training data, and further outputs an evaluation base building component and evaluation base building equipment which are the same as the processed building components and processed building equipment in the processed building drawing. A computer program characterized by causing a computer to perform a process that includes: an evaluation base information acquisition step of inputting building drawings and building information and acquiring evaluation base building drawings and evaluation base building information, as well as evaluation base building components and evaluation base building equipment provided in the evaluation base building drawings; a boundary identification step of comparing grid lines along building modules based on building drawings and building information with evaluation base building information and identifying evaluation base building components and evaluation base building equipment that meet predetermined conditions as boundary lines constituting the building; a wall identification step of identifying detailed wall information, including wall type and wall size, based on boundary lines, evaluation base building drawings, and evaluation base building information; a room identification step of identifying detailed room information, including room type and room size, based on boundary lines, evaluation base building drawings, and evaluation base building information; and an output step of outputting evaluation data necessary for house evaluation based on evaluation base building drawings, evaluation base building information, detailed room information acquired by the room identification step, and detailed wall information acquired by the wall identification step.

[0015] An information processing device according to one aspect of the present invention includes: a reading unit that reads a building drawing comprising at least one of building components and building equipment, and building information which is detailed information relating to the building components and building equipment; a processing unit that performs labeling and coloring on the building components and building equipment contained in the building drawing and adds processing information to the building information; a training data acquisition unit that acquires as training data a processed building drawing comprising at least one of the processed building components and processed building equipment processed by the processing unit based on the building drawing and building information, and processed building information which is detailed information relating to the processed building components and processed building equipment; and a learning model that, when input data comprising a building drawing and building information is input, outputs an evaluation base building drawing and evaluation base building information which are the same as the processed building drawing and processed building information, respectively, based on the training data, and further outputs an evaluation base building component and evaluation base building equipment which are the same as the processed building components and processed building equipment contained in the processed building drawing, respectively, and evaluates The system includes: an evaluation base information acquisition unit that acquires evaluation base building drawings and evaluation base building information, as well as evaluation base building components and evaluation base building equipment contained in the evaluation base building drawings; a boundary identification unit that extracts grid lines composed of meridians and parallels along the rectangle of the building module calculated based on the building drawings and building information, or grid lines composed of meridians and parallels from a rectangle of any size, compares the grid lines with the evaluation base building information, and identifies evaluation base building components and evaluation base building equipment that overlap with the grid lines as boundary lines constituting the building; a wall identification unit that identifies detailed wall information, including the type and size of the wall, based on the boundary lines, evaluation base building drawings, and evaluation base building information; a room identification unit that identifies detailed room information, including the type and size of the room, based on the boundary lines, evaluation base building drawings, and evaluation base building information; and an output unit that outputs evaluation data necessary for house evaluation based on the evaluation base building drawings, evaluation base building information, detailed room information acquired by the room identification unit, and detailed wall information acquired by the wall identification unit.

[0016] An information processing method according to one aspect of the present invention includes: a reading step of reading a building drawing comprising at least one of building components and building equipment, and building information which is detailed information relating to the building components and building equipment; a processing step of labeling and coloring the building components and building equipment in the building drawing and adding processing information to the building information; a training data acquisition step of acquiring a processed building drawing comprising at least one of the processed building components and processed building equipment processed based on the building drawing and building information, and processed building information which is detailed information relating to the processed building components and processed building equipment, as training data; and inputting building drawings and building information into a learning model that, when input data comprising building drawings and building information is input, outputs evaluation base building drawings and evaluation base building information which are the same as the processed building drawings and processed building information, respectively, based on the training data, and further outputs evaluation base building components and evaluation base building equipment which are the same as the processed building components and processed building equipment in the processed building drawings, respectively, and evaluation base building The process includes: an evaluation base information acquisition step that acquires building drawings and evaluation base building information, as well as evaluation base building components and evaluation base building equipment provided in the evaluation base building drawings; a boundary identification step that extracts grid lines composed of meridians and parallels along the rectangle of the building module calculated based on the building drawings and building information, or grid lines composed of meridians and parallels from a rectangle of any size, compares the grid lines with the evaluation base building information, and identifies evaluation base building components and evaluation base building equipment that overlap with the grid lines as boundary lines constituting the building; a wall identification step that identifies detailed wall information, including the type and size of the wall, based on the boundary lines, evaluation base building drawings, and evaluation base building information; a room identification step that identifies detailed room information, including the type and size of the room, based on the boundary lines, evaluation base building drawings, and evaluation base building information; and an output step that outputs evaluation data necessary for house evaluation based on the evaluation base building drawings, evaluation base building information, detailed room information acquired by the room identification step, and detailed wall information acquired by the wall identification step.

[0017] A computer program according to one aspect of the present invention includes a reading step of reading a building drawing comprising at least one of building components and building equipment, and building information which is detailed information relating to the building components and building equipment; a processing step of labeling and coloring the building components and building equipment in the building drawing and adding processing information to the building information; a training data acquisition step of acquiring a processed building drawing comprising at least one of the processed building components and processed building equipment processed based on the building drawing and building information, and processed building information which is detailed information relating to the processed building components and processed building equipment, as training data; and a learning model that, when input data comprising a building drawing and building information is input, outputs an evaluation base building drawing and evaluation base building information identical to the processed building drawing and processed building information, respectively, based on the training data, and further outputs an evaluation base building component and evaluation base building equipment identical to the processed building components and processed building equipment in the processed building drawing, respectively, and inputs a building drawing and building information into a learning model, and The computer is made to perform a process that includes: an evaluation basis information acquisition step of acquiring evaluation basis building information and evaluation basis building components and evaluation basis building equipment provided in the evaluation basis building drawings; a boundary identification step of extracting grid lines composed of meridians and parallels along the rectangle of the building module calculated based on the building drawings and building information, or grid lines composed of meridians and parallels from a rectangle of any size, comparing the grid lines with the evaluation basis building information, and identifying evaluation basis building components and evaluation basis building equipment that overlap with the grid lines as boundary lines constituting the building; a wall identification step of identifying detailed wall information including the type and size of the wall based on the boundary lines, evaluation basis building drawings, and evaluation basis building information; a room identification step of identifying detailed room information including the type and size of the room based on the boundary lines, evaluation basis building drawings, and evaluation basis building information; and an output step of outputting evaluation data necessary for house evaluation based on the evaluation basis building drawings, evaluation basis building information, detailed room information obtained by the room identification step, and detailed wall information obtained by the wall identification step.

Advantages of the Invention

[0018] According to the present invention, in house evaluation, it becomes possible to continuously execute drawing analysis processing, score addition processing, and score count calculation processing, and it is possible to significantly reduce the amount of work such as the score item input operation and score item correction operation that are repeated for each house. As a result, since the working time required for calculating the score of a house including score correction can be significantly shortened, more efficient processing can be realized. Furthermore, since partial modification of the score items and correction items once added is possible, it is possible to flexibly respond when there are scores to be changed, added, or deleted, and there is an effect that work efficiency can be improved. Furthermore, by utilizing a grid, which is a common unit related to the building structure, for specifying the evaluation basis building components and evaluation basis building facilities, the processing content of AI can be simplified and the processing speed can be significantly increased.

[0019] In addition, according to the present invention, the operator is released from long-time, repetitive simple work that requires great concentration, released from fatigue and mistakes associated with fatigue, and leads to a reduction in lawsuits by taxpayers caused by mistakes in house evaluation and fluctuations in evaluations that depend on the operator. Therefore, it becomes possible to contribute to Goal 3, "Good health and well-being for all," Goal 8, "Decent work and economic growth," and Goal 9, "Build the infrastructure for industry and innovation" of the Sustainable Development Goals (SDGs) led by the United Nations.

Brief Explanation of Drawings

[0020] [Figure 1] It is an explanatory diagram regarding the generation process of the learning model according to Embodiments 1 and 2 of the present invention. [Figure 2] It is an explanatory diagram regarding the generation process of the learning model according to Embodiments 1 and 2 of the present invention. [Figure 3] It is an explanatory diagram regarding the generation process of the learning model according to Embodiments 1 and 2 of the present invention. [Figure 4]This is a schematic diagram relating to the processing of building drawings and building information according to Embodiments 1 and 2 of the present invention. [Figure 5] This is a schematic diagram relating to building drawings according to Embodiments 1 and 2 of the present invention. [Figure 6] This is a schematic diagram relating to building information according to Embodiments 1 and 2 of the present invention. [Figure 7] This is a schematic diagram relating to building information according to Embodiments 1 and 2 of the present invention. [Figure 8] This is a schematic diagram relating to the floor plan of a building according to Embodiments 1 and 2 of the present invention. [Figure 9] This is a schematic diagram relating to fabricated building drawings according to Embodiments 1 and 2 of the present invention. [Figure 10] This is a schematic diagram relating to fabricated building drawings according to Embodiments 1 and 2 of the present invention. [Figure 11] These are explanatory diagrams relating to fabricated building drawings according to Embodiments 1 and 2 of the present invention. [Figure 12] This is a flowchart illustrating the processing of building drawings and building information according to Embodiments 1 and 2 of the present invention. [Figure 13] This is a flowchart illustrating the process of generating learning models according to embodiments 1 and 2 of the present invention. [Figure 14] This is a block diagram showing the configuration of an information processing device according to Embodiment 1 of the present invention. [Figure 15] This is a block diagram showing the configuration of an information processing device according to Embodiment 1 of the present invention. [Figure 16] This is a block diagram showing the configuration of an information processing device according to Embodiment 1 of the present invention. [Figure 17] This flowchart shows the processing procedure for outputting house evaluation data by an information processing device according to Embodiment 1 of the present invention. [Figure 18] This is a flowchart relating to the processing procedure for outputting house evaluation data by an information processing device according to Embodiment 1 of the present invention. [Figure 19] This is a flowchart relating to the processing procedure for outputting house evaluation data by an information processing device according to Embodiment 1 of the present invention. [Figure 20] This is a flowchart relating to the processing procedure for outputting house evaluation data by an information processing device according to Embodiment 1 of the present invention. [Figure 21] This is a flowchart relating to the processing procedure for outputting evaluation base building drawings by an information processing device according to Embodiment 1 of the present invention. [Figure 22] This is a schematic diagram of the evaluation base building drawings that can be obtained through the learning models according to Embodiments 1 and 2 of the present invention. [Figure 23] This is a schematic diagram relating to a floor plan of a building drawing used for evaluation calculations according to Embodiments 1 and 2 of the present invention. [Figure 24] This is a schematic diagram for identifying boundaries related to an information processing method according to Embodiment 1 of the present invention. [Figure 25] This is a schematic diagram for identifying boundaries related to an information processing method according to Embodiment 1 of the present invention. [Figure 26] This is a schematic diagram for identifying boundaries related to an information processing method according to Embodiment 1 of the present invention. [Figure 27] This is a schematic diagram for identifying boundaries related to an information processing method according to Embodiment 1 of the present invention. [Figure 28] This is a schematic diagram for identifying boundaries related to an information processing method according to Embodiment 1 of the present invention. [Figure 29] This is a schematic diagram for identifying boundaries related to an information processing method according to Embodiment 1 of the present invention. [Figure 30] This is a schematic diagram for identifying boundaries related to an information processing method according to Embodiment 1 of the present invention. [Figure 31] This is a schematic diagram for identifying boundaries related to an information processing method according to Embodiment 1 of the present invention. [Figure 32] This diagram is a schematic diagram for identifying boundaries related to the information processing methods according to Embodiments 1 and 2 of the present invention. [Figure 33] This is a schematic diagram for identifying a room, relating to the information processing method according to Embodiments 1 and 2 of the present invention. [Figure 34]This is a schematic diagram for identifying a room, relating to the information processing method according to Embodiments 1 and 2 of the present invention. [Figure 35] This is a schematic diagram for identifying a room, relating to the information processing method according to Embodiments 1 and 2 of the present invention. [Figure 36] This is a schematic diagram for identifying a room, relating to the information processing method according to Embodiments 1 and 2 of the present invention. [Figure 37] This is a schematic diagram for identifying a room, relating to the information processing method according to Embodiments 1 and 2 of the present invention. [Figure 38] This is a schematic diagram for identifying a room, relating to the information processing method according to Embodiments 1 and 2 of the present invention. [Figure 39] This is a schematic diagram for identifying a room, relating to the information processing method according to Embodiments 1 and 2 of the present invention. [Figure 40] This is a schematic diagram for identifying a room, relating to the information processing method according to Embodiments 1 and 2 of the present invention. [Figure 41] This is a block diagram showing the configuration of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 42] This is a flowchart showing how the information processing device according to Embodiments 1 and 2 of the present invention performs three-dimensional display processing. [Figure 43] This diagram illustrates the three-dimensional display processing of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 44] This diagram illustrates the three-dimensional display processing of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 45] This diagram illustrates the three-dimensional display processing of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 46] This diagram illustrates the three-dimensional display processing of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 47] This diagram illustrates the three-dimensional display processing of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 48] This diagram illustrates the three-dimensional display processing of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 49] This diagram illustrates the three-dimensional display processing of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 50] This diagram illustrates the three-dimensional display processing of the information processing device according to Embodiments 1 and 2 of the present invention. [Figure 51] This is a block diagram showing the configuration of an information processing device according to Embodiment 2 of the present invention. [Figure 52] This is a block diagram showing the configuration of an information processing device according to Embodiment 2 of the present invention. [Figure 53] This flowchart shows the processing procedure for outputting house evaluation data by the information processing device according to Embodiment 2 of the present invention. [Figure 54] This flowchart shows the processing procedure for outputting house evaluation data by the information processing device according to Embodiment 2 of the present invention. [Figure 55] This flowchart shows the processing procedure for outputting house evaluation data by the information processing device according to Embodiment 2 of the present invention. [Modes for carrying out the invention]

[0021] Embodiments of the present invention will be described below with reference to the drawings. However, the components described in the following embodiments are merely examples and are not intended to limit the technical scope of the present invention to them alone. In this specification, the terms "figure" and "drawing" may, depending on the context, represent concepts or specific data. When "figure" and "drawing" refer to data, they are images of any format.

[0022] For the sake of clarity, unless otherwise specified, the same symbols assigned to each figure indicate the same or equivalent part, and elements with similar structure and / or function may be intended, and unnecessarily detailed explanations may be omitted. Furthermore, redundant explanations will be simplified or omitted as appropriate. Furthermore, in this embodiment, the symbol "~" may be used to represent a numerical range, but the numbers written before and after "~" are included in that numerical range. (Embodiment 1) [Learning Model]

[0023] Figures 1-4 are explanatory diagrams regarding the generation process of the learning model 62 used in the information processing device 1 shown in Figure 14. Figure 1 conceptually illustrates the process of generating the learning model 62 by performing machine learning. As shown in Figure 1, the neural network that generates the learning model 62 comprises an input layer that receives information, an intermediate layer that inherits information from the input layer and performs a wide variety of calculations, and an output layer where the values ​​obtained by applying weights from the input layer and the intermediate layer and processing with an activation function are shown. By comparing the results obtained in the output layer with the training data and correcting and adjusting the errors from the output layer to the input layer, it becomes possible to perform more appropriate learning even in complex neural networks with many intermediate layers.

[0024] As shown in Figure 2, the input layer has multiple neurons that receive input such as building drawings and building information contained in the input data, and processed building drawings and processed building information obtained by processing the building drawings and building information respectively, and information about each pixel contained in the processed building drawings and processed building information contained in the training data, and passes the input information about pixels, etc. to the intermediate layer. The intermediate layer has multiple neurons that extract information related to images of processed building drawings and information related to processed buildings, and passes the extracted information to the output layer.

[0025] Note that although Figure 1 shows three intermediate layers, it is not limited to this. For example, if the learning model 62 is a CNN, the intermediate layers have a configuration in which convolution layers that convolve the pixel values ​​of each pixel input from the input layer and pooling layers that map the pixel values ​​convolved in the convolution layers are alternately connected, compressing the pixel information of the processed building drawing and ultimately extracting the image features. In Figure 1, the convolution layers and pooling layers are omitted from the description. As shown in Figure 3, the output layer outputs the evaluation base building drawings and evaluation base building information based on the image features output from the intermediate layer.

[0026] The learning model 62 is trained to ensure that the processed building drawings and processed building information, which are obtained by processing building drawings and building information respectively, match the evaluation base building drawings and evaluation base building information. When building drawings and building information are input, the model is trained to output evaluation base building drawings and evaluation base building information that match the processed building drawings and processed building information, which are obtained by processing building drawings and building information respectively.

[0027] Here, a processed building drawing is a building drawing to which labels and colors have been added to each of the multiple building components and building equipment included in the building drawing. Specifically, as shown in Figure 4, label information and color information are added to the pixels belonging to each building component and building equipment in the building drawing data, and processed building information is obtained by adding this added information (processed information) to the building information.

[0028] The building drawings include site plans, floor plans, elevations, electrical and heating wiring diagrams, unfolded drawings, foundation plans, foundation cross-sections, structural plans, hardware plans, cross-sections, special specifications for electrical equipment installation, special specifications for mechanical equipment installation, outdoor water supply and drainage equipment drawings, etc. Figure 5 shows a floor plan and elevations according to Embodiment 1 of the present invention.

[0029] A floor plan is a drawing that shows the shape of a building and its positional relationship to the site. It is a drawing of a horizontal cross-section at a height of about 1 meter from the floor surface of each floor, and is also a layout drawing, used to understand the layout and internal structure of a building. It displays the projection view from above the object, the layout, floor height, area, wall structure, opening direction of openings, doors and windows, built-in furniture, and the arrangement of equipment, and is filled with detailed dimensions. Floor plans are the most basic drawings in design documents and are often used as headings or indexes for other drawings. It is a figure drawn by looking down from directly above at a cross-section of a building or civil engineering structure that has been cut horizontally at a certain height, and drawn to an appropriate scale. The floor plan described in Embodiment 1 of the present invention is a drawing that shows the shape of each floor and describes the floor area and the method of calculating the area.

[0030] Elevation drawings show the overall exterior of a building. Unless otherwise specified, such as when the building is adjacent to a neighboring property, it is customary to create three-dimensional drawings of the four cardinal directions (east, west, north, and south). The shape of the exterior walls, doors, windows, and entrances, as well as the reference ground level, are illustrated, and checks for side slopes and road slopes are also performed in these drawings. Projections onto a vertical plane include front views and side views of the object. The scale is typically around 1 / 50 to 1 / 100. Elevation drawings have a strong character as exterior design drawings of the building, and detailed dimensions are often omitted, so they are also called "elevation drawings." The drawings are traditionally written from left to right in a counterclockwise direction, but recently, it is common to create three-dimensional images using CG or color perspectives.

[0031] Furthermore, building components refer to elements that make up a building, such as exterior walls, interior walls, fixtures, and floors. Building equipment refers to various facilities installed in a building, and includes systems and devices consisting of machinery, piping, wiring, and equipment that allow for the selective use of air, water, electricity, gas, etc.

[0032] Building information refers to detailed information about each building component and building equipment, including the name, layout, and size of each component and building equipment. Building information also includes a finishing schedule, as shown in Figure 6, which summarizes the finishes of various parts of the building, and specifications, as shown in Figure 7, which lists everything from major components like the foundation, structure, roof, and exterior walls to equipment-related items like kitchens and washbasins. The finishing schedule is a drawing showing the finishing materials for the floors, walls, and ceilings of each room. Finishing schedules and specifications consist of tables and text. Furthermore, the finishing schedule includes an exterior finishing schedule showing finishes for the "outside of the house" such as the roof and exterior walls, and an interior finishing schedule showing finishes for the "inside of the house" (interior finishes) such as the walls, floors, and ceilings of each room.

[0033] Next, the processed building drawing shown in Figure 9 is created by adding label information such as the building component name and building equipment name, as well as associated color information, to each pixel of the building component and building equipment segment included in the building drawing shown in Figure 8. The information such as the building component name and building equipment name, and the associated color information, are shown, for example, as follows: exterior wall = 1 (ochre), interior wall = 2 (blue-green), living room = 3 (yellow-green). The building components and building equipment are processed and obtained as processed building components and processed building equipment. The processed building information includes detailed information about the processed building components and processed building equipment.

[0034] Processed building drawings are colored through processing, and processed building information has labels and color information added to the building information through processing. The added information such as labels and colors is called processed additional information. Figures 10 and 11 show the fabricated building drawing shown in Figure 9 broken down into its individual fabricated building components and fabricated building equipment. [Processing drawing generation] Figure 12 is a flowchart showing an example of the processing procedure for processing building drawings and building information by the control unit 10 of the information processing device 1 shown in Figure 15.

[0035] For example, the control unit 10 of the information processing device 1 shown in Figure 14 reads the building drawing and building information (S01). Next, the control unit 10 performs processing to add label information and color information to the building drawing and building information (S02). Next, the control unit 10 acquires the processed building drawing and processed building information from which the building drawing and building information have been processed (S03). [Method for generating a learning model] Figure 13 is a flowchart showing an example of the processing procedure for generating a learning model 62 by the control unit 10 of the information processing device 1 shown in Figure 14. The control unit 10 shown in Figure 14 acquires processed building drawings and processed building information, respectively, as training data (S11).

[0036] Next, when the control unit 10 receives training data, it generates a learning model 62 (trained model) that outputs evaluation base building drawings and evaluation base building information that match the processing building drawings and processing building information, respectively (S12). Figure 21 is a flowchart illustrating how to obtain evaluation base building drawings and evaluation base building information from building drawings and building information using the trained model 62 (pre-trained model). When the control unit 10 receives building drawings and building information as input (S111), it uses the learning model 62 (trained model) to output the evaluation base building drawings and evaluation base building information (S112). The output evaluation base building drawings are shown in Figure 22.

[0037] Specifically, the control unit 10 inputs the building drawings and building information contained in the input data, as well as the processed building drawings and processed building information obtained by processing the training data, into the input layer of the neural network, and outputs the evaluation base building drawings and evaluation base building information corresponding to the building drawings and building information, respectively, from the output layer. The control unit 10 compares the evaluation base building drawings and evaluation base building information with the correct values ​​of the training data (label information and color information for each pixel, etc.), and optimizes the parameters (weights, etc.) used in the calculation processing in the hidden layer so that the evaluation base building drawings and evaluation base building information output from the output layer approaches the correct values. These parameters include, for example, the weights (connection coefficients) between neurons and the coefficients of the activation function used in each neuron. The method of parameter optimization is not particularly limited, but for example, the information processing device 1 can optimize various parameters using backpropagation.

[0038] Furthermore, increasing the types and number of processed building drawings and processed building information, and increasing the number of training iterations, will optimize the learning model 62 and improve its accuracy. The control unit 10 stores the generated learning model 62 in the auxiliary storage unit 60 and terminates the series of processes.

[0039] Although the learning algorithm used to generate the learning model 62 according to Embodiment 1 of the present invention is described as semantic segmentation, it is not limited to semantic segmentation and can be applied to learning algorithms constructed using other learning algorithms such as neural networks, SVM (Support Vector Machine), Bayesian networks, and regression trees.

[0040] Furthermore, while the image processing method according to Embodiment 1 of the present invention utilizes discrimination using a trained model based on semantic segmentation, it is not limited to this, and other image processing methods may be used. For example, a trained model modeled using gradient boosting, random forest, etc., can be used to distinguish between fabricated building drawings and evaluation base building drawings. In that case, the control unit 10 can, as a discrimination means, for example, divide the image into meshes, obtain the mean and standard deviation of RGB in each mesh, and use the obtained values ​​as explanatory variables. That is, the control unit 10, as a discrimination means, inputs explanatory variables obtained from each of a large number of training images into a trained model whose parameters have been updated so that the output value obtained matches the annotation of the training image, and then performs discrimination by inputting explanatory variables obtained from the image into the trained model. [Semantic Segmentation] Semantic segmentation can be used in the machine learning model according to Embodiment 1 of the present invention.

[0041] Semantic segmentation is a deep learning algorithm that associates a label or category with every single pixel in an image, and is used to recognize clusters of pixels that form characteristic categories.

[0042] As a technique used in semantic segmentation, for example, Fully Convolutional Networks (FCNs) can obtain similar results even if the fully connected layers of a general CNN are replaced with convolutional layers by considering a 1x1 convolution that covers the entire region; SegNet is an Encoder-Decoder type FCN; U-Net is an Encoder-Decoder type characterized by "skip connections" that skip and connect low-dimensional features to high-dimensional features; PSPNet is an Encoder-Decoder type that uses Spatial Pyramid Pooling to obtain rich surrounding context and enable high-precision semantic segmentation; v1 uses an Atrous convolution (Dilated convolution) technique for the convolutional layer; v2 adds Atrous Spatial Pyramid Pooling (ASPP), which is inspired by Spatial Pyramid Pooling; and v3 uses an improved version of the ASPP added in v2, called "Improved ASPP," as well as v1, DeepLab (v1~v3+) has several improvements, including the elimination of post-processing using CRF in v2, the change from "multiscale image processing" in v2 to "multiscale feature processing" to improve computational efficiency, the introduction of Batch Normalization, and further improvements in v3+, such as the addition of a simple and effective decoder module, the introduction of the Xception model in the backbone, and the construction of a faster and more powerful network by applying depthwise separable convolution to both Atrous Spatial Pyramid Pooling and the decoder module. [Information Processing Device] Figure 14 is a block diagram showing the schematic configuration of the information processing device 1 according to Embodiment 1 of the present invention.

[0043] Information Processing Device 1 is an information processing device capable of various information processing and information transmission / reception, and is a computer. Computers are classified according to their purpose of use, specifications, specs, performance, etc., into personal computers (PCs), workstations, server computers (servers), mainframes, supercomputers (supercomputers), ultracomputers, minicomputers (minicomputers), office computers (office computers), pocket computers (pocket computers), microcomputers (microcomputers), personal digital assistants (PDAs), and programmable logic controllers (PLCs), but all of these can be applied to the Information Processing Device 1. Furthermore, it is also possible for a cloud computer connected via a network N such as the Internet to perform processing on the Information Processing Device 1. The information processing device 1 according to Embodiment 1 of the present invention is a personal computer, which will be described below.

[0044] The information processing device 1 according to Embodiment 1 of the present invention reads building drawings and building information, inputs processed building drawings and processed building information, which are images processed (processed) based on the read building drawings and building information, into a learning model, trains the learning model to output evaluation base building drawings and evaluation base building information that match the processed building drawings and processed building information, respectively, and outputs evaluation base building drawings and evaluation base building information, which are basic information for detecting, identifying, specifying and digitizing the information necessary for house evaluation, using a learning model 62 that has been trained by machine learning, and performs processing to calculate the scoring items necessary for house evaluation and the score for each scoring item from the building drawings and building information and the processed additional information. The learning model 62 is intended to be used as a program module that is part of artificial intelligence software. In the following description of Embodiment 1 of the present invention, we will explain the case in which information necessary for house valuation (house valuation data) is obtained when building drawings and building information are read. As shown in Figure 14, the information processing device 1 comprises a control unit 10, a main memory unit 50, a communication unit 30, an input unit 40, an output unit 20, an auxiliary memory unit 60, and a display unit 70.

[0045] The control unit 10 has one or more arithmetic processing units such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), and GPU (Graphics Processing Unit), and performs various information processing, control processing, etc. related to the information processing device 1 by reading and executing the program 63 stored in the auxiliary storage unit 60. Each functional unit in Figure 14 is executed by the control unit 10 operating based on the program 63.

[0046] The control unit 10 includes, as functional units, a reading unit 11, a processing unit 12, a training data acquisition unit 13, an evaluation basic information acquisition unit 14, a boundary identification unit 15, a room identification unit 16, a correction unit 17, a wall identification unit 18, an evaluation information acquisition unit 19, and an output unit 20.

[0047] The reading unit 11 reads a building drawing that includes at least one of the building components and building equipment, and building information which is detailed information about the building components and building equipment.

[0048] The processing unit 12 performs image processing (image processing) on ​​the imported building drawings and building information, specifically on the building components and building equipment contained in the building drawings, by adding labels and colors, and by adding processing information to the building information.

[0049] The training data acquisition unit 13 acquires as training data a processed building drawing which includes at least one of processed building components and processed building equipment processed by the processing unit 12 based on the building drawing and building information, and processed building information which is detailed information about the processed building components and processed building equipment.

[0050] The evaluation basic information acquisition unit 14, upon receiving input data comprising building drawings and building information, outputs evaluation basic building drawings and evaluation basic building information identical to those of the processed building drawings and processed building information, respectively, based on training data. Furthermore, it inputs building drawings and building information into a learning model 62 that outputs evaluation basic building components and evaluation basic building equipment identical to those of the processed building drawings, respectively, and acquires evaluation basic building drawings (Figure 22) and evaluation basic building information, as well as evaluation basic building components and evaluation basic building equipment contained in the evaluation basic building drawings.

[0051] The boundary identification unit 15 extracts information regarding the exterior walls, interior walls, and wall thickness from the evaluation base building drawings and evaluation base building information, and identifies the building outline formed by this information as the boundary line. The room identification unit 16 identifies detailed room information, including the room type and room size, based on the boundary line, the evaluation base building drawing, and the evaluation base building information.

[0052] The correction unit 17 corrects the boundary line identified by the boundary identification unit 15 by adjusting and moving the position of the boundary line so that it is configured along the rectangle of the building module indicated by the grid lines. Here, a building module is a basic dimension or standard unit that serves as a design standard in architecture, and refers to units such as meters, shaku, and ken, which are used for things like the distance between columns in a building or the dimensions of tatami mats. In many houses in Japan, the "shaku module" with a unit of "910 millimeters = 3 shaku" is used.

[0053] The wall identification unit 18 identifies detailed wall information, including the wall type and wall size, based on the boundary line corrected by the correction unit 17, the evaluation base building drawing, and the evaluation base building information.

[0054] The evaluation information acquisition unit 19 acquires evaluation building drawings and evaluation building information based on evaluation base building drawings and evaluation base building information, detailed room information acquired by the room identification unit 16, and detailed wall information acquired by the wall identification unit 18.

[0055] The output unit 20 outputs evaluation data necessary for house evaluation based on the evaluation base building drawings and evaluation base building information, detailed room information obtained by the room identification unit, and detailed wall information obtained by the wall identification unit. Here, the evaluation data is, for example, information necessary for calculating the reconstruction cost score, and includes the standard score for each score item, correction coefficient, and calculation unit.

[0056] Here, the scoring items are items for assigning standard scores based on classifications such as the types and quality of materials commonly used for each part, and the manner of construction. The standard scores are calculated based on the construction costs relative to the "standard quantity," according to the classification of the scoring items. The standard quantity refers to the amount of construction required per unit for each part of a house when constructing a new house that is standard for each structure and use as defined in the "Reconstruction Cost Scoring Standards Table."

[0057] Furthermore, the standard score is calculated based on the cost equivalent to the construction cost, which is determined by the price level in the special ward area at a predetermined time based on the base year, according to the classification of the scoring items, with one yen of that cost representing one point. The correction items and correction coefficients are used to adjust for differences in the amount of work performed on the house being evaluated compared to the standard amount of work performed on each part.

[0058] The unit of calculation is (m, m) for the convenience of assigning scores. 2 , m 3 The scores are shown per unit (e.g., t, piece). Therefore, the reconstruction cost score for each part is calculated by multiplying the standard score by the prescribed calculation unit.

[0059] Furthermore, the output unit 20 also outputs the evaluation building drawings and evaluation building information acquired by the evaluation information acquisition unit 19. The evaluation building drawings and evaluation building information include all the digitized data of the building drawings and building information, and, if necessary, the operator includes correction coefficients and corrected information when there are fluctuations in the calculation results of the learning model 62.

[0060] The main memory unit 50 is a temporary storage area such as SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), or flash memory, and temporarily stores data necessary for the control unit 10 to perform calculation processing. The communication unit 30 is a communication module for performing communication-related processing, and transmits and receives building drawings and building information with the outside. The input unit 40 is a keyboard for inputting characters and symbols, a mouse for specifying the coordinates of the pointer and sending signals to control its position, etc. The display unit 70 is a display that displays characters and graphics, and displays the loaded architectural drawings, etc., and the scoring items and scores necessary for the calculated house evaluation. The display unit 70 also displays setting input information, setting change information, and setting confirmation information for various functional units that constitute the information processing device 1.

[0061] The auxiliary storage unit 60 is a large-capacity memory, hard disk, etc., and stores the program 63 and other data necessary for the control unit 10 to execute processing. The auxiliary storage unit 60 also stores the drawing / information DB 61 and the learning model 62. The drawing / information DB 61 is a database that stores data related to building drawings and building information, processed building drawings and processed building information, evaluation base building drawings and evaluation base building information, line segment building drawings and line segment building information, evaluation building drawings and evaluation building information, etc.

[0062] The program 63 stored in the auxiliary storage unit 60 may be provided from a recording medium on which the program 63 is recorded in a readable format. The recording medium is, for example, a portable memory such as a USB (Universal Serial Bus) memory, an SD (Secure Digital) card, a microSD card, or a CompactFlash®. The program 63 recorded on the recording medium is read from the recording medium using a reading device (not shown in the figure) and stored in the auxiliary storage unit 60. Furthermore, if the information processing device 1 is equipped with a communication unit capable of communicating with an external communication device, the program 63 stored in the auxiliary storage unit 60 may be provided by communication via the communication unit.

[0063] Furthermore, an external storage device connected to the information processing device 1 can be used as the auxiliary storage unit 60. In addition, a multicomputer consisting of multiple computers can be used as the information processing device 1, and a virtual machine virtually constructed by software can also be used. Furthermore, the control unit 10 can also add, delete, and edit the data and programs contained in the drawing / information DB 61, learning model 62, and program 63 provided in the auxiliary storage unit 60.

[0064] Next, the boundary identification unit 15 compares the evaluation base building information with grid lines along the building modules configured based on the building drawings and building information. As a result of the comparison, it identifies the evaluation base building components and evaluation base building equipment that meet the predetermined conditions as the boundary lines constituting the building.

[0065] The boundary identification unit 15 includes a grid line extraction unit 151 and a boundary determination unit 152. The grid line extraction unit 151 extracts grid lines composed of meridians and parallels along building modules calculated based on building drawings and building information, or grid lines composed of meridians and parallels of an arbitrary size. The boundary determination unit 152 compares the grid lines with the evaluation base building drawings, and determines the boundary line when the wall information, which is information about the exterior and interior walls contained in the evaluation base building drawings and evaluation base building information, is included in the grid line band which is a certain distance from the grid lines, and the overlapping portion of the wall information and grid is used as the wall boundary.

[0066] The room identification unit 16 includes a section identification unit 161 that identifies an area enclosed by a boundary line as a partitioned space within the building based on the boundary line, and a room identification unit 162 that identifies the type of room for a section by applying information on labels and colors contained in the evaluation base building drawings and evaluation base building information, which include evaluation base building components and evaluation base building equipment, to each pixel of the corresponding section and adopting the information on the most common type of label and color within the section. [Information Processing Methods] Figure 17 is a flowchart illustrating an example of a processing procedure for outputting data necessary for house evaluation using the information processing device 1 according to Embodiment 1 of the present invention.

[0067] First, the reading unit 11 reads building drawings, such as those shown in Figures 5 and 8, which include at least one of the building components and building equipment, and building information, such as those shown in Figures 6 and 7, which are detailed information about the building components and building equipment (S21).

[0068] Next, the processing unit 12 performs processing (image processing) on ​​the loaded building drawings and building information, specifically on the building components and building equipment contained in the building drawings, by adding labels and colors, and then adds the processing information to the building information (S22).

[0069] Next, the training data acquisition unit 13 acquires as training data a processed building drawing which includes at least one of the processed building components and processed building equipment processed by the processing unit 12 based on the building drawing and building information, and processed building information which is detailed information about the processed building components and processed building equipment as shown in Figure 9 (S23).

[0070] The evaluation basic information acquisition unit 14 acquires evaluation basic building drawings and evaluation basic building information, as well as evaluation basic building components and evaluation basic building equipment contained in the evaluation basic building drawings, by inputting input data containing building drawings and building information into the learning model 62 (S24). Here, the learning model 62 is a trained model in machine learning that, when input data containing building drawings and building information is input, outputs evaluation basic building drawings and evaluation basic building information that are the same as those of the processed building drawings and processed building information, respectively, based on training data, and further outputs evaluation basic building components and evaluation basic building equipment contained in the processed building drawings, respectively, as well as evaluation basic building components and evaluation basic building equipment contained in the same evaluation basic building drawings.

[0071] The grid line extraction unit 151 of the boundary identification unit 15 extracts grid line information shown in Figure 24 from the building information for evaluation calculation shown in Figure 23, as shown in Figure 19 (S251). Figure 25 is a diagram that clearly shows the relationship between the building information and the grid lines. Next, the boundary determination unit 152 of the boundary identification unit 15 compares the evaluation base building drawing shown in Figure 26 with the grid lines in Figure 24, aligning them with the building module as shown in Figure 27. The boundary determination unit 152 determines a wall in the evaluation base building drawing that has the same axial direction with respect to the grid line and is included in the range of distance d on both sides with respect to the grid line for, for example, 50% or more, as a valid wall, and determines the line segment of the grid line corresponding to the length of that wall as the boundary of the building. Here, the percentage of walls in the evaluation base building drawing that fall within a distance d on both sides of the grid line is set at 50%, but this is merely an example, and it is possible to adopt and apply any appropriate percentage such as 80%, 60%, or 20% depending on the accuracy of the processing, etc. Furthermore, the distance d can be applied to even a single pixel, which is the smallest unit or element that possesses color information (hue and gradation) when handling images on a computer. It can also be applied to, for example, three pixels, and any size can be adopted and applied as appropriate. Note that Figure 29 corresponds to region α shown in Figure 28. In this way, the boundary identification unit 15 identifies the outline of the building formed by these line segments as a boundary line defined as the center line of the wall thickness as shown in Figure 32 (S25).

[0072] Even though walls exist in the evaluation base building drawing shown in Figure 30, the boundary identification unit 15 determines that the walls do not exist, as shown by the black circles in Figure 31. As a result of S25, the line segment building drawing shown in Figure 32 can be obtained.

[0073] Next, the room identification unit 16 identifies detailed room information, including the room type and room size, based on the boundary line, the evaluation base building drawing, and the evaluation base building information (S26).

[0074] More specifically, as shown in Figure 20, the section identification unit 161 identifies the area enclosed by the boundary line as a section of a partitioned space inside the building, based on the boundary line (S261). First, as shown in Figure 34, the unit searches for vectors assigned to all interior walls in the boundary line drawing, using the rightward vector assigned to the side corresponding to the interior wall as a reference. As shown in Figure 35(a), when searching for interior wall vectors, if the boundary line branches, the unit selects a downward search so that the vectors rotate clockwise. As shown in Figure 35(b), the unit selects a leftward search so that the vectors rotate clockwise. As shown in Figure 35(c), similar to Figures 35(a) and (b), the unit selects an upward search so that the vectors rotate clockwise. As a result, the unit completes the search process by connecting to the reference vector from which the search was started, and identifies it as a closed section. Similarly, as shown in Figure 33, the unit searches for vectors assigned to the locations corresponding to the interior walls in all boundary line drawings and identifies the sections.

[0075] The room identification unit 162 applies the label and color information contained in the evaluation base building drawing and evaluation base building information, which include the evaluation base building components and evaluation base building equipment, to each pixel of the corresponding section, and identifies the type of room for a section by adopting the label and color information that is most frequent within the section (S262). That is, for example, the label and color information contained in the evaluation base building drawing, which includes the evaluation base building components and evaluation base building equipment shown in Figure 36(a), is applied to the corresponding section of the boundary line drawing shown in Figure 36(b), and the identification information (label and color information) that is most frequent is adopted as the identification information contained in that section. Information about rooms is identified from the identification information adopted for that section. Figure 37 shows a diagram in which rooms in the boundary line drawing have been identified by the room identification unit 162.

[0076] Next, the wall identification unit 18 identifies detailed wall information, including the type and size of the wall, based on the boundary line corrected by the correction unit 17, the evaluation base building drawing, and the evaluation base building information (S28). The wall identification unit 18 identifies the type, size, etc. of the wall in the corrected boundary line drawing shown in Figure 37, based on the evaluation base building drawing which includes the evaluation base building components and evaluation base building equipment shown in Figure 40(a), and the evaluation base building information.

[0077] The evaluation information acquisition unit 19 acquires acquired evaluation building drawings and evaluation building information corresponding to boundary line drawings as shown in Figure 40(b), based on evaluation base building drawings and evaluation base building information, detailed room information acquired by room identification unit 16, and detailed wall information acquired by wall identification unit 18.

[0078] Next, the output unit 20 outputs the evaluation data necessary for house evaluation based on the evaluation base building drawings and evaluation base building information, the detailed room information obtained by the room identification unit, and the detailed wall information obtained by the wall identification unit. The output unit 20 also outputs the evaluation building drawings and evaluation building information obtained by the evaluation information acquisition unit 19 (S29).

[0079] Next, as shown in Figure 18, the correction unit 17 can also make corrections (S25-1) by adjusting and moving the boundary after it has been identified (S25) based on the operator's instructions. The control unit 10 can also make corrections (S26-1) by adjusting and changing the size, type, etc. of a room after it has been identified (S26) based on the operator's instructions. It can also make corrections (S27-1) by adjusting and moving a wall after it has been identified (S27) based on the operator's instructions. Figure 38 shows an example of performing a correction by shifting the boundary line. If there are special dimensions such as those for closets, an auxiliary dimension (shown by the dashed line in Figure 39) is added, and the correction is performed by shifting to that auxiliary dimension. (Three-dimensional display processing)

[0080] As shown in Figure 41, the information processing device 1 according to Embodiment 1 of the present invention further comprises a three-dimensional processing unit 80 that displays evaluation building drawings and evaluation building information three-dimensionally. The three-dimensional processing unit 80 enables the information processing device 1 to generate and display evaluation building drawings and evaluation building information acquired by the evaluation information acquisition unit 19 as a virtual three-dimensional building model on a virtual three-dimensional space composed of a three-dimensional Cartesian coordinate system. The three-dimensional processing unit 80 includes a three-dimensional transformation unit 81, an alignment unit 82, a spatial shape calculation unit 83, a three-dimensional display unit 84, and a three-dimensional editing unit 85. The three-dimensional transformation unit 81 assigns coordinates to the elements that constitute the shapes of walls and fixtures in the evaluation building drawings and evaluation building information, and more specifically applies the geometric elements such as vertices, edges, and angles that constitute the shape of the building elements to a three-dimensional Cartesian coordinate system. The alignment unit 82 aligns the relative positional relationships between the walls and the fixtures in the evaluation building drawings and evaluation building information.

[0081] The spatial shape calculation unit 83 calculates the interior and exterior shapes of the building in a virtual three-dimensional space based on the evaluation building drawings, the evaluation building information, and the alignment results obtained by the alignment unit 82. When building elements, or combinations thereof, are rotated or moved in the three-dimensional virtual space, the shape of the building elements is deformed so that they are displayed in a shape appropriate to the operator's vision. The three-dimensional display unit 84 displays the building, which consists of the evaluation building drawings and evaluation building information, as an image in a virtual three-dimensional space based on the calculation results from the spatial shape calculation unit 83. The 3D editing unit 85 receives editing instructions from the operator to move, change, delete, or process evaluation building drawings and evaluation building information in a virtual 3D space. It can edit evaluation building drawings and evaluation building information according to the received editing instructions, and can also intuitively move, rotate, disassemble, and integrate building elements displayed in the 3D virtual space. Therefore, operators can gain a more detailed understanding of the building's structure by combining and breaking down the various elements of the building information.

[0082] Figure 42 is a flowchart showing how the information processing device 1 displays evaluation building drawings and evaluation building information in three dimensions. The three-dimensional transformation unit 81 assigns three-dimensional coordinates to multiple building elements of the evaluation building drawing in a three-dimensional virtual space (S271). Next, the alignment unit 82 aligns the relative positional relationships and relative sizes between the elements of the multiple building elements (S272). Next, the spatial shape calculation unit 83 calculates the display shapes of multiple building elements, such as multiple building elements, so that they are reflected in the operator's vision as being equivalent to reality. Next, the three-dimensional display unit 84 displays the building elements in three dimensions on the virtual three-dimensional space based on the results calculated by the alignment unit 82 and the spatial shape calculation unit 83, etc. Figures 43-50 show the three-dimensional shape of a building displayed in a virtual three-dimensional space based on the evaluation building drawings and evaluation building information. By reviewing these three-dimensional assembly drawings, it becomes possible to accurately grasp the relative positions and sizes of multiple building elements, thereby minimizing human error in house evaluations.

[0083] (Embodiment 2) [Information Processing Device] Figure 51 is a block diagram of the information processing device 2 according to Embodiment 2 of the present invention. As shown in Figure 51, the information processing device 2 according to Embodiment 2 of the present invention differs from the information processing device 1 according to Embodiment 1 of the present invention in that, instead of a boundary identification unit 15 that compares grid lines along a building module based on building drawings and building information with evaluation base building information and identifies evaluation base building components and evaluation base building equipment that meet predetermined conditions as boundary lines constituting a building, it extracts grid lines composed of meridians and latitudes along a rectangle of a building module calculated based on building drawings and building information, or grid lines composed of meridians and latitudes composed of a rectangle of any size, compares the grid lines with the evaluation base building information, and identifies evaluation base building components and evaluation base building equipment that overlap with the grid lines as boundary lines constituting a building.

[0084] Furthermore, as shown in Figure 52, the boundary identification unit 215 according to Embodiment 2 of the present invention includes a boundary line movement unit 1151, an arbitrary boundary line movement unit 1152, and a boundary line determination unit 1153. The boundary line movement unit 1151 compares the grid lines of the building module unit with the evaluation base building information and moves evaluation base building components and evaluation base building equipment that do not overlap with the grid lines but belong to a certain width range of the grid lines so that they overlap with the nearest grid line. The arbitrary boundary line movement unit 1152 moves the identified boundary line to an arbitrary position based on the evaluation base building drawings and evaluation base building information. The boundary determination unit 1153 determines the boundary line as the wall boundary after the movement. The boundary identification unit 215 identifies the evaluation base building components and evaluation base building equipment moved by the boundary line movement unit 1151 and / or arbitrary boundary line movement unit 1152 as boundaries constituting the building.

[0085] [Information Processing Methods] Figure 53 is a flowchart illustrating the information processing method using the information processing device 2 according to Embodiment 2 of the present invention. The information processing method by the information processing device 2 according to Embodiment 2 of the present invention differs from the information processing method by the information processing device 1 according to Embodiment 1 of the present invention in that, as shown in Figure 53, it includes a boundary identification step (S25) in which it extracts grid lines composed of meridians and parallels along the rectangle of the building module calculated based on the building drawing and building information, or grid lines composed of meridians and parallels composed of rectangles of arbitrary size, compares the grid lines with the evaluation base building information, and identifies evaluation base building components and evaluation base building equipment that overlap with the grid lines as boundary lines constituting the building. Here, as shown in Figure 54, the information processing method by the information processing device 2 according to Embodiment 2 of the present invention allows the correction unit 217 to correct (S35-1) to adjust and move the boundary after it has identified (S35) based on the operator's instructions, the control unit 10 to correct (S36-1) to adjust and change the size, type, etc. of the room after it has identified (S36) based on the operator's instructions, and the correction (S37-1) to adjust and move the wall after it has identified (S37) based on the operator's instructions.

[0086] Figure 55 is a flowchart illustrating the process by which the boundary identification unit 215 identifies the boundary. The boundary line movement unit 1151 of the boundary identification unit 215 moves the boundary formed by the evaluation base building components and evaluation base building equipment to the grid line set on the evaluation base building (S351). The arbitrary boundary line movement unit 1152 of the boundary identification unit 215 moves the boundary, which is composed of evaluation base building components and evaluation base building equipment, to any position according to the operator's instructions and as necessary (S352). Next, the boundary determination unit 1153 of the boundary identification unit 215 determines the boundary moved by the boundary movement unit 1151 and / or the arbitrary boundary movement unit 1152 as the appropriate boundary.

[0087] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the invention is indicated by the claims, not in the sense described above, and all modifications are intended to be in the sense and scope equivalent to the claims.

[0088] Furthermore, the processes or operations described above can be freely modified, as long as no inconsistencies arise in the processes or operations, such as using data that should not yet be available at a given step. The embodiments described above are merely examples for illustrating the present invention, and the present invention is not limited to these embodiments. The present invention can be implemented in various forms without departing from its essence. [Explanation of Symbols]

[0089] 1. Information Processing Device 10 Control Unit 11, 211 Reading section 12, 212 Processing section 13,213 Training Data Acquisition Unit 14,214 Evaluation Basic Information Acquisition Department 15, 215 Boundary identification part 16, 216 Room Identification Section 17, 217 Correction section 18, 218 Wall specific part 19, 219 Evaluation Information Acquisition Department 20, 220 Output section 30, 230 Communications Department 40, 240 Input section 50, 250 Main memory 60, 260 Auxiliary storage 61,261 Drawings / Information Database 62,262 Learning Models 63,263 programs 70, 270 display section 80,280 Three-dimensional processing units 81, 281 Three-dimensional transformation unit 82, 282 matching part 83, 283 Space shape calculation section 84, 284 3D display section 85, 285 3D Editorial Department 151 Grid line extraction section 152 Boundary Determination Section 161 Lot Identification Section 162 Room Identification Unit 1151 Boundary line shift section 1152 Arbitrary boundary line movement part 1153 Boundary Determination Section N Network

Claims

1. A reading unit that reads building drawings that include at least one of the building components and building equipment, and building information which is detailed information relating to the building components and building equipment, A processing unit that applies labeling and coloring to the building components and building equipment provided in the building drawings, and adds information related to the processing to the building information, A training data acquisition unit acquires, as training data, a processed building drawing comprising at least one of processed building components and processed building equipment processed by the processing unit based on the building drawing and the building information, and processed building information which is detailed information relating to the processed building components and the processed building equipment. A learning model that, upon input data comprising the aforementioned building drawings and building information, outputs evaluation base building drawings and evaluation base building information identical to the processed building drawings and processed building information, respectively, based on the training data, and further outputs evaluation base building components and evaluation base building equipment identical to the processed building components and processed building equipment contained in the processed building drawings, respectively, and an evaluation base information acquisition unit that inputs the building drawings and building information and acquires the evaluation base building drawings and evaluation base building information, and the evaluation base building components and evaluation base building equipment contained in the evaluation base building drawings, A boundary identification unit compares grid lines along building modules based on the building drawings and building information with the evaluation base building information, and identifies the evaluation base building components and evaluation base building equipment that meet predetermined conditions as boundary lines constituting the building, A wall identification unit that identifies detailed information about the wall, including the type and size of the wall, based on the boundary line and the evaluation base building drawing and the evaluation base building information, A room identification unit that identifies detailed information about the room, including the type of room and the size of the room, based on the boundary line, the evaluation base building drawing and the evaluation base building information, An information processing device comprising an output unit that outputs evaluation data necessary for house evaluation based on the evaluation base building drawings and evaluation base building information, detailed information of the room obtained by the room identification unit and detailed information of the wall obtained by the wall identification unit.

2. The boundary identification unit is, A grid line extraction unit extracts grid lines composed of meridians and parallels along the building module calculated based on the building drawings and building information, or grid lines composed of meridians and parallels of an arbitrary size. A boundary determination unit compares the grid lines with the evaluation base building drawing, and when wall information, which is information about the exterior and interior walls contained in the evaluation base building drawing and the evaluation base building information, is included in the grid line band at a certain distance from the grid lines, the boundary line determination unit determines the boundary line with the overlapping portion of the wall information and the grid as the boundary of the wall. The information processing apparatus according to claim 1, characterized by comprising the above.

3. The aforementioned room identification unit is, A partition identification unit identifies the area enclosed by the boundary line as a partition of a separate space within the building, based on the aforementioned boundary line. The room identification unit identifies the type of room in a section by applying the label and color information contained in the evaluation foundation building drawings and evaluation foundation building information, which include the evaluation foundation building components and evaluation foundation building equipment, to each pixel of the corresponding section, and by adopting the label and color information of the most frequent type within the section. The information processing apparatus according to claim 2, characterized by comprising the above.

4. The information processing apparatus according to claim 3, further comprising a correction unit that corrects the boundary line identified by the boundary identification unit by adjusting and moving it to an arbitrary position, and / or corrects the detailed information of the room identified by the room identification unit and / or the detailed information of the wall identified by the wall identification unit.

5. The information processing apparatus according to claim 4, further comprising an evaluation information acquisition unit that acquires an evaluation building drawing and evaluation building information based on the evaluation base building drawing and evaluation base building information, detailed information of the room acquired by the room identification unit and detailed information of the wall acquired by the wall identification unit.

6. An information processing device that generates the evaluation building drawings and evaluation building information acquired by the evaluation information acquisition unit as a virtual three-dimensional building model on a virtual three-dimensional space composed of a three-dimensional Cartesian coordinate system, A three-dimensional transformation unit applies the elements constituting the shapes of the walls and fixtures in the aforementioned evaluation building drawings and evaluation building information to the three-dimensional Cartesian coordinate system, A matching unit that aligns the relative positional relationship of the walls and fixtures in the evaluation building drawings and the evaluation building information, A spatial shape calculation unit calculates the interior and exterior shapes of the building in the virtual three-dimensional space based on the matching results obtained by matching the evaluation building drawings, the evaluation building information, and the matching unit, The information processing apparatus according to claim 5, further comprising a three-dimensional display unit that displays the building, composed of the evaluation building drawing and the evaluation building information, as an image in the virtual three-dimensional space based on the calculation results from the spatial shape calculation unit.

7. The information processing apparatus according to claim 6, further comprising a three-dimensional editing unit that receives editing instructions to move, change, delete, or process the evaluation building drawings and evaluation building information in the virtual three-dimensional space, and edits the evaluation building drawings and evaluation building information in accordance with the received editing instructions.

8. A reading step of reading a building drawing that includes at least one of the building components and building equipment, and building information which is detailed information relating to the building components and building equipment, A processing step involves labeling and coloring the building components and building equipment provided in the building drawings, and adding information related to the processing to the building information. A training data acquisition step is performed to acquire, as training data, a processed building drawing comprising at least one of the processed building components and processed building equipment processed based on the building drawing and the building information, respectively, and processed building information which is detailed information relating to the processed building components and the processed building equipment. An evaluation base information acquisition step involves inputting the building drawings and building information into a learning model that, upon inputting the building drawings and building information, outputs evaluation base building drawings and evaluation base building information identical to the processed building drawings and processed building information, respectively, based on the training data, and further outputs evaluation base building components and evaluation base building equipment identical to the processed building components and processed building equipment contained in the processed building drawings, respectively, and acquiring evaluation base information, the evaluation base building drawings and evaluation base building information, and the evaluation base building components and evaluation base building equipment contained in the evaluation base building drawings, respectively. A boundary identification step involves comparing grid lines along building modules based on the building drawings and building information with the evaluation base building information, and identifying the evaluation base building components and evaluation base building equipment that meet predetermined conditions as boundary lines constituting the building; A wall identification step that identifies detailed information about the wall, including the type of wall and the size of the wall, based on the boundary line, the evaluation base building drawing and the evaluation base building information, A room identification step that identifies detailed information about the room, including the type of room and the size of the room, based on the boundary line, the evaluation base building drawing and the evaluation base building information, An information processing method characterized by including an output step that outputs evaluation data necessary for house evaluation based on the evaluation base building drawings and evaluation base building information, detailed information of the room obtained by the room identification step and detailed information of the wall obtained by the wall identification step.

9. The boundary identification step described above is: A grid line extraction step of extracting grid lines composed of meridians and parallels along the building module calculated based on the building drawings and building information, or grid lines composed of meridians and parallels of an arbitrary size, The information processing method according to claim 8, characterized in that it includes a boundary determination step of comparing the grid lines with the evaluation base building drawing, and determining the boundary line when the wall information, which is information relating to the exterior and interior walls contained in the evaluation base building drawing and the evaluation base building information, is included in the grid line band having a certain distance from the grid lines, and the overlapping portion of the wall information and the grid is used as the boundary of the wall.

10. The aforementioned room identification step is, A partition identification step in which, based on the aforementioned boundary line, the area enclosed by the boundary line is identified as a partition of a separated space within the building, The information processing method according to claim 9, further comprising a room identification step of identifying the type of room for a section by applying the label and color information contained in the evaluation foundation building drawing and evaluation foundation building information, which include the evaluation foundation building components and the evaluation foundation building equipment, to each pixel of the corresponding section, and adopting the most common type of label and color information within the section.

11. The information processing method according to claim 10, further comprising a correction step of correcting the boundary line identified in the boundary identification step by adjusting and moving it to an arbitrary position, and / or correcting the detailed information of the room identified in the room identification step and / or the detailed information of the wall identified in the wall identification step.

12. The information processing method according to claim 11, further comprising an evaluation information acquisition step of acquiring evaluation building drawings and evaluation building information based on the evaluation base building drawings and evaluation base building information, detailed information of the room acquired by the room identification step and detailed information of the wall acquired by the wall identification step.

13. The information processing method comprises generating the acquired evaluation building drawings and evaluation building information as a virtual three-dimensional building model on a virtual three-dimensional space composed of a three-dimensional Cartesian coordinate system, wherein the evaluation information acquisition step generates the acquired evaluation building drawings and evaluation building information as a virtual three-dimensional building model on a virtual three-dimensional space composed of a three-dimensional Cartesian coordinate system. A three-dimensional transformation step in which the elements constituting the shape of the walls and fixtures in the evaluation building drawings and evaluation building information are applied to the three-dimensional Cartesian coordinate system, A matching step to align the relative positional relationship of the walls and fixtures in the evaluation building drawings and the evaluation building information, A spatial shape calculation step that calculates the interior and exterior shapes of the building in the virtual three-dimensional space based on the matching result obtained by matching the evaluation building drawings, the evaluation building information, and the matching step, The information processing method according to claim 12, further comprising a three-dimensional display step of displaying the building, which is composed of the evaluation building drawing and the evaluation building information, as an image in the virtual three-dimensional space based on the calculation result of the spatial shape calculation step.

14. The information processing method according to claim 13, further comprising a three-dimensional editing step of receiving editing instructions to move, change, delete, or process the evaluation building drawings and evaluation building information in the virtual three-dimensional space, and editing the evaluation building drawings and evaluation building information in accordance with the received editing instructions.

15. A reading step of reading a building drawing that includes at least one of the building components and building equipment, and building information which is detailed information relating to the building components and building equipment, A processing step involves labeling and coloring the building components and building equipment provided in the building drawings, and adding information related to the processing to the building information. A training data acquisition step is performed to acquire, as training data, a processed building drawing comprising at least one of the processed building components and processed building equipment processed based on the building drawing and the building information, respectively, and processed building information which is detailed information relating to the processed building components and the processed building equipment. An evaluation base information acquisition step involves inputting the building drawings and building information into a learning model that, upon inputting the building drawings and building information, outputs evaluation base building drawings and evaluation base building information identical to the processed building drawings and processed building information, respectively, based on the training data, and further outputs evaluation base building components and evaluation base building equipment identical to the processed building components and processed building equipment contained in the processed building drawings, respectively, and acquiring evaluation base information, the evaluation base building drawings and evaluation base building information, and the evaluation base building components and evaluation base building equipment contained in the evaluation base building drawings, respectively. A boundary identification step involves comparing grid lines along building modules based on the building drawings and building information with the evaluation base building information, and identifying the evaluation base building components and evaluation base building equipment that meet predetermined conditions as boundary lines constituting the building; A wall identification step that identifies detailed information about the wall, including the type of wall and the size of the wall, based on the boundary line, the evaluation base building drawing and the evaluation base building information, A room identification step that identifies detailed information about the room, including the type of room and the size of the room, based on the boundary line, the evaluation base building drawing and the evaluation base building information, A computer program characterized by causing a computer to perform a process that includes an output step of outputting evaluation data necessary for house evaluation based on the evaluation base building drawings and evaluation base building information, detailed information of the room obtained by the room identification step and detailed information of the wall obtained by the wall identification step.

16. A persistent computer-readable storage medium, wherein the persistent computer-readable storage medium stores computer instructions, the computer instructions enable a computer to carry out the method according to any one of claims 8 to 15.

17. A reading unit that reads building drawings that include at least one of the building components and building equipment, and building information which is detailed information relating to the building components and building equipment, A processing unit that applies labeling and coloring to the building components and building equipment provided in the building drawings, and adds information related to the processing to the building information, A training data acquisition unit acquires, as training data, a processed building drawing comprising at least one of processed building components and processed building equipment processed by the processing unit based on the building drawing and the building information, and processed building information which is detailed information relating to the processed building components and the processed building equipment. A learning model that, upon input data comprising the aforementioned building drawings and building information, outputs evaluation base building drawings and evaluation base building information identical to the processed building drawings and processed building information, respectively, based on the training data, and further outputs evaluation base building components and evaluation base building equipment identical to the processed building components and processed building equipment contained in the processed building drawings, respectively, and an evaluation base information acquisition unit that inputs the building drawings and building information and acquires the evaluation base building drawings and evaluation base building information, and the evaluation base building components and evaluation base building equipment contained in the evaluation base building drawings, A boundary identification unit extracts grid lines composed of meridians and parallels along the rectangle of the building module calculated based on the building drawings and building information, or grid lines composed of meridians and parallels from a rectangle of any size, compares the grid lines with the evaluation base building information, and identifies the evaluation base building components and evaluation base building equipment that overlap with the grid lines as boundary lines constituting the building, A wall identification unit that identifies detailed information about the wall, including the type and size of the wall, based on the boundary line, the evaluation base building drawing, and the evaluation base building information, A room identification unit that identifies detailed information about the room, including the type of room and the size of the room, based on the boundary line, the evaluation base building drawing, and the evaluation base building information, An information processing device comprising an output unit that outputs evaluation data necessary for house evaluation based on the evaluation base building drawings and evaluation base building information, detailed information of the room obtained by the room identification unit and detailed information of the wall obtained by the wall identification unit.

18. The boundary identification unit is, A boundary line movement unit compares the grid lines of the building module unit with the evaluation base building information and moves the evaluation base building components and evaluation base building equipment that do not overlap with the grid lines but belong to a certain width range of the grid lines so as to overlap with the nearest grid line. An arbitrary boundary line movement unit that moves the identified boundary line to an arbitrary position based on the evaluation base building drawings and the evaluation base building information, The system includes a boundary determination unit that determines the boundary line after the movement, using the boundary line as the boundary of the wall, The information processing device according to claim 17, characterized in that the evaluation foundation building components and evaluation foundation building equipment moved by the boundary line moving unit and / or the arbitrary boundary line moving unit are identified as boundaries constituting the building.

19. The aforementioned room identification unit is, A partition identification unit identifies the area enclosed by the boundary line as a partition of a separate space within the building, based on the aforementioned boundary line. The room identification unit identifies the type of room in a section by applying the label and color information contained in the evaluation foundation building drawings and evaluation foundation building information, which include the evaluation foundation building components and evaluation foundation building equipment, to each pixel of the corresponding section, and by adopting the label and color information of the most frequent type within the section. The information processing apparatus according to claim 18, characterized by comprising the above.

20. The information processing apparatus according to claim 19, further comprising a correction unit that corrects the boundary line identified by the boundary identification unit by adjusting and moving it to an arbitrary position, and / or corrects the detailed information of the room identified by the room identification unit and / or the detailed information of the wall identified by the wall identification unit.

21. The information processing apparatus according to claim 20, further comprising an evaluation information acquisition unit that acquires evaluation building drawings and evaluation building information based on the evaluation base building drawings and evaluation base building information, detailed information of the room acquired by the room identification unit and detailed information of the wall acquired by the wall identification unit.

22. An information processing device that generates the evaluation building drawings and evaluation building information acquired by the evaluation information acquisition unit as a virtual three-dimensional building model on a virtual three-dimensional space composed of a three-dimensional Cartesian coordinate system, A three-dimensional transformation unit applies the elements constituting the shapes of the walls and fixtures in the aforementioned evaluation building drawings and evaluation building information to the three-dimensional Cartesian coordinate system, A matching unit that aligns the relative positional relationship of the walls and fixtures in the evaluation building drawings and the evaluation building information, A spatial shape calculation unit calculates the interior and exterior shapes of the building in the virtual three-dimensional space based on the matching results obtained by matching the evaluation building drawings, the evaluation building information, and the matching unit, A three-dimensional display unit displays the building, which is composed of the evaluation building drawing and the evaluation building information, as an image in the virtual three-dimensional space based on the calculation results by the spatial shape calculation unit. The information processing apparatus according to claim 21, further comprising the above.

23. The information processing apparatus according to claim 22, further comprising a three-dimensional editing unit that receives editing instructions to move, change, delete, or process the evaluation building drawings and evaluation building information in the virtual three-dimensional space, and edits the evaluation building drawings and evaluation building information in accordance with the received editing instructions.

24. A reading step of reading a building drawing that includes at least one of the building components and building equipment, and building information which is detailed information relating to the building components and building equipment, A processing step involves labeling and coloring the building components and building equipment provided in the building drawings, and adding information related to the processing to the building information. A training data acquisition step is performed to acquire, as training data, a processed building drawing comprising at least one of the processed building components and processed building equipment processed based on the building drawing and the building information, respectively, and processed building information which is detailed information relating to the processed building components and the processed building equipment. An evaluation base information acquisition step involves inputting the building drawings and building information into a learning model that, upon inputting the building drawings and building information, outputs evaluation base building drawings and evaluation base building information identical to the processed building drawings and processed building information, respectively, based on the training data, and further outputs evaluation base building components and evaluation base building equipment identical to the processed building components and processed building equipment contained in the processed building drawings, respectively, and acquiring evaluation base information, the evaluation base building drawings and evaluation base building information, and the evaluation base building components and evaluation base building equipment contained in the evaluation base building drawings, respectively. A boundary identification step involves extracting grid lines composed of meridians and parallels along the rectangle of the building module calculated based on the building drawings and building information, or grid lines composed of meridians and parallels from a rectangle of any size, comparing the grid lines with the evaluation base building information, and identifying the evaluation base building components and evaluation base building equipment that overlap with the grid lines as boundary lines constituting the building; A wall identification step, which identifies detailed information about the wall, including the type of wall and the size of the wall, based on the boundary line, the evaluation base building drawing, and the evaluation base building information, A room identification step that identifies detailed information about the room, including the type of room and the size of the room, based on the boundary line, the evaluation base building drawing, and the evaluation base building information, An information processing method characterized by including an output step that outputs evaluation data necessary for house evaluation based on the evaluation base building drawings and evaluation base building information, detailed information of the room obtained by the room identification step and detailed information of the wall obtained by the wall identification step.

25. The boundary identification step described above is: A boundary line movement step involves comparing the grid lines of the building module unit with the evaluation base building information, and moving the evaluation base building components and evaluation base building equipment that do not overlap with the grid lines but belong to a certain width range of the grid lines so that they overlap with the nearest grid line. An arbitrary boundary line movement step is performed to move the identified boundary line to an arbitrary position based on the evaluation base building drawing and the evaluation base building information. The system includes a boundary determination step of determining the boundary line after movement, with the boundary line after movement being the boundary line of the wall, The information processing method according to claim 24, characterized in that the evaluation foundation building components and evaluation foundation building equipment moved by the boundary line movement step and / or the arbitrary boundary line movement step are identified as boundaries constituting the building.

26. The aforementioned room identification step is, A partition identification step in which, based on the aforementioned boundary line, the area enclosed by the boundary line is identified as a partition of a separated space within the building, Room identification step: Apply the label and color information contained in the evaluation foundation building drawing and evaluation foundation building information, which include the evaluation foundation building components and evaluation foundation building equipment, to each pixel of the corresponding section, and select the label and color information of the most frequent type within the section to identify the type of room for the section. The information processing method according to claim 25, characterized by including the following.

27. The information processing method according to claim 26, further comprising a correction step of correcting the boundary line identified in the boundary identification step by adjusting and moving it to an arbitrary position, and / or correcting the detailed information of the room identified in the room identification step and / or the detailed information of the wall identified in the wall identification step.

28. The information processing method according to claim 27, further comprising an evaluation information acquisition step of acquiring evaluation building drawings and evaluation building information based on the evaluation base building drawings and evaluation base building information, detailed information of the room acquired by the room identification step and detailed information of the wall acquired by the wall identification step.

29. The information processing device generates the evaluation building drawings and evaluation building information acquired in the evaluation information acquisition step as a virtual three-dimensional building model on a virtual three-dimensional space composed of a three-dimensional Cartesian coordinate system, A three-dimensional transformation step in which the elements constituting the shape of the walls and fixtures in the evaluation building drawings and evaluation building information are applied to the three-dimensional Cartesian coordinate system, A matching step to align the relative positional relationship of the walls and fixtures in the evaluation building drawings and the evaluation building information, A spatial shape calculation step that calculates the interior and exterior shapes of the building in the virtual three-dimensional space based on the matching result obtained by matching the evaluation building drawings, the evaluation building information, and the matching step, A three-dimensional display step, which displays the building, composed of the evaluation building drawing and the evaluation building information, as an image in the virtual three-dimensional space based on the calculation results from the spatial shape calculation step. The information processing method according to claim 28, further comprising the above.

30. The information processing method according to claim 29, further comprising a three-dimensional editing step of receiving editing instructions to move, change, delete, or process the evaluation building drawings and evaluation building information in the virtual three-dimensional space, and editing the evaluation building drawings and evaluation building information in accordance with the received editing instructions.

31. A reading step of reading a building drawing that includes at least one of the building components and building equipment, and building information which is detailed information relating to the building components and building equipment, A processing step involves labeling and coloring the building components and building equipment provided in the building drawings, and adding information related to the processing to the building information. A training data acquisition step is performed to acquire, as training data, a processed building drawing comprising at least one of the processed building components and processed building equipment processed based on the building drawing and the building information, respectively, and processed building information which is detailed information relating to the processed building components and the processed building equipment. An evaluation base information acquisition step involves inputting the building drawings and building information into a learning model that, upon inputting the building drawings and building information, outputs evaluation base building drawings and evaluation base building information identical to the processed building drawings and processed building information, respectively, based on the training data, and further outputs evaluation base building components and evaluation base building equipment identical to the processed building components and processed building equipment contained in the processed building drawings, respectively, and acquiring evaluation base information, the evaluation base building drawings and evaluation base building information, and the evaluation base building components and evaluation base building equipment contained in the evaluation base building drawings, respectively. A boundary identification step involves extracting grid lines composed of meridians and parallels along the rectangle of the building module calculated based on the building drawings and building information, or grid lines composed of meridians and parallels from a rectangle of any size, comparing the grid lines with the evaluation base building information, and identifying the evaluation base building components and evaluation base building equipment that overlap with the grid lines as boundary lines constituting the building; A wall identification step, which identifies detailed information about the wall, including the type of wall and the size of the wall, based on the boundary line, the evaluation base building drawing, and the evaluation base building information, A room identification step that identifies detailed information about the room, including the type of room and the size of the room, based on the boundary line, the evaluation base building drawing, and the evaluation base building information, A computer program characterized by causing a computer to perform a process that includes an output step of outputting evaluation data necessary for house evaluation based on the evaluation base building drawings and evaluation base building information, detailed information of the room obtained by the room identification step and detailed information of the wall obtained by the wall identification step.

32. A persistent computer-readable storage medium, wherein the persistent computer-readable storage medium stores computer instructions, the computer instructions enable a computer to carry out the method according to any one of claims 24 to 31.

Images