Information processing device, information processing method, and program
The information processing device uses architectural model data to estimate user reactions to interior design by identifying space features and applying a learning model, allowing for effective evaluation of design impact.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- GEOCREATES INC
- Filing Date
- 2024-12-19
- Publication Date
- 2026-07-01
Smart Images
Figure 2026109007000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.
Background Art
[0002] Conventionally, in building design, building model data such as BIM (Building Information Modeling) data has been generated using CAD (Computer Aided Design) software or the like. For example, Patent Document 1 discloses an apparatus for generating BIM data including information related to the interior of a building.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] When designing the interior of a building, it is required to evaluate what kind of influence the designed interior has on users. In contrast, there has been a problem that building model data including information related to the interior of a building has not been effectively utilized.
[0005] Therefore, the present invention has been made in view of these points, and an object thereof is to enable evaluation of the influence of the interior on users by using building model data including information related to the interior.
Means for Solving the Problems
[0006] An information processing device according to a first aspect of the present invention includes: an acquisition unit that acquires architectural model data showing the three-dimensional shape of a building including the interior space of the building and the state of the interior of the building; an identification unit that identifies features of the interior space of the building that can be seen by a user based on the three-dimensional shape of the interior space of the building shown by the architectural model data acquired by the acquisition unit and the state of the interior; an estimation unit that estimates the user's reaction to the interior space by inputting information showing the features of the interior space identified by the identification unit to a learning model that outputs information showing the user's reaction corresponding to the features in response to input information showing the features, and acquiring information showing the user's reaction corresponding to the features of the interior space from the learning model; and an output unit that outputs information showing the reaction estimated by the estimation unit.
[0007] The acquisition unit acquires the architectural model data showing the shape and placement of each of the multiple objects constituting the interior of the building, and the identification unit may identify the amount of wall or floor space in the interior of the building that is visible to the user as the characteristic, based on the three-dimensional shape of the interior space of the building and the shape and placement of each of the multiple objects constituting the interior.
[0008] The acquisition unit acquires the architectural model data showing the shape and placement position of each of the multiple objects constituting the interior of the building, and the identification unit may identify as a feature the curvature ratio, which represents the ratio of the number of curved parts visible to the user in the interior space to the number of shaped parts visible to the user in the interior space, based on the three-dimensional shape of the interior space of the building and the shape and placement position of each of the multiple objects constituting the interior space.
[0009] The acquisition unit acquires the architectural model data showing the shape, placement, and material of each of the multiple objects constituting the interior of the building, and the identification unit may identify the ratio of the surface area of an object made of a predetermined material to the surface area of the building and the objects visible to the user in the interior space as the characteristic, based on the three-dimensional shape of the interior space of the building and the shape, placement, and material of each of the multiple objects constituting the interior.
[0010] The acquisition unit acquires the architectural model data showing the shape, placement position, and color of each of the multiple objects constituting the interior of the building, and the identification unit may identify the ratio of the surface area of an object of a predetermined color to the surface area of the building and the objects visible to the user in the interior space, based on the three-dimensional shape of the interior space of the building and the shape, placement position, and color of each of the multiple objects constituting the interior, as the characteristic.
[0011] The estimation unit inputs information indicating the features of the internal space identified by the identification unit into the learning model, which outputs information indicating the user's psychological state as a user's response to the features, and obtains information indicating the user's psychological state corresponding to the features of the internal space from the learning model, thereby estimating the psychological state of the user when the user is present in the internal space, and the output unit may output the information indicating the psychological state estimated by the estimation unit.
[0012] The estimation unit inputs information indicating the features of the internal space identified by the identification unit into the learning model, which outputs the user's biological information indicating the user's biological response corresponding to the features, in response to input information indicating the features, and obtains the user's biological information corresponding to the features of the internal space from the learning model to estimate the user's biological response when the user is present in the internal space. The output unit may output the biological information indicating the biological response estimated by the estimation unit.
[0013] The learning model may be a model that has been trained using as training data information that indicates the characteristics of the interior space identified by analyzing each of the multiple images taken of the interior space of each of the multiple buildings, and information that indicates the user's reaction when the user views each of the multiple images.
[0014] The identifying unit may define the interior space shown in the captured image obtained by photographing the interior space of the building with an omnidirectional camera capable of capturing images in all directions at the user's position in the building corresponding to the architectural model data as the interior space of the building visible to the user, and identify the characteristics of said interior space.
[0015] A second aspect of the present invention relates to an information processing method comprising: acquiring architectural model data, which is executed by a computer, that shows the three-dimensional shape of a building including its interior space and the state of the interior of the building; identifying features of the interior space of the building that are visible to the user based on the three-dimensional shape of the interior space of the building shown in the acquired architectural model data and the state of the interior; estimating the user's reaction to the interior space by inputting information showing the identified features of the interior space to a learning model that outputs information showing the user's reaction corresponding to the features in response to input information showing the features, and acquiring information showing the user's reaction corresponding to the features of the interior space from the learning model; and outputting the estimated information showing the reaction.
[0016] A program according to a third aspect of the present invention causes a computer to function as: an acquisition unit that acquires architectural model data showing the three-dimensional shape of a building including its interior space and the state of the interior of the building; an identification unit that identifies features of the interior space of the building that are visible to the user based on the three-dimensional shape of the interior space of the building shown by the architectural model data acquired by the acquisition unit and the state of the interior; an estimation unit that estimates the user's reaction to the interior space by inputting information showing the features of the interior space identified by the identification unit into a learning model that outputs information showing the user's reaction corresponding to the features in response to input information showing the features, and acquiring information showing the user's reaction corresponding to the features of the interior space from the learning model; and an output unit that outputs information showing the reaction estimated by the estimation unit. [Effects of the Invention]
[0017] According to the present invention, it is possible to evaluate the impact of interior design on users by using architectural model data that includes information about the interior design. [Brief explanation of the drawing]
[0018] [Figure 1] This is a diagram illustrating the overview of an information processing device. [Figure 2] This diagram shows the functional configuration of an information processing device. [Figure 3] This figure shows examples of identifying parts with a shape that can be separated and viewed. [Figure 4] This figure shows an example of the analysis results screen. [Modes for carrying out the invention]
[0019] [Overview of Information Processing Device 1] FIG. 1 is a diagram showing an overview of the information processing apparatus 1. The information processing apparatus 1 is a computer that estimates a user's reaction to a space. The information processing apparatus 1 is communicably connected to an analyst terminal 2 used by an analyst A who analyzes the user's reaction to the space. The user is a person who uses the space. For example, when the space is an interior space of a building, the user is a person who passes through the interior space of the building or a person who stays inside the building.
[0020] The information processing apparatus 1 acquires building model data, which is three-dimensional model data showing the three-dimensional shape of a predetermined building corresponding to the space for which the user's reaction is to be estimated and showing the state of the interior decoration in the building, from the analyst terminal 2 ((1) in FIG. 1). The information processing apparatus 1 specifies the features of the interior space of the building visible to the user based on the three-dimensional shape of the interior space of the building shown by the acquired building model data and the state of the interior decoration of the building ((2) in FIG. 1).
[0021] The information processing apparatus 1 can estimate the user's reaction using a learning model that outputs reaction information, which is information indicating the user's reaction corresponding to the feature, in response to the input of feature information, which is information indicating the features of the interior space of the building. The user's reaction is, for example, the impression the user has of the building after visually recognizing the entire interior space of the building or a biological reaction for specifying the impression. The information processing apparatus 1 inputs the feature information indicating the specified features of the interior space into the learning model ((3) in FIG. 1) and acquires the reaction information corresponding to the feature from the learning model ((4) in FIG. 1), thereby estimating the user's reaction to the interior space.
[0022] The information processing apparatus 1 outputs the reaction information indicating the estimated user's reaction to the analyst terminal 2 ((5) in FIG. 1). By doing so, the information processing apparatus 1 can evaluate the influence of the interior decoration of the building on the user using the building model data including information on the interior decoration of the building.
[0023] [Functional Configuration of Information Processing Apparatus 1] Next, we will explain the functional configuration of the information processing device 1. Figure 2 is a diagram showing the functional configuration of the information processing device 1. The information processing device 1 comprises a communication unit 11, a storage unit 12, and a control unit 13. The communication unit 11 is a communication interface for sending and receiving data with the analyst terminal 2 via networks such as the Internet or Wi-Fi, or short-range wireless communication such as Bluetooth (registered trademark).
[0024] The memory unit 12 is, for example, a ROM (Read Only Memory) and a RAM (Random Access Memory). The memory unit 12 stores various programs for making the information processing device 1 function. For example, the memory unit 12 stores a program that makes the control unit 13 of the information processing device 1 function as an acquisition unit 131, a identification unit 132, an estimation unit 133, and an output unit 134.
[0025] Furthermore, the memory unit 12 stores a program that functions as a learning model, which, in response to input of feature information indicating the characteristics of the interior space of a building, outputs psychological state information indicating the user's psychological state as response information indicating the user's reaction corresponding to said features. The learning model is a model that has been trained using information indicating the characteristics of the interior space identified by analyzing multiple images taken of the interior space of each of multiple buildings, and response information indicating the user's reaction when the user views each of those multiple images, as training data.
[0026] Here, the characteristics of the interior space include, for example, the amount of walls and floors in the interior space, the curvature ratio, the green view ratio, and the wood view ratio. The curvature ratio is the ratio of the number of curved parts visible to the user in the interior space to the total number of parts with shapes visible to the user in the interior space. The wood / green view ratio is the proportion of green objects, etc. that are visible. The wood view ratio is the proportion of wooden objects, etc. that are visible in the interior space. The user's psychological state includes the user's mental state, such as a relaxed state, and the emotional state the user experiences, such as a sense of openness, security, and immersion.
[0027] The control unit 13 is, for example, a CPU (Central Processing Unit). The control unit 13 controls the functions of the information processing device 1 by executing various programs stored in the memory unit 12. By executing the programs stored in the memory unit 12, the control unit 13 functions as an acquisition unit 131, a identification unit 132, an estimation unit 133, and an output unit 134.
[0028] The acquisition unit 131 acquires architectural model data that shows the three-dimensional shape of a building, including the interior space of a given building, and the state of the interior of the building. The architectural model data is, for example, interior BIM data that designs the interior of a building. The architectural model data includes building information, which is information about the materials used in the building, and object information, which is information about multiple objects that make up the interior of the building.
[0029] Building information includes information to identify the three-dimensional shape of the building, such as the shape, dimensions, and placement of the components used in the building. It also includes information on the color, materials, and finishes of the components. Object information includes information to identify the interior condition of the building, such as the shape, color, materials, and placement of each of multiple objects within the building.
[0030] The identification unit 132 identifies the features of the building's interior space that are visible to the user, based on the three-dimensional shape of the building's interior space indicated by the architectural model data acquired by the acquisition unit 131 and the state of the building's interior. For example, the identification unit 132 identifies the features of the building's interior space that are visible to the user by identifying the state of the interior space based on the building information and object information included in the architectural model data.
[0031] Specifically, first, the identification unit 132 identifies the three-dimensional shape of the interior space based on the shape, dimensions, and placement of the components included in the building information indicated by the building model data. Then, based on the identified three-dimensional shape of the building's interior space and the shape and placement of each of the multiple objects that constitute the building's interior, as indicated by the object information included in the building model data, the identification unit 132 identifies the amount of wall and floor space visible to the user as characteristics of the building's interior space. Here, the building's interior space visible to the user refers to all the spaces within the building that the user can see by walking around the building.
[0032] For example, the identification unit 132 identifies the surface area of the walls and floors of the interior space in a state where no objects are placed, as the wall quantity and floor quantity, based on the three-dimensional shape of the identified interior space. The identification unit 132 identifies the placement state in which objects are placed in the interior space, based on the shape, dimensions, and placement position of each of the multiple objects included in the object information. Then, the identification unit 132 identifies the surface area of the walls and floors that are shielded by each of the multiple objects in the placement state, as the shielded wall quantity and floor quantity. The identification unit 132 identifies the wall quantity and floor quantity of the building's interior space that is visible to the user as a characteristic of the building's interior space by subtracting the wall quantity and floor quantity that is shielded by each of the multiple objects from the wall quantity and floor quantity of the interior space in a state where no objects are placed.
[0033] Furthermore, the specific unit 132 identifies the ratio of the surface area of an object made of a predetermined material to the surface area of the building and objects visible to the user in the interior space, based on the three-dimensional shape of the building's interior space and the shape, placement, and material of each of the multiple objects that constitute the interior of the building.
[0034] For example, the identification unit 132 identifies the arrangement state, which is the state in which objects are placed in the interior space, based on the shape, dimensions, and placement position of each of the multiple objects included in the object information. Based on the shape, dimensions, and placement position of each of the multiple objects and the shape, dimensions, and placement position of the members included in the building information, the identification unit 132 identifies the positional relationship of each of the multiple objects with respect to the walls and floors of the building's interior space in the arrangement state. Based on the identified positional relationship, the identification unit 132 identifies the parts of each of the multiple objects that are visible to the user in the building's interior space. For example, if an object is placed in contact with a wall and a floor, the identification unit 132 identifies the parts of the object that are not in contact with the wall and floor as the parts of the object that are visible to the user. Then, based on the dimensions of the object corresponding to the identified parts of the object, the identification unit 132 identifies the surface area of the parts of the object that are visible to the user.
[0035] Furthermore, the identification unit 132 uses the sum of the surface areas of the walls and floors, which are the amount of wall and floor space visible to the user within the building's interior, as the visible surface area of the building within the building's interior. The identification unit 132 then identifies the visible surface area of the building and objects within the building's interior by adding the visible surface area of each of the identified objects with the visible surface area of the building within the building's interior.
[0036] Furthermore, the identification unit 132 identifies members and objects that use a predetermined material based on the materials that make up the members used in the building included in the building information and the materials of each of the multiple objects. Based on the shape, dimensions and placement position of each of the multiple members and objects of the predetermined material and the shape, dimensions and placement position of each of the multiple members and objects of other materials, the identification unit 132 identifies the parts of each of the multiple members and objects of the predetermined material that are visible to the user in the arrangement state in which each of the multiple objects is placed.
[0037] The identification unit 132 identifies the surface area of the user-visible portion of the specified material component based on the dimensions of the component corresponding to the user-visible portion of the specified material component. Similarly, the identification unit 132 identifies the surface area of the user-visible portion of the specified material object based on the dimensions of the specified material object and the dimensions of the specified material component and object corresponding to the specified portion.
[0038] The identification unit 132 then identifies the ratio of the surface area of an object made of a predetermined material to the surface area of buildings and objects visible to the user in the identified interior space as a characteristic of the building's interior space. For example, if the predetermined material is wood, the identification unit 132 identifies the wood visibility ratio, which is the ratio of the surface area of wood visible in the interior space to the surface area of buildings and objects visible to the user in the identified interior space, as a characteristic of the building's interior space. In this way, the information processing device 1 can use the wood visibility ratio in the building's interior space as characteristic information for estimating the user's reaction to the interior space.
[0039] Furthermore, the identification unit 132 identifies the ratio of the surface area of an object of a predetermined color to the surface area of the building and objects visible to the user in the interior space, based on the three-dimensional shape of the building's interior space and the shape, placement, and color of each of the multiple objects that constitute the building's interior, as a characteristic of the interior space.
[0040] In this case, as described above, the identification unit 132 identifies the surface area of buildings and objects visible to the user in the interior space. The identification unit 132 also identifies members and objects of a predetermined color based on the colors of the materials constituting the members used in the building included in the building information and the colors of each of the multiple objects. The identification unit 132 identifies the surface area of members and objects using the predetermined color that are visible to the user in the interior space of the building visible to the user.
[0041] The identification unit 132 then identifies the ratio of the surface area of objects of a predetermined color to the surface area of buildings and objects visible to the user in the identified interior space as a characteristic of the building's interior space. For example, if the predetermined color is green, the identification unit 132 identifies the green view ratio, which is the ratio of the surface area of green-colored components and objects visible in the interior space to the surface area of buildings and objects visible to the user in the identified interior space, as a characteristic of the building's interior space. In this way, the information processing device 1 can use the green view ratio in the building's interior space as characteristic information for estimating the user's reaction to the interior space.
[0042] Furthermore, the specific unit 132 identifies a curvature ratio as a characteristic of the building's interior space, which represents the ratio of the number of curved parts visible to the user in the interior space to the number of shaped parts visible to the user in the interior space, based on the three-dimensional shape of the building's interior space and the shape and placement position of each of the multiple objects that constitute the building's interior.
[0043] For example, the identification unit 132 identifies the shapes formed on the wall surface and floor surface within the user's visible range when the multiple objects are arranged, i.e., when the interior is finished, based on the three-dimensional shape of the identified interior space and the shape and placement position of each of the multiple objects, and also identifies the shapes of the multiple objects visible to the user. Then, the identification unit 132 determines whether the user can separately see each of the identified multiple shapes, and identifies the parts of the shapes that the user can separately see.
[0044] Figure 3 shows an example of identifying parts with a shape that can be separated and visually identified. Figure 3(a) shows a part of the internal space of the object whose shape is to be identified, and Figure 3(b) shows an example of identifying parts with a shape that can be separated and visually identified in the internal space shown in Figure 3(a). As shown in Figure 3(b), the identification unit 132 identifies walls, floors, and objects that can be separated by contour lines as parts with a single shape. In the example shown in Figure 3(b), it can be seen that three parts A to C are identified corresponding to the side, two parts D and E are identified for the ceiling, one part F is identified for the floor, and two parts G and H with different shapes are identified for two objects placed on the floor.
[0045] The identification unit 132 counts the number of parts with the identified shape and identifies the number of parts with that shape as the number of parts with a shape that can be separated and visually identified by the user in the internal space. For each of the identified parts with the identified shape, the identification unit 132 determines whether or not it has a curved shape and identifies the number of parts with a curved shape. For example, the identification unit 132 identifies that the number of parts A to H in the space shown in Figure 3(b) is 8, and identifies that the number of parts E, G, and H with a curved shape in the space shown in Figure 3(b) is 3.
[0046] The identification unit 132 identifies the curvature ratio, which is the ratio of the number of curved parts to the number of parts with shapes visible to the identified user, as a characteristic of the building's interior space. The identification unit 132 identifies the curvature ratio in the example shown in Figure 3(b) as 3 / 8 = 37.5%. In this way, the information processing device 1 can use the curvature ratio of the building's interior space as characteristic information for estimating the user's reaction to the interior space.
[0047] Furthermore, the specific unit 132 identifies the characteristics of the building's interior space that can be seen by the user by identifying the state of the interior space based on the building information and object information included in the architectural model data, but is not limited to this.
[0048] The identification unit 132 may define the interior space shown in the captured image obtained by photographing the interior space of the building with an omnidirectional camera capable of capturing images in all directions at multiple locations in the building corresponding to the architectural model data where a user can be positioned, as the interior space of the building visible to the user, and identify the characteristics of said interior space.
[0049] In this case, the identification unit 132 generates a three-dimensional model of the building's interior space based on architectural model data, and places virtual cameras of an omnidirectional camera at multiple locations within the interior space where the user can be positioned. The identification unit 132 may, for example, divide the building's interior space into subspaces of a predetermined size and place a virtual camera in each of the subspaces, or it may receive the placement locations of the virtual cameras from the analyst terminal 2 and place the virtual cameras at the received placement locations.
[0050] The identification unit 132 identifies the interior space visible to the user as the interior space of the building, based on the interior space captured by each of the multiple virtual cameras positioned to photograph the interior space. Then, the identification unit 132 identifies the characteristics of the interior space based on the state of the interior space shown in each of the multiple virtual cameras. In this way, the information processing device 1 can identify the characteristics of the interior space of the building, similar to how the state of the interior space is identified based on building information and object information included in the building model data.
[0051] The estimation unit 133 takes information indicating the characteristics of the interior space of a predetermined building, identified by the identification unit 132, as input to a learning model that outputs response information indicating the user's response corresponding to the characteristic in response to the input of characteristic information indicating a characteristic, and estimates the user's response to the interior space of a predetermined building by obtaining response information indicating the user's response corresponding to the characteristics of the interior space from the learning model.
[0052] When the identification unit 132 identifies the characteristics of the interior space, the estimation unit 133 executes a program stored in the memory unit 12 that functions as a learning model, causing the control unit 13 to function as the learning model. The estimation unit 133 inputs information indicating the characteristics of the interior space identified by the identification unit 132 to the learning model, and obtains psychological state information from the learning model that indicates the psychological state as reaction information indicating the user's reaction to the characteristics, thereby estimating the user's psychological state, which is the user's reaction to the interior space of a given building.
[0053] The output unit 134 outputs reaction information indicating the user's reaction to the interior space of a predetermined building estimated by the estimation unit 133. The output unit 134 also outputs psychological state information indicating the user's psychological state, which is reaction information indicating the user's reaction to the interior space of a predetermined building estimated by the estimation unit 133, to the analyst terminal 2.
[0054] The output unit 134 outputs an analysis results screen to the analyst terminal 2, which includes, for example, a thumbnail image of the architectural model data and graphs showing the state of each of the user's multiple psychological states. Figure 4 shows an example of the analysis results screen. In Figure 4, it can be seen that a radar chart showing the state of each of the user's multiple psychological states is displayed alongside the thumbnail image of the architectural model data. This allows the analyst to understand the user's psychological state when they view the interior space of the building as shown in the architectural model data.
[0055] The output unit 134 outputs a thumbnail image of the architectural model data and psychological state information indicating the user's psychological state to the analysis results screen. However, it may also output feature information indicating the characteristics of the interior space identified by the identification unit 132. In this way, the analyst can understand the characteristics of the interior space based on the analysis results, and can also analyze the correspondence between the characteristics of the interior space and the user's psychological state.
[0056] [Example 1] In the above-described embodiment, the learning model takes feature information indicating the characteristics of the interior space of a building as input and outputs psychological state information indicating the user's psychological state as response information indicating the user's response corresponding to said feature, but it is not limited to this.
[0057] The learning model may output bio-response information indicating the user's biological responses as response information that shows the user's response corresponding to the feature information input. User bio-response information includes heart rate variability and sweating when the user is calm, and states in the user's brainwaves where alpha waves indicating the user is relaxed are detected.
[0058] The estimation unit 133 then inputs information indicating the characteristics of the interior space of a predetermined building, identified by the identification unit 132, into the learning model. By acquiring bio-response information from the learning model as response information indicating the user's reaction corresponding to the characteristics of the interior space, the estimation unit 133 estimates the user's reaction to the interior space of the predetermined building. The output unit 134 then outputs bio-response information indicating the user's bio-response, which is the response information indicating the user's reaction to the interior space of the predetermined building estimated by the estimation unit 133, to the analyst terminal 2. In this way, the analyst can confirm the user's bio-response to the interior space of the building and evaluate the impact of the interior design on the user based on the bio-response.
[0059] Furthermore, the learning model may output, in response to feature information input, response information that indicates the user's response to that feature, including psychological state information indicating the user's psychological state and biological response information indicating the user's biological response.
[0060] The estimation unit 133 then inputs information indicating the characteristics of the interior space of a predetermined building, identified by the identification unit 132, to the learning model. By acquiring psychological state information and bio-response information from the learning model as response information indicating the user's response corresponding to the characteristics of the interior space, the estimation unit 133 estimates the user's response to the interior space of the predetermined building. The output unit 134 then outputs to the analyst terminal 2 the psychological state information indicating the user's psychological state and bio-response information indicating the user's bio-response, which are response information indicating the user's response to the interior space of the predetermined building estimated by the estimation unit 133. In this way, the analyst can confirm the user's psychological state and bio-response to the interior space of the building and evaluate the impact of the interior design on the user based on the psychological state and bio-response.
[0061] [Differentiation 2] Furthermore, in the above-described embodiment, the architectural model data is assumed to be three-dimensional model data showing the three-dimensional shape of a predetermined building, but it is not limited to this. The architectural model data may also be three-dimensional model data showing the three-dimensional shape of a city composed of multiple buildings. In this case, the identification unit 132 identifies the characteristics of the city composed of multiple buildings based on the three-dimensional model data.
[0062] The estimation unit 133 takes information indicating the spatial characteristics of the city identified by the identification unit 132 as input to a learning model that outputs information indicating user responses corresponding to the characteristics of the city, and estimates the user's response to the spatial characteristics of the city by obtaining information indicating user responses corresponding to the spatial characteristics of the city from the learning model. The output unit 134 outputs the information indicating the user's response to the spatial characteristics of the city as shown by the three-dimensional model data, estimated by the estimation unit 133, to the analyst terminal 2. In this way, the analyst can evaluate the impact that the spatial characteristics of the city as shown by the three-dimensional model data have on the user.
[0063] [Effects of this embodiment] As described above, the information processing device 1 according to this embodiment inputs the characteristics of the interior space of a building shown in the architectural model data into a learning model, obtains information from the learning model indicating the user's reaction corresponding to the characteristics of the interior space, estimates the user's reaction to the interior space, and outputs information indicating the estimated user's reaction. In this way, the information processing device 1 can use architectural model data that includes information about the interior of the building to evaluate the impact that the interior of a building has on the user.
[0064] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of its gist. For example, all or part of the apparatus can be configured by functionally or physically distributing and integrating in any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combinations are combined with the effects of the original embodiments. [Explanation of Symbols]
[0065] 1. Information Processing Device 2. Analyst terminal 11 Communications Department 12 Storage section 13 Control Unit 131 Acquisition Department 132 Specific part 133 Estimation Department 134 Output section
Claims
1. An acquisition unit that acquires architectural model data showing the three-dimensional shape of the building, including the interior space of the building, and the condition of the interior of the building, Based on the three-dimensional shape of the building's interior space shown by the building model data acquired by the acquisition unit and the condition of the interior, the identification unit identifies the features of the building's interior space that can be seen by the user. An estimation unit estimates the user's response to the internal space by inputting information indicating the features of the internal space identified by the identification unit into a learning model that outputs information indicating the user's response corresponding to the features of the internal space in response to input information indicating the features of the internal space, and obtaining information indicating the user's response corresponding to the features of the internal space from the learning model. An output unit that outputs information indicating the reaction estimated by the estimation unit, An information processing device having
2. The acquisition unit acquires the architectural model data, which shows the shape and placement position of each of the multiple objects that constitute the interior of the building. The specified unit identifies the amount of wall space or floor space of the building's interior space that is visible to the user as the characteristic, based on the three-dimensional shape of the building's interior space and the shape and position of each of the multiple objects constituting the interior. The information processing apparatus according to claim 1.
3. The acquisition unit acquires the architectural model data, which shows the shape and placement position of each of the multiple objects that constitute the interior of the building. The specified part identifies a curvature ratio as a feature, which represents the ratio of the number of curved parts visible to the user in the interior space to the number of shaped parts visible to the user in the interior space, based on the three-dimensional shape of the interior space of the building and the shape and position of each of the multiple objects constituting the interior. The information processing apparatus according to claim 1.
4. The acquisition unit acquires the architectural model data showing the shape, placement, and material of each of the multiple objects that constitute the interior of the building. The specified unit identifies the ratio of the surface area of an object made of a predetermined material to the surface area of the building and the objects visible to the user in the interior space, based on the three-dimensional shape of the interior space of the building and the shapes, positions, and materials of each of the multiple objects constituting the interior. The information processing apparatus according to claim 1.
5. The acquisition unit acquires the architectural model data showing the shape, placement, and color of each of the multiple objects that constitute the interior of the building. The specified unit identifies the ratio of the surface area of an object of a predetermined color to the surface area of the building and the objects visible to the user in the interior space, based on the three-dimensional shape of the interior space of the building and the shape, position, and color of each of the multiple objects constituting the interior. The information processing apparatus according to claim 1.
6. The estimation unit inputs information indicating the features of the internal space identified by the identification unit into the learning model, which outputs information indicating the user's psychological state as a user's response to the features, in response to input information indicating the features, and obtains information indicating the user's psychological state corresponding to the features of the internal space from the learning model, thereby estimating the psychological state of the user when the user is present in the internal space. The output unit outputs information indicating the psychological state estimated by the estimation unit. The information processing apparatus according to claim 1.
7. The estimation unit inputs information indicating the features of the internal space identified by the identification unit into the learning model, which outputs the user's biometric information indicating the user's biometric response corresponding to the features, in response to input information indicating the features, and obtains the user's biometric information corresponding to the features of the internal space from the learning model, thereby estimating the user's biometric response when the user is present in the internal space. The output unit outputs the biological information indicating the biological response estimated by the estimation unit. The information processing apparatus according to claim 1.
8. The aforementioned learning model is a model that has been trained using as training data information that indicates the characteristics of the interior space identified by analyzing each of the multiple images taken of the interior space of each of the multiple buildings, and information that indicates the user's reaction when the user views each of the multiple images. The information processing apparatus according to claim 1.
9. The identifying unit identifies the interior space of a building that is visible to the user, based on the image obtained by capturing the interior space of the building with an omnidirectional camera capable of capturing all directions at the user's position in the building corresponding to the architectural model data, and identifies the characteristics of the interior space. The information processing apparatus according to claim 1.
10. A computer executes The steps include obtaining architectural model data that shows the three-dimensional shape of the building, including the interior space of the building, and the condition of the interior of the building, A step of identifying the features of the building's interior space that can be seen by the user, based on the three-dimensional shape of the building's interior space shown in the acquired architectural model data and the condition of the interior, The steps include: inputting information indicating the identified features of the internal space into a learning model that outputs information indicating the user's response corresponding to the features in response to input information indicating the features, and obtaining information indicating the user's response corresponding to the features of the internal space from the learning model to estimate the user's response to the internal space; A step of outputting information indicating the estimated reaction, An information processing method having
11. Computers, An acquisition unit that acquires architectural model data showing the three-dimensional shape of the building, including the interior space of the building, and the condition of the interior of the building. Based on the three-dimensional shape of the building's interior space shown in the architectural model data acquired by the acquisition unit and the condition of the interior, the identification unit identifies the features of the building's interior space that can be seen by the user. An estimation unit estimates the user's response to the internal space by inputting information indicating the features of the internal space identified by the identification unit into a learning model that outputs information indicating the user's response corresponding to the features of the internal space, and obtaining information indicating the user's response corresponding to the features of the internal space from the learning model, and An output unit that outputs information indicating the reaction estimated by the estimation unit. A program that makes it function as such.