system

Abstract

The system according to this embodiment aims to facilitate the customization of furniture designs and to enable efficient and accurate material procurement. [Solution] The system according to the embodiment comprises an image analysis unit, a modeling unit, a design proposal unit, a material list creation unit, a purchase list provision unit, and an assembly support unit. The image analysis unit analyzes a photograph of the room provided by the user. The modeling unit passes the data extracted by the image analysis unit to a 3D modeling tool. The design proposal unit proposes furniture designs within the 3D model generated by the modeling unit. The material list creation unit creates a list of necessary materials based on the design proposed by the design proposal unit. The purchase list provision unit provides the purchase list created by the material list creation unit. The assembly support unit provides video support for the assembly procedure based on the purchase list provided by the purchase list provision unit.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there have been problems that customizing furniture designs requires time and effort, and it is difficult to procure materials efficiently and accurately.

[0005] The system according to the embodiment aims to facilitate the customization of furniture designs and achieve efficient and accurate material procurement.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an image analysis unit, a modeling unit, a design proposal unit, a material list creation unit, a purchase list provision unit, and an assembly support unit. The image analysis unit analyzes a photograph of the room provided by the user. The modeling unit passes the data extracted by the image analysis unit to a 3D modeling tool. The design proposal unit proposes furniture designs within the 3D model generated by the modeling unit. The material list creation unit creates a list of necessary materials based on the design proposed by the design proposal unit. The purchase list provision unit provides the purchase list created by the material list creation unit. The assembly support unit provides video support for the assembly procedure based on the purchase list provided by the purchase list provision unit. [Effects of the Invention]

[0007] The system according to this embodiment facilitates the customization of furniture designs and enables efficient and accurate material procurement. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the tagged communication I / F (Interface) is an interface that includes a communication processor and an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The DIY furniture making support system according to an embodiment of the present invention is a system that analyzes photos of a room provided by the user, generates a 3D model, proposes furniture designs, creates material lists, provides purchasing lists, and supports assembly. The DIY furniture making support system analyzes photos of the room provided by the user and extracts the room's characteristics and dimensions. For example, it can accurately determine the height of the walls and the location of windows in the room. Next, the extracted data is passed to a 3D modeling tool to generate a precise spatial model. This 3D model reflects the actual dimensions and characteristics of the room and is used to simulate furniture placement and design. Subsequently, the generating AI proposes furniture designs within the 3D model. The user provides feedback on this design, and the generating AI adjusts the design based on that feedback. For example, if the user desires a specific color or material, the generating AI proposes a revised design that reflects that request. Furthermore, the generating AI creates a list of necessary materials and presents information on nearby suppliers and prices. This allows the user to procure materials efficiently and accurately. For example, it provides a list of lumber and screws that can be purchased at a nearby home improvement store. Finally, the generating AI provides a shopping list with barcodes or 2D codes (e.g., QR code®) and supports assembly instructions with videos. Users can assemble the furniture accurately by watching these videos. For example, the assembly procedure is explained in detail, showing the necessary tools and parts for each step. This system makes it easier to realize custom designs and significantly reduces the effort involved. It also enables accurate material procurement and improves cost efficiency. Furthermore, the assembly process becomes clearer, improving the user's DIY experience. Thus, the DIY furniture making support system can efficiently support DIY furniture making by analyzing photos of the user's room, generating 3D models, suggesting furniture designs, creating material lists, providing shopping lists, and supporting assembly.

[0029] The DIY furniture making support system according to this embodiment comprises an image analysis unit, a modeling unit, a design proposal unit, a material list creation unit, a purchase list provision unit, and an assembly support unit. The image analysis unit analyzes a photograph of the room provided by the user. The image analysis unit extracts the characteristics and dimensions of the room, for example, using a generative AI. For example, the image analysis unit can accurately determine the height of the walls and the position of the windows in the room. The image analysis unit can also extract characteristics from the photograph of the room using a generative AI. For example, the image analysis unit can use a generative AI model that takes a photograph of the room as input and outputs the characteristics of the room. The modeling unit passes the data extracted by the image analysis unit to a 3D modeling tool. The modeling unit generates a precise spatial model, for example, using a generative AI. The modeling unit can also generate a 3D model that reflects the actual dimensions and characteristics of the room, using a generative AI. For example, the modeling unit can use a generative AI model that takes the extracted data as input and outputs a 3D model. The design proposal unit proposes furniture designs within the 3D model generated by the modeling unit. The design proposal unit proposes furniture designs, for example, using a generative AI. The design proposal unit can also propose designs that meet user requirements using generative AI. For example, the design proposal unit can use a generative AI model that takes a 3D model as input and outputs furniture designs. The material list creation unit creates a list of necessary materials based on the design proposed by the design proposal unit. The material list creation unit can create a material list using, for example, generative AI. The material list creation unit can also create a material list efficiently and accurately using generative AI. For example, the material list creation unit can use a generative AI model that takes a design as input and outputs a material list. The purchase list provision unit provides the purchase list created by the material list creation unit. The purchase list provision unit can provide a purchase list using, for example, generative AI. The purchase list provision unit can also provide information on nearby suppliers and prices using generative AI. For example, the purchase list provision unit can use a generative AI model that takes a material list as input and outputs a purchase list.The assembly support unit provides video-based support for the assembly procedure based on the purchase list provided by the purchase list provision unit. The assembly support unit can, for example, use a generative AI to provide video-based support for the assembly procedure. The assembly support unit can also use a generative AI to help the user assemble the furniture accurately. For example, the assembly support unit can use a generative AI model that takes a purchase list as input and outputs an assembly procedure. As a result, the DIY furniture making support system according to this embodiment can efficiently support DIY furniture making by analyzing photos of the user's room, generating a 3D model, proposing furniture designs, creating material lists, providing purchase lists, and providing assembly support.

[0030] The image analysis unit analyzes photos of rooms provided by users. For example, it uses generative AI to extract room features and dimensions. Specifically, when a user uploads a photo of a room taken with a smartphone or digital camera to the system, the image analysis unit receives the photo as input. The generative AI recognizes major structural elements in the image, such as walls, floors, ceilings, windows, and doors, and measures their dimensions. For example, it can accurately determine the height and width of walls, the position and size of windows, and the position of doors. This allows for a detailed analysis of the room's layout and dimensions, providing basic data for 3D modeling. Furthermore, the image analysis unit can also extract visual features such as the room's color tone, lighting conditions, and furniture arrangement. This helps in understanding the overall atmosphere and style of the room, which can be used for subsequent design proposals. The image analysis unit can also extract features from room photos using generative AI. For example, the image analysis unit can use a generative AI model that takes a room photo as input and outputs room features. This generative AI model is pre-trained with a large amount of room photo data, allowing it to extract room features with high accuracy. This allows us to quickly and accurately obtain room information from photos provided by the user and proceed to the next step.

[0031] The modeling unit passes the data extracted by the image analysis unit to the 3D modeling tool. The modeling unit generates a precise spatial model, for example, using generative AI. Specifically, it receives room dimensions and feature data provided by the image analysis unit as input and uses this to create a detailed 3D model of the room using the 3D modeling tool. The generative AI can generate a 3D model that reflects the actual dimensions and features of the room. For example, the modeling unit can use a generative AI model that takes the extracted data as input and outputs a 3D model. This generative AI model accurately places structural elements such as walls, floors, ceilings, windows, and doors based on the room's dimension data, recreating a realistic 3D space. Furthermore, by reflecting the room's color tone and lighting conditions, a more realistic model can be created. In addition, the modeling unit can also reflect the user's desired furniture placement and design. For example, if a user inputs their desired location and design for specific furniture, a corresponding 3D model can be generated. This allows the user to visually confirm the optimal furniture placement and design for their room. The modeling unit can also use generative AI to generate a 3D model that reflects the actual dimensions and features of the room. For example, the modeling unit can use a generative AI model that takes extracted data as input and outputs a 3D model. This allows users to visually check the optimal furniture arrangement and design for their room.

[0032] The design proposal department proposes furniture designs within 3D models generated by the modeling department. For example, the design proposal department uses generative AI to propose furniture designs. Specifically, it generates optimal furniture designs based on user requests and room characteristics. The generative AI considers elements such as the user's desired style, function, and color scheme, and places appropriate furniture within the 3D model of the room. For example, the design proposal department can use a generative AI model that takes a 3D model as input and outputs furniture designs. This generative AI model is pre-trained with data on a variety of furniture designs, allowing it to propose designs that meet user requests with high accuracy. Furthermore, the design proposal department provides an interface that allows users to review the proposed designs and make modifications or adjustments as needed. For example, users can review the placement and design of the proposed furniture within the 3D model and change the color, size, and placement. This allows users to customize the design to their liking, resulting in a more satisfying design. The design proposal department can also use generative AI to propose designs that meet user requests. For example, the design proposal department can use a generative AI model that takes a 3D model as input and outputs furniture designs. This allows users to visually check the furniture designs that best suit their room.

[0033] The materials list creation unit creates a list of necessary materials based on the design proposed by the design proposal unit. The materials list creation unit uses, for example, generative AI to create the materials list. Specifically, it calculates the types and quantities of materials needed based on the furniture design data provided by the design proposal unit. The generative AI can efficiently and accurately create a materials list by considering the furniture structure and the characteristics of the materials used. For example, the materials list creation unit can use a generative AI model that takes a design as input and outputs a materials list. This generative AI model is pre-trained with diverse furniture production data and can generate the optimal materials list for each design. Furthermore, the materials list creation unit can customize the materials list according to the user's desired materials and budget. For example, if a user wants to use a specific type of wood or metal, a materials list can be created to meet that request. This allows the user to select materials that suit their preferences and budget. The materials list creation unit can also efficiently and accurately create materials lists using generative AI. For example, the materials list creation unit can use a generative AI model that takes a design as input and outputs a materials list. This allows the user to visually confirm the optimal furniture design for their room.

[0034] The purchasing list provision unit provides purchasing lists created by the material list creation unit. The purchasing list provision unit provides purchasing lists using, for example, a generative AI. Specifically, it provides information on nearby suppliers and prices based on the material list provided by the material list creation unit. The generative AI can suggest optimal suppliers by considering the user's location, budget, and material types. For example, the purchasing list provision unit can use a generative AI model that takes a material list as input and outputs a purchasing list. This generative AI model is pre-trained with data on diverse suppliers and prices, enabling it to provide the optimal purchasing list for each user. Furthermore, the purchasing list provision unit can customize purchasing lists according to the user's desired suppliers and price range. For example, if a user wants to purchase materials from a specific store or online shop, a purchasing list can be created to meet that request. This allows the user to select materials that suit their preferences and budget. The purchasing list provision unit can also provide information on nearby suppliers and prices using the generative AI. For example, the purchasing list provision unit can use a generative AI model that takes a material list as input and outputs a purchasing list. This allows the user to visually confirm the optimal furniture design for their room.

[0035] The assembly support unit provides video-based support for assembly procedures based on the purchase list provided by the purchase list provision unit. The assembly support unit can, for example, use generative AI to provide video-based support for assembly procedures. Specifically, it generates videos that explain the furniture assembly procedure in detail based on the materials purchased by the user. The generative AI considers the characteristics of each material and the assembly procedure to support the user in accurately assembling the furniture. For example, the assembly support unit can use a generative AI model that takes the purchase list as input and outputs assembly procedures. This generative AI model is pre-trained with diverse furniture assembly data and can provide the optimal assembly procedure for each user. Furthermore, the assembly support unit can also provide real-time support for problems and questions that the user encounters during assembly. For example, if the user encounters difficulty at a particular step, the assembly support unit will suggest a solution to that problem, helping the user proceed with the assembly smoothly. This allows users to assemble furniture at their own pace and create high-quality DIY furniture. The assembly support unit can also use generative AI to support users in accurately assembling furniture. For example, the assembly support unit can use a generative AI model that takes the purchase list as input and outputs assembly procedures. This allows users to visually check the furniture designs that best suit their room.

[0036] The design proposal department includes a feedback reception department that receives user feedback and adjusts the design accordingly. The design proposal department can, for example, use generative AI to receive user feedback. The design proposal department can also use generative AI to re-propose designs that meet user requirements. For instance, the design proposal department can use a generative AI model that takes user feedback as input and outputs a design. This allows for design adjustments based on user feedback, enabling the creation of custom designs that meet user needs.

[0037] The material list creation unit includes a procurement information provision unit that provides information on nearby suppliers and prices. The material list creation unit provides information on nearby suppliers and prices, for example, using a generative AI. The material list creation unit can also provide procurement information efficiently and accurately using a generative AI. For example, the material list creation unit can use a generative AI model that takes a material list as input and outputs procurement information. This allows users to procure materials efficiently and accurately by providing information on nearby suppliers and prices.

[0038] The assembly support unit includes a video provision unit that provides assembly instructions with video. The assembly support unit can, for example, use generative AI to provide assembly instructions with video. The assembly support unit can also use generative AI to support users in accurately assembling furniture. For example, the assembly support unit can use a generative AI model that takes a purchase list as input and outputs assembly instructions. This allows users to accurately assemble furniture by providing assembly instructions with video.

[0039] The image analysis unit improves analysis accuracy by considering the room's lighting conditions. For example, the image analysis unit considers the room's lighting conditions using generative AI. The image analysis unit can also improve analysis accuracy based on lighting conditions using generative AI. For example, the image analysis unit can use a generative AI model that takes lighting conditions as input and outputs analysis accuracy. For example, if the room lighting is dim, the image analysis unit automatically adjusts the brightness of the image and performs the analysis. If the room lighting is too bright, the image analysis unit adjusts the contrast of the image and performs the analysis. If the room lighting is natural light, the image analysis unit performs the analysis in a way that minimizes the effect of shadows. In this way, analysis accuracy is improved by considering the room's lighting conditions.

[0040] The image analysis unit optimizes the analysis results by considering the furniture arrangement and color scheme when analyzing photos of a room. For example, the image analysis unit uses generative AI to consider the furniture arrangement and color scheme. The image analysis unit can also optimize the analysis results based on the furniture arrangement and color scheme using generative AI. For example, the image analysis unit can use a generative AI model that takes the furniture arrangement and color scheme as input and outputs analysis results. For example, it can analyze the furniture arrangement to accurately understand the room layout. It can analyze the furniture color scheme to extract the room's design theme. It can combine the furniture arrangement and color scheme to analyze the overall atmosphere of the room. In this way, the analysis results are optimized by considering the furniture arrangement and color scheme.

[0041] The image analysis unit improves analysis accuracy by referencing the user's past photos of the room when analyzing photos of the room. For example, the image analysis unit can use generative AI to reference the user's past photos of the room. The image analysis unit can also improve analysis accuracy based on past photos using generative AI. For example, the image analysis unit can use a generative AI model that takes past photos as input and outputs analysis accuracy. For example, it can analyze changes in the current room based on the user's past photos of the room. It references the user's past photos of the room and extracts similar features. It compares the user's past photos of the room and selects the optimal analysis method. As a result, analysis accuracy is improved by referencing the user's past photos of the room.

[0042] The image analysis unit modifies its analysis algorithm according to the room's purpose when analyzing a photograph of a room. For example, the image analysis unit considers the room's purpose using generative AI. The image analysis unit can also modify the analysis algorithm based on the purpose using generative AI. For example, the image analysis unit can use a generative AI model that takes the purpose as input and outputs an analysis algorithm. For example, in the case of a living room, the image analysis unit performs an analysis that emphasizes the arrangement of furniture and color scheme. In the case of a bedroom, the image analysis unit performs an analysis that emphasizes lighting and bed placement. In the case of a kitchen, the image analysis unit performs an analysis that emphasizes storage space and workspace. By changing the analysis algorithm according to the room's purpose, more appropriate analysis results can be obtained.

[0043] The modeling unit improves the realism of 3D models by considering the materials and textures of the room when generating them. For example, the modeling unit uses a generative AI to consider the materials and textures of the room. The modeling unit can also improve the realism of the model based on materials and textures using a generative AI. For example, the modeling unit can use a generative AI model that takes materials and textures as input and outputs realism. For example, it can analyze the material of the room's walls and reflect it in the 3D model. It can analyze the texture of the room's floor and reflect it in the 3D model. It can analyze the material and texture of the room's furniture and reflect it in the 3D model. In this way, the realism of the 3D model is improved by considering the materials and textures of the room.

[0044] The modeling unit optimizes the appearance of a 3D model by simulating the room's lighting conditions when generating the model. For example, the modeling unit can use a generative AI to simulate the room's lighting conditions. The modeling unit can also use a generative AI to optimize the model's appearance based on the lighting conditions. For example, the modeling unit can use a generative AI model that takes lighting conditions as input and outputs the appearance. For example, it can simulate the room's lighting conditions and reflect them in the 3D model. It can simulate the effect of natural light in the room and reflect it in the 3D model. It can simulate the effect of artificial light in the room and reflect it in the 3D model. In this way, the appearance of the 3D model is optimized by simulating the room's lighting conditions.

[0045] The modeling unit improves generation accuracy by referencing the user's past 3D models when generating 3D models. For example, the modeling unit can use a generation AI to reference the user's past 3D models. The modeling unit can also improve generation accuracy based on past models using a generation AI. For example, the modeling unit can use a generation AI model that takes past models as input and outputs generation accuracy. For example, it can generate the current 3D model based on the user's past 3D models. It references the user's past 3D models and extracts similar features. It compares the user's past 3D models and selects the optimal generation method. As a result, generation accuracy is improved by referencing the user's past 3D models.

[0046] The modeling unit modifies its generation algorithm according to the room's purpose when generating 3D models. For example, the modeling unit considers the room's purpose using a generation AI. The modeling unit can also modify the generation algorithm based on the purpose using a generation AI. For example, the modeling unit can use a generation AI model that takes the purpose as input and outputs a generation algorithm. For example, in the case of a living room, the modeling unit generates a 3D model that emphasizes furniture arrangement and color scheme. In the case of a bedroom, the modeling unit generates a 3D model that emphasizes lighting and bed placement. In the case of a kitchen, the modeling unit generates a 3D model that emphasizes storage space and workspace. By changing the generation algorithm according to the room's purpose, a more appropriate 3D model can be generated.

[0047] The design proposal department improves the accuracy of its proposals by referring to the user's past design history. For example, the design proposal department can use generative AI to refer to the user's past design history. The design proposal department can also use generative AI to improve the accuracy of proposals based on past history. For example, the design proposal department can use a generative AI model that takes past history as input and outputs the accuracy of the proposal. For example, it can make current design proposals based on the user's past design history. It can refer to the user's past design history and propose similar designs. It can compare the user's past design history and make the optimal design proposal. In this way, the accuracy of proposals is improved by referring to the user's past design history.

[0048] The design proposal department applies different design algorithms depending on the room's purpose and theme when making design proposals. For example, the design proposal department uses generative AI to consider the room's purpose and theme. The design proposal department can also use generative AI to apply design algorithms based on the purpose and theme. For example, the design proposal department can use a generative AI model that takes the purpose and theme as input and outputs a design algorithm. For example, in the case of a living room, the design proposal department will make a design proposal that emphasizes furniture arrangement and color scheme. In the case of a bedroom, the design proposal department will make a design proposal that emphasizes lighting and bed placement. In the case of a kitchen, the design proposal department will make a design proposal that emphasizes storage space and workspace. By applying different design algorithms according to the room's purpose and theme, it becomes possible to make the optimal design proposal.

[0049] The design proposal department prioritizes proposing highly relevant designs by considering the user's geographical location when making design proposals. For example, the design proposal department can use generative AI to consider the user's geographical location. The design proposal department can also use generative AI to prioritize proposing highly relevant designs based on geographical location. For example, the design proposal department can use a generative AI model that takes geographical location as input and outputs highly relevant designs. For example, it can propose designs suitable for the local climate based on the user's geographical location. For example, it can propose designs suitable for the local culture based on the user's geographical location. For example, it can propose designs suitable for the local architectural style based on the user's geographical location. This makes it possible to propose highly relevant designs by considering the user's geographical location.

[0050] The design proposal department analyzes users' social media activity and proposes relevant designs when making design proposals. For example, the design proposal department can use generative AI to analyze users' social media activity. The design proposal department can also use generative AI to propose relevant designs based on social media activity. For example, the design proposal department can use a generative AI model that takes social media activity as input and outputs relevant designs. For instance, it can analyze users' social media activity and propose designs they like. It can analyze users' social media activity and propose designs that are in line with current trends. It can analyze users' social media activity and propose designs that match the preferences of their friends and followers. This makes it possible to propose relevant designs by analyzing users' social media activity.

[0051] The material list creation unit improves the accuracy of the material list by referring to the user's past material usage history when creating the list. For example, the material list creation unit can refer to the user's past material usage history using a generative AI. The material list creation unit can also improve the accuracy of the list based on past history using a generative AI. For example, the material list creation unit can use a generative AI model that takes past history as input and outputs the accuracy of the list. For example, it can create a current material list based on the user's past material usage history. It refers to the user's past material usage history and lists similar materials. It compares the user's past material usage history and creates an optimal material list. In this way, the accuracy of the list is improved by referring to the user's past material usage history.

[0052] The materials list creation unit applies different materials list creation algorithms depending on the room's purpose and theme when creating a materials list. For example, the materials list creation unit considers the room's purpose and theme using generative AI. The materials list creation unit can also apply a materials list creation algorithm based on the purpose and theme using generative AI. For example, the materials list creation unit can use a generative AI model that takes the purpose and theme as input and outputs a materials list creation algorithm. For example, in the case of a living room, the materials list creation unit creates a materials list that emphasizes furniture arrangement and color scheme. In the case of a bedroom, the materials list creation unit creates a materials list that emphasizes lighting and bed placement. In the case of a kitchen, the materials list creation unit creates a materials list that emphasizes storage space and workspace. In this way, by applying different materials list creation algorithms according to the room's purpose and theme, the optimal materials list can be created.

[0053] The material list creation unit prioritizes listing highly relevant materials by considering the user's geographical location when creating a material list. For example, the material list creation unit can use a generative AI to consider the user's geographical location. The material list creation unit can also prioritize listing highly relevant materials based on geographical location using a generative AI. For example, the material list creation unit can use a generative AI model that takes geographical location as input and outputs highly relevant materials. For example, it can list materials available at nearby home improvement stores based on the user's geographical location. It can also list materials suitable for the local climate based on the user's geographical location. By considering the user's geographical location, it can prioritize listing highly relevant materials.

[0054] The material list creation unit analyzes the user's social media activity and lists relevant materials when creating a material list. The material list creation unit can analyze the user's social media activity using, for example, generative AI. The material list creation unit can also list relevant materials based on social media activity using generative AI. For example, the material list creation unit can use a generative AI model that takes social media activity as input and outputs relevant materials. For example, it can analyze the user's social media activity and list their preferred materials. It can analyze the user's social media activity and list materials that match current trends. It can analyze the user's social media activity and list materials that match the preferences of their friends and followers. In this way, by analyzing the user's social media activity, relevant materials can be listed.

[0055] The purchase list provider improves the accuracy of the list by referring to the user's past purchase history when providing the list. The purchase list provider can, for example, use a generative AI to refer to the user's past purchase history. The purchase list provider can also improve the accuracy of the list based on past history using a generative AI. For example, the purchase list provider can use a generative AI model that takes past history as input and outputs the accuracy of the list. For example, it can create a current purchase list based on the user's past purchase history. It can refer to the user's past purchase history and list similar suppliers. It can compare the user's past purchase history and create an optimal purchase list. In this way, the accuracy of the list is improved by referring to the user's past purchase history.

[0056] The purchasing list provider applies different purchasing list provision algorithms depending on the room's purpose and theme when providing purchasing lists. For example, the purchasing list provider uses a generative AI to consider the room's purpose and theme. The purchasing list provider can also use a generative AI to apply a purchasing list provision algorithm based on the purpose and theme. For example, the purchasing list provider can use a generative AI model that takes the purpose and theme as input and outputs a purchasing list provision algorithm. For example, in the case of a living room, the purchasing list provider provides a purchasing list that emphasizes furniture arrangement and color scheme. In the case of a bedroom, the purchasing list provider provides a purchasing list that emphasizes lighting and bed placement. In the case of a kitchen, the purchasing list provider provides a purchasing list that emphasizes storage space and workspace. In this way, by applying different purchasing list provision algorithms depending on the room's purpose and theme, the optimal purchasing list can be provided.

[0057] The purchasing list provider, when providing a purchasing list, prioritizes listing highly relevant suppliers by considering the user's geographical location. For example, the purchasing list provider can use generative AI to consider the user's geographical location. The purchasing list provider can also use generative AI to prioritize listing highly relevant suppliers based on geographical location. For example, the purchasing list provider can use a generative AI model that takes geographical location as input and outputs highly relevant suppliers. For example, it can list suppliers available at nearby home improvement stores based on the user's geographical location. It can also list suppliers suitable for the local climate based on the user's geographical location. By considering the user's geographical location, it can prioritize listing highly relevant suppliers.

[0058] The purchase list provider analyzes the user's social media activity and lists relevant retailers when providing purchase lists. For example, the purchase list provider uses generative AI to analyze the user's social media activity. The purchase list provider can also use generative AI to list relevant retailers based on social media activity. For example, the purchase list provider can use a generative AI model that takes social media activity as input and outputs relevant retailers. For example, it can analyze the user's social media activity and list preferred retailers. It can analyze the user's social media activity and list retailers that match current trends. It can analyze the user's social media activity and list retailers that match the preferences of their friends and followers. This allows for the listing of relevant retailers by analyzing the user's social media activity.

[0059] The assembly support unit improves the accuracy of assembly procedures by referring to the user's past assembly history when providing assembly instructions. For example, the assembly support unit can refer to the user's past assembly history using generative AI. The assembly support unit can also improve the accuracy of procedures based on past history using generative AI. For example, the assembly support unit can use a generative AI model that takes past history as input and outputs the accuracy of the procedures. For example, it can create the current assembly procedure based on the user's past assembly history. It can refer to the user's past assembly history and provide similar procedures. It can compare the user's past assembly history and create the optimal assembly procedure. In this way, the accuracy of the procedures is improved by referring to the user's past assembly history.

[0060] The assembly support unit applies different assembly procedure provision algorithms depending on the room's purpose and theme when providing assembly instructions. For example, the assembly support unit considers the room's purpose and theme using generative AI. The assembly support unit can also apply assembly procedure provision algorithms based on the purpose and theme using generative AI. For example, the assembly support unit can use a generative AI model that takes the purpose and theme as input and outputs an assembly procedure provision algorithm. For example, in the case of a living room, the assembly support unit provides assembly instructions that emphasize furniture arrangement and color scheme. In the case of a bedroom, the assembly support unit provides assembly instructions that emphasize lighting and bed placement. In the case of a kitchen, the assembly support unit provides assembly instructions that emphasize storage space and workspace. By applying different assembly procedure provision algorithms depending on the room's purpose and theme, the optimal assembly procedure can be provided.

[0061] The assembly support unit, when providing assembly instructions, prioritizes providing highly relevant instructions by considering the user's geographical location information. For example, the assembly support unit considers the user's geographical location information using generative AI. The assembly support unit can also prioritize providing highly relevant instructions based on geographical location information using generative AI. For example, the assembly support unit can use a generative AI model that takes geographical location information as input and outputs highly relevant instructions. For example, it can provide assembly instructions suitable for the local climate based on the user's geographical location information. For example, it can provide assembly instructions suitable for the local culture based on the user's geographical location information. For example, when providing assembly instructions suitable for the local architectural style based on the user's geographical location information, it analyzes the user's social media activity to provide relevant instructions. For example, the assembly support unit analyzes the user's social media activity using generative AI. The assembly support unit can also provide relevant instructions based on social media activity using generative AI. For example, the assembly support unit can use a generative AI model that takes social media activity as input and outputs relevant instructions. For example, it can analyze the user's social media activity and provide preferred assembly instructions. For example, it can analyze the user's social media activity and provide assembly instructions that match current trends. It analyzes users' social media activity and provides customized instructions tailored to the preferences of their friends and followers. This allows for the provision of relevant instructions based on the analysis of users' social media activity.

[0062] The feedback receiving unit improves the accuracy of feedback reception by referring to the user's past feedback history when receiving feedback. The feedback receiving unit can, for example, use generative AI to refer to the user's past feedback history. The feedback receiving unit can also improve the accuracy of reception based on past history using generative AI. For example, the feedback receiving unit can use a generative AI model that takes past history as input and outputs the accuracy of reception. For example, it can receive current feedback based on the user's past feedback history. It can refer to the user's past feedback history and receive similar feedback. It can compare the user's past feedback history and select the optimal feedback reception method. In this way, the accuracy of reception is improved by referring to the user's past feedback history.

[0063] The feedback receiving unit, when receiving feedback, prioritizes receiving highly relevant feedback by considering the user's geographical location information. For example, the feedback receiving unit can use generative AI to consider the user's geographical location information. The feedback receiving unit can also use generative AI to prioritize receiving highly relevant feedback based on geographical location information. For example, the feedback receiving unit can use a generative AI model that takes geographical location information as input and outputs highly relevant feedback. For example, it can prioritize feedback suitable for the local climate based on the user's geographical location information. For example, it can prioritize feedback suitable for the local culture based on the user's geographical location information. For example, it can prioritize feedback suitable for the local architectural style based on the user's geographical location information. This allows for the prioritization of highly relevant feedback by considering the user's geographical location information.

[0064] The procurement information provider improves the accuracy of the information by referring to the user's past procurement history when providing procurement information. The procurement information provider can, for example, use generative AI to refer to the user's past procurement history. The procurement information provider can also improve the accuracy of the information based on past history using generative AI. For example, the procurement information provider can use a generative AI model that takes past history as input and outputs the accuracy of the information. For example, it can provide current procurement information based on the user's past procurement history. It can refer to the user's past procurement history and provide similar suppliers. It can compare the user's past procurement history and provide optimal procurement information. In this way, the accuracy of the information is improved by referring to the user's past procurement history.

[0065] The Procurement Information Provision Department, when providing procurement information, prioritizes providing highly relevant suppliers by considering the user's geographical location. For example, the Procurement Information Provision Department considers the user's geographical location using generative AI. The Procurement Information Provision Department can also prioritize providing highly relevant suppliers based on geographical location using generative AI. For example, the Procurement Information Provision Department can use a generative AI model that takes geographical location as input and outputs highly relevant suppliers. For example, it can prioritize providing nearby suppliers based on the user's geographical location. It can also prioritize providing suppliers suitable for the local climate based on the user's geographical location. This allows for the prioritization of highly relevant suppliers by considering the user's geographical location.

[0066] The Procurement Information Provision Department analyzes users' social media activity and provides relevant suppliers when providing procurement information. For example, the Procurement Information Provision Department uses generative AI to analyze users' social media activity. The Procurement Information Provision Department can also use generative AI to provide relevant suppliers based on social media activity. For example, the Procurement Information Provision Department can use a generative AI model that takes social media activity as input and outputs relevant suppliers. For example, it can analyze users' social media activity and provide preferred suppliers. It can analyze users' social media activity and provide suppliers that match current trends. It can analyze users' social media activity and provide suppliers that match the preferences of their friends and followers. In this way, by analyzing users' social media activity, it is possible to provide relevant suppliers.

[0067] The video provisioning unit improves the accuracy of its provision by referring to the user's past video viewing history when providing videos. For example, the video provisioning unit can use generative AI to refer to the user's past video viewing history. The video provisioning unit can also use generative AI to improve the accuracy of its provision based on past history. For example, the video provisioning unit can use a generative AI model that takes past history as input and outputs the accuracy of its provision. For example, it can provide current videos based on the user's past video viewing history. It can refer to the user's past video viewing history and provide similar videos. It can compare the user's past video viewing history and provide the most suitable video. In this way, the accuracy of provision is improved by referring to the user's past video viewing history.

[0068] The video provision department prioritizes providing highly relevant videos by considering the user's geographical location information when providing videos. For example, the video provision department considers the user's geographical location information using generative AI. The video provision department can also prioritize providing highly relevant videos based on geographical location information using generative AI. For example, the video provision department can use a generative AI model that takes geographical location information as input and outputs highly relevant videos. For example, it can provide videos suitable for the local climate based on the user's geographical location information. For example, it can provide videos suitable for the local culture based on the user's geographical location information. For example, it can provide videos suitable for the local architectural style based on the user's geographical location information. In this way, by considering the user's geographical location information, it is possible to prioritize providing highly relevant videos.

[0069] The video provision department analyzes the user's social media activity and provides relevant videos when providing videos. For example, the video provision department uses generative AI to analyze the user's social media activity. The video provision department can also use generative AI to provide relevant videos based on social media activity. For example, the video provision department can use a generative AI model that takes social media activity as input and outputs relevant videos. For example, it can analyze the user's social media activity and provide videos they like. It can analyze the user's social media activity and provide videos that match current trends. It can analyze the user's social media activity and provide videos that match the preferences of their friends and followers. In this way, by analyzing the user's social media activity, it is possible to provide relevant videos.

[0070] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0071] The DIY furniture making support system can provide more accurate design suggestions by referencing the user's past design history. For example, it can suggest current designs based on the designs and materials the user has previously selected. It can also analyze the user's preferences by referring to past feedback and make suggestions accordingly. Furthermore, it can refer to photos of furniture the user has created in the past and suggest similar designs. This allows for design suggestions that are tailored to the user's preferences.

[0072] The DIY furniture making support system can propose designs tailored to the user's geographical location. For example, it can suggest warm materials and designs to users living in cold climates, and cool materials and designs to users living in warmer climates. It can also propose designs that match the local culture and architectural style. This enables the system to provide optimal design proposals suited to each region.

[0073] The DIY furniture making support system can analyze a user's social media activity to suggest designs that align with current trends. For example, it can suggest designs based on influencers and brands the user follows. It can also analyze posts the user has "liked" or shared to suggest designs that the user might like. Furthermore, it can suggest designs that match the preferences of the user's friends and followers. This enables the system to provide optimal design suggestions based on the user's social media activity.

[0074] The DIY furniture making support system can create a more accurate material list by referring to the user's past material usage history. For example, it can create a current material list based on materials the user has used in the past. It can also refer to the user's past projects and list similar materials. Furthermore, it can refer to the user's past feedback and list preferred materials. This allows for the creation of a material list tailored to the user's preferences.

[0075] The DIY furniture making support system can create a list of materials suitable for the user's region, taking into account their geographical location. For example, it can list materials with high insulation properties for users living in cold climates, and materials with good ventilation for users living in warmer regions. It can also list materials suitable for the local climate and environment. This allows for the creation of an optimal material list tailored to the user's region.

[0076] The DIY furniture making support system can analyze a user's social media activity to create a list of materials that match current trends. For example, it can list materials used by influencers and brands the user follows. It can also analyze posts the user "likes" and shares to list their preferred materials. Furthermore, it can create material lists tailored to the preferences of the user's friends and followers. This allows for the creation of an optimal material list based on the user's social media activity.

[0077] The DIY furniture making support system can provide a more accurate shopping list by referencing the user's past purchase history. For example, it can create a current shopping list based on materials and tools the user has purchased in the past. It can also refer to the user's past projects and list similar suppliers. Furthermore, it can refer to the user's past feedback and list preferred suppliers. This allows the system to provide a shopping list tailored to the user's preferences.

[0078] The following briefly describes the processing flow for example form 1.

[0079] Step 1: The image analysis unit analyzes the room photos provided by the user. The image analysis unit uses generation AI to extract room features and dimensions, accurately determining the height of the walls, the location of windows, and other details of the room. Step 2: The modeling unit passes the data extracted by the image analysis unit to a 3D modeling tool and generates a precise spatial model using a generation AI. This generates a 3D model that reflects the actual dimensions and characteristics of the room. Step 3: The design proposal department proposes furniture designs within the 3D models generated by the modeling department. The design proposal department uses the generation AI to propose furniture designs that meet the user's requirements. Step 4: The materials list creation unit creates a list of necessary materials based on the design proposed by the design proposal unit. The materials list creation unit uses a generation AI to create the materials list efficiently and accurately. Step 5: The purchasing list provision unit provides the purchasing list created by the material list creation unit. The purchasing list provision unit uses a generation AI to provide information on nearby suppliers and prices. Step 6: The assembly support unit provides video-based support for the assembly procedure based on the purchase list provided by the purchase list provision unit. The assembly support unit uses generating AI to help the user assemble the furniture accurately.

[0080] (Example of form 2) The DIY furniture making support system according to an embodiment of the present invention is a system that analyzes photos of a room provided by the user, generates a 3D model, proposes furniture designs, creates material lists, provides shopping lists, and supports assembly. The DIY furniture making support system analyzes photos of the room provided by the user and extracts the room's characteristics and dimensions. For example, it can accurately determine the height of the walls and the position of the windows. Next, the extracted data is passed to a 3D modeling tool to generate a precise spatial model. This 3D model reflects the actual dimensions and characteristics of the room and is used to simulate furniture placement and design. Subsequently, the generating AI proposes furniture designs within the 3D model. The user provides feedback on this design, and the generating AI adjusts the design based on that feedback. For example, if the user desires a specific color or material, the generating AI proposes a revised design that reflects that request. Furthermore, the generating AI creates a list of necessary materials and presents information on nearby suppliers and prices. This allows the user to procure materials efficiently and accurately. For example, it provides a list of lumber and screws that can be purchased at a nearby home improvement store. Finally, the generating AI provides a shopping list with barcodes or 2D codes (e.g., QR codes) and supports the assembly procedure with videos. Users can assemble furniture accurately while watching this video. For example, the assembly procedure is explained in detail, showing the necessary tools and parts for each step. This system makes it easy to realize custom designs and significantly reduces the effort involved. It also enables accurate material procurement and improves cost efficiency. Furthermore, the assembly process becomes clearer, improving the user's DIY experience. Thus, the DIY furniture making support system can efficiently support DIY furniture making by analyzing photos of the user's room, generating 3D models, providing furniture design suggestions, creating material lists, offering purchasing lists, and providing assembly support.

[0081] The DIY furniture making support system according to this embodiment comprises an image analysis unit, a modeling unit, a design proposal unit, a material list creation unit, a purchase list provision unit, and an assembly support unit. The image analysis unit analyzes a photograph of the room provided by the user. The image analysis unit extracts the characteristics and dimensions of the room, for example, using a generative AI. For example, the image analysis unit can accurately determine the height of the walls and the position of the windows in the room. The image analysis unit can also extract characteristics from the photograph of the room using a generative AI. For example, the image analysis unit can use a generative AI model that takes a photograph of the room as input and outputs the characteristics of the room. The modeling unit passes the data extracted by the image analysis unit to a 3D modeling tool. The modeling unit generates a precise spatial model, for example, using a generative AI. The modeling unit can also generate a 3D model that reflects the actual dimensions and characteristics of the room, using a generative AI. For example, the modeling unit can use a generative AI model that takes the extracted data as input and outputs a 3D model. The design proposal unit proposes furniture designs within the 3D model generated by the modeling unit. The design proposal unit proposes furniture designs, for example, using a generative AI. The design proposal unit can also propose designs that meet user requirements using generative AI. For example, the design proposal unit can use a generative AI model that takes a 3D model as input and outputs furniture designs. The material list creation unit creates a list of necessary materials based on the design proposed by the design proposal unit. The material list creation unit can create a material list using, for example, generative AI. The material list creation unit can also create a material list efficiently and accurately using generative AI. For example, the material list creation unit can use a generative AI model that takes a design as input and outputs a material list. The purchase list provision unit provides the purchase list created by the material list creation unit. The purchase list provision unit can provide a purchase list using, for example, generative AI. The purchase list provision unit can also provide information on nearby suppliers and prices using generative AI. For example, the purchase list provision unit can use a generative AI model that takes a material list as input and outputs a purchase list.The assembly support unit provides video-based support for the assembly procedure based on the purchase list provided by the purchase list provision unit. The assembly support unit can, for example, use a generative AI to provide video-based support for the assembly procedure. The assembly support unit can also use a generative AI to help the user assemble the furniture accurately. For example, the assembly support unit can use a generative AI model that takes a purchase list as input and outputs an assembly procedure. As a result, the DIY furniture making support system according to this embodiment can efficiently support DIY furniture making by analyzing photos of the user's room, generating a 3D model, proposing furniture designs, creating material lists, providing purchase lists, and providing assembly support.

[0082] The image analysis unit analyzes photos of rooms provided by users. For example, it uses generative AI to extract room features and dimensions. Specifically, when a user uploads a photo of a room taken with a smartphone or digital camera to the system, the image analysis unit receives the photo as input. The generative AI recognizes major structural elements in the image, such as walls, floors, ceilings, windows, and doors, and measures their dimensions. For example, it can accurately determine the height and width of walls, the position and size of windows, and the position of doors. This allows for a detailed analysis of the room's layout and dimensions, providing basic data for 3D modeling. Furthermore, the image analysis unit can also extract visual features such as the room's color tone, lighting conditions, and furniture arrangement. This helps in understanding the overall atmosphere and style of the room, which can be used for subsequent design proposals. The image analysis unit can also extract features from room photos using generative AI. For example, the image analysis unit can use a generative AI model that takes a room photo as input and outputs room features. This generative AI model is pre-trained with a large amount of room photo data, allowing it to extract room features with high accuracy. This allows us to quickly and accurately obtain room information from photos provided by the user and proceed to the next step.

[0083] The modeling unit passes the data extracted by the image analysis unit to the 3D modeling tool. The modeling unit generates a precise spatial model, for example, using generative AI. Specifically, it receives room dimensions and feature data provided by the image analysis unit as input and uses this to create a detailed 3D model of the room using the 3D modeling tool. The generative AI can generate a 3D model that reflects the actual dimensions and features of the room. For example, the modeling unit can use a generative AI model that takes the extracted data as input and outputs a 3D model. This generative AI model accurately places structural elements such as walls, floors, ceilings, windows, and doors based on the room's dimension data, recreating a realistic 3D space. Furthermore, by reflecting the room's color tone and lighting conditions, a more realistic model can be created. In addition, the modeling unit can also reflect the user's desired furniture placement and design. For example, if a user inputs their desired location and design for specific furniture, a corresponding 3D model can be generated. This allows the user to visually confirm the optimal furniture placement and design for their room. The modeling unit can also use generative AI to generate a 3D model that reflects the actual dimensions and features of the room. For example, the modeling unit can use a generative AI model that takes extracted data as input and outputs a 3D model. This allows users to visually check the optimal furniture arrangement and design for their room.

[0084] The design proposal department proposes furniture designs within 3D models generated by the modeling department. For example, the design proposal department uses generative AI to propose furniture designs. Specifically, it generates optimal furniture designs based on user requests and room characteristics. The generative AI considers elements such as the user's desired style, function, and color scheme, and places appropriate furniture within the 3D model of the room. For example, the design proposal department can use a generative AI model that takes a 3D model as input and outputs furniture designs. This generative AI model is pre-trained with data on a variety of furniture designs, allowing it to propose designs that meet user requests with high accuracy. Furthermore, the design proposal department provides an interface that allows users to review the proposed designs and make modifications or adjustments as needed. For example, users can review the placement and design of the proposed furniture within the 3D model and change the color, size, and placement. This allows users to customize the design to their liking, resulting in a more satisfying design. The design proposal department can also use generative AI to propose designs that meet user requests. For example, the design proposal department can use a generative AI model that takes a 3D model as input and outputs furniture designs. This allows users to visually check the furniture designs that best suit their room.

[0085] The materials list creation unit creates a list of necessary materials based on the design proposed by the design proposal unit. The materials list creation unit uses, for example, generative AI to create the materials list. Specifically, it calculates the types and quantities of materials needed based on the furniture design data provided by the design proposal unit. The generative AI can efficiently and accurately create a materials list by considering the furniture structure and the characteristics of the materials used. For example, the materials list creation unit can use a generative AI model that takes a design as input and outputs a materials list. This generative AI model is pre-trained with diverse furniture production data and can generate the optimal materials list for each design. Furthermore, the materials list creation unit can customize the materials list according to the user's desired materials and budget. For example, if a user wants to use a specific type of wood or metal, a materials list can be created to meet that request. This allows the user to select materials that suit their preferences and budget. The materials list creation unit can also efficiently and accurately create materials lists using generative AI. For example, the materials list creation unit can use a generative AI model that takes a design as input and outputs a materials list. This allows the user to visually confirm the optimal furniture design for their room.

[0086] The purchasing list provision unit provides purchasing lists created by the material list creation unit. The purchasing list provision unit provides purchasing lists using, for example, a generative AI. Specifically, it provides information on nearby suppliers and prices based on the material list provided by the material list creation unit. The generative AI can suggest optimal suppliers by considering the user's location, budget, and material types. For example, the purchasing list provision unit can use a generative AI model that takes a material list as input and outputs a purchasing list. This generative AI model is pre-trained with data on diverse suppliers and prices, enabling it to provide the optimal purchasing list for each user. Furthermore, the purchasing list provision unit can customize purchasing lists according to the user's desired suppliers and price range. For example, if a user wants to purchase materials from a specific store or online shop, a purchasing list can be created to meet that request. This allows the user to select materials that suit their preferences and budget. The purchasing list provision unit can also provide information on nearby suppliers and prices using the generative AI. For example, the purchasing list provision unit can use a generative AI model that takes a material list as input and outputs a purchasing list. This allows the user to visually confirm the optimal furniture design for their room.

[0087] The assembly support unit provides video-based support for assembly procedures based on the purchase list provided by the purchase list provision unit. The assembly support unit can, for example, use generative AI to provide video-based support for assembly procedures. Specifically, it generates videos that explain the furniture assembly procedure in detail based on the materials purchased by the user. The generative AI considers the characteristics of each material and the assembly procedure to support the user in accurately assembling the furniture. For example, the assembly support unit can use a generative AI model that takes the purchase list as input and outputs assembly procedures. This generative AI model is pre-trained with diverse furniture assembly data and can provide the optimal assembly procedure for each user. Furthermore, the assembly support unit can also provide real-time support for problems and questions that the user encounters during assembly. For example, if the user encounters difficulty at a particular step, the assembly support unit will suggest a solution to that problem, helping the user proceed with the assembly smoothly. This allows users to assemble furniture at their own pace and create high-quality DIY furniture. The assembly support unit can also use generative AI to support users in accurately assembling furniture. For example, the assembly support unit can use a generative AI model that takes the purchase list as input and outputs assembly procedures. This allows users to visually check the furniture designs that best suit their room.

[0088] The design proposal department includes a feedback reception department that receives user feedback and adjusts the design accordingly. The design proposal department can, for example, use generative AI to receive user feedback. The design proposal department can also use generative AI to re-propose designs that meet user requirements. For instance, the design proposal department can use a generative AI model that takes user feedback as input and outputs a design. This allows for design adjustments based on user feedback, enabling the creation of custom designs that meet user needs.

[0089] The material list creation unit includes a procurement information provision unit that provides information on nearby suppliers and prices. The material list creation unit provides information on nearby suppliers and prices, for example, using a generative AI. The material list creation unit can also provide procurement information efficiently and accurately using a generative AI. For example, the material list creation unit can use a generative AI model that takes a material list as input and outputs procurement information. This allows users to procure materials efficiently and accurately by providing information on nearby suppliers and prices.

[0090] The assembly support unit includes a video provision unit that provides assembly instructions with video. The assembly support unit can, for example, use generative AI to provide assembly instructions with video. The assembly support unit can also use generative AI to support users in accurately assembling furniture. For example, the assembly support unit can use a generative AI model that takes a purchase list as input and outputs assembly instructions. This allows users to accurately assemble furniture by providing assembly instructions with video.

[0091] The image analysis unit estimates the user's emotions and adjusts the analysis method of the room photograph based on the estimated user emotions. The image analysis unit can estimate the user's emotions using, for example, generative AI. The image analysis unit can also adjust the analysis method based on the user's emotions using generative AI. For example, the image analysis unit can use a generative AI model that takes the user's emotions as input and outputs an analysis method. For example, if the user is relaxed, the image analysis unit performs a detailed analysis and extracts the room's features in detail. If the user is in a hurry, the image analysis unit performs a simplified analysis and extracts only the main features. If the user is excited, the image analysis unit performs an analysis that focuses on color and design. By adjusting the analysis method according to the user's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The image analysis unit improves analysis accuracy by considering the room's lighting conditions. For example, the image analysis unit considers the room's lighting conditions using generative AI. The image analysis unit can also improve analysis accuracy based on lighting conditions using generative AI. For example, the image analysis unit can use a generative AI model that takes lighting conditions as input and outputs analysis accuracy. For example, if the room lighting is dim, the image analysis unit automatically adjusts the brightness of the image and performs the analysis. If the room lighting is too bright, the image analysis unit adjusts the contrast of the image and performs the analysis. If the room lighting is natural light, the image analysis unit performs the analysis in a way that minimizes the effect of shadows. In this way, analysis accuracy is improved by considering the room's lighting conditions.

[0093] The image analysis unit optimizes the analysis results by considering the furniture arrangement and color scheme when analyzing photos of a room. For example, the image analysis unit uses generative AI to consider the furniture arrangement and color scheme. The image analysis unit can also optimize the analysis results based on the furniture arrangement and color scheme using generative AI. For example, the image analysis unit can use a generative AI model that takes the furniture arrangement and color scheme as input and outputs analysis results. For example, it can analyze the furniture arrangement to accurately understand the room layout. It can analyze the furniture color scheme to extract the room's design theme. It can combine the furniture arrangement and color scheme to analyze the overall atmosphere of the room. In this way, the analysis results are optimized by considering the furniture arrangement and color scheme.

[0094] The image analysis unit estimates the user's emotions and adjusts the display method of the analysis results based on the estimated user emotions. The image analysis unit estimates the user's emotions, for example, using generative AI. The image analysis unit can also use generative AI to adjust the display method of the analysis results based on the user's emotions. For example, the image analysis unit can use a generative AI model that takes the user's emotions as input and outputs a display method. For example, if the user is relaxed, the image analysis unit displays detailed analysis results. If the user is in a hurry, the image analysis unit displays concise analysis results. If the user is excited, the image analysis unit displays visually appealing analysis results. By adjusting the display method of the analysis results according to the user's emotions, it becomes possible to display the results in a way that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The image analysis unit improves analysis accuracy by referencing the user's past photos of the room when analyzing photos of the room. For example, the image analysis unit can use generative AI to reference the user's past photos of the room. The image analysis unit can also improve analysis accuracy based on past photos using generative AI. For example, the image analysis unit can use a generative AI model that takes past photos as input and outputs analysis accuracy. For example, it can analyze changes in the current room based on the user's past photos of the room. It references the user's past photos of the room and extracts similar features. It compares the user's past photos of the room and selects the optimal analysis method. As a result, analysis accuracy is improved by referencing the user's past photos of the room.

[0096] The image analysis unit modifies its analysis algorithm according to the room's purpose when analyzing a photograph of a room. For example, the image analysis unit considers the room's purpose using generative AI. The image analysis unit can also modify the analysis algorithm based on the purpose using generative AI. For example, the image analysis unit can use a generative AI model that takes the purpose as input and outputs an analysis algorithm. For example, in the case of a living room, the image analysis unit performs an analysis that emphasizes the arrangement of furniture and color scheme. In the case of a bedroom, the image analysis unit performs an analysis that emphasizes lighting and bed placement. In the case of a kitchen, the image analysis unit performs an analysis that emphasizes storage space and workspace. By changing the analysis algorithm according to the room's purpose, more appropriate analysis results can be obtained.

[0097] The modeling unit estimates the user's emotions and adjusts the 3D model generation method based on the estimated user emotions. The modeling unit estimates the user's emotions, for example, using generative AI. The modeling unit can also use generative AI to adjust the 3D model generation method based on the user's emotions. For example, the modeling unit can use a generative AI model that takes the user's emotions as input and outputs a generation method. For example, if the user is relaxed, the modeling unit generates a detailed 3D model. If the user is in a hurry, the modeling unit generates a simplified 3D model. If the user is excited, the modeling unit generates a visually appealing 3D model. This allows for the generation of more appropriate 3D models by adjusting the 3D model generation method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The modeling unit improves the realism of 3D models by considering the materials and textures of the room when generating them. For example, the modeling unit uses a generative AI to consider the materials and textures of the room. The modeling unit can also improve the realism of the model based on materials and textures using a generative AI. For example, the modeling unit can use a generative AI model that takes materials and textures as input and outputs realism. For example, it can analyze the material of the room's walls and reflect it in the 3D model. It can analyze the texture of the room's floor and reflect it in the 3D model. It can analyze the material and texture of the room's furniture and reflect it in the 3D model. In this way, the realism of the 3D model is improved by considering the materials and textures of the room.

[0099] The modeling unit optimizes the appearance of a 3D model by simulating the room's lighting conditions when generating the model. For example, the modeling unit can use a generative AI to simulate the room's lighting conditions. The modeling unit can also use a generative AI to optimize the model's appearance based on the lighting conditions. For example, the modeling unit can use a generative AI model that takes lighting conditions as input and outputs the appearance. For example, it can simulate the room's lighting conditions and reflect them in the 3D model. It can simulate the effect of natural light in the room and reflect it in the 3D model. It can simulate the effect of artificial light in the room and reflect it in the 3D model. In this way, the appearance of the 3D model is optimized by simulating the room's lighting conditions.

[0100] The modeling unit estimates the user's emotions and adjusts the display method of the 3D model based on the estimated user emotions. The modeling unit estimates the user's emotions, for example, using generative AI. The modeling unit can also use generative AI to adjust the display method of the 3D model based on the user's emotions. For example, the modeling unit can use a generative AI model that takes the user's emotions as input and outputs a display method. For example, if the user is relaxed, the modeling unit displays a detailed 3D model. If the user is in a hurry, the modeling unit displays a concise 3D model. If the user is excited, the modeling unit displays a visually appealing 3D model. This allows for a display that is easy for the user to understand by adjusting the display method of the 3D model according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The modeling unit improves generation accuracy by referencing the user's past 3D models when generating 3D models. For example, the modeling unit can use a generation AI to reference the user's past 3D models. The modeling unit can also improve generation accuracy based on past models using a generation AI. For example, the modeling unit can use a generation AI model that takes past models as input and outputs generation accuracy. For example, it can generate the current 3D model based on the user's past 3D models. It references the user's past 3D models and extracts similar features. It compares the user's past 3D models and selects the optimal generation method. As a result, generation accuracy is improved by referencing the user's past 3D models.

[0102] The modeling unit modifies its generation algorithm according to the room's purpose when generating 3D models. For example, the modeling unit considers the room's purpose using a generation AI. The modeling unit can also modify the generation algorithm based on the purpose using a generation AI. For example, the modeling unit can use a generation AI model that takes the purpose as input and outputs a generation algorithm. For example, in the case of a living room, the modeling unit generates a 3D model that emphasizes furniture arrangement and color scheme. In the case of a bedroom, the modeling unit generates a 3D model that emphasizes lighting and bed placement. In the case of a kitchen, the modeling unit generates a 3D model that emphasizes storage space and workspace. By changing the generation algorithm according to the room's purpose, a more appropriate 3D model can be generated.

[0103] The design proposal department estimates the user's emotions and adjusts the presentation of the design proposal based on the estimated emotions. For example, the design proposal department might use generative AI to estimate the user's emotions. It can also use generative AI to adjust the presentation of the design proposal based on the user's emotions. For example, the design proposal department could use a generative AI model that takes the user's emotions as input and outputs a presentation method. For instance, if the user is relaxed, the design proposal department would provide a detailed design proposal. If the user is in a hurry, the design proposal department would provide a concise design proposal. If the user is excited, the design proposal department would provide a visually appealing design proposal. By adjusting the presentation of the design proposal according to the user's emotions, it becomes possible to provide proposals that are easy for the user to understand. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The design proposal department improves the accuracy of its proposals by referring to the user's past design history. For example, the design proposal department can use generative AI to refer to the user's past design history. The design proposal department can also use generative AI to improve the accuracy of proposals based on past history. For example, the design proposal department can use a generative AI model that takes past history as input and outputs the accuracy of the proposal. For example, it can make current design proposals based on the user's past design history. It can refer to the user's past design history and propose similar designs. It can compare the user's past design history and make the optimal design proposal. In this way, the accuracy of proposals is improved by referring to the user's past design history.

[0105] The design proposal department applies different design algorithms depending on the room's purpose and theme when making design proposals. For example, the design proposal department uses generative AI to consider the room's purpose and theme. The design proposal department can also use generative AI to apply design algorithms based on the purpose and theme. For example, the design proposal department can use a generative AI model that takes the purpose and theme as input and outputs a design algorithm. For example, in the case of a living room, the design proposal department will make a design proposal that emphasizes furniture arrangement and color scheme. In the case of a bedroom, the design proposal department will make a design proposal that emphasizes lighting and bed placement. In the case of a kitchen, the design proposal department will make a design proposal that emphasizes storage space and workspace. By applying different design algorithms according to the room's purpose and theme, it becomes possible to make the optimal design proposal.

[0106] The design proposal department estimates the user's emotions and prioritizes design proposals based on those emotions. The design proposal department can estimate user emotions using, for example, generative AI. It can also use generative AI to prioritize design proposals based on user emotions. For example, the design proposal department can use a generative AI model that takes user emotions as input and outputs priorities. For instance, if the user is relaxed, the design proposal department prioritizes detailed design proposals. If the user is in a hurry, the design proposal department prioritizes concise design proposals. If the user is excited, the design proposal department prioritizes visually appealing design proposals. This allows for optimal proposals for the user by prioritizing design proposals according to their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The design proposal department prioritizes proposing highly relevant designs by considering the user's geographical location when making design proposals. For example, the design proposal department can use generative AI to consider the user's geographical location. The design proposal department can also use generative AI to prioritize proposing highly relevant designs based on geographical location. For example, the design proposal department can use a generative AI model that takes geographical location as input and outputs highly relevant designs. For example, it can propose designs suitable for the local climate based on the user's geographical location. For example, it can propose designs suitable for the local culture based on the user's geographical location. For example, it can propose designs suitable for the local architectural style based on the user's geographical location. This makes it possible to propose highly relevant designs by considering the user's geographical location.

[0108] The design proposal department analyzes users' social media activity and proposes relevant designs when making design proposals. For example, the design proposal department can use generative AI to analyze users' social media activity. The design proposal department can also use generative AI to propose relevant designs based on social media activity. For example, the design proposal department can use a generative AI model that takes social media activity as input and outputs relevant designs. For instance, it can analyze users' social media activity and propose designs they like. It can analyze users' social media activity and propose designs that are in line with current trends. It can analyze users' social media activity and propose designs that match the preferences of their friends and followers. This makes it possible to propose relevant designs by analyzing users' social media activity.

[0109] The material list creation unit estimates the user's emotions and adjusts the material list creation method based on the estimated user emotions. The material list creation unit estimates the user's emotions, for example, using generative AI. The material list creation unit can also adjust the material list creation method based on the user's emotions using generative AI. For example, the material list creation unit can use a generative AI model that takes the user's emotions as input and outputs a creation method. For example, if the user is relaxed, the material list creation unit creates a detailed material list. If the user is in a hurry, the material list creation unit creates a concise material list. If the user is excited, the material list creation unit creates a visually appealing material list. In this way, by adjusting the material list creation method according to the user's emotions, the optimal material list for the user can be created. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0110] The material list creation unit improves the accuracy of the material list by referring to the user's past material usage history when creating the list. For example, the material list creation unit can refer to the user's past material usage history using a generative AI. The material list creation unit can also improve the accuracy of the list based on past history using a generative AI. For example, the material list creation unit can use a generative AI model that takes past history as input and outputs the accuracy of the list. For example, it can create a current material list based on the user's past material usage history. It refers to the user's past material usage history and lists similar materials. It compares the user's past material usage history and creates an optimal material list. In this way, the accuracy of the list is improved by referring to the user's past material usage history.

[0111] The materials list creation unit applies different materials list creation algorithms depending on the room's purpose and theme when creating a materials list. For example, the materials list creation unit considers the room's purpose and theme using generative AI. The materials list creation unit can also apply a materials list creation algorithm based on the purpose and theme using generative AI. For example, the materials list creation unit can use a generative AI model that takes the purpose and theme as input and outputs a materials list creation algorithm. For example, in the case of a living room, the materials list creation unit creates a materials list that emphasizes furniture arrangement and color scheme. In the case of a bedroom, the materials list creation unit creates a materials list that emphasizes lighting and bed placement. In the case of a kitchen, the materials list creation unit creates a materials list that emphasizes storage space and workspace. In this way, by applying different materials list creation algorithms according to the room's purpose and theme, the optimal materials list can be created.

[0112] The material list creation unit estimates the user's emotions and adjusts the display method of the material list based on the estimated user emotions. The material list creation unit estimates the user's emotions, for example, using generative AI. The material list creation unit can also adjust the display method of the material list based on the user's emotions using generative AI. For example, the material list creation unit can use a generative AI model that takes the user's emotions as input and outputs a display method. For example, if the user is relaxed, the material list creation unit displays a detailed material list. If the user is in a hurry, the material list creation unit displays a concise material list. If the user is excited, the material list creation unit displays a visually appealing material list. In this way, by adjusting the display method of the material list according to the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0113] The material list creation unit prioritizes listing highly relevant materials by considering the user's geographical location when creating a material list. For example, the material list creation unit can use a generative AI to consider the user's geographical location. The material list creation unit can also prioritize listing highly relevant materials based on geographical location using a generative AI. For example, the material list creation unit can use a generative AI model that takes geographical location as input and outputs highly relevant materials. For example, it can list materials available at nearby home improvement stores based on the user's geographical location. It can also list materials suitable for the local climate based on the user's geographical location. By considering the user's geographical location, it can prioritize listing highly relevant materials.

[0114] The material list creation unit analyzes the user's social media activity and lists relevant materials when creating a material list. The material list creation unit can analyze the user's social media activity using, for example, generative AI. The material list creation unit can also list relevant materials based on social media activity using generative AI. For example, the material list creation unit can use a generative AI model that takes social media activity as input and outputs relevant materials. For example, it can analyze the user's social media activity and list their preferred materials. It can analyze the user's social media activity and list materials that match current trends. It can analyze the user's social media activity and list materials that match the preferences of their friends and followers. In this way, by analyzing the user's social media activity, relevant materials can be listed.

[0115] The purchase list provider estimates the user's emotions and adjusts the method of providing the purchase list based on the estimated emotions. The purchase list provider estimates the user's emotions, for example, using generative AI. The purchase list provider can also adjust the method of providing the purchase list based on the user's emotions using generative AI. For example, the purchase list provider can use a generative AI model that takes the user's emotions as input and outputs a method of provision. For example, if the user is relaxed, the purchase list provider provides a detailed purchase list. If the user is in a hurry, the purchase list provider provides a concise purchase list. If the user is excited, the purchase list provider provides a visually appealing purchase list. In this way, by adjusting the method of providing the purchase list according to the user's emotions, the optimal purchase list can be provided to the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0116] The purchase list provider improves the accuracy of the list by referring to the user's past purchase history when providing the list. The purchase list provider can, for example, use a generative AI to refer to the user's past purchase history. The purchase list provider can also improve the accuracy of the list based on past history using a generative AI. For example, the purchase list provider can use a generative AI model that takes past history as input and outputs the accuracy of the list. For example, it can create a current purchase list based on the user's past purchase history. It can refer to the user's past purchase history and list similar suppliers. It can compare the user's past purchase history and create an optimal purchase list. In this way, the accuracy of the list is improved by referring to the user's past purchase history.

[0117] The purchasing list provider applies different purchasing list provision algorithms depending on the room's purpose and theme when providing purchasing lists. For example, the purchasing list provider uses a generative AI to consider the room's purpose and theme. The purchasing list provider can also use a generative AI to apply a purchasing list provision algorithm based on the purpose and theme. For example, the purchasing list provider can use a generative AI model that takes the purpose and theme as input and outputs a purchasing list provision algorithm. For example, in the case of a living room, the purchasing list provider provides a purchasing list that emphasizes furniture arrangement and color scheme. In the case of a bedroom, the purchasing list provider provides a purchasing list that emphasizes lighting and bed placement. In the case of a kitchen, the purchasing list provider provides a purchasing list that emphasizes storage space and workspace. In this way, by applying different purchasing list provision algorithms depending on the room's purpose and theme, the optimal purchasing list can be provided.

[0118] The shopping list provider estimates the user's emotions and determines the priority of the shopping list based on the estimated emotions. The shopping list provider can estimate the user's emotions using, for example, generative AI. The shopping list provider can also determine the priority of the shopping list based on the user's emotions using generative AI. For example, the shopping list provider can use a generative AI model that takes the user's emotions as input and outputs a priority. For example, if the user is relaxed, the shopping list provider will prioritize detailed shopping lists. If the user is in a hurry, the shopping list provider will prioritize concise shopping lists. If the user is excited, the shopping list provider will prioritize visually appealing shopping lists. In this way, by determining the priority of shopping lists according to the user's emotions, the optimal list for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0119] The purchasing list provider, when providing a purchasing list, prioritizes listing highly relevant suppliers by considering the user's geographical location. For example, the purchasing list provider can use generative AI to consider the user's geographical location. The purchasing list provider can also use generative AI to prioritize listing highly relevant suppliers based on geographical location. For example, the purchasing list provider can use a generative AI model that takes geographical location as input and outputs highly relevant suppliers. For example, it can list suppliers available at nearby home improvement stores based on the user's geographical location. It can also list suppliers suitable for the local climate based on the user's geographical location. By considering the user's geographical location, it can prioritize listing highly relevant suppliers.

[0120] The purchase list provider analyzes the user's social media activity and lists relevant retailers when providing purchase lists. For example, the purchase list provider uses generative AI to analyze the user's social media activity. The purchase list provider can also use generative AI to list relevant retailers based on social media activity. For example, the purchase list provider can use a generative AI model that takes social media activity as input and outputs relevant retailers. For example, it can analyze the user's social media activity and list preferred retailers. It can analyze the user's social media activity and list retailers that match current trends. It can analyze the user's social media activity and list retailers that match the preferences of their friends and followers. This allows for the listing of relevant retailers by analyzing the user's social media activity.

[0121] The assembly support unit estimates the user's emotions and adjusts the method of providing assembly instructions based on the estimated user emotions. The assembly support unit estimates the user's emotions, for example, using generative AI. The assembly support unit can also use generative AI to adjust the method of providing assembly instructions based on the user's emotions. For example, the assembly support unit can use a generative AI model that takes the user's emotions as input and outputs a method of provision. For example, if the user is relaxed, the assembly support unit provides detailed assembly instructions. If the user is in a hurry, the assembly support unit provides concise assembly instructions. If the user is excited, the assembly support unit provides visually appealing assembly instructions. In this way, by adjusting the method of providing assembly instructions according to the user's emotions, the optimal procedure for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0122] The assembly support unit improves the accuracy of assembly procedures by referring to the user's past assembly history when providing assembly instructions. For example, the assembly support unit can refer to the user's past assembly history using generative AI. The assembly support unit can also improve the accuracy of procedures based on past history using generative AI. For example, the assembly support unit can use a generative AI model that takes past history as input and outputs the accuracy of the procedures. For example, it can create the current assembly procedure based on the user's past assembly history. It can refer to the user's past assembly history and provide similar procedures. It can compare the user's past assembly history and create the optimal assembly procedure. In this way, the accuracy of the procedures is improved by referring to the user's past assembly history.

[0123] The assembly support unit applies different assembly procedure provision algorithms depending on the room's purpose and theme when providing assembly instructions. For example, the assembly support unit considers the room's purpose and theme using generative AI. The assembly support unit can also apply assembly procedure provision algorithms based on the purpose and theme using generative AI. For example, the assembly support unit can use a generative AI model that takes the purpose and theme as input and outputs an assembly procedure provision algorithm. For example, in the case of a living room, the assembly support unit provides assembly instructions that emphasize furniture arrangement and color scheme. In the case of a bedroom, the assembly support unit provides assembly instructions that emphasize lighting and bed placement. In the case of a kitchen, the assembly support unit provides assembly instructions that emphasize storage space and workspace. By applying different assembly procedure provision algorithms depending on the room's purpose and theme, the optimal assembly procedure can be provided.

[0124] The assembly support unit estimates the user's emotions and determines the priority of assembly steps based on the estimated emotions. The assembly support unit estimates the user's emotions, for example, using generative AI. The assembly support unit can also determine the priority of assembly steps based on the user's emotions using generative AI. For example, the assembly support unit can use a generative AI model that takes the user's emotions as input and outputs priorities. For example, if the user is relaxed, the assembly support unit prioritizes detailed assembly steps. If the user is in a hurry, the assembly support unit prioritizes concise assembly steps. If the user is excited, the assembly support unit prioritizes visually appealing assembly steps. This allows the user to be provided with the most optimal steps by determining the priority of assembly steps according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0125] The assembly support unit, when providing assembly instructions, prioritizes providing highly relevant instructions by considering the user's geographical location information. For example, the assembly support unit considers the user's geographical location information using generative AI. The assembly support unit can also prioritize providing highly relevant instructions based on geographical location information using generative AI. For example, the assembly support unit can use a generative AI model that takes geographical location information as input and outputs highly relevant instructions. For example, it can provide assembly instructions suitable for the local climate based on the user's geographical location information. For example, it can provide assembly instructions suitable for the local culture based on the user's geographical location information. For example, when providing assembly instructions suitable for the local architectural style based on the user's geographical location information, it analyzes the user's social media activity to provide relevant instructions. For example, the assembly support unit analyzes the user's social media activity using generative AI. The assembly support unit can also provide relevant instructions based on social media activity using generative AI. For example, the assembly support unit can use a generative AI model that takes social media activity as input and outputs relevant instructions. For example, it can analyze the user's social media activity and provide preferred assembly instructions. For example, it can analyze the user's social media activity and provide assembly instructions that match current trends. It analyzes users' social media activity and provides customized instructions tailored to the preferences of their friends and followers. This allows for the provision of relevant instructions based on the analysis of users' social media activity.

[0126] The feedback receiving unit estimates the user's emotions and adjusts the feedback receiving method based on the estimated emotions. The feedback receiving unit estimates the user's emotions, for example, using generative AI. The feedback receiving unit can also use generative AI to adjust the feedback receiving method based on the user's emotions. For example, the feedback receiving unit can use a generative AI model that takes the user's emotions as input and outputs a receiving method. For example, if the user is relaxed, the feedback receiving unit will receive detailed feedback. If the user is in a hurry, the feedback receiving unit will receive concise feedback. If the user is excited, the feedback receiving unit will receive visually appealing feedback. In this way, by adjusting the feedback receiving method according to the user's emotions, the user can receive the most appropriate feedback. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0127] The feedback receiving unit improves the accuracy of feedback reception by referring to the user's past feedback history when receiving feedback. The feedback receiving unit can refer to the user's past feedback history, for example, using generative AI. The feedback receiving unit can also improve the accuracy of reception based on past history using generative AI. For example, for feed purposes, feedback prioritization is determined based on the user's emotions. The feedback receiving unit can estimate the user's emotions, for example, using generative AI. The feedback receiving unit can also determine feedback prioritization based on the user's emotions using generative AI. For example, the feedback receiving unit can use a generative AI model that takes the user's emotions as input and outputs priorities. For example, if the user is relaxed, the feedback receiving unit prioritizes detailed feedback. If the user is in a hurry, the feedback receiving unit prioritizes concise feedback. If the user is excited, the feedback receiving unit prioritizes visually appealing feedback. This ensures that the most appropriate feedback for the user is received preferentially by determining feedback prioritization according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0128] The feedback receiving unit improves the accuracy of feedback reception by referring to the user's past feedback history when receiving feedback. The feedback receiving unit can, for example, use generative AI to refer to the user's past feedback history. The feedback receiving unit can also improve the accuracy of reception based on past history using generative AI. For example, the feedback receiving unit can use a generative AI model that takes past history as input and outputs the accuracy of reception. For example, it can receive current feedback based on the user's past feedback history. It can refer to the user's past feedback history and receive similar feedback. It can compare the user's past feedback history and select the optimal feedback reception method. In this way, the accuracy of reception is improved by referring to the user's past feedback history.

[0129] The feedback receiver estimates the user's emotions and determines the priority of feedback based on the estimated emotions. The feedback receiver can estimate the user's emotions using, for example, generative AI. The feedback receiver can also determine the priority of feedback based on the user's emotions using generative AI. For example, the feedback receiver can use a generative AI model that takes the user's emotions as input and outputs priorities. For example, if the user is relaxed, the feedback receiver prioritizes detailed feedback. If the user is in a hurry, the feedback receiver prioritizes concise feedback. If the user is excited, the feedback receiver prioritizes visually appealing feedback. This ensures that the most appropriate feedback is received preferentially by determining the priority of feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0130] The feedback receiving unit, when receiving feedback, prioritizes receiving highly relevant feedback by considering the user's geographical location information. For example, the feedback receiving unit can use generative AI to consider the user's geographical location information. The feedback receiving unit can also use generative AI to prioritize receiving highly relevant feedback based on geographical location information. For example, the feedback receiving unit can use a generative AI model that takes geographical location information as input and outputs highly relevant feedback. For example, it can prioritize feedback suitable for the local climate based on the user's geographical location information. For example, it can prioritize feedback suitable for the local culture based on the user's geographical location information. For example, it can prioritize feedback suitable for the local architectural style based on the user's geographical location information. This allows for the prioritization of highly relevant feedback by considering the user's geographical location information.

[0131] The procurement information provider estimates the user's emotions and adjusts the method of providing procurement information based on the estimated emotions. The procurement information provider can estimate the user's emotions, for example, using generative AI. The procurement information provider can also use generative AI to adjust the method of providing procurement information based on the user's emotions. For example, the procurement information provider can use a generative AI model that takes the user's emotions as input and outputs a method of provision. For example, if the user is relaxed, the procurement information provider will provide detailed procurement information. If the user is in a hurry, the procurement information provider will provide concise procurement information. If the user is excited, the procurement information provider will provide visually appealing procurement information. In this way, by adjusting the method of providing procurement information according to the user's emotions, the optimal procurement information for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0132] The procurement information provider improves the accuracy of the information by referring to the user's past procurement history when providing procurement information. The procurement information provider can, for example, use generative AI to refer to the user's past procurement history. The procurement information provider can also improve the accuracy of the information based on past history using generative AI. For example, the procurement information provider can use a generative AI model that takes past history as input and outputs the accuracy of the information. For example, it can provide current procurement information based on the user's past procurement history. It can refer to the user's past procurement history and provide similar suppliers. It can compare the user's past procurement history and provide optimal procurement information. In this way, the accuracy of the information is improved by referring to the user's past procurement history.

[0133] The procurement information provider estimates the user's emotions and prioritizes procurement information based on the estimated emotions. The procurement information provider can estimate user emotions using, for example, generative AI. The procurement information provider can also prioritize procurement information based on user emotions using generative AI. For example, the procurement information provider can use a generative AI model that takes user emotions as input and outputs priorities. For example, if the user is relaxed, the procurement information provider prioritizes detailed procurement information. If the user is in a hurry, the procurement information provider prioritizes concise procurement information. If the user is excited, the procurement information provider prioritizes visually appealing procurement information. This allows for the provision of optimal information to the user by prioritizing procurement information according to their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0134] The Procurement Information Provision Department, when providing procurement information, prioritizes providing highly relevant suppliers by considering the user's geographical location. For example, the Procurement Information Provision Department considers the user's geographical location using generative AI. The Procurement Information Provision Department can also prioritize providing highly relevant suppliers based on geographical location using generative AI. For example, the Procurement Information Provision Department can use a generative AI model that takes geographical location as input and outputs highly relevant suppliers. For example, it can prioritize providing nearby suppliers based on the user's geographical location. It can also prioritize providing suppliers suitable for the local climate based on the user's geographical location. This allows for the prioritization of highly relevant suppliers by considering the user's geographical location.

[0135] The Procurement Information Provision Department analyzes users' social media activity and provides relevant suppliers when providing procurement information. For example, the Procurement Information Provision Department uses generative AI to analyze users' social media activity. The Procurement Information Provision Department can also use generative AI to provide relevant suppliers based on social media activity. For example, the Procurement Information Provision Department can use a generative AI model that takes social media activity as input and outputs relevant suppliers. For example, it can analyze users' social media activity and provide preferred suppliers. It can analyze users' social media activity and provide suppliers that match current trends. It can analyze users' social media activity and provide suppliers that match the preferences of their friends and followers. In this way, by analyzing users' social media activity, it is possible to provide relevant suppliers.

[0136] The video delivery unit estimates the user's emotions and adjusts the video delivery method based on the estimated emotions. The video delivery unit can estimate the user's emotions, for example, using generative AI. The video delivery unit can also adjust the video delivery method based on the user's emotions using generative AI. For example, the video delivery unit can use a generative AI model that takes the user's emotions as input and outputs a delivery method. For example, if the user is relaxed, the video delivery unit will provide detailed video. If the user is in a hurry, the video delivery unit will provide concise video. If the user is excited, the video delivery unit will provide visually appealing video. In this way, by adjusting the video delivery method according to the user's emotions, the optimal video for the user can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0137] The video provisioning unit improves the accuracy of its provision by referring to the user's past video viewing history when providing videos. For example, the video provisioning unit can use generative AI to refer to the user's past video viewing history. The video provisioning unit can also use generative AI to improve the accuracy of its provision based on past history. For example, the video provisioning unit can use a generative AI model that takes past history as input and outputs the accuracy of its provision. For example, it can provide current videos based on the user's past video viewing history. It can refer to the user's past video viewing history and provide similar videos. It can compare the user's past video viewing history and provide the most suitable video. In this way, the accuracy of provision is improved by referring to the user's past video viewing history.

[0138] The video delivery unit estimates the user's emotions and prioritizes videos based on the estimated emotions. The video delivery unit can estimate the user's emotions, for example, using generative AI. The video delivery unit can also prioritize videos based on the user's emotions using generative AI. For example, the video delivery unit can use a generative AI model that takes the user's emotions as input and outputs priorities. For example, if the user is relaxed, the video delivery unit will prioritize detailed videos. If the user is in a hurry, the video delivery unit will prioritize concise videos. If the user is excited, the video delivery unit will prioritize visually appealing videos. In this way, by prioritizing videos according to the user's emotions, the most suitable videos for the user can be preferentially provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0139] The video provision department prioritizes providing highly relevant videos by considering the user's geographical location information when providing videos. For example, the video provision department considers the user's geographical location information using generative AI. The video provision department can also prioritize providing highly relevant videos based on geographical location information using generative AI. For example, the video provision department can use a generative AI model that takes geographical location information as input and outputs highly relevant videos. For example, it can provide videos suitable for the local climate based on the user's geographical location information. For example, it can provide videos suitable for the local culture based on the user's geographical location information. For example, it can provide videos suitable for the local architectural style based on the user's geographical location information. In this way, by considering the user's geographical location information, it is possible to prioritize providing highly relevant videos.

[0140] The video provision department analyzes the user's social media activity and provides relevant videos when providing videos. For example, the video provision department uses generative AI to analyze the user's social media activity. The video provision department can also use generative AI to provide relevant videos based on social media activity. For example, the video provision department can use a generative AI model that takes social media activity as input and outputs relevant videos. For example, it can analyze the user's social media activity and provide videos they like. It can analyze the user's social media activity and provide videos that match current trends. It can analyze the user's social media activity and provide videos that match the preferences of their friends and followers. In this way, by analyzing the user's social media activity, it is possible to provide relevant videos.

[0141] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0142] The DIY furniture making support system can estimate the user's emotions and suggest furniture designs based on those emotions. For example, if the user is relaxed, the system can suggest furniture with calming colors and simple designs. If the user is excited, the system can suggest furniture with bright colors and unique designs. If the user is stressed, the system can suggest designs and materials that have a relaxing effect. This allows for optimal design suggestions tailored to the user's emotions.

[0143] The DIY furniture making support system can provide more accurate design suggestions by referencing the user's past design history. For example, it can suggest current designs based on the designs and materials the user has previously selected. It can also analyze the user's preferences by referring to past feedback and make suggestions accordingly. Furthermore, it can refer to photos of furniture the user has created in the past and suggest similar designs. This allows for design suggestions that are tailored to the user's preferences.

[0144] The DIY furniture making support system can propose designs tailored to the user's geographical location. For example, it can suggest warm materials and designs to users living in cold climates, and cool materials and designs to users living in warmer climates. It can also propose designs that match the local culture and architectural style. This enables the system to provide optimal design proposals suited to each region.

[0145] The DIY furniture making support system can analyze a user's social media activity to suggest designs that align with current trends. For example, it can suggest designs based on influencers and brands the user follows. It can also analyze posts the user has "liked" or shared to suggest designs that the user might like. Furthermore, it can suggest designs that match the preferences of the user's friends and followers. This enables the system to provide optimal design suggestions based on the user's social media activity.

[0146] The DIY furniture making support system can estimate the user's emotions and adjust how the material list is created based on those emotions. For example, if the user is relaxed, the system can create a detailed material list. If the user is in a hurry, the system can create a concise material list. And if the user is excited, the system can create a visually appealing material list. This allows for the creation of an optimal material list tailored to the user's emotions.

[0147] The DIY furniture making support system can create a more accurate material list by referring to the user's past material usage history. For example, it can create a current material list based on materials the user has used in the past. It can also refer to the user's past projects and list similar materials. Furthermore, it can refer to the user's past feedback and list preferred materials. This allows for the creation of a material list tailored to the user's preferences.

[0148] The DIY furniture making support system can create a list of materials suitable for the user's region, taking into account their geographical location. For example, it can list materials with high insulation properties for users living in cold climates, and materials with good ventilation for users living in warmer regions. It can also list materials suitable for the local climate and environment. This allows for the creation of an optimal material list tailored to the user's region.

[0149] The DIY furniture making support system can analyze a user's social media activity to create a list of materials that match current trends. For example, it can list materials used by influencers and brands the user follows. It can also analyze posts the user "likes" and shares to list their preferred materials. Furthermore, it can create material lists tailored to the preferences of the user's friends and followers. This allows for the creation of an optimal material list based on the user's social media activity.

[0150] The DIY furniture making support system can estimate the user's emotions and adjust how it provides a shopping list based on those emotions. For example, if the user is relaxed, the system can provide a detailed shopping list. If the user is in a hurry, the system can provide a concise shopping list. And if the user is excited, the system can provide a visually appealing shopping list. This allows the system to provide the optimal shopping list tailored to the user's emotions.

[0151] The DIY furniture making support system can provide a more accurate shopping list by referencing the user's past purchase history. For example, it can create a current shopping list based on materials and tools the user has purchased in the past. It can also refer to the user's past projects and list similar suppliers. Furthermore, it can refer to the user's past feedback and list preferred suppliers. This allows the system to provide a shopping list tailored to the user's preferences.

[0152] The following briefly describes the processing flow for example form 2.

[0153] Step 1: The image analysis unit analyzes the room photos provided by the user. The image analysis unit uses generation AI to extract room features and dimensions, accurately determining the height of the walls, the location of windows, and other details of the room. Step 2: The modeling unit passes the data extracted by the image analysis unit to a 3D modeling tool and generates a precise spatial model using a generation AI. This generates a 3D model that reflects the actual dimensions and characteristics of the room. Step 3: The design proposal department proposes furniture designs within the 3D models generated by the modeling department. The design proposal department uses the generation AI to propose furniture designs that meet the user's requirements. Step 4: The materials list creation unit creates a list of necessary materials based on the design proposed by the design proposal unit. The materials list creation unit uses a generation AI to create the materials list efficiently and accurately. Step 5: The purchasing list provision unit provides the purchasing list created by the material list creation unit. The purchasing list provision unit uses a generation AI to provide information on nearby suppliers and prices. Step 6: The assembly support unit provides video-based support for the assembly procedure based on the purchase list provided by the purchase list provision unit. The assembly support unit uses generating AI to help the user assemble the furniture accurately.

[0154] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0156] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements described above, including the image analysis unit, modeling unit, design proposal unit, material list creation unit, purchase list provision unit, and assembly support unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the image analysis unit acquires a photograph of the room using the camera 42 of the smart device 14 and analyzes it using the specific processing unit 290 of the data processing unit 12. The modeling unit generates a 3D model using the specific processing unit 290 of the data processing unit 12. The design proposal unit proposes furniture designs using the specific processing unit 290 of the data processing unit 12. The material list creation unit creates a material list using the specific processing unit 290 of the data processing unit 12. The purchase list provision unit provides a purchase list using the specific processing unit 290 of the data processing unit 12. The assembly support unit supports the assembly procedure with video using the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0158] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0159] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0160] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0161] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0162] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0164] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0165] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0166] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0167] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0168] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0170] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0172] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements described above, including the image analysis unit, modeling unit, design proposal unit, material list creation unit, purchase list provision unit, and assembly support unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the image analysis unit acquires a photograph of a room using the camera 42 of the smart glasses 214 and analyzes it using the specific processing unit 290 of the data processing unit 12. The modeling unit generates a 3D model using the specific processing unit 290 of the data processing unit 12. The design proposal unit proposes furniture designs using the specific processing unit 290 of the data processing unit 12. The material list creation unit creates a material list using the specific processing unit 290 of the data processing unit 12. The purchase list provision unit provides a purchase list using the specific processing unit 290 of the data processing unit 12. The assembly support unit supports the assembly procedure with video using the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0174] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0175] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0176] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0177] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0178] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0179] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0180] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0181] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0182] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0183] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0184] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0185] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0186] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0187] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0188] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0189] Each of the multiple elements described above, including the image analysis unit, modeling unit, design proposal unit, material list creation unit, purchase list provision unit, and assembly support unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the image analysis unit acquires a photograph of the room using the camera 42 of the headset terminal 314 and analyzes it using the specific processing unit 290 of the data processing unit 12. The modeling unit generates a 3D model using the specific processing unit 290 of the data processing unit 12. The design proposal unit proposes furniture designs using the specific processing unit 290 of the data processing unit 12. The material list creation unit creates a material list using the specific processing unit 290 of the data processing unit 12. The purchase list provision unit provides a purchase list using the specific processing unit 290 of the data processing unit 12. The assembly support unit supports the assembly procedure with video using the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0190] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0191] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0192] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0193] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0194] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0195] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0196] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0197] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0198] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0199] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0200] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0201] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0202] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0203] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0204] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0205] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0206] Each of the multiple elements described above, including the image analysis unit, modeling unit, design proposal unit, material list creation unit, purchase list provision unit, and assembly support unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the image analysis unit acquires a photograph of a room using the camera 42 of the robot 414 and analyzes it using the specific processing unit 290 of the data processing unit 12. The modeling unit generates a 3D model using the specific processing unit 290 of the data processing unit 12. The design proposal unit proposes furniture designs using the specific processing unit 290 of the data processing unit 12. The material list creation unit creates a material list using the specific processing unit 290 of the data processing unit 12. The purchase list provision unit provides a purchase list using the specific processing unit 290 of the data processing unit 12. The assembly support unit supports the assembly procedure with video using the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0207] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0208] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0209] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0210] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0211] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0212] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0213] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0214] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0215] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0216] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0217] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0218] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0219] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0220] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0221] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0222] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0223] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0224] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0225] (Note 1) The image analysis unit analyzes user-provided photos of the room, A modeling unit that passes the data extracted by the image analysis unit to a 3D modeling tool, A design proposal unit proposes furniture designs within the 3D model generated by the aforementioned modeling unit, A materials list creation unit creates a list of necessary materials based on the design proposed by the aforementioned design proposal unit, A purchasing list providing unit that provides the purchasing list created by the material list creation unit, The assembly support unit provides video support for the assembly procedure based on the purchase list provided by the purchase list provision unit. A system characterized by the following features. (Note 2) The aforementioned design proposal department, It includes a feedback reception section to receive user feedback and adjust the design. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned material list creation unit, It includes a procurement information department that provides information on nearby suppliers and pricing. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned assembly support section is It features a video display section that provides assembly instructions with accompanying video. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned image analysis unit, The system estimates the user's emotions and adjusts the analysis method of the room photos based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned image analysis unit, Improve analysis accuracy by taking room lighting conditions into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned image analysis unit, When analyzing photos of a room, the analysis results are optimized by taking into account the furniture arrangement and color scheme. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned image analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned image analysis unit, When analyzing photos of a room, we improve the accuracy of the analysis by referring to the user's past photos of the room. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned image analysis unit, When analyzing photos of a room, the analysis algorithm is changed according to the room's purpose. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned modeling unit is It estimates the user's emotions and adjusts the 3D model generation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned modeling unit is When generating 3D models, consider the materials and textures of the room to improve the realism of the model. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned modeling unit is When generating 3D models, the lighting conditions of the room are simulated to optimize the appearance of the model. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned modeling unit is It estimates the user's emotions and adjusts how the 3D model is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned modeling unit is When generating 3D models, the system improves generation accuracy by referencing the user's past 3D models. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned modeling unit is When generating 3D models, the generation algorithm is changed according to the room's purpose. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned design proposal department, It estimates the user's emotions and adjusts the way design proposals are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned design proposal department, When making design proposals, we refer to the user's past design history to improve the accuracy of the proposals. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned design proposal department, When making design proposals, different design algorithms are applied depending on the room's purpose and theme. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned design proposal department, It estimates user emotions and prioritizes design proposals based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned design proposal department, When proposing designs, we prioritize suggesting highly relevant designs by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned design proposal department, When proposing designs, we analyze users' social media activity and propose relevant designs. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned material list creation unit, We estimate the user's emotions and adjust how the material list is created based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned material list creation unit, When creating a material list, we improve the accuracy of the list by referring to the user's past material usage history. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned material list creation unit, When creating a materials list, different materials list creation algorithms are applied depending on the room's purpose and theme. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned material list creation unit, The system estimates the user's emotions and adjusts how the material list is displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned material list creation unit, When creating a materials list, the system prioritizes listing materials that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned material list creation unit, When creating a list of materials, we analyze the user's social media activity to list relevant materials. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned purchasing list provision unit, We estimate the user's emotions and adjust how the purchase list is provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned purchasing list provision unit, When providing shopping lists, we improve the accuracy of the lists by referring to the user's past purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned purchasing list provision unit, When providing shopping lists, different shopping list provision algorithms are applied depending on the room's purpose and theme. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned purchasing list provision unit, It estimates the user's emotions and prioritizes the purchase list based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned purchasing list provision unit, When providing a shopping list, the system prioritizes listing highly relevant suppliers by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned purchasing list provision unit, When providing a shopping list, we analyze the user's social media activity to list relevant retailers. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned assembly support section is The system estimates the user's emotions and adjusts the way assembly instructions are provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned assembly support section is When providing assembly instructions, we improve the accuracy of the instructions by referring to the user's past assembly history. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned assembly support section is When providing assembly instructions, different assembly instruction algorithms are applied depending on the room's purpose and theme. The system according to Appendix 1, characterized in that (Appendix 38) The assembly support part estimates the user's emotion and determines the priority of the assembly procedure based on the estimated user's emotion The system according to Appendix 1, characterized in that (Appendix 39) The assembly support part when providing the assembly procedure, preferentially provides highly relevant procedures in consideration of the user's geographical location information The system according to Appendix 1, characterized in that (Appendix 40) The assembly support part when providing the assembly procedure, analyzes the user's social media activities and provides relevant procedures The system according to Appendix 1, characterized in that (Appendix 41) The feedback reception part estimates the user's emotion and adjusts the feedback reception method based on the estimated user's emotion The system according to Appendix 2, characterized in that (Appendix 42) The feedback reception part when receiving feedback, refers to the user's past feedback history to improve the reception accuracy The system according to Appendix 2, characterized in that (Appendix 43) The feedback reception part estimates the user's emotion and determines the priority of the feedback based on the estimated user's emotion The system according to Appendix 2, characterized in that (Appendix 44) The feedback reception part when receiving feedback, preferentially receives highly relevant feedback in consideration of the user's geographical location information The system according to Appendix 2, characterized in that (Note 45) The aforementioned procurement information provision department, We estimate user sentiment and adjust the way procurement information is provided based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 46) The aforementioned procurement information provision department, When providing procurement information, we improve the accuracy of the information by referring to the user's past procurement history. The system described in Appendix 3, characterized by the features described herein. (Note 47) The aforementioned procurement information provision department, It estimates user sentiment and prioritizes procurement information based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 48) The aforementioned procurement information provision department, When providing procurement information, we prioritize providing relevant suppliers by taking into account the user's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 49) The aforementioned procurement information provision department, When providing procurement information, we analyze the user's social media activity and provide relevant suppliers. The system described in Appendix 3, characterized by the features described herein. (Note 50) The aforementioned video provision unit, The system estimates the user's emotions and adjusts the way the video is delivered based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 51) The aforementioned video provision unit, When providing videos, we improve the accuracy of the service by referring to the user's past video viewing history. The system described in Appendix 4, characterized by the features described herein. (Note 52) The aforementioned video provision unit, It estimates the user's emotions and determines the priority of videos based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 53) The aforementioned video provision unit, When providing videos, we prioritize providing videos that are highly relevant to the user, taking into account their geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 54) The aforementioned video provision unit, When providing videos, we analyze users' social media activity and provide relevant videos. The system described in Appendix 4, characterized by the features described herein. [Explanation of symbols]

[0226] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The image analysis unit analyzes user-provided photos of the room, A modeling unit that passes the data extracted by the image analysis unit to a 3D modeling tool, A design proposal unit proposes furniture designs within the 3D model generated by the aforementioned modeling unit, A materials list creation unit creates a list of necessary materials based on the design proposed by the aforementioned design proposal unit, A purchasing list providing unit that provides the purchasing list created by the material list creation unit, The assembly support unit provides video support for the assembly procedure based on the purchase list provided by the purchase list provision unit. A system characterized by the following features.

2. The aforementioned design proposal department, It includes a feedback reception section to receive user feedback and adjust the design. The system according to feature 1.

3. The aforementioned material list creation unit, It includes a procurement information department that provides information on nearby suppliers and pricing. The system according to feature 1.

4. The aforementioned assembly support section is It features a video display section that provides assembly instructions with accompanying video. The system according to feature 1.

5. The aforementioned image analysis unit, The system estimates the user's emotions and adjusts the analysis method of the room photos based on the estimated user emotions. The system according to feature 1.

6. The aforementioned image analysis unit, Improve analysis accuracy by taking room lighting conditions into consideration. The system according to feature 1.

7. The aforementioned image analysis unit, When analyzing photos of a room, the analysis results are optimized by taking into account the furniture arrangement and color scheme. The system according to feature 1.

8. The aforementioned image analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system according to feature 1.

9. The aforementioned image analysis unit, When analyzing photos of a room, we improve the accuracy of the analysis by referring to the user's past photos of the room. The system according to feature 1.

Images