Data processing device, data processing method, and data processing program

Abstract

To provide a data processing device capable of supporting achievement of a custom-built house by a user, a data processing method, and a data processing program.SOLUTION: A data processing device comprise an input unit 292 which acquires user data, a processing unit 294 which performs specific processing using a data generation model for generating prescribed inference results according to the user data, and an output unit 296 which outputs the results of specific processing to a prescribed device. The input unit 292 acquires constraint data indicative of constraints on a custom-built house as user data from the device. The processing unit 294 performs processing for deriving building data indicative of a building subject to custom-built house as specific processing using an output of the data generation model when constraint data was input.SELECTED DRAWING: Figure 3

Description

Technical Field

[0004] , , ,

[0005] , , , , as

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing program.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including 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] However, in the prior art, no consideration has been given to custom construction, and there is room for improvement in assisting the realization of custom construction by users.

Means for Solving the Problems

[0005] A first aspect according to the technology of the present disclosure includes an input unit that acquires user data, a processing unit that performs specific processing using a data generation model that generates a predetermined inference result according to the user data, and an output unit that outputs the result of the specific processing to a predetermined device. The input unit acquires, as user data from the device, constraint condition data indicating constraint conditions related to custom construction, and the processing unit outputs the output of the data generation model when the constraint condition data is input. asThis is a data processing device that performs a specific process to derive building data indicating the building to be built under custom construction.

[0006] A second aspect relating to the technology of this disclosure is: Computers The system acquires user data, performs specific processing using a data generation model that generates predetermined inference results based on the user data, and outputs the results of the specific processing to a predetermined device. Execute the process A data processing method, Computers The device retrieves constraint data indicating the constraints related to custom-built construction as user data, and outputs the data generation model when the constraint data is input. as The process of deriving building data that indicates the building to be built as a custom-built structure is performed as a specific process. Execute the process This is a data processing method.

[0007] A third aspect of the technology of this disclosure is a process that acquires user data, performs a specific process using a data generation model that generates a predetermined inference result corresponding to the user data, and outputs the result of the specific process to a predetermined device, wherein constraint condition data indicating constraints related to custom-built construction is acquired from the device as user data, and the output of the data generation model when the constraint condition data is input as It is a data processing program that instructs a computer to perform a specific process: deriving building data that indicates the building to be built as a custom-built structure. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system. [Figure 2] This is a conceptual diagram illustrating an example of the essential functions of a data processing device and a smart device. [Figure 3] The functional configuration of a specific processing unit of a data processing device is shown in general terms. [Figure 4A] This shows an emotion map where multiple emotions are mapped. [Figure 4B] This shows an emotion map where multiple emotions are mapped. [Figure 5] Schematically shows an example of the operation flow of a specific process by a data processing device. [Figure 6] It is a diagram showing an example of a constraint condition for a building. [Figure 7] It is a diagram showing an example of the process of a conventional custom-built building. [Figure 8] It is a diagram showing an example of data generated by a data generation model. [Figure 9] It is a flowchart showing an example of the flow of a first specific process executed by a data processing device. [Figure 10] It is a diagram showing an example of a conversation when acquiring requirement condition data in a data processing device. [Figure 11] It is a flowchart showing an example of the flow of a second specific process executed by a data processing device. [Figure 12] It is a diagram showing an example of a proposal selection screen. [Figure 13] It is a flowchart showing an example of the flow of a third specific process executed by a data processing device. [Figure 14] It is a schematic diagram showing the overall processing flow by a data processing system. [Figure 15] It is a diagram used to explain the effect by a data processing device.

Embodiments for Carrying Out the Invention

[0009] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a data processing program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

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

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

[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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0016] Figure 1 shows an example of the configuration of the data processing system 10 according to the embodiment.

[0017] As shown in Figure 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. An example of the smart device 14 is a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of this disclosure.

[0018] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The processor 46 transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the processor 28 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to a person by outputting it in a form perceptible to the person (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, 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 "data processing 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] The storage 32 stores the data generation model 58. The data generation model 58 is used by the identification processing unit 290. The storage 32 also stores the emotion identification model 59.

[0026] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0027] Next, we will explain the processing of the specific processing unit 290 when the data processing device 12 performs specific processing to support the realization of a custom-built house by the user.

[0028] As shown in Figure 3, the specific processing unit 290 includes an input unit 292, a processing unit 294, and an output unit 296.

[0029] The input unit 292 acquires user input received by the smart device 14. Specifically, it acquires at least one of the following data from the user: text, voice, or image, received by the smart device 14.

[0030] The processing unit 294 performs specific processing using the data generation model 58. Specifically, it inputs character, voice, and image data entered by the user into the data generation model 58 and obtains the generation result. It also generates the result of the specific processing based on the generation result.

[0031] The output unit 296 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 then 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.

[0032] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0033] The emotion identification model 59 determines the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 can determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 4A). The user's emotion determined by the emotion identification model 59 can be used for specific processing.

[0034] Figure 4A 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.

[0035] 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.

[0036] 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.

[0037] 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, motorcycles, etc., 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, for example, based 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.

[0038] 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."

[0039] 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 4B. Figure 4B shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0040] Next, the operation of the data processing system 10 will be explained.

[0041] An example of the flow of a specific processing method will be explained with reference to Figure 5. Note that the flow of a specific processing method shown in Figure 5 is an example of a "data processing method" related to the technology disclosed herein.

[0042] In step S300, the processing unit 294 determines whether or not a predetermined trigger condition is met.

[0043] If the trigger condition is met in step S300 (step S300; Yes), the data processing system 10 proceeds to step S301. On the other hand, if the trigger condition is not met in step S300 (step S300; No), the data processing system 10 terminates the specific processing.

[0044] In step S301, the processing unit 294 generates a prompt by adding an instruction to the text representing the input to obtain the result of a specific process.

[0045] In step S303, the processing unit 294 inputs the generated prompt to the data generation model 58 and obtains the result of a specific process based on the output of the data generation model 58.

[0046] In step S304, the output unit 296 outputs the result of the specific process to the smart device 14 and terminates the specific process.

[0047] Incidentally, while the demand for custom-built homes, such as detached houses, has been increasing in recent years, custom-built homes involve many stages and constraints, and require a great deal of work from both the client and the construction company's representative. In particular, a great deal of effort is required before construction of the building in question (hereinafter simply referred to as "the building") can begin.

[0048] For example, as shown in Figure 6, there are many constraints on a building, such as the area and shape of the land on which the building will be constructed (hereinafter simply referred to as "land"), floor area ratio and building coverage ratio, setback regulations and height restrictions, conditions related to structural calculations of the building, conditions related to electricity, conditions related to water and sewage, and conditions related to soundproofing. For example, constraints related to electricity include whether or not all-electric systems are necessary and whether or not gas piping is necessary. Also, for example, constraints related to water and sewage include the location of water-related areas such as kitchens, bathrooms, toilets, and washrooms, and in particular, with regard to sewage, if there is not a proper slope, problems such as water not flowing properly will occur. Also, constraints related to soundproofing include conditions such as the thickness of the walls, and the thickness of the walls affects the soundproofing performance, which in turn affects the floor plan and budget.

[0049] These constraints, such as land area, land shape, building coverage ratio, floor area ratio, setback regulations, and height restrictions, are uniquely determined by the land on which the building is to be constructed. However, other constraints are greatly influenced by the client's requests, and therefore, the client's requests must also be taken into consideration. Here, "client" includes not only the client themselves, but also their family members, relatives, and other related parties. In the following, constraints determined by the land will be referred to as "land conditions," and other constraints related to the client's requests will be referred to as "requested conditions."

[0050] Furthermore, as shown in Figure 7 as an example, many steps are required when undertaking custom-built construction. In the example shown in Figure 7, the first step is to consider the budget and create an image of the building; the second step is to select a house builder (hereinafter also referred to as "construction company") and find land; and the third step is to propose a floor plan and present a budget plan. This part alone generally takes about 2 to 3 months. Next, in the example shown in Figure 7, the fourth step is to sign a construction contract, and the fifth step is to have detailed discussions and finalize the plan. This part alone generally takes about 3 to 4 months. Furthermore, in the example shown in Figure 7, the sixth step is to start construction, and the seventh step is to complete and hand over the building. This part generally takes about 4 to 6 months.

[0051] Thus, undertaking a custom-built home involves many stages, and even just getting to the point where construction begins generally takes about six months.

[0052] Therefore, the specific processing according to this embodiment performs processing to support the process up to the start of construction of a building when building a custom-built house.

[0053] The specific processing of this embodiment will be described in more detail below with reference to Figures 8 to 15. The specific processing of this embodiment has the following functions in order to achieve the following objectives.

[0054] In other words, regarding the challenge that there is room for improvement in supporting users in realizing custom-built homes, the specific processing is: Using the data generation model 58, we support users in creating design images, blueprints, construction schedules, and cost estimates for their desired custom-built homes. The goal is to design 90% of creative buildings while meeting all building requirements, including land floor area ratio, building coverage ratio, setback regulations, height restrictions, and budget. • Create a competitive environment among construction companies and support contracts for actually building houses. • By accumulating design images, design drawings, schedules, cost estimates, etc. obtained from various construction companies as training data, the performance of the data generation model 58 will be improved. It has the following function.

[0055] In other words, the input unit 292 of the data processing device 12 according to this embodiment acquires constraint data indicating constraints related to custom-built construction as user data from the smart device 14. Furthermore, the processing unit 294 according to this embodiment performs a specific process of deriving building data indicating the building to be built using the output of the data generation model 58 when the constraint data is input. In particular, the input unit 292 according to this embodiment acquires at least a portion of the constraint data through a conversation with the building owner using the data generation model 58.

[0056] Furthermore, in the data processing system 10 according to this embodiment, the constraint data includes at least one (both in this embodiment) of the land condition data indicating the above-mentioned land conditions relating to the land on which the building will be constructed, and the request condition data indicating the above-mentioned request conditions relating to the requests of the building owner. Furthermore, in the data processing system 10 according to this embodiment, the building data includes at least one (all in this embodiment) of the design drawing data indicating the design drawings of the building, the design image data indicating the design image of the building, the construction schedule data indicating the construction schedule for the building, and the cost estimate data indicating the estimated cost required for the construction of the building.

[0057] In this embodiment, data representing the area and shape of the land (hereinafter referred to as "land drawing data") is used as data representing the area and shape of the land in the land condition data, but this is not the only option. For example, data describing the area and shape of the land in text may be used as data representing the area and shape of the land in the land condition data.

[0058] On the other hand, as shown in Figure 8 as an example, the data processing system 10 according to this embodiment includes two data generation models: a first data generation model 58A used for the above-mentioned conversation, and a second data generation model 58B used for deriving building data. Specifically, the input unit 292 according to this embodiment obtains the desired condition data in the constraint condition data by conversing with the user using the first data generation model 58A. Furthermore, the processing unit 294 according to this embodiment derives design drawing data, design image data, construction schedule data, and cost estimation data using the land condition data, desired condition data, and the second data generation model 58B.

[0059] Thus, in this embodiment, the data generation model 58 includes two models, the first data generation model 58A and the second data generation model 58B, but it is not limited to this. For example, these models may be included as a single model integrated into the data generation model 58.

[0060] In this embodiment, the input unit 292 acquires land condition data by having the user input information indicating the building site (in this embodiment, information indicating latitude and longitude) and using that information to search an external database, but it is not limited to this. For example, the user may be asked to input an address (residential address) instead of latitude and longitude, and the data may be acquired by searching the external database using that address, or the data may be acquired by having the user directly input the land condition data. Furthermore, the land conditions indicated by the land condition data are not limited to the area, shape, building coverage ratio, floor area ratio, setback regulations, and height restrictions mentioned above, but any conditions that restrict a building on the corresponding land may be applied, such as the boundary line of the adjacent property or the distance from the road to the building.

[0061] Furthermore, in the data processing system 10 according to this embodiment, data showing a walkthrough video of at least one (both in this embodiment) of the exterior and interior of a building is applied as design image data, but this is not limited to this. For example, instead of a walkthrough video, data showing a perspective drawing of at least one of the exterior and interior of a building may be applied as design image data.

[0062] Furthermore, the processing unit 294 according to this embodiment derives a plurality of building data that satisfy the above constraints as selection candidates, the output unit 296 outputs the selection candidates to the smart device 14, and the input unit 292 further obtains a selection instruction from the user from the selection candidates. As a result, the user can select the desired one from a plurality of building data that satisfy the constraints, thereby improving user satisfaction.

[0063] Furthermore, the processing unit 294 according to this embodiment further executes a contract support process as a specific process to assist in the conclusion of a construction contract between the building owner and the construction company that constructs the building, using at least one (both in this embodiment) of the above constraints and the building data. Here, the processing unit 294 according to this embodiment executes the contract support process with a predetermined number of construction companies as candidate companies to conclude a construction contract with the owner.

[0064] Specifically, the processing unit 294 according to this embodiment transmits, via the output unit 296, at least one (in this embodiment, both) of the building data derived by a specific process and the constraints corresponding to the building data, along with a request for quotation, as described later, to the multiple construction companies. In response, the multiple construction companies refer to the building data and constraints received from the data processing unit 12, create a proposal document showing contract terms that satisfy the various conditions indicated by the constraints as much as possible, and transmit proposal data showing the proposal document to the data processing unit 12. The processing unit 294 according to this embodiment then receives the proposal data transmitted from the multiple construction companies via the input unit 292. The processing unit 294 then displays a proposal selection screen on the smart device 14 via the output unit 296, which displays multiple proposals presented by the multiple construction companies indicated by the received proposal data in a selectable format. As a result, the user can compare and consider proposals from multiple construction companies, thereby improving user satisfaction.

[0065] Furthermore, the processing unit 294 according to this embodiment further executes a process as a specific process for training the data generation model 58 using design documents (in this embodiment, design drawing data, design image data, schedule data, and cost estimate data applied as building data) created by the construction company with which the above construction contract was concluded with the client, based on the building data. In particular, the processing unit 294 according to this embodiment further executes a process as a specific process for paying consideration to the corresponding construction company for the provision of the design documents.

[0066] Next, with reference to Figures 9 to 15, the operation of the data processing device 12 according to this embodiment when executing specific processing will be explained. In the following, specific processing will be divided into three processes: specific processing that mainly supports the creation of building data (hereinafter referred to as "first specific processing"), specific processing that mainly supports the conclusion of construction contracts (hereinafter referred to as "second specific processing"), and specific processing that mainly trains the data generation model 58 (here, the second data generation model 58B) (hereinafter referred to as "third specific processing"). The first specific processing, the second specific processing, and the third specific processing are executed by the processor 28 executing the specific processing program 56 stored in the storage 32.

[0067] First, the operation of the data processing device 12 when executing the first specific processing will be explained with reference to Figures 9 and 10. Figure 9 is a flowchart showing an example of the flow of the first specific processing executed by the data processing device 12, and Figure 10 is a diagram showing an example of a conversation when acquiring request condition data in the data processing device 12. The processing flow shown in Figure 9 is an example of a data processing method relating to the technology of this disclosure. Here, in order to avoid confusion, we will explain the case where the first data generation model 58A and the second data generation model 58B have already been constructed. Furthermore, here we will explain the case where the building owner is the user of the smart device 14 (hereinafter simply referred to as "user"), and the execution of the first specific processing is started when the user instructs the start of execution of the first specific processing via the smart device 14 (hereinafter referred to as "target device").

[0068] In step S10, the input unit 292 acquires land condition data as described above, and in step S12, the input unit 292 acquires desired condition data using the first data generation model 58A as described above.

[0069] When acquiring requirements data using the first data generation model 58A, as shown in Figure 10 as an example, the process begins by first asking the user about the reason for constructing the building, and then, based on the answer, further questions are asked, along with specific suggestions. By repeating this exchange, requirements data indicating the requirements of the building owner regarding the building is acquired.

[0070] In step S14, the processing unit 294 inputs the acquired land condition data and desired condition data into the second data generation model 58B to derive building data including design drawing data, design image data, construction schedule data, and cost estimate data. As mentioned above, the processing unit 294 derives multiple building data as selection candidates that satisfy the constraints indicated by the land condition data and desired condition data.

[0071] Therefore, in step S16, the output unit 296 controls the target device to display a building data selection screen (not shown) that displays multiple derived building data in a selectable format. In response to this control, the building data selection screen is displayed on the display 40A of the target device, and the user selects the desired data from the displayed building data via the touch panel 38A. In response, the target device transmits identification information to the data processing device 12 to identify the building data specified by the user.

[0072] Therefore, in step S18, the input unit 292 obtains the user's selection result by receiving specific information transmitted from the target device. In step S20, the processing unit 294 registers the building data identified by the received specific information (hereinafter referred to as "selected building data") and at least one (both in this embodiment) of the constraint conditions (land condition data and desired condition data) corresponding to the selected building data by storing them in the storage unit 32, and then terminates the first identification process. The selected building data and constraint conditions registered here will also be referred to as "registered data" below.

[0073] By the way, if a user wants an estimate of the costs required to construct the building indicated by the selected building data (hereinafter referred to as "construction cost estimate"), they will request such a construction cost estimate.

[0074] Next, the operation of the data processing device 12 when executing the second specific processing will be explained with reference to Figures 11 and 12. Figure 11 is a flowchart showing an example of the flow of the second specific processing executed by the data processing device 12, and Figure 12 is a diagram showing an example of the proposal selection screen. The second specific processing according to this embodiment is started when the user receives the above-mentioned request for construction cost estimation from the target device.

[0075] In step S30, the processing unit 294 executes a fee receipt process, which is the process of receiving payment (in this embodiment, a fee) from the user who requested the construction cost estimate for the presentation of the proposal.

[0076] In step S32, the output unit 296 sends a request for an estimate (hereinafter referred to as "estimate request") to several construction companies that have been pre-contracted to be introduced to the user (hereinafter referred to as "contracted construction companies"), along with the registration data corresponding to the user, for the construction of a building corresponding to the registration data.

[0077] Upon receiving a request for a quote, the contracted construction company refers to the constraints and building data indicated in the registered data received along with the quote request, and together creates the aforementioned design documents and proposal documents, and transmits the design document data and proposal data to the data processing device 12. At this time, the contracted construction company makes adjustments to the design drawings indicated in the selected building data in the received registered data to conform to the building materials it can provide, and then creates design document data and proposal data that satisfy the received constraints.

[0078] Therefore, in step S34, the input unit 292 waits until it has received combinations of proposal data and design document data from all contracted construction companies. In step S36, the output unit 296 controls the target device to display a proposal selection screen configured in advance to present the proposals indicated by the proposal data, using the combinations of proposal data and design document data received from the multiple contracted construction companies. In response to this control, the target device displays a proposal selection screen on the display 40A, as shown in Figure 12 as an example.

[0079] As shown in Figure 12, the proposal selection screen according to this embodiment displays a message prompting the user to specify either a desired proposal from the displayed proposals or the name of the construction company corresponding to that proposal. In addition, the proposal selection screen according to this embodiment displays the proposals indicated by the proposal data received from the multiple contracted construction companies, along with information indicating the name of the corresponding construction company. When the proposal selection screen is displayed on the display 40A, the user specifies the display area of ​​the desired proposal from the displayed proposals, or the display area of ​​the name of the contracted construction company corresponding to that proposal, via the touch panel 38A. In response, the target device transmits identification information to the data processing device 12 to identify the proposal specified by the user. Thus, in this embodiment, only the proposals indicated by the proposal data received from multiple contracted construction companies are displayed, but this is not the only form. For example, in addition to the proposal, the design documents indicated by the design document data corresponding to the proposal may also be displayed.

[0080] Therefore, in step S38, the input unit 292 obtains the user's selection result by receiving specific information transmitted from the target device. In step S40, the output unit 296 transmits acceptance information to the target construction company (hereinafter referred to as the "accepting construction company") corresponding to the proposal indicated by the received specific information, indicating that the proposal it submitted has been accepted by the user. By receiving this acceptance information, the accepting construction company can understand that its proposal has been accepted by the user.

[0081] In step S42, the processing unit 294 executes a predetermined contract support process to assist the user in concluding a construction contract between the user and the adopted construction company, and then terminates the second specific processing. In this embodiment, the contract support process is applied to assist the adopted construction company and the user in directly concluding a contract using a construction contract in a face-to-face setting, but it is not limited to this. For example, the contract support process may be applied to assist the adopted construction company and the user in concluding a contract using a construction contract electronically via the internet or the like without direct face-to-face contact. Furthermore, in this embodiment, the above contract support process also includes a process to have the adopted construction company pay and receive consideration (a fee in this embodiment) for assisting in the construction contract, but it goes without saying that it is not limited to this.

[0082] Next, with reference to Figure 13, the operation of the data processing device 12 when executing the third specific processing will be explained. Figure 13 is a flowchart showing an example of the flow of the third specific processing executed by the data processing device 12. In this embodiment, the third specific processing is started when the administrator of the data processing device 12 instructs the hiring construction company to start the execution of the third specific processing in order to have them provide the created design documents. Furthermore, in order to avoid confusion, the case in which the target hiring construction company is specified in advance will be explained here.

[0083] In step S50, the processing unit 294 executes a data usage contract process, which is the process of entering into a contract with the target construction company to provide the design document data showing the created design documents for a fee. At this time, the processing unit 294 may determine the price of the design document data according to the type, quantity, accuracy, etc. of the design document data to be provided, or it may apply a uniform price.

[0084] In step S52, the input unit 292 acquires the design document data by receiving it from the target construction company, and in step S54, the processing unit 294 registers the received design document data by storing it in the storage 32.

[0085] In step S56, the processing unit 294 determines whether the number of design document data registered in the storage 32 that has not been used to train the second data generation model 58B (hereinafter referred to as "untrained design document data") is equal to or greater than a predetermined number. If the determination is negative, the third specific processing is terminated; if the determination is positive, the process proceeds to step S58. In this embodiment, the predetermined number is set in advance by the administrator of the data processing device 12 or the like, according to the accuracy required for the second data generation model 58B, the frequency of registration of design document data, etc., but the embodiment is not limited to this form. For example, a fixed number may be applied as the predetermined number.

[0086] In step S58, the processing unit 294 trains the second data generation model 58B using all untrained design document data and the constraints corresponding to said untrained design document data, and then terminates the third identification process. The constraints used in this training are those set in the registered data registered in step S20 of the first identification process.

[0087] The following describes the overall flow of processing performed by the first to third specific processing steps, with reference to Figure 14. Figure 14 is a schematic diagram showing the overall processing flow by the data processing system 10.

[0088] In the first specific processing, the data processing device 12 acquires land condition data, including land drawing data, and acquires requested condition data through conversation with the user using the first data generation model 58A. The data processing device 12 according to this embodiment then inputs the acquired land condition data and requested condition data into the second data generation model 58B. As a result, the data processing device 12 derives multiple building data sets, including design drawing data, that satisfy the constraints indicated by the land condition data and requested condition data, and presents them to the user. In response, the user selects the desired building data from the presented multiple building data sets and, if necessary, makes the above-mentioned request for quotation.

[0089] When a user requests a quote, the data processing device 12 executes a second specific processing to request quotes from each of the contracted construction companies. In response, each contracted construction company creates proposal data, including design document data, and sends it to the data processing device 12.

[0090] Once proposal data and design document data are obtained from each of the contracted construction companies, the data processing device 12 presents the user with the proposals from each of the multiple contracted construction companies as indicated by the obtained proposal data. The user then refers to the proposals and selects the contracted construction company corresponding to the desired proposal. The data processing device 12 then notifies the contracted construction company (adopted construction company) selected by the user of the selection result.

[0091] The data processing device 12 then performs processing to support the conclusion of construction contracts between the user and the hiring construction company, and also collects a fee (consideration) from the hiring construction company.

[0092] Furthermore, the data processing system 10 uses the design document data provided by the hiring construction company as training data to train the second data generation model 58B. This allows for the effective use of the design document data.

[0093] Through the processes described above, from the first to the third specific processes, the amount of work required can be significantly reduced compared to the current custom-built construction process, as schematically shown in Figure 15 as an example. As a result, it becomes possible to realize a larger number of custom-built construction projects.

[0094] As described above, the data processing system 10 according to this embodiment includes an input unit 292 for acquiring user data, a processing unit 294 for performing specific processing using a data generation model 58 that generates predetermined inference results according to the user data, and an output unit 296 for outputting the results of the specific processing to a predetermined device. The input unit 292 acquires constraint data indicating constraints related to custom-built construction as user data from the device, and the processing unit 294 performs a specific processing that derives building data indicating the building to be built using the output of the data generation model 58 when the constraint data is input. Therefore, it can support the realization of custom-built construction by the user.

[0095] Furthermore, in the data processing system 10 according to this embodiment, the input unit 292 acquires at least a portion of the constraint condition data through a conversation with the building owner using the data generation model 58. Therefore, compared to the case where at least a portion of the constraint condition data is not acquired through such a conversation, the data can be acquired in a more natural manner.

[0096] Furthermore, in the data processing system 10 according to this embodiment, two data generation models are applied as the data generation model 58: a first data generation model 58A for conversation and a second data generation model 58B used in specific processing. Therefore, compared to the case where these models are configured with a single data generation model, each of these models can perform its respective function with higher accuracy.

[0097] Furthermore, in the data processing system 10 according to this embodiment, the constraint data includes land condition data relating to the land on which the building will be constructed, and request condition data relating to the requests of the building owner. Therefore, building data can be derived as satisfying the constraints indicated by this data.

[0098] Furthermore, in the data processing system 10 according to this embodiment, the building data includes design drawing data showing the design drawings of the building, design image data showing the design image of the building, construction schedule data showing the construction schedule for the building, and cost estimate data showing the estimated cost required for the construction of the building. Therefore, this data can be derived as building data.

[0099] Furthermore, in the data processing system 10 according to this embodiment, the design image data is data that shows a walkthrough video targeting at least one of the exterior and interior of the building. Therefore, compared to the case where the design image data is data that shows the design using still images, it is possible to create a more realistic experience.

[0100] Furthermore, in the data processing system 10 according to this embodiment, multiple building data that satisfy the constraints are derived as selection candidates, and these selection candidates are output to the device, while the system also obtains selection instructions from the user from among the selection candidates. Therefore, user satisfaction can be improved compared to the case where only one building data is derived.

[0101] Furthermore, the data processing system 10 according to this embodiment further executes a contract support process as a specific process, which uses constraints and building data to assist in the conclusion of a construction contract between the building owner and the construction company that builds the building. Therefore, the construction contract can be concluded efficiently.

[0102] Furthermore, in the data processing system 10 according to this embodiment, a predetermined number of construction companies are designated as candidate companies to conclude construction contracts with the client, and contract support processing is performed. Therefore, compared to the case where only a single construction company is designated as a candidate company to conclude a construction contract, user satisfaction can be improved.

[0103] Furthermore, the data processing system 10 according to this embodiment further executes a specific process for training the data generation model 58 using design documents created based on building data by a construction company with which a construction contract has been concluded with the client. Therefore, the design documents created by this system can be effectively used for training the data generation model 58.

[0104] Furthermore, the data processing system 10 according to this embodiment also performs a specific process of paying the corresponding construction company for the provision of design documents. Therefore, it can also generate profits for the construction company.

[0105] Furthermore, since the data processing system 10 according to this embodiment is designed to provide a wide range of support related to custom-built construction, applying this system could potentially eliminate at least a portion of the work currently performed by the government to obtain building permits, thereby reducing the enormous amount of manpower (= taxpayer money) required for such building permits.

[0106] Furthermore, while the data processing system 10 according to this embodiment is primarily intended for fully custom-built homes, it is not limited to this. The data processing system 10 according to this embodiment can also be applied to semi-custom-built homes, pre-built homes that incorporate the customer's preferences, condominiums, and the like.

[0107] In the above embodiment, the case in which the fee receipt process is performed before presenting the proposal to the user in the second specific processing was described, but the embodiment is not limited to this form. For example, the fee receipt process may be performed after presenting the proposal to the user.

[0108] Furthermore, although the above embodiment described a case where each contracted construction company creates only one set of proposal data and design document data, the configuration is not limited to this. For example, each contracted construction company may create multiple sets of proposal data and design document data that satisfy the respective constraints. This configuration can further improve user satisfaction.

[0109] Furthermore, although the above embodiment describes a case in which the second data generation model 58B simultaneously derives design drawing data, design image data, schedule data, and cost estimation data, the embodiment is not limited to this form. For example, in the first step, only the design drawing data may be derived by the first data generation model, and in the second step, the derived design drawing data may be input into the second data generation model to derive the remaining design image data, schedule data, and cost estimation data.

[0110] Furthermore, while the above embodiment describes a case in which design drawing data, design image data, construction schedule data, and cost estimation data are derived by the second data generation model 58B, the embodiment is not limited to this form. For example, in addition to these data, structural calculation report data showing the structural calculation report may also be derived by the second data generation model 58B. As a variation of this form, the structural calculation report data may be derived using widely available 3D CAD (Computer Aided Design) software capable of structural calculations.

[0111] Furthermore, although the system related to this disclosure has been primarily described in terms of the functions of the specific processing unit 290 of the data processing device 12, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer, or as an application that runs on a smartphone, etc. The method related to this disclosure may be provided to users in the form of SaaS (Software as a Service).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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 the like 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.

[0121] 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.

[0122] In relation to the above, the following additional information is disclosed.

[0123] <Note 1> An input section for acquiring user data, A processing unit that performs specific processing using a data generation model that generates predetermined inference results according to the user data, The system includes an output unit that outputs the result of the specified processing to a predetermined device, The input unit acquires constraint data indicating constraints related to custom-built construction as user data from the device, The processing unit performs the process of deriving building data indicating the building to be built using the output of the data generation model when the constraint data is input, as the specific processing. Data processing device. <Note 2> The input unit acquires at least a portion of the constraint data through a conversation with the building owner using the data generation model. The data processing device described in Appendix 1. <Note 3> The data generation model includes two data generation models: a first data generation model for conducting the conversation and a second data generation model used in the specific processing. The data processing device described in Appendix 2. <Note 4> The aforementioned constraint data includes at least one of the land condition data relating to the land on which the building will be constructed, and the request condition data relating to the requests of the building's owner. A data processing device described in any one of the appendices 1 through 3. <Note 5> The building data includes at least one of the following: design drawing data showing the design drawings of the building; design image data showing the design image of the building; construction schedule data showing the construction schedule for the building; and cost estimate data showing an estimate of the costs required for the construction of the building. A data processing device described in any one of the appendices 1 through 4. <Note 6> The aforementioned design image data is data showing a walkthrough video of at least one of the exterior and interior of the building. The data processing device described in Appendix 5. <Note 7> The processing unit derives a plurality of building data that satisfy the constraints as selection candidates for the building data, The output unit outputs the selected candidates to the device. The input unit further obtains a selection instruction from the user from the selection candidates. A data processing device described in any one of the appendices 1 through 6. <Note 8> The processing unit further executes a contract support process as the specified process, which uses at least one of the constraints and the building data to assist in the conclusion of a construction contract between the building owner and the construction company that constructs the building. A data processing device described in any one of the appendices 1 through 7. <Note 9> The processing unit executes the contract support process, designating a predetermined number of construction companies as candidate companies to conclude the construction contract with the client. The data processing device described in Appendix 8. <Note 10> The processing unit further executes, as the specified process, a process for training the data generation model using design documents created based on the building data by the construction company with which the construction contract was concluded with the client. The data processing device described in Appendix 8 or Appendix 9. <Note 11> The processing unit further performs the process of paying the corresponding construction company the consideration for the provision of the design documents as the specified process. The data processing device described in Appendix 10. [Explanation of symbols]

[0124] 10 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 22 Computers 24 Databases 26 Communication I / F 28 processors 30 RAM 32 storage 34 bus 36 Computer 38 Reception device 38A Touch Panel 38B Microphone 40 Output device 40A Display 40B speaker 42 cameras 44 Communication I / F 46 processors 46A Control Unit 48 RAM 50 storage 52 bus 54 Network 56 Specific Processing Program 58 Data Generation Models 58A First Data Generation Model 58B Second Data Generation Model 59 Emotion Identification Models 60 Reception Output Program 290 Specific Processing Unit 292 Input section 294 Processing Unit 296 Output section 400 Emotion Map 900 Emotion Map

Claims

1. An input section for acquiring user data, A processing unit that performs specific processing using a data generation model that generates predetermined inference results according to the user data, The system includes an output unit that outputs the result of the specified processing to a predetermined device, The input unit acquires constraint data indicating constraints related to custom-built construction as user data from the device, The processing unit performs the process of deriving building data indicating the building to be the subject of the custom-built construction as the output of the data generation model when the constraint condition data is input, as the specific processing. A data processing device, The aforementioned constraint data includes both land condition data relating to the land on which the building will be constructed, and requirement condition data relating to the requirements of the building's owner. The aforementioned land condition data are conditions that restrict buildings on the land, The processing unit further executes, as the specified processing, a contract support process that assists in the conclusion of a construction contract between the building owner and the construction company that constructs the building, using at least one of the constraints and the building data, and a process that uses design document data, which shows the design documents created by the construction company that has concluded the construction contract with the owner based on the building data, as output data, and uses the constraint data corresponding to the design document data as input data to train the data generation model. Data processing device.

2. The input unit acquires at least a portion of the constraint data through a conversation with the building owner using the data generation model. The data processing device according to claim 1.

3. The data generation model includes two data generation models: a first data generation model for conducting the conversation and a second data generation model used in the specific processing. The data processing apparatus according to claim 2.

4. The building data includes at least one of the following: design drawing data showing the design drawings of the building; design image data showing the design image of the building; construction schedule data showing the construction schedule for the building; and cost estimate data showing an estimate of the costs required for the construction of the building. The data processing device according to claim 1.

5. The aforementioned design image data is data showing a walkthrough video of at least one of the exterior and interior of the building. The data processing device according to claim 4.

6. The processing unit derives a plurality of building data that satisfy the constraints as selection candidates for the building data, The output unit outputs the selected candidates to the device. The input unit further obtains a selection instruction from the user from the selection candidates. The data processing device according to claim 1.

7. The processing unit executes the contract support process, designating a predetermined number of construction companies as candidate companies to conclude the construction contract with the client. The data processing device according to claim 1.

8. The processing unit further performs the process of paying the corresponding construction company the consideration for the provision of the design documents as the specified process. The data processing device according to claim 1.

9. Computers Retrieve user data, A specific processing is performed using a data generation model that generates predetermined inference results according to the user data. A data processing method that performs a process to output the result of the specified processing to a predetermined device, The aforementioned computer, From the aforementioned device, constraint data indicating constraints related to custom-built construction is acquired as user data. As the output of the data generation model when the constraint data is input, the process of deriving building data indicating the building to be the subject of the custom-built construction is performed as the specific process. A data processing method that performs processing, The aforementioned constraint data includes both land condition data relating to the land on which the building will be constructed, and requirement condition data relating to the requirements of the building's owner. The aforementioned land condition data are conditions that restrict buildings on the land, The aforementioned computer, The specified process further involves performing a contract support process that assists in the conclusion of a construction contract between the client of the building and the construction company that constructs the building, using at least one of the aforementioned constraints and the aforementioned building data, and using design document data, which shows the design documents created by the construction company that has concluded the construction contract with the client based on the building data, as output data, and using the constraints data corresponding to the said design document data as input data to train the data generation model. Data processing method.

10. Retrieve user data, A specific processing is performed using a data generation model that generates predetermined inference results according to the user data. A process that outputs the result of the aforementioned specific process to a predetermined device, From the aforementioned device, constraint data indicating constraints related to custom-built construction is acquired as user data. As the output of the data generation model when the constraint data is input, the process of deriving building data indicating the building to be the subject of the custom-built construction is performed as the specific process. It is a data processing program that causes a computer to perform the processing. The aforementioned constraint data includes both land condition data relating to the land on which the building will be constructed, and requirement condition data relating to the requirements of the building's owner. The aforementioned land condition data are conditions that restrict buildings on the land, The aforementioned computer, The specified process further involves performing a contract support process that assists in the conclusion of a construction contract between the client of the building and the construction company that constructs the building, using at least one of the aforementioned constraints and the aforementioned building data, and using design document data, which shows the design documents created by the construction company that has concluded the construction contract with the client based on the building data, as output data, and using the constraints data corresponding to the said design document data as input data to train the data generation model. Data processing program.

Images