system

Abstract

We provide the system. [Solution] A system for optimizing the budget of a renovation project, A means of inputting user project information, Means including a terminal that transmits the input information to a server, Means including a server for collecting past project data and market price data, A means including a server that calculates budget allocation using an AI model generated based on the collected data, A means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal, Means including a terminal that displays the transmitted proposal to the user, A system that includes this.

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 character of the chatbot, 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 a renovation project, it is difficult to optimize the budget and manage costs, and there is often a problem of wasteful expenditure. An efficient solution to this problem is required. In particular, it is difficult to appropriately allocate costs according to the scale and content of the project and to propose cost reduction that reflects the latest market information. For this reason, there is a need for a method that allows a business operator planning a renovation project to efficiently carry out the project while suppressing wasteful expenditure.

Means for Solving the Problems

[0005] This invention provides a system for optimizing the budget of a renovation project. Specifically, it includes a terminal where the user inputs project information and transmits it to a server. The server collects historical project data and market price data, and uses a generated AI model based on the collected data to calculate budget allocation. Based on the calculation results, it generates cost reduction suggestions and sends them to the terminal for display to the user. It can also receive user feedback and input data back into the AI ​​model for re-evaluation. Furthermore, based on the collected data, it uses scraping techniques to obtain the latest discount information from the internet. This series of steps can optimize the budget of a renovation project and reduce unnecessary spending.

[0006] A "user" refers to an individual or company planning a renovation project and providing the information entered into the system.

[0007] "Project information" refers to detailed information about the property to be renovated, including area, number of rooms, desired materials and equipment, and budget limit.

[0008] A "terminal" refers to an input device or device used by a user to input project information and send it to a server.

[0009] A "server" refers to a processing unit that collects project information, historical data, and market price information, calculates budget allocation using a generative AI model, and generates cost reduction proposals.

[0010] "Past project data" refers to information about previously implemented renovation projects, including historical data such as budget allocation and actual costs.

[0011] "Market price data" refers to price information for materials and equipment in the current market, and is used to estimate the actual costs of renovations.

[0012] A "generative AI model" is an artificial intelligence model used to optimize budget allocation for renovation projects based on collected data.

[0013] "Budget allocation" is the process of assigning an appropriate budget amount to each item and material in a renovation project.

[0014] "Cost reduction suggestions" refer to proposals made to users to reduce unnecessary spending, based on collected data and the results of AI models.

[0015] "Feedback" refers to information such as additional requests, changes to conditions, and opinions that users enter after reviewing a proposal.

[0016] "Web scraping" is a technique for automatically collecting data from the internet, and it is used to obtain the latest discount information, etc. [Brief explanation of the drawing]

[0017] [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]It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be described.

[0020] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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), and the like.

[0021] 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.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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 control unit 46A 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 specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] The 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.

[0036] 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.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention is a system that supports budget optimization in renovation projects and consists of a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, and a feedback / re-evaluation phase. Its detailed operation is described below.

[0039] User input phase

[0040] The user enters basic information about the renovation project into the terminal. This information includes the area to be renovated, the number of rooms, desired materials (e.g., high-quality flooring, marble countertops), required equipment (e.g., new kitchen and bathroom), and budget limit. The entered information is sent from the terminal to the server.

[0041] Data collection phase

[0042] The server collects data on similar renovation projects from a database of past projects. It also retrieves current market price information from a market price database. Furthermore, it uses scraping techniques to collect the latest discount information from the internet.

[0043] Model Application Phase

[0044] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. This model analyzes historical data and market trends to provide efficient allocation results.

[0045] Proposal generation phase

[0046] The server generates cost reduction proposals based on budget allocation results obtained from the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and incorporation of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0047] Proposal review phase

[0048] The user reviews the proposal displayed on the device. If they are dissatisfied with the proposal, or have additional requests or changes to the conditions, they enter them into the device. The device then sends the user's feedback to the server.

[0049] Feedback and re-evaluation phase

[0050] The server receives feedback from the user, re-inputs it into the model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. By repeating this process, the system can provide the most suitable optimization budget for the user's needs.

[0051] Specific example

[0052] For example, suppose a user is planning a renovation of a 100-square-meter home, desires high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and has a budget limit of 5 million yen. The server retrieves data from similar past projects, gathers market price data, and collects the latest discount information through web scraping. The AI ​​model analyzes this data and presents budget allocation and cost reduction suggestions as follows:

[0053] High-quality flooring costs 1.5 million yen, but using an alternative could reduce the cost to 1.2 million yen.

[0054] A marble countertop costs 500,000 yen, but by using recycled materials, the cost can be reduced to 400,000 yen.

[0055] Kitchen equipment can be reduced by 1.2 million yen, bathroom equipment by 800,000 yen, and after applying discount information, these can be reduced to 1.1 million yen and 700,000 yen respectively.

[0056] Other 1 million yen

[0057] In this way, users can obtain a concrete plan optimized for their budget. Throughout this process, user feedback is incorporated, and even more optimal suggestions are repeatedly provided, enabling the successful execution of an optimized renovation project.

[0058] The following describes the processing flow.

[0059] Step 1:

[0060] The user uses a device to enter basic information about the renovation project. This information includes the area to be renovated, the number of rooms, desired materials and equipment, and the budget limit.

[0061] Step 2:

[0062] The terminal sends project information entered by the user to the server. The information sent includes all the project details entered.

[0063] Step 3:

[0064] The server receives the submitted project information and searches the past project database. Simultaneously, it retrieves current market price information from the market price database. It also collects the latest discount information from the internet using scraping techniques.

[0065] Step 4:

[0066] The server analyzes collected historical project data and market price information, and inputs this into a generating AI model.

[0067] Step 5:

[0068] The server uses a generated AI model to analyze the input data and calculate the appropriate budget allocation for each item in the renovation project. This calculation includes the optimal cost for each material and equipment.

[0069] Step 6:

[0070] The server generates further cost-reduction suggestions based on the AI ​​model's calculation results. These suggestions include comparisons with market prices based on user preferences, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information.

[0071] Step 7:

[0072] The server converts the budget allocation and cost reduction proposals it generates into a data format such as JSON and sends it to the terminal.

[0073] Step 8:

[0074] The terminal displays the suggestions received from the server to the user. The user reviews and confirms the suggested plan.

[0075] Step 9:

[0076] The user enters feedback on the proposed plan. This feedback may include additional requests or changes to the terms and conditions.

[0077] Step 10:

[0078] The device sends user feedback to the server.

[0079] Step 11:

[0080] The server receives user feedback and, if necessary, re-inputs it into the model for re-evaluation. This re-evaluation generates new suggestions.

[0081] Step 12:

[0082] The server sends the newly generated proposal back to the terminal, which then displays it to the user. This process is repeated until the optimal plan that best satisfies the user is determined.

[0083] (Example 1)

[0084] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] Budgeting for renovation projects is complex and requires considering many factors. Therefore, manually determining the optimal budget allocation requires a tremendous amount of time and effort from the user. Furthermore, constantly checking market price fluctuations and discount information is time-consuming, making it difficult to obtain optimal cost-saving proposals. To address these challenges, there is a need for a user-friendly system that efficiently optimizes budgets.

[0086] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0087] In this invention, the server includes means for inputting user project information, means including a terminal for transmitting the input information to the server, means including a server for collecting past project data and market price data, means including a server for calculating budget allocation using a generation AI model based on the collected data, means including a server for generating cost reduction proposals based on the calculation results and transmitting them to the terminal, means including a terminal for displaying the transmitted proposals to the user, means including a server for receiving user feedback and re-inputting data into the generation AI model for re-evaluation, and means including a server for obtaining the latest discount information from the internet using a scraping technique based on the collected data. This enables the user to obtain the optimal budget allocation efficiently and quickly. Furthermore, since re-evaluation reflecting feedback is possible, flexible proposals tailored to the user's needs can be made.

[0088] "User project information" refers to detailed information about the renovation project, such as the area, number of rooms, desired materials, necessary equipment, and budget limit.

[0089] A "terminal" is an electronic device used by users to input information and communicate with a server. Specifically, this includes personal computers, tablets, and smartphones.

[0090] A "server" is a computing system used for data collection, analysis, generation, budget allocation calculations using AI models, generation of cost reduction proposals, and processing user feedback.

[0091] "Past project data" refers to data related to previously carried out renovation projects, including budget, materials used, construction details, and duration.

[0092] "Market price data" refers to information about the current market value of materials and equipment needed for home renovations. This data is used to understand price fluctuations and trends.

[0093] A "generative AI model" is an artificial intelligence algorithm that automatically calculates and generates budget allocation and cost reduction proposals based on collected data.

[0094] "Cost reduction suggestions" are proposals for efficiently using the user's budget, and include recommendations for alternative materials, comparisons of market prices, and incorporation of the latest discount information.

[0095] "Web scraping" is a technique for automatically collecting specific data from publicly available information on the internet.

[0096] "Feedback" refers to opinions, additional requests, and information regarding changes to terms and conditions provided by users in response to suggestions.

[0097] "Re-evaluation" is the process of running the generated AI model again based on user feedback to generate new suggestions.

[0098] This invention is a system that supports budget optimization in renovation projects. The system consists of the following phases: user input phase, data collection phase, model application phase, proposal generation phase, proposal confirmation phase, and feedback / re-evaluation phase. The specific implementation methods for each phase are described below.

[0099] User input phase

[0100] The user enters basic information about the renovation project via a terminal. This information includes the area to be renovated, the number of rooms, desired materials, necessary equipment, and budget limit. For example, the user might enter "100 square meter residence, 3 rooms, high-quality flooring, marble countertops, new kitchen and bathroom, budget limit of 5 million yen." The terminal then sends this information to the server.

[0101] Data collection phase

[0102] The server collects data on similar renovation projects from a database of past projects. It also obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0103] Model Application Phase

[0104] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. This model analyzes historical data and market trends to provide efficient allocation results. The generative AI model is input with historical project data and market price information, and outputs a budget allocation result such as "1.5 million yen for high-quality flooring, 500,000 yen for marble countertops, 1.2 million yen for kitchen equipment, 800,000 yen for bathroom equipment, and 1 million yen for other items."

[0105] Proposal generation phase

[0106] The server generates cost reduction proposals based on budget allocation results obtained from the generated AI model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0107] Proposal review phase

[0108] Users review the proposals displayed on their devices. If they are dissatisfied with the proposals or have additional requests or changes to the conditions, they enter them into their devices and send them to the server.

[0109] Feedback and re-evaluation phase

[0110] The server receives user feedback, re-inputs it into the generated AI model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. This ensures that the user receives an optimized renovation plan that best suits their needs.

[0111] Example of a prompt

[0112] "We are planning a renovation of a 100-square-meter residence. We would like high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, with a budget limit of 5 million yen. Please propose a budget allocation based on similar past project data and market price information."

[0113] This system utilizes AI models generated from user input to analyze historical data and market trends, providing efficient and optimal allocation of renovation budgets. By incorporating user feedback and re-evaluating the system, it can flexibly respond to user needs and provide the best possible proposals.

[0114] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0115] Step 1: User Input Phase

[0116] Detailed explanation:

[0117] The user uses a terminal to enter basic information about the renovation project. This information includes the area to be renovated, the number of rooms, desired materials, necessary equipment, and budget limit.

[0118] input:

[0119] Information on a "100 square meter residence, 3 rooms, high-quality flooring, marble countertops, new kitchen and bathroom, budget limit of 5 million yen."

[0120] Specific actions:

[0121] The user enters the required information on their device and clicks the submit button.

[0122] output:

[0123] The device sends this information to the server.

[0124] Step 2: Data Collection Phase

[0125] Detailed explanation:

[0126] The server collects data on similar renovation projects from a database of past projects. It also obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0127] input:

[0128] User project information.

[0129] Specific actions:

[0130] The server queries a database of past projects to retrieve similar project data. Similarly, the server retrieves current market price information from a market price database and uses web scraping to collect the latest discount information.

[0131] output:

[0132] Collected data (past project data, current market price information, latest discount information).

[0133] Step 3: Model Application Phase

[0134] Detailed explanation:

[0135] Based on the collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item.

[0136] input:

[0137] Past project data, current market price information, and the latest discount information.

[0138] Specific actions:

[0139] The server formats the data and inputs it into the generative AI model. The generative AI model analyzes this data and calculates efficient budget allocation results.

[0140] output:

[0141] Budget allocation results calculated by a generative AI model.

[0142] Step 4: Proposal Generation Phase

[0143] Detailed explanation:

[0144] The server generates cost reduction proposals based on budget allocation results obtained from the generated AI model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and incorporation of the latest discount information.

[0145] input:

[0146] Budget allocation results for generative AI models.

[0147] Specific actions:

[0148] The server generates cost reduction proposals based on the budget allocation results. This includes comparing prices with market prices, recommending alternatives, and applying the latest discount information.

[0149] output:

[0150] The generated cost reduction proposals.

[0151] Step 5: Proposal Review Phase

[0152] Detailed explanation:

[0153] Users review the proposals displayed on their devices. If they are dissatisfied with the proposals or have additional requests or changes to the conditions, they enter them into their devices and send them to the server.

[0154] input:

[0155] The generated cost reduction proposals.

[0156] Specific actions:

[0157] The user reviews the proposal on their device, enters any necessary feedback or changes to the conditions, and submits it.

[0158] output:

[0159] User feedback.

[0160] Step 6: Feedback and Re-evaluation Phase

[0161] Detailed explanation:

[0162] The server receives feedback from the user, re-inputs it into the generated AI model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user.

[0163] input:

[0164] User feedback.

[0165] Specific actions:

[0166] The server analyzes the feedback and inputs it back into the generating AI model to generate new suggestions.

[0167] output:

[0168] A re-evaluated new proposal.

[0169] ---

[0170] By sequentially executing the specific processing steps described above, the system of the present invention proposes the optimal renovation plan within the user's budget and, if necessary, re-evaluates it based on user feedback.

[0171] (Application Example 1)

[0172] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0173] Conventional budget optimization systems for renovation projects could only perform partial optimizations based solely on user-provided information, making it difficult to reflect specific market trends and cost-reduction suggestions in store renovation projects. Furthermore, they lacked sufficient capabilities to incorporate user feedback in real time and re-evaluate using generative AI models. This resulted in problems such as budget overruns or underruns in store renovation projects.

[0174] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0175] This invention includes a server comprising: a device for inputting user project information; a device including a terminal for transmitting the input information to an information processing device; a device including an information processing device for collecting past project data and market price data; a device including an information processing device for calculating budget allocation using a generated AI model based on the collected data; a device including an information processing device for generating cost reduction proposals based on the calculation results and transmitting them to the terminal; and a device including a terminal for displaying the transmitted proposals to the user; and a system characterized by being designed to optimize budget allocation in store renovation projects. This makes it possible to accurately reflect market trends and cost reduction proposals in store renovation projects and to incorporate user feedback in real time.

[0176] A "device for inputting user project information" refers to a terminal or device used by users to input basic information about renovation or store remodeling projects.

[0177] "Devices including terminals that transmit to information processing devices" refers to terminals used to transmit information entered by users to information processing devices in servers or cloud systems.

[0178] "Device including an information processing device for collecting past project data and market price data" refers to a device used to collect past data and current market price information related to renovations and store remodeling.

[0179] "An information processing device including an information processing device that calculates budget allocation using a generative AI model" refers to an information processing device that uses an AI model to calculate budget allocation based on collected data.

[0180] "An information processing device that generates cost reduction proposals and transmits them to the terminal" refers to an information processing device that creates cost reduction proposals based on the generated budget allocation results and transmits that information to the user's terminal.

[0181] "Device including a terminal that displays the transmitted proposal to the user" refers to a terminal that displays cost reduction proposals transmitted from the server to the user.

[0182] A "system characterized by being designed to optimize budget allocation in store renovation projects" refers to a system specifically designed to optimize the budget for store renovation projects.

[0183] This invention is a system for optimizing the budget in store renovation projects. The specific details of implementing this system are described below.

[0184] User input phase

[0185] The user enters basic information about the store renovation project into a dedicated terminal. This information includes the area to be renovated, the number of rooms, desired materials (e.g., flooring, countertops), required equipment (e.g., a new kitchen and bathroom), and a budget limit. The user enters the information and sends it to the server via the terminal.

[0186] Data collection phase

[0187] The server collects data on past store renovation projects from a database. It also retrieves current market price information from a market price database. Furthermore, it uses scraping techniques to collect the latest discount information from the internet. This data is used to optimize the budget.

[0188] Model Application Phase

[0189] Based on project data and market price information collected on the server, a generative AI model is used to calculate the budget allocation for each item. The generative AI model analyzes historical data and market trends to provide efficient budget allocation results. Specifically, it uses the Python Scikit-learn library and leverages algorithms such as RandomForestRegressor.

[0190] Proposal generation phase

[0191] The server generates cost reduction proposals based on budget allocation results obtained from the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0192] Proposal review phase

[0193] The user reviews the suggestions displayed on their device. If they are dissatisfied with the suggestions, or have additional requests or changes to the conditions, they enter them on their device. The user's feedback is sent to the server.

[0194] Feedback and re-evaluation phase

[0195] The server receives feedback from the user and, if necessary, re-inputs it into the generated AI model for re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. By repeating this process, it is possible to provide the most suitable optimized budget for the user's needs.

[0196] Specific example

[0197] For example, if a user enters information such as "area 100 square meters, 3 rooms, desired flooring, budget 5 million yen," the server retrieves similar past project data and gathers market price data and the latest discount information. A generative AI model analyzes this data and displays budget allocation and cost reduction suggestions like the following:

[0198] High-quality flooring costs 1.5 million yen, but using an alternative can reduce the cost to 1.2 million yen.

[0199] A marble countertop costs 500,000 yen, but this can be reduced to 400,000 yen by using reusable materials.

[0200] Kitchen equipment costs 1.2 million yen, and bathroom equipment costs 800,000 yen, but after applying discount information, these can be reduced to 1.1 million yen and 700,000 yen respectively.

[0201] Other 1 million yen

[0202] In this way, users can obtain a concrete plan optimized for their budget. Furthermore, by incorporating user feedback and repeatedly providing even more optimal suggestions, it becomes possible to execute an optimized store renovation project.

[0203] Example of a prompt

[0204] "Users, please enter your store renovation plan:"

[0205] Area: 100 square meters

[0206] Number of rooms: 3

[0207] Desired material: Flooring

[0208] Budget: 5 million yen

[0209] As described above, the present invention is a system that optimizes the budget for store renovation projects and provides optimal proposals tailored to the user's needs.

[0210] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0211] Step 1:

[0212] The user uses a terminal to input basic information about the store renovation project. This information includes area, number of rooms, desired materials, required equipment, and budget limit. Once input is complete, the information is sent to the server. For example, input data might include "Area: 100 square meters, Number of rooms: 3, Flooring desired, Budget: 5 million yen."

[0213] Step 2:

[0214] The server collects past similar project data and market price data based on the project information received from the user. Past project data is obtained from a database, and current market price information is obtained from a market price database. In addition, the server collects the latest discount information from the internet using scraping techniques. As a result, a large amount of reference data is accumulated on the server along with the user's input information.

[0215] Step 3:

[0216] The server uses a generative AI model to calculate budget allocation based on the collected data. This model is implemented using the Python Scikit-learn library and employs algorithms such as RandomForestRegressor. The server provides the model with the user's project information and collected data as input and outputs the budget allocation results. For example, the budget allocation results might include 1.5 million yen for high-quality flooring, 500,000 yen for marble countertops, 1.2 million yen for kitchen equipment, and 800,000 yen for bathroom equipment.

[0217] Step 4:

[0218] The server generates cost reduction proposals based on the budget allocation results obtained by the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. Specifically, it creates proposals to reduce the cost of high-quality flooring to 1.2 million yen, marble countertops to 400,000 yen, kitchen equipment to 1.1 million yen, and bathroom equipment to 700,000 yen. These proposals are then sent to the terminal.

[0219] Step 5:

[0220] The user reviews the suggestions displayed on their device. If the user is dissatisfied with the content or has additional requests or changes to the conditions, they enter them into the device. For example, feedback such as "I don't want a flooring alternative" is possible. This feedback is sent to the server.

[0221] Step 6:

[0222] The server receives feedback from the user and, if necessary, re-inputs it into the generated AI model for re-evaluation. This generates new suggestions, which are then sent back to the terminal. By repeating this process, it is possible to provide an optimized budget that best suits the user's needs.

[0223] By following these steps, efficient and cost-effective budget allocation can be achieved even in store renovation projects. Furthermore, it becomes possible to incorporate user feedback in real time and provide the optimal renovation plan.

[0224] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0225] This invention provides a system that enables more personalized proposals by combining a system for optimizing renovation project budgets with an emotion engine that recognizes user emotions. The system includes a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, a feedback and re-evaluation phase, and an emotion analysis phase. Its detailed operation is described below.

[0226] User input phase

[0227] First, the user uses a terminal to input basic information about the renovation project. This includes details such as area, number of rooms, desired materials and equipment, and budget limit. In addition, the input interface on the terminal incorporates an emotion engine that recognizes the user's emotions through their facial expressions and voice.

[0228] Data collection phase

[0229] The terminal transmits project information and sentiment information entered by the user to the server. The server searches a database of past projects and collects data on similar renovation projects. In addition, it obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0230] Model Application Phase

[0231] Based on collected project data and market price information, the server uses a generative AI model to calculate budget allocation for each item. Furthermore, by incorporating user emotional information from an emotion engine, the user's psychological state is reflected in the optimization of budget allocation.

[0232] Proposal generation phase

[0233] The server generates cost reduction suggestions based on calculation results from the generated AI model. These suggestions include comparisons with market prices adjusted based on user sentiment information, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information.

[0234] Proposal review phase

[0235] The server sends the generated proposal to the terminal in a data format such as JSON. The terminal displays the received proposal to the user. The user reviews the proposed plan. At this point, they also check whether the proposal aligns with their feelings.

[0236] Feedback and re-evaluation phase

[0237] The user provides feedback on the proposed plan. The terminal receiving the feedback sends it to the server. The server receives the user's feedback and re-enters it into the model as needed for re-evaluation. The re-evaluation generates a new proposal. This process is repeated to provide the optimized budget and proposal that best suits the user's needs.

[0238] Emotion analysis phase

[0239] The emotion engine also plays a crucial role when users provide feedback. While users are entering their feedback, it continuously monitors their emotions and uses that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify its approach to certain items.

[0240] Specific example

[0241] For example, if a user plans to renovate a 100-square-meter home, desires high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and has a budget limit of 5 million yen, the emotion engine analyzes the user's emotions regarding these requests from their facial expressions and voice. The server retrieves similar past project data and, based on market price data, the latest discount information obtained through scraping, and the user's emotion information, suggests the optimal budget allocation and generates cost-saving proposals. If the user expresses dissatisfaction with the proposal, the emotion engine detects this, and the server incorporates this information into a new proposal, which is then presented to the user again. Through this process, the user can obtain an optimized renovation plan while minimizing unnecessary spending.

[0242] This series of processes allows users to execute renovation projects that efficiently utilize their budget while also increasing emotional satisfaction.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The user uses a terminal to input basic information about their renovation project. This information includes area, number of rooms, desired materials, equipment, and budget limit. The terminal also has an emotion engine that recognizes the user's emotions through their facial expressions and voice while they are inputting information.

[0246] Step 2:

[0247] The terminal sends emotional information along with project information entered by the user to the server.

[0248] Step 3:

[0249] The server receives the submitted project information and searches the past project database. It also retrieves current market price information from the market price database and collects the latest discount information from the internet using scraping techniques.

[0250] Step 4:

[0251] The server analyzes collected historical project data, market price information, scraped data, and sentiment information, and inputs this into a generative AI model.

[0252] Step 5:

[0253] The server uses a generated AI model to analyze input data, calculates appropriate budget allocations for each item in the renovation project, and adjusts the budget allocation to match the user's psychological state based on emotional information.

[0254] Step 6:

[0255] The server generates further cost-reduction suggestions based on the AI ​​model's calculation results. These suggestions include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The suggestions are optimized by taking sentiment into account.

[0256] Step 7:

[0257] The server converts the budget allocation and cost reduction proposals it generates into a data format such as JSON and sends it to the terminal.

[0258] Step 8:

[0259] The device displays suggestions received from the server to the user. The user reviews and examines the suggested plans. While viewing the suggestions, the emotion engine analyzes the user's facial expressions and reactions to collect emotional information.

[0260] Step 9:

[0261] Users provide feedback on the proposed plan. This feedback can include additional requests, changes to conditions, and emotional responses.

[0262] Step 10:

[0263] The device sends user feedback and sentiment information to the server.

[0264] Step 11:

[0265] The server receives user feedback and, if necessary, re-enters it into the model for re-evaluation. This re-evaluation generates new suggestions. During this process, the suggestions are adjusted based on the acquired sentiment information.

[0266] Step 12:

[0267] The server sends the newly generated suggestion back to the terminal, which then displays it to the user. The sentiment engine continues to monitor the user's emotions and collects new sentiment information as needed. This process is repeated until the optimal plan that best satisfies the user is determined.

[0268] (Example 2)

[0269] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0270] Conventional budget optimization systems for renovation projects often fail to adequately address user satisfaction because they prioritize budget allocation and cost reduction proposals without considering user emotions. Furthermore, they lacked sufficient mechanisms for incorporating and re-evaluating user feedback. As a result, proposals sometimes failed to meet user expectations, leading to a lack of effective renovation plans.

[0271] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0272] In this invention, the server includes means for inputting the user's project information and the user's emotional information, means for collecting past project data, market price data, and the latest discount information from the internet, means for calculating budget allocation using a generated AI model based on the collected data, means for reflecting the user's emotional information in the budget allocation, and means for analyzing the user's emotions when the user provides feedback. This makes it possible to propose an optimal renovation plan that takes the user's emotions into consideration, thereby increasing user satisfaction and providing an effective renovation plan.

[0273] "User project information" refers to detailed information about the renovation project, such as the area, number of rooms, desired materials and equipment, and budget limit.

[0274] "User emotional information" refers to information that shows the psychological response of the user, analyzed through their facial expressions and voice.

[0275] A "terminal" refers to an electronic device used by a user to input information and communicate with a server.

[0276] "Past project data" refers to data that includes records and detailed information about previously carried out renovation projects.

[0277] "Market price data" refers to data that includes current price information for materials, equipment, and services related to home renovation.

[0278] "Latest discount information" refers to currently applicable discount information obtained by scraping from the internet.

[0279] The "generation AI model" is an AI-based algorithm for calculating budget allocation and cost reduction proposals based on the collected data.

[0280] "Budget allocation" refers to the allocation of funds for each item in the renovation project.

[0281] "Cost reduction proposal" refers to specific proposals for efficiently using the user's project budget to obtain the maximum effect at the minimum cost.

[0282] "Feedback" is information indicating the evaluation and opinions of the user on the proposed plan.

[0283] The "emotion engine" is a software or hardware system that analyzes emotions through the user's expressions and voices.

[0284] The present invention is a system that enables more individualized proposals by combining an emotion engine that recognizes the user's emotions with a system for optimizing the budget of a renovation project. This system includes the configurations of a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, a feedback / re-evaluation phase, and an emotion analysis phase.

[0285] First, the user uses a terminal to input the basic information of the renovation project. This includes detailed information such as the area, number of rooms, desired materials / equipment, and budget ceiling. Furthermore, an emotion engine is incorporated into the input interface on the terminal to recognize emotions through the user's expressions and voices. The emotion engine collects and analyzes the expressions and voices of the user during the input operation through a web camera and a microphone.

[0286] Next, the terminal sends project information and sentiment information entered by the user to the server. The server searches the past project database and collects data on similar renovation projects. Furthermore, it obtains current market price information from the market price database and collects the latest discount information from the internet using scraping techniques.

[0287] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. User sentiment information is also incorporated to reflect the user's psychological state in optimizing the budget allocation. The generative AI model is an algorithm that optimizes budget allocation according to user requests, and it performs calculations based on prompt text input.

[0288] For example, if a user inputs information that they are planning a 100-square-meter home renovation, desire high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and have a budget limit of 5 million yen, the emotion engine will analyze the user's emotions regarding these requests from their facial expressions and voice. The server will retrieve similar past project data, and based on market price data, the latest discount information obtained through scraping, and the user's emotion information, it will suggest the optimal budget allocation and generate cost-saving proposals. An example of this prompt message would be: "The user has entered that they desire a 100-square-meter home renovation, requesting high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, with a budget limit of 5 million yen. Please optimize the budget allocation based on past project data and market price data. Also, please consider the user's emotion information regarding the proposed content."

[0289] In the proposal generation phase, the server generates cost reduction proposals based on the calculation results of the generation AI model. These proposals include a comparison with market prices adjusted based on the user's sentiment information, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The server sends the generated proposals to the terminal in a data format such as JSON. The terminal displays the received proposals to the user, who reviews the proposed plan. At this time, the user also checks whether the proposal content matches their sentiment.

[0290] In the feedback and re-evaluation phase, the user inputs feedback on the proposed plan. The terminal receiving the feedback sends it to the server. The server receives the user's feedback and, if necessary, re-inputs it into the generated AI model for re-evaluation. The re-evaluation generates a new proposal, and by repeating this process, the system provides the optimized budget and proposal that best suits the user's needs.

[0291] Finally, in the emotion analysis phase, the emotion engine also plays a crucial role during feedback, analyzing the user's facial expressions and voice, and using that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify the approach to specific items.

[0292] This series of processes allows users to execute renovation projects that efficiently utilize their budget while also increasing emotional satisfaction.

[0293] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0294] Step 1: User Input Phase

[0295] Specific operation: The user enters basic information about the renovation project through the terminal's input interface. This includes area, number of rooms, desired materials and equipment, and budget limit. The terminal also has an emotion engine built in, which collects facial expressions and voice via the webcam and microphone during the input process.

[0296] Input: Area, number of rooms, desired materials / equipment, budget limit, user's facial expression and voice.

[0297] Output: User project information and sentiment information

[0298] Data processing / calculations: None

[0299] Step 2: Data Collection Phase

[0300] Specific operation: The terminal converts the project information and sentiment information entered by the user into JSON format and sends it to the server. The server collects historical project data, market price data, and the latest discount information by scraping from the internet.

[0301] Input: User project information and sentiment information

[0302] Output: Historical project data, market price data, and the latest discount information.

[0303] Data processing and calculation: The server receives data in JSON format and collects related information from databases and the internet.

[0304] Step 3: Model Application Phase

[0305] Specific operation: The server uses a generated AI model based on the collected data to calculate the budget allocation for each item. At the same time, it incorporates user sentiment information to reflect psychological factors in the budget allocation.

[0306] Input: Past project data, market price data, latest discount information, user sentiment information

[0307] Output: Optimized budget allocation

[0308] Data processing and calculation: The server sends a prompt sentence to the generative AI model to calculate the budget allocation. At this time, the user's sentiment information is incorporated for adjustment.

[0309] Step 4: Proposal generation phase

[0310] Specific operations: The server generates a cost reduction proposal based on the calculation results of the generative AI model. This proposal includes comparison with market prices, recommendation of alternatives, proposal of reusable materials, and reflection of the latest discount information. The proposal result is sent to the terminal in JSON format.

[0311] Input: Optimized budget allocation

[0312] Output: Cost reduction proposal

[0313] Data processing and calculation: The server analyzes the budget allocation result and generates the proposal content. This is sent to the terminal in JSON format.

[0314] Step 5: Proposal confirmation phase

[0315] Specific operations: The server sends the generated proposal to the terminal, and the terminal displays the received proposal to the user. The user checks and reviews the proposed plan. At this time, it is also confirmed whether the proposal content matches the user's sentiment.

[0316] Input: Cost reduction proposal

[0317] Output: User review and emotional reaction

[0318] Data processing and calculation: None

[0319] Step 6: Feedback and Re-evaluation Phase

[0320] Specific operation: The user inputs feedback on the proposed content, and the device sends this to the server. The server analyzes the feedback and, if necessary, re-inputs it into the generating AI model for re-evaluation. A new proposal is generated and provided to the user again.

[0321] Input: User feedback and sentiment information

[0322] Output: New proposal

[0323] Data processing and calculation: The server analyzes the feedback and re-inputs it into the generating AI model to generate new suggestions.

[0324] Step 7: Emotional Analysis Phase

[0325] Specific operation: The emotion engine continuously monitors user emotions as they provide feedback and uses that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify its approach to certain items.

[0326] Input: User sentiment information

[0327] Output: Improved suggestions

[0328] Data Processing and Calculation: The emotion engine analyzes the emotion data during feedback, sends the results to the server, and incorporates them into the suggestions.

[0329] (Application Example 2)

[0330] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0331] In modern renovation projects, it's crucial to optimize the user's budget while providing proposals tailored to their individual needs. However, traditional systems simply perform mechanical calculations based on input information, failing to consider user emotions or real-time reactions. As a result, user satisfaction declined, and effective budget allocation became difficult.

[0332] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's project information, means including a terminal for transmitting the input information to the server, means including a server for collecting past project data and market price data, means including a server for calculating budget allocation using a generated AI model based on the collected data, means including an emotion engine for recognizing the user's emotions in real time and reflecting them in the proposed content, and means including a terminal for displaying the transmitted proposal to the user. This makes it possible to optimize the renovation budget and provide personalized proposals while taking emotions into consideration.

[0333] "Means for inputting user project information" refers to a device or software that provides an interface for users to input information related to a renovation project (e.g., area, number of rooms, desired materials / equipment, budget limit, etc.).

[0334] "Means including a terminal that transmits the input information to the server" refers to a device or apparatus equipped with the function of transmitting project information entered by a user to a remote server.

[0335] "Means including a server for collecting past project data and market price data" refers to a server that collects and stores data on past renovation projects and data on current market prices.

[0336] "Means including a server that calculates budget allocation using a generative AI model based on the collected data" refers to a server that uses collected project data and market price data to calculate the optimal budget allocation using a generative AI model.

[0337] "Means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal" refers to a server that creates cost reduction proposals based on budget allocations calculated by a generation AI model and transmits them to the user's terminal.

[0338] "Means including an emotion engine for recognizing user emotions in real time and reflecting them in proposals" refers to an emotion analysis engine that analyzes user emotions in real time from facial expressions and voice, and reflects the results in renovation proposals.

[0339] "Means including a terminal that displays the transmitted proposal to the user" refers to a terminal or device that has the function of displaying the renovation proposal transmitted from the server to the user.

[0340] This invention is a system that optimizes the budget for renovation projects while providing personalized suggestions that reflect the user's emotions. The system is designed to assist users in selecting renovation-related products in physical stores using smart glasses.

[0341] Hardware and software to be used

[0342] Hardware:

[0343] Smart glasses (e.g., Google Glass)

[0344] software:

[0345] Emotional engine (e.g., Affectiva)

[0346] Generative AI models (e.g., GPT models, or custom models)

[0347] Specific operation of the system

[0348] 1. User input phase:

[0349] A user wearing smart glasses inputs project information (e.g., size of the renovation area, desired design, budget, etc.) via voice. The smart glasses' camera and microphone capture the user's facial expressions and voice, and this data is transmitted to the server in real time.

[0350] 2. Data Collection Phase:

[0351] The server receives project and sentiment information submitted by users and collects relevant data from historical project data and market price databases. Furthermore, it uses scraping techniques to obtain the latest discount information from the internet.

[0352] 3. Model Application Phase:

[0353] The server uses a generative AI model based on the collected data to calculate budget allocation. It also incorporates user emotional information from an emotion engine to reflect the user's psychological state in the budget allocation process.

[0354] 4. Proposal generation phase:

[0355] The server generates cost-saving suggestions based on calculation results from a generative AI model and emotional information. These suggestions include recommendations for cost-effective alternatives, suggestions for reusable materials, and the incorporation of the latest discount information. The suggestions are sent from the server to the smart glasses and displayed to the user.

[0356] 5. Feedback and Re-evaluation Phase:

[0357] The user reviews the suggestions and provides feedback via voice input. The smart glasses simultaneously capture the user's facial expressions and send them to the server. The server then re-evaluates the feedback and generates new suggestions.

[0358] Specific example

[0359] For example, suppose a user wants a high-quality leather sofa and has a budget of 200,000 yen. Smart glasses analyze the user's preferences from their facial expressions and voice, and present a list of optimal products based on past purchase data and market prices. The system monitors the user's reactions in real time and adjusts its suggestions based on changes in their emotions.

[0360] Examples of prompts for generative AI models

[0361] "The user wants a high-quality leather sofa, and their budget is 200,000 yen. Please suggest the best option within that budget."

[0362] "The user is looking for a 50m² area for renovation." 2 I'm looking for furniture for my living room. Please provide optimized suggestions based on emotional analysis.

[0363] This system allows users to receive optimized proposals that are emotionally satisfying while minimizing unnecessary expenses in their renovation projects.

[0364] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0365] Step 1:

[0366] The user wears smart glasses and inputs basic information about their renovation project via voice. Specifically, they provide information such as the size of the renovation area, desired design, and budget. The smart glasses' camera and microphone capture the user's facial expressions and voice, and transmit this data to the server in real time. Input: User's voice data and facial expression data. Output: User's project information and emotion data.

[0367] Step 2:

[0368] The server receives project information and sentiment information submitted by users, and collects relevant data from historical project data and market price databases. It also uses scraping techniques to obtain the latest discount information from the internet. Input: User project information and sentiment data. Output: Historical project data, market price data, and latest discount information.

[0369] Step 3:

[0370] The server uses a generative AI model based on the collected data to calculate budget allocation. Specifically, project information is input to the generative AI model as prompts, and the optimal budget allocation is calculated. In addition, user emotion information from an emotion engine is incorporated to reflect the user's psychological state in the budget allocation. Input: Past project data, market price data, latest discount information, and user emotion data. Output: Budget allocation calculation results reflecting emotions.

[0371] Step 4:

[0372] The server generates cost reduction proposals based on calculation results from a generative AI model. These proposals include recommendations for cost-effective alternatives, suggestions for reusable materials, and the incorporation of the latest discount information. The generated proposals are sent from the server to the smart glasses. Input: Budget allocation calculation results reflecting emotions. Output: Cost reduction proposals.

[0373] Step 5:

[0374] The smart glasses display suggestions sent from the server to the user. The user reviews the suggestions and provides feedback via voice. The smart glasses also capture the user's facial expressions simultaneously with the feedback and send this data to the server. Input: Cost reduction suggestions and user feedback. Output: User reaction data and feedback data.

[0375] Step 6:

[0376] The server re-evaluates user feedback and generates new suggestions. Specifically, it inputs the sentiment data and feedback data again into the AI ​​model to create optimized new suggestions. The new suggestions are then sent back to the smart glasses and displayed to the user. Input: User reaction data and feedback data. Output: Re-evaluated suggestions.

[0377] 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.

[0378] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. 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 shown 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.

[0379] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0380] [Second Embodiment]

[0381] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0386] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0387] 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.

[0388] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0389] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0390] The 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.

[0391] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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.

[0392] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0393] This invention is a system that supports budget optimization in renovation projects and consists of a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, and a feedback / re-evaluation phase. Its detailed operation is described below.

[0394] User input phase

[0395] The user enters basic information about the renovation project into the terminal. This information includes the area to be renovated, the number of rooms, desired materials (e.g., high-quality flooring, marble countertops), required equipment (e.g., new kitchen and bathroom), and budget limit. The entered information is sent from the terminal to the server.

[0396] Data collection phase

[0397] The server collects data on similar renovation projects from a database of past projects. It also retrieves current market price information from a market price database. Furthermore, it uses scraping techniques to collect the latest discount information from the internet.

[0398] Model Application Phase

[0399] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. This model analyzes historical data and market trends to provide efficient allocation results.

[0400] Proposal generation phase

[0401] The server generates cost reduction proposals based on budget allocation results obtained from the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and incorporation of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0402] Proposal review phase

[0403] The user reviews the proposal displayed on the device. If they are dissatisfied with the proposal, or have additional requests or changes to the conditions, they enter them into the device. The device then sends the user's feedback to the server.

[0404] Feedback and re-evaluation phase

[0405] The server receives feedback from the user, re-inputs it into the model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. By repeating this process, the system can provide the most suitable optimization budget for the user's needs.

[0406] Specific example

[0407] For example, suppose a user is planning a renovation of a 100-square-meter home, desires high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and has a budget limit of 5 million yen. The server retrieves data from similar past projects, gathers market price data, and collects the latest discount information through web scraping. The AI ​​model analyzes this data and presents budget allocation and cost reduction suggestions as follows:

[0408] High-quality flooring costs 1.5 million yen, but using an alternative could reduce the cost to 1.2 million yen.

[0409] A marble countertop costs 500,000 yen, but by using recycled materials, the cost can be reduced to 400,000 yen.

[0410] Kitchen equipment can be reduced by 1.2 million yen, bathroom equipment by 800,000 yen, and after applying discount information, these can be reduced to 1.1 million yen and 700,000 yen respectively.

[0411] Other 1 million yen

[0412] In this way, users can obtain a concrete plan optimized for their budget. Throughout this process, user feedback is incorporated, and even more optimal suggestions are repeatedly provided, enabling the successful execution of an optimized renovation project.

[0413] The following describes the processing flow.

[0414] Step 1:

[0415] The user uses a device to enter basic information about the renovation project. This information includes the area to be renovated, the number of rooms, desired materials and equipment, and the budget limit.

[0416] Step 2:

[0417] The terminal sends project information entered by the user to the server. The information sent includes all the project details entered.

[0418] Step 3:

[0419] The server receives the submitted project information and searches the past project database. Simultaneously, it retrieves current market price information from the market price database. It also collects the latest discount information from the internet using scraping techniques.

[0420] Step 4:

[0421] The server analyzes collected historical project data and market price information, and inputs this into a generating AI model.

[0422] Step 5:

[0423] The server uses a generated AI model to analyze the input data and calculate the appropriate budget allocation for each item in the renovation project. This calculation includes the optimal cost for each material and equipment.

[0424] Step 6:

[0425] The server generates further cost-reduction suggestions based on the AI ​​model's calculation results. These suggestions include comparisons with market prices based on user preferences, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information.

[0426] Step 7:

[0427] The server converts the budget allocation and cost reduction proposals it generates into a data format such as JSON and sends it to the terminal.

[0428] Step 8:

[0429] The terminal displays the suggestions received from the server to the user. The user reviews and confirms the suggested plan.

[0430] Step 9:

[0431] The user enters feedback on the proposed plan. This feedback may include additional requests or changes to the terms and conditions.

[0432] Step 10:

[0433] The device sends user feedback to the server.

[0434] Step 11:

[0435] The server receives user feedback and, if necessary, re-inputs it into the model for re-evaluation. This re-evaluation generates new suggestions.

[0436] Step 12:

[0437] The server sends the newly generated proposal back to the terminal, which then displays it to the user. This process is repeated until the optimal plan that best satisfies the user is determined.

[0438] (Example 1)

[0439] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0440] Budgeting for renovation projects is complex and requires considering many factors. Therefore, manually determining the optimal budget allocation requires a tremendous amount of time and effort from the user. Furthermore, constantly checking market price fluctuations and discount information is time-consuming, making it difficult to obtain optimal cost-saving proposals. To address these challenges, there is a need for a user-friendly system that efficiently optimizes budgets.

[0441] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0442] In this invention, the server includes means for inputting user project information, means including a terminal for transmitting the input information to the server, means including a server for collecting past project data and market price data, means including a server for calculating budget allocation using a generation AI model based on the collected data, means including a server for generating cost reduction proposals based on the calculation results and transmitting them to the terminal, means including a terminal for displaying the transmitted proposals to the user, means including a server for receiving user feedback and re-inputting data into the generation AI model for re-evaluation, and means including a server for obtaining the latest discount information from the internet using a scraping technique based on the collected data. This enables the user to obtain the optimal budget allocation efficiently and quickly. Furthermore, since re-evaluation reflecting feedback is possible, flexible proposals tailored to the user's needs can be made.

[0443] "User project information" refers to detailed information about the renovation project, such as the area, number of rooms, desired materials, necessary equipment, and budget limit.

[0444] A "terminal" is an electronic device used by users to input information and communicate with a server. Specifically, this includes personal computers, tablets, and smartphones.

[0445] A "server" is a computing system used for data collection, analysis, generation, budget allocation calculations using AI models, generation of cost reduction proposals, and processing user feedback.

[0446] "Past project data" refers to data related to previously carried out renovation projects, including budget, materials used, construction details, and duration.

[0447] "Market price data" refers to information about the current market value of materials and equipment needed for home renovations. This data is used to understand price fluctuations and trends.

[0448] A "generative AI model" is an artificial intelligence algorithm that automatically calculates and generates budget allocation and cost reduction proposals based on collected data.

[0449] "Cost reduction suggestions" are proposals for efficiently using the user's budget, and include recommendations for alternative materials, comparisons of market prices, and incorporation of the latest discount information.

[0450] "Web scraping" is a technique for automatically collecting specific data from publicly available information on the internet.

[0451] "Feedback" refers to opinions, additional requests, and information regarding changes to terms and conditions provided by users in response to suggestions.

[0452] "Re-evaluation" is the process of running the generated AI model again based on user feedback to generate new suggestions.

[0453] This invention is a system that supports budget optimization in renovation projects. The system consists of the following phases: user input phase, data collection phase, model application phase, proposal generation phase, proposal confirmation phase, and feedback / re-evaluation phase. The specific implementation methods for each phase are described below.

[0454] User input phase

[0455] The user enters basic information about the renovation project via a terminal. This information includes the area to be renovated, the number of rooms, desired materials, necessary equipment, and budget limit. For example, the user might enter "100 square meter residence, 3 rooms, high-quality flooring, marble countertops, new kitchen and bathroom, budget limit of 5 million yen." The terminal then sends this information to the server.

[0456] Data collection phase

[0457] The server collects data on similar renovation projects from a database of past projects. It also obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0458] Model Application Phase

[0459] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. This model analyzes historical data and market trends to provide efficient allocation results. The generative AI model is input with historical project data and market price information, and outputs a budget allocation result such as "1.5 million yen for high-quality flooring, 500,000 yen for marble countertops, 1.2 million yen for kitchen equipment, 800,000 yen for bathroom equipment, and 1 million yen for other items."

[0460] Proposal generation phase

[0461] The server generates cost reduction proposals based on budget allocation results obtained from the generated AI model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0462] Proposal review phase

[0463] Users review the proposals displayed on their devices. If they are dissatisfied with the proposals or have additional requests or changes to the conditions, they enter them into their devices and send them to the server.

[0464] Feedback and re-evaluation phase

[0465] The server receives user feedback, re-inputs it into the generated AI model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. This ensures that the user receives an optimized renovation plan that best suits their needs.

[0466] Example of a prompt

[0467] "We are planning a renovation of a 100-square-meter residence. We would like high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, with a budget limit of 5 million yen. Please propose a budget allocation based on similar past project data and market price information."

[0468] This system utilizes AI models generated from user input to analyze historical data and market trends, providing efficient and optimal allocation of renovation budgets. By incorporating user feedback and re-evaluating the system, it can flexibly respond to user needs and provide the best possible proposals.

[0469] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0470] Step 1: User Input Phase

[0471] Detailed explanation:

[0472] The user uses a terminal to enter basic information about the renovation project. This information includes the area to be renovated, the number of rooms, desired materials, necessary equipment, and budget limit.

[0473] input:

[0474] Information on a "100 square meter residence, 3 rooms, high-quality flooring, marble countertops, new kitchen and bathroom, budget limit of 5 million yen."

[0475] Specific actions:

[0476] The user enters the required information on their device and clicks the submit button.

[0477] output:

[0478] The device sends this information to the server.

[0479] Step 2: Data Collection Phase

[0480] Detailed explanation:

[0481] The server collects data on similar renovation projects from a database of past projects. It also obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0482] input:

[0483] User project information.

[0484] Specific actions:

[0485] The server queries a database of past projects to retrieve similar project data. Similarly, the server retrieves current market price information from a market price database and uses web scraping to collect the latest discount information.

[0486] output:

[0487] Collected data (past project data, current market price information, latest discount information).

[0488] Step 3: Model Application Phase

[0489] Detailed explanation:

[0490] Based on the collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item.

[0491] input:

[0492] Past project data, current market price information, and the latest discount information.

[0493] Specific actions:

[0494] The server formats the data and inputs it into the generative AI model. The generative AI model analyzes this data and calculates efficient budget allocation results.

[0495] output:

[0496] Budget allocation results calculated by a generative AI model.

[0497] Step 4: Proposal Generation Phase

[0498] Detailed explanation:

[0499] The server generates cost reduction proposals based on budget allocation results obtained from the generated AI model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and incorporation of the latest discount information.

[0500] input:

[0501] Budget allocation results for generative AI models.

[0502] Specific actions:

[0503] The server generates cost reduction proposals based on the budget allocation results. This includes comparing prices with market prices, recommending alternatives, and applying the latest discount information.

[0504] output:

[0505] The generated cost reduction proposals.

[0506] Step 5: Proposal Review Phase

[0507] Detailed explanation:

[0508] Users review the proposals displayed on their devices. If they are dissatisfied with the proposals or have additional requests or changes to the conditions, they enter them into their devices and send them to the server.

[0509] input:

[0510] The generated cost reduction proposals.

[0511] Specific actions:

[0512] The user reviews the proposal on their device, enters any necessary feedback or changes to the conditions, and submits it.

[0513] output:

[0514] User feedback.

[0515] Step 6: Feedback and Re-evaluation Phase

[0516] Detailed explanation:

[0517] The server receives feedback from the user, re-inputs it into the generated AI model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user.

[0518] input:

[0519] User feedback.

[0520] Specific actions:

[0521] The server analyzes the feedback and inputs it back into the generating AI model to generate new suggestions.

[0522] output:

[0523] A re-evaluated new proposal.

[0524] ---

[0525] By sequentially executing the specific processing steps described above, the system of the present invention proposes the optimal renovation plan within the user's budget and, if necessary, re-evaluates it based on user feedback.

[0526] (Application Example 1)

[0527] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0528] Conventional budget optimization systems for renovation projects could only perform partial optimizations based solely on user-provided information, making it difficult to reflect specific market trends and cost-reduction suggestions in store renovation projects. Furthermore, they lacked sufficient capabilities to incorporate user feedback in real time and re-evaluate using generative AI models. This resulted in problems such as budget overruns or underruns in store renovation projects.

[0529] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0530] This invention includes a server comprising: a device for inputting user project information; a device including a terminal for transmitting the input information to an information processing device; a device including an information processing device for collecting past project data and market price data; a device including an information processing device for calculating budget allocation using a generated AI model based on the collected data; a device including an information processing device for generating cost reduction proposals based on the calculation results and transmitting them to the terminal; and a device including a terminal for displaying the transmitted proposals to the user; and a system characterized by being designed to optimize budget allocation in store renovation projects. This makes it possible to accurately reflect market trends and cost reduction proposals in store renovation projects and to incorporate user feedback in real time.

[0531] A "device for inputting user project information" refers to a terminal or device used by users to input basic information about renovation or store remodeling projects.

[0532] "Devices including terminals that transmit to information processing devices" refers to terminals used to transmit information entered by users to information processing devices in servers or cloud systems.

[0533] "Device including an information processing device for collecting past project data and market price data" refers to a device used to collect past data and current market price information related to renovations and store remodeling.

[0534] "An information processing device including an information processing device that calculates budget allocation using a generative AI model" refers to an information processing device that uses an AI model to calculate budget allocation based on collected data.

[0535] "An information processing device that generates cost reduction proposals and transmits them to the terminal" refers to an information processing device that creates cost reduction proposals based on the generated budget allocation results and transmits that information to the user's terminal.

[0536] "Device including a terminal that displays the transmitted proposal to the user" refers to a terminal that displays cost reduction proposals transmitted from the server to the user.

[0537] A "system characterized by being designed to optimize budget allocation in store renovation projects" refers to a system specifically designed to optimize the budget for store renovation projects.

[0538] This invention is a system for optimizing the budget in store renovation projects. The specific details of implementing this system are described below.

[0539] User input phase

[0540] The user enters basic information about the store renovation project into a dedicated terminal. This information includes the area to be renovated, the number of rooms, desired materials (e.g., flooring, countertops), required equipment (e.g., a new kitchen and bathroom), and a budget limit. The user enters the information and sends it to the server via the terminal.

[0541] Data collection phase

[0542] The server collects data on past store renovation projects from a database. It also retrieves current market price information from a market price database. Furthermore, it uses scraping techniques to collect the latest discount information from the internet. This data is used to optimize the budget.

[0543] Model Application Phase

[0544] Based on project data and market price information collected on the server, a generative AI model is used to calculate the budget allocation for each item. The generative AI model analyzes historical data and market trends to provide efficient budget allocation results. Specifically, it uses the Python Scikit-learn library and leverages algorithms such as RandomForestRegressor.

[0545] Proposal generation phase

[0546] The server generates cost reduction proposals based on budget allocation results obtained from the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0547] Proposal review phase

[0548] The user reviews the suggestions displayed on their device. If they are dissatisfied with the suggestions, or have additional requests or changes to the conditions, they enter them on their device. The user's feedback is sent to the server.

[0549] Feedback and re-evaluation phase

[0550] The server receives feedback from the user and, if necessary, re-inputs it into the generated AI model for re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. By repeating this process, it is possible to provide the most suitable optimized budget for the user's needs.

[0551] Specific example

[0552] For example, if a user enters information such as "area 100 square meters, 3 rooms, desired flooring, budget 5 million yen," the server retrieves similar past project data and gathers market price data and the latest discount information. A generative AI model analyzes this data and displays budget allocation and cost reduction suggestions like the following:

[0553] High-quality flooring costs 1.5 million yen, but using an alternative can reduce the cost to 1.2 million yen.

[0554] A marble countertop costs 500,000 yen, but this can be reduced to 400,000 yen by using reusable materials.

[0555] Kitchen equipment costs 1.2 million yen, and bathroom equipment costs 800,000 yen, but after applying discount information, these can be reduced to 1.1 million yen and 700,000 yen respectively.

[0556] Other 1 million yen

[0557] In this way, users can obtain a concrete plan optimized for their budget. Furthermore, by incorporating user feedback and repeatedly providing even more optimal suggestions, it becomes possible to execute an optimized store renovation project.

[0558] Example of a prompt

[0559] "Users, please enter your store renovation plan:"

[0560] Area: 100 square meters

[0561] Number of rooms: 3

[0562] Desired material: Flooring

[0563] Budget: 5 million yen

[0564] As described above, the present invention is a system that optimizes the budget for store renovation projects and provides optimal proposals tailored to the user's needs.

[0565] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0566] Step 1:

[0567] The user uses a terminal to input basic information about the store renovation project. This information includes area, number of rooms, desired materials, required equipment, and budget limit. Once input is complete, the information is sent to the server. For example, input data might include "Area: 100 square meters, Number of rooms: 3, Flooring desired, Budget: 5 million yen."

[0568] Step 2:

[0569] The server collects past similar project data and market price data based on the project information received from the user. Past project data is obtained from a database, and current market price information is obtained from a market price database. In addition, the server collects the latest discount information from the internet using scraping techniques. As a result, a large amount of reference data is accumulated on the server along with the user's input information.

[0570] Step 3:

[0571] The server uses a generative AI model to calculate budget allocation based on the collected data. This model is implemented using the Python Scikit-learn library and employs algorithms such as RandomForestRegressor. The server provides the model with the user's project information and collected data as input and outputs the budget allocation results. For example, the budget allocation results might include 1.5 million yen for high-quality flooring, 500,000 yen for marble countertops, 1.2 million yen for kitchen equipment, and 800,000 yen for bathroom equipment.

[0572] Step 4:

[0573] The server generates cost reduction proposals based on the budget allocation results obtained by the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. Specifically, it creates proposals to reduce the cost of high-quality flooring to 1.2 million yen, marble countertops to 400,000 yen, kitchen equipment to 1.1 million yen, and bathroom equipment to 700,000 yen. These proposals are then sent to the terminal.

[0574] Step 5:

[0575] The user reviews the suggestions displayed on their device. If the user is dissatisfied with the content or has additional requests or changes to the conditions, they enter them into the device. For example, feedback such as "I don't want a flooring alternative" is possible. This feedback is sent to the server.

[0576] Step 6:

[0577] The server receives feedback from the user and, if necessary, re-inputs it into the generated AI model for re-evaluation. This generates new suggestions, which are then sent back to the terminal. By repeating this process, it is possible to provide an optimized budget that best suits the user's needs.

[0578] By following these steps, efficient and cost-effective budget allocation can be achieved even in store renovation projects. Furthermore, it becomes possible to incorporate user feedback in real time and provide the optimal renovation plan.

[0579] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0580] This invention provides a system that enables more personalized proposals by combining a system for optimizing renovation project budgets with an emotion engine that recognizes user emotions. The system includes a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, a feedback and re-evaluation phase, and an emotion analysis phase. Its detailed operation is described below.

[0581] User input phase

[0582] First, the user uses a terminal to input basic information about the renovation project. This includes details such as area, number of rooms, desired materials and equipment, and budget limit. In addition, the input interface on the terminal incorporates an emotion engine that recognizes the user's emotions through their facial expressions and voice.

[0583] Data collection phase

[0584] The terminal transmits project information and sentiment information entered by the user to the server. The server searches a database of past projects and collects data on similar renovation projects. In addition, it obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0585] Model Application Phase

[0586] Based on collected project data and market price information, the server uses a generative AI model to calculate budget allocation for each item. Furthermore, by incorporating user emotional information from an emotion engine, the user's psychological state is reflected in the optimization of budget allocation.

[0587] Proposal generation phase

[0588] The server generates cost reduction suggestions based on calculation results from the generated AI model. These suggestions include comparisons with market prices adjusted based on user sentiment information, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information.

[0589] Proposal review phase

[0590] The server sends the generated proposal to the terminal in a data format such as JSON. The terminal displays the received proposal to the user. The user reviews the proposed plan. At this point, they also check whether the proposal aligns with their feelings.

[0591] Feedback and re-evaluation phase

[0592] The user provides feedback on the proposed plan. The terminal receiving the feedback sends it to the server. The server receives the user's feedback and re-enters it into the model as needed for re-evaluation. The re-evaluation generates a new proposal. This process is repeated to provide the optimized budget and proposal that best suits the user's needs.

[0593] Emotion analysis phase

[0594] The emotion engine also plays a crucial role when users provide feedback. While users are entering their feedback, it continuously monitors their emotions and uses that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify its approach to certain items.

[0595] Specific example

[0596] For example, if a user plans to renovate a 100-square-meter home, desires high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and has a budget limit of 5 million yen, the emotion engine analyzes the user's emotions regarding these requests from their facial expressions and voice. The server retrieves similar past project data and, based on market price data, the latest discount information obtained through scraping, and the user's emotion information, suggests the optimal budget allocation and generates cost-saving proposals. If the user expresses dissatisfaction with the proposal, the emotion engine detects this, and the server incorporates this information into a new proposal, which is then presented to the user again. Through this process, the user can obtain an optimized renovation plan while minimizing unnecessary spending.

[0597] This series of processes allows users to execute renovation projects that efficiently utilize their budget while also increasing emotional satisfaction.

[0598] The following describes the processing flow.

[0599] Step 1:

[0600] The user uses a terminal to input basic information about their renovation project. This information includes area, number of rooms, desired materials, equipment, and budget limit. The terminal also has an emotion engine that recognizes the user's emotions through their facial expressions and voice while they are inputting information.

[0601] Step 2:

[0602] The terminal sends emotional information along with project information entered by the user to the server.

[0603] Step 3:

[0604] The server receives the submitted project information and searches the past project database. It also retrieves current market price information from the market price database and collects the latest discount information from the internet using scraping techniques.

[0605] Step 4:

[0606] The server analyzes collected historical project data, market price information, scraped data, and sentiment information, and inputs this into a generative AI model.

[0607] Step 5:

[0608] The server uses a generated AI model to analyze input data, calculates appropriate budget allocations for each item in the renovation project, and adjusts the budget allocation to match the user's psychological state based on emotional information.

[0609] Step 6:

[0610] The server generates further cost-reduction suggestions based on the AI ​​model's calculation results. These suggestions include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The suggestions are optimized by taking sentiment into account.

[0611] Step 7:

[0612] The server converts the budget allocation and cost reduction proposals it generates into a data format such as JSON and sends it to the terminal.

[0613] Step 8:

[0614] The device displays suggestions received from the server to the user. The user reviews and examines the suggested plans. While viewing the suggestions, the emotion engine analyzes the user's facial expressions and reactions to collect emotional information.

[0615] Step 9:

[0616] Users provide feedback on the proposed plan. This feedback can include additional requests, changes to conditions, and emotional responses.

[0617] Step 10:

[0618] The device sends user feedback and sentiment information to the server.

[0619] Step 11:

[0620] The server receives user feedback and, if necessary, re-enters it into the model for re-evaluation. This re-evaluation generates new suggestions. During this process, the suggestions are adjusted based on the acquired sentiment information.

[0621] Step 12:

[0622] The server sends the newly generated suggestion back to the terminal, which then displays it to the user. The sentiment engine continues to monitor the user's emotions and collects new sentiment information as needed. This process is repeated until the optimal plan that best satisfies the user is determined.

[0623] (Example 2)

[0624] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0625] Conventional budget optimization systems for renovation projects often fail to adequately address user satisfaction because they prioritize budget allocation and cost reduction proposals without considering user emotions. Furthermore, they lacked sufficient mechanisms for incorporating and re-evaluating user feedback. As a result, proposals sometimes failed to meet user expectations, leading to a lack of effective renovation plans.

[0626] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0627] In this invention, the server includes means for inputting the user's project information and the user's emotional information, means for collecting past project data, market price data, and the latest discount information from the internet, means for calculating budget allocation using a generated AI model based on the collected data, means for reflecting the user's emotional information in the budget allocation, and means for analyzing the user's emotions when the user provides feedback. This makes it possible to propose an optimal renovation plan that takes the user's emotions into consideration, thereby increasing user satisfaction and providing an effective renovation plan.

[0628] "User project information" refers to detailed information about the renovation project, such as the area, number of rooms, desired materials and equipment, and budget limit.

[0629] "User emotional information" refers to information that shows the psychological response of the user, analyzed through their facial expressions and voice.

[0630] A "terminal" refers to an electronic device used by a user to input information and communicate with a server.

[0631] "Past project data" refers to data that includes records and detailed information about previously carried out renovation projects.

[0632] "Market price data" refers to data that includes current price information for materials, equipment, and services related to home renovation.

[0633] "Latest discount information" refers to currently applicable discount information obtained by scraping from the internet.

[0634] A "generative AI model" is an artificial intelligence-based algorithm used to calculate budget allocation and cost reduction proposals based on collected data.

[0635] "Budget allocation" refers to the allocation of funds to each item in a renovation project.

[0636] A "cost reduction proposal" refers to specific suggestions for efficiently using a user's project budget and achieving maximum results with minimum cost.

[0637] "Feedback" refers to information that shows the user's evaluation and opinion on the proposed plan.

[0638] An "emotion engine" is a software or hardware system that analyzes a user's emotions through their facial expressions and voice.

[0639] This invention provides a system that enables more personalized proposals by combining a system for optimizing the budget of a renovation project with an emotion engine that recognizes the user's emotions. The system includes a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, a feedback and re-evaluation phase, and an emotion analysis phase.

[0640] First, the user uses a terminal to input basic information about the renovation project. This includes detailed information such as area, number of rooms, desired materials and equipment, and budget limit. Furthermore, the input interface on the terminal incorporates an emotion engine that recognizes the user's emotions through their facial expressions and voice. The emotion engine collects and analyzes the user's facial expressions and voice through a webcam and microphone while they are performing the input task.

[0641] Next, the terminal sends project information and sentiment information entered by the user to the server. The server searches the past project database and collects data on similar renovation projects. Furthermore, it obtains current market price information from the market price database and collects the latest discount information from the internet using scraping techniques.

[0642] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. User sentiment information is also incorporated to reflect the user's psychological state in optimizing the budget allocation. The generative AI model is an algorithm that optimizes budget allocation according to user requests, and it performs calculations based on prompt text input.

[0643] For example, if a user inputs information that they are planning a 100-square-meter home renovation, desire high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and have a budget limit of 5 million yen, the emotion engine will analyze the user's emotions regarding these requests from their facial expressions and voice. The server will retrieve similar past project data, and based on market price data, the latest discount information obtained through scraping, and the user's emotion information, it will suggest the optimal budget allocation and generate cost-saving proposals. An example of this prompt message would be: "The user has entered that they desire a 100-square-meter home renovation, requesting high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, with a budget limit of 5 million yen. Please optimize the budget allocation based on past project data and market price data. Also, please consider the user's emotion information regarding the proposed content."

[0644] In the proposal generation phase, the server generates cost reduction proposals based on the calculation results of the generation AI model. These proposals include a comparison with market prices adjusted based on the user's sentiment information, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The server sends the generated proposals to the terminal in a data format such as JSON. The terminal displays the received proposals to the user, who reviews the proposed plan. At this time, the user also checks whether the proposal content matches their sentiment.

[0645] In the feedback and re-evaluation phase, the user inputs feedback on the proposed plan. The terminal receiving the feedback sends it to the server. The server receives the user's feedback and, if necessary, re-inputs it into the generated AI model for re-evaluation. The re-evaluation generates a new proposal, and by repeating this process, the system provides the optimized budget and proposal that best suits the user's needs.

[0646] Finally, in the emotion analysis phase, the emotion engine also plays a crucial role during feedback, analyzing the user's facial expressions and voice, and using that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify the approach to specific items.

[0647] This series of processes allows users to execute renovation projects that efficiently utilize their budget while also increasing emotional satisfaction.

[0648] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0649] Step 1: User Input Phase

[0650] Specific operation: The user enters basic information about the renovation project through the terminal's input interface. This includes area, number of rooms, desired materials and equipment, and budget limit. The terminal also has an emotion engine built in, which collects facial expressions and voice via the webcam and microphone during the input process.

[0651] Input: Area, number of rooms, desired materials / equipment, budget limit, user's facial expression and voice.

[0652] Output: User project information and sentiment information

[0653] Data processing / calculations: None

[0654] Step 2: Data Collection Phase

[0655] Specific operation: The terminal converts the project information and sentiment information entered by the user into JSON format and sends it to the server. The server collects historical project data, market price data, and the latest discount information by scraping from the internet.

[0656] Input: User project information and sentiment information

[0657] Output: Historical project data, market price data, and the latest discount information.

[0658] Data processing and calculation: The server receives data in JSON format and collects related information from databases and the internet.

[0659] Step 3: Model Application Phase

[0660] Specific operation: The server uses a generated AI model based on the collected data to calculate the budget allocation for each item. At the same time, it incorporates user sentiment information to reflect psychological factors in the budget allocation.

[0661] Input: Historical project data, market price data, latest discount information, user sentiment information

[0662] Output: Optimized budget allocation

[0663] Data processing and calculation: The server sends prompt messages to the generated AI model to calculate budget allocation. During this process, user sentiment information is incorporated and adjusted.

[0664] Step 4: Proposal Generation Phase

[0665] Specific operation: The server generates cost reduction suggestions based on the calculation results of the generated AI model. These suggestions include comparison with market prices, recommendations for alternatives, suggestions for reusable materials, and incorporation of the latest discount information. The suggested results are sent to the terminal in JSON format.

[0666] Input: Optimized budget allocation

[0667] Output: Cost reduction proposals

[0668] Data processing and calculation: The server analyzes the budget allocation results and generates proposals. These are then sent to the terminal in JSON format.

[0669] Step 5: Proposal Review Phase

[0670] Specific operation: The server sends the generated proposal to the terminal, and the terminal displays the received proposal to the user. The user reviews the proposed plan. At this time, they also check whether the proposal matches their feelings.

[0671] Input: Cost reduction proposal

[0672] Output: User reviews and sentiment reactions

[0673] Data processing / calculations: None

[0674] Step 6: Feedback and Re-evaluation Phase

[0675] Specific operation: The user inputs feedback on the proposed content, and the device sends this to the server. The server analyzes the feedback and, if necessary, re-inputs it into the generating AI model for re-evaluation. A new proposal is generated and provided to the user again.

[0676] Input: User feedback and sentiment information

[0677] Output: New proposal

[0678] Data processing and calculation: The server analyzes the feedback and re-inputs it into the generating AI model to generate new suggestions.

[0679] Step 7: Emotional Analysis Phase

[0680] Specific operation: The emotion engine continuously monitors user emotions as they provide feedback and uses that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify its approach to certain items.

[0681] Input: User sentiment information

[0682] Output: Improved suggestions

[0683] Data Processing and Calculation: The emotion engine analyzes the emotion data during feedback, sends the results to the server, and incorporates them into the suggestions.

[0684] (Application Example 2)

[0685] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0686] In modern renovation projects, it's crucial to optimize the user's budget while providing proposals tailored to their individual needs. However, traditional systems simply perform mechanical calculations based on input information, failing to consider user emotions or real-time reactions. As a result, user satisfaction declined, and effective budget allocation became difficult.

[0687] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's project information, means including a terminal for transmitting the input information to the server, means including a server for collecting past project data and market price data, means including a server for calculating budget allocation using a generated AI model based on the collected data, means including an emotion engine for recognizing the user's emotions in real time and reflecting them in the proposed content, and means including a terminal for displaying the transmitted proposal to the user. This makes it possible to optimize the renovation budget and provide personalized proposals while taking emotions into consideration.

[0688] "Means for inputting user project information" refers to a device or software that provides an interface for users to input information related to a renovation project (e.g., area, number of rooms, desired materials / equipment, budget limit, etc.).

[0689] "Means including a terminal that transmits the input information to the server" refers to a device or apparatus equipped with the function of transmitting project information entered by a user to a remote server.

[0690] "Means including a server for collecting past project data and market price data" refers to a server that collects and stores data on past renovation projects and data on current market prices.

[0691] "Means including a server that calculates budget allocation using a generative AI model based on the collected data" refers to a server that uses collected project data and market price data to calculate the optimal budget allocation using a generative AI model.

[0692] "Means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal" refers to a server that creates cost reduction proposals based on budget allocations calculated by a generation AI model and transmits them to the user's terminal.

[0693] "Means including an emotion engine for recognizing user emotions in real time and reflecting them in proposals" refers to an emotion analysis engine that analyzes user emotions in real time from facial expressions and voice, and reflects the results in renovation proposals.

[0694] "Means including a terminal that displays the transmitted proposal to the user" refers to a terminal or device that has the function of displaying the renovation proposal transmitted from the server to the user.

[0695] This invention is a system that optimizes the budget for renovation projects while providing personalized suggestions that reflect the user's emotions. The system is designed to assist users in selecting renovation-related products in physical stores using smart glasses.

[0696] Hardware and software to be used

[0697] Hardware:

[0698] Smart glasses (e.g., Google Glass)

[0699] software:

[0700] Emotional engine (e.g., Affectiva)

[0701] Generative AI models (e.g., GPT models, or custom models)

[0702] Specific operation of the system

[0703] 1. User input phase:

[0704] A user wearing smart glasses inputs project information (e.g., size of the renovation area, desired design, budget, etc.) via voice. The smart glasses' camera and microphone capture the user's facial expressions and voice, and this data is transmitted to the server in real time.

[0705] 2. Data Collection Phase:

[0706] The server receives project and sentiment information submitted by users and collects relevant data from historical project data and market price databases. Furthermore, it uses scraping techniques to obtain the latest discount information from the internet.

[0707] 3. Model Application Phase:

[0708] The server uses a generative AI model based on the collected data to calculate budget allocation. It also incorporates user emotional information from an emotion engine to reflect the user's psychological state in the budget allocation process.

[0709] 4. Proposal generation phase:

[0710] The server generates cost-saving suggestions based on calculation results from a generative AI model and emotional information. These suggestions include recommendations for cost-effective alternatives, suggestions for reusable materials, and the incorporation of the latest discount information. The suggestions are sent from the server to the smart glasses and displayed to the user.

[0711] 5. Feedback and Re-evaluation Phase:

[0712] The user reviews the suggestions and provides feedback via voice input. The smart glasses simultaneously capture the user's facial expressions and send them to the server. The server then re-evaluates the feedback and generates new suggestions.

[0713] Specific example

[0714] For example, suppose a user wants a high-quality leather sofa and has a budget of 200,000 yen. Smart glasses analyze the user's preferences from their facial expressions and voice, and present a list of optimal products based on past purchase data and market prices. The system monitors the user's reactions in real time and adjusts its suggestions based on changes in their emotions.

[0715] Examples of prompts for generative AI models

[0716] "The user wants a high-quality leather sofa, and their budget is 200,000 yen. Please suggest the best option within that budget."

[0717] "The user is looking for a 50m² area for renovation." 2 I'm looking for furniture for my living room. Please provide optimized suggestions based on emotional analysis.

[0718] This system allows users to receive optimized proposals that are emotionally satisfying while minimizing unnecessary expenses in their renovation projects.

[0719] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0720] Step 1:

[0721] The user wears smart glasses and inputs basic information about their renovation project via voice. Specifically, they provide information such as the size of the renovation area, desired design, and budget. The smart glasses' camera and microphone capture the user's facial expressions and voice, and transmit this data to the server in real time. Input: User's voice data and facial expression data. Output: User's project information and emotion data.

[0722] Step 2:

[0723] The server receives project information and sentiment information submitted by users, and collects relevant data from historical project data and market price databases. It also uses scraping techniques to obtain the latest discount information from the internet. Input: User project information and sentiment data. Output: Historical project data, market price data, and latest discount information.

[0724] Step 3:

[0725] The server uses a generative AI model based on the collected data to calculate budget allocation. Specifically, project information is input to the generative AI model as prompts, and the optimal budget allocation is calculated. In addition, user emotion information from an emotion engine is incorporated to reflect the user's psychological state in the budget allocation. Input: Past project data, market price data, latest discount information, and user emotion data. Output: Budget allocation calculation results reflecting emotions.

[0726] Step 4:

[0727] The server generates cost reduction proposals based on calculation results from a generative AI model. These proposals include recommendations for cost-effective alternatives, suggestions for reusable materials, and the incorporation of the latest discount information. The generated proposals are sent from the server to the smart glasses. Input: Budget allocation calculation results reflecting emotions. Output: Cost reduction proposals.

[0728] Step 5:

[0729] The smart glasses display suggestions sent from the server to the user. The user reviews the suggestions and provides feedback via voice. The smart glasses also capture the user's facial expressions simultaneously with the feedback and send this data to the server. Input: Cost reduction suggestions and user feedback. Output: User reaction data and feedback data.

[0730] Step 6:

[0731] The server re-evaluates user feedback and generates new suggestions. Specifically, it inputs the sentiment data and feedback data again into the AI ​​model to create optimized new suggestions. The new suggestions are then sent back to the smart glasses and displayed to the user. Input: User reaction data and feedback data. Output: Re-evaluated suggestions.

[0732] 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.

[0733] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. 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 shown 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.

[0734] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0735] [Third Embodiment]

[0736] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0737] 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.

[0738] 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).

[0739] 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.

[0740] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0741] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0742] 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.

[0743] 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.

[0744] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0745] The 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.

[0746] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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.

[0747] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0748] This invention is a system that supports budget optimization in renovation projects and consists of a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, and a feedback / re-evaluation phase. Its detailed operation is described below.

[0749] User input phase

[0750] The user enters basic information about the renovation project into the terminal. This information includes the area to be renovated, the number of rooms, desired materials (e.g., high-quality flooring, marble countertops), required equipment (e.g., new kitchen and bathroom), and budget limit. The entered information is sent from the terminal to the server.

[0751] Data collection phase

[0752] The server collects data on similar renovation projects from a database of past projects. It also retrieves current market price information from a market price database. Furthermore, it uses scraping techniques to collect the latest discount information from the internet.

[0753] Model Application Phase

[0754] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. This model analyzes historical data and market trends to provide efficient allocation results.

[0755] Proposal generation phase

[0756] The server generates cost reduction proposals based on budget allocation results obtained from the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and incorporation of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0757] Proposal review phase

[0758] The user reviews the proposal displayed on the device. If they are dissatisfied with the proposal, or have additional requests or changes to the conditions, they enter them into the device. The device then sends the user's feedback to the server.

[0759] Feedback and re-evaluation phase

[0760] The server receives feedback from the user, re-inputs it into the model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. By repeating this process, the system can provide the most suitable optimization budget for the user's needs.

[0761] Specific example

[0762] For example, suppose a user is planning a renovation of a 100-square-meter home, desires high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and has a budget limit of 5 million yen. The server retrieves data from similar past projects, gathers market price data, and collects the latest discount information through web scraping. The AI ​​model analyzes this data and presents budget allocation and cost reduction suggestions as follows:

[0763] High-quality flooring costs 1.5 million yen, but using an alternative could reduce the cost to 1.2 million yen.

[0764] A marble countertop costs 500,000 yen, but by using recycled materials, the cost can be reduced to 400,000 yen.

[0765] Kitchen equipment can be reduced by 1.2 million yen, bathroom equipment by 800,000 yen, and after applying discount information, these can be reduced to 1.1 million yen and 700,000 yen respectively.

[0766] Other 1 million yen

[0767] In this way, users can obtain a concrete plan optimized for their budget. Throughout this process, user feedback is incorporated, and even more optimal suggestions are repeatedly provided, enabling the successful execution of an optimized renovation project.

[0768] The following describes the processing flow.

[0769] Step 1:

[0770] The user uses a device to enter basic information about the renovation project. This information includes the area to be renovated, the number of rooms, desired materials and equipment, and the budget limit.

[0771] Step 2:

[0772] The terminal sends project information entered by the user to the server. The information sent includes all the project details entered.

[0773] Step 3:

[0774] The server receives the submitted project information and searches the past project database. Simultaneously, it retrieves current market price information from the market price database. It also collects the latest discount information from the internet using scraping techniques.

[0775] Step 4:

[0776] The server analyzes collected historical project data and market price information, and inputs this into a generating AI model.

[0777] Step 5:

[0778] The server uses a generated AI model to analyze the input data and calculate the appropriate budget allocation for each item in the renovation project. This calculation includes the optimal cost for each material and equipment.

[0779] Step 6:

[0780] The server generates further cost-reduction suggestions based on the AI ​​model's calculation results. These suggestions include comparisons with market prices based on user preferences, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information.

[0781] Step 7:

[0782] The server converts the budget allocation and cost reduction proposals it generates into a data format such as JSON and sends it to the terminal.

[0783] Step 8:

[0784] The terminal displays the suggestions received from the server to the user. The user reviews and confirms the suggested plan.

[0785] Step 9:

[0786] The user enters feedback on the proposed plan. This feedback may include additional requests or changes to the terms and conditions.

[0787] Step 10:

[0788] The device sends user feedback to the server.

[0789] Step 11:

[0790] The server receives user feedback and, if necessary, re-inputs it into the model for re-evaluation. This re-evaluation generates new suggestions.

[0791] Step 12:

[0792] The server sends the newly generated proposal back to the terminal, which then displays it to the user. This process is repeated until the optimal plan that best satisfies the user is determined.

[0793] (Example 1)

[0794] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0795] Budgeting for renovation projects is complex and requires considering many factors. Therefore, manually determining the optimal budget allocation requires a tremendous amount of time and effort from the user. Furthermore, constantly checking market price fluctuations and discount information is time-consuming, making it difficult to obtain optimal cost-saving proposals. To address these challenges, there is a need for a user-friendly system that efficiently optimizes budgets.

[0796] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0797] In this invention, the server includes means for inputting user project information, means including a terminal for transmitting the input information to the server, means including a server for collecting past project data and market price data, means including a server for calculating budget allocation using a generation AI model based on the collected data, means including a server for generating cost reduction proposals based on the calculation results and transmitting them to the terminal, means including a terminal for displaying the transmitted proposals to the user, means including a server for receiving user feedback and re-inputting data into the generation AI model for re-evaluation, and means including a server for obtaining the latest discount information from the internet using a scraping technique based on the collected data. This enables the user to obtain the optimal budget allocation efficiently and quickly. Furthermore, since re-evaluation reflecting feedback is possible, flexible proposals tailored to the user's needs can be made.

[0798] "User project information" refers to detailed information about the renovation project, such as the area, number of rooms, desired materials, necessary equipment, and budget limit.

[0799] A "terminal" is an electronic device used by users to input information and communicate with a server. Specifically, this includes personal computers, tablets, and smartphones.

[0800] A "server" is a computing system used for data collection, analysis, generation, budget allocation calculations using AI models, generation of cost reduction proposals, and processing user feedback.

[0801] "Past project data" refers to data related to previously carried out renovation projects, including budget, materials used, construction details, and duration.

[0802] "Market price data" refers to information about the current market value of materials and equipment needed for home renovations. This data is used to understand price fluctuations and trends.

[0803] A "generative AI model" is an artificial intelligence algorithm that automatically calculates and generates budget allocation and cost reduction proposals based on collected data.

[0804] "Cost reduction suggestions" are proposals for efficiently using the user's budget, and include recommendations for alternative materials, comparisons of market prices, and incorporation of the latest discount information.

[0805] "Web scraping" is a technique for automatically collecting specific data from publicly available information on the internet.

[0806] "Feedback" refers to opinions, additional requests, and information regarding changes to terms and conditions provided by users in response to suggestions.

[0807] "Re-evaluation" is the process of running the generated AI model again based on user feedback to generate new suggestions.

[0808] This invention is a system that supports budget optimization in renovation projects. The system consists of the following phases: user input phase, data collection phase, model application phase, proposal generation phase, proposal confirmation phase, and feedback / re-evaluation phase. The specific implementation methods for each phase are described below.

[0809] User input phase

[0810] The user enters basic information about the renovation project via a terminal. This information includes the area to be renovated, the number of rooms, desired materials, necessary equipment, and budget limit. For example, the user might enter "100 square meter residence, 3 rooms, high-quality flooring, marble countertops, new kitchen and bathroom, budget limit of 5 million yen." The terminal then sends this information to the server.

[0811] Data collection phase

[0812] The server collects data on similar renovation projects from a database of past projects. It also obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0813] Model Application Phase

[0814] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. This model analyzes historical data and market trends to provide efficient allocation results. The generative AI model is input with historical project data and market price information, and outputs a budget allocation result such as "1.5 million yen for high-quality flooring, 500,000 yen for marble countertops, 1.2 million yen for kitchen equipment, 800,000 yen for bathroom equipment, and 1 million yen for other items."

[0815] Proposal generation phase

[0816] The server generates cost reduction proposals based on budget allocation results obtained from the generated AI model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0817] Proposal review phase

[0818] Users review the proposals displayed on their devices. If they are dissatisfied with the proposals or have additional requests or changes to the conditions, they enter them into their devices and send them to the server.

[0819] Feedback and re-evaluation phase

[0820] The server receives user feedback, re-inputs it into the generated AI model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. This ensures that the user receives an optimized renovation plan that best suits their needs.

[0821] Example of a prompt

[0822] "We are planning a renovation of a 100-square-meter residence. We would like high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, with a budget limit of 5 million yen. Please propose a budget allocation based on similar past project data and market price information."

[0823] This system utilizes AI models generated from user input to analyze historical data and market trends, providing efficient and optimal allocation of renovation budgets. By incorporating user feedback and re-evaluating the system, it can flexibly respond to user needs and provide the best possible proposals.

[0824] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0825] Step 1: User Input Phase

[0826] Detailed explanation:

[0827] The user uses a terminal to enter basic information about the renovation project. This information includes the area to be renovated, the number of rooms, desired materials, necessary equipment, and budget limit.

[0828] input:

[0829] Information on a "100 square meter residence, 3 rooms, high-quality flooring, marble countertops, new kitchen and bathroom, budget limit of 5 million yen."

[0830] Specific actions:

[0831] The user enters the required information on their device and clicks the submit button.

[0832] output:

[0833] The device sends this information to the server.

[0834] Step 2: Data Collection Phase

[0835] Detailed explanation:

[0836] The server collects data on similar renovation projects from a database of past projects. It also obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0837] input:

[0838] User project information.

[0839] Specific actions:

[0840] The server queries a database of past projects to retrieve similar project data. Similarly, the server retrieves current market price information from a market price database and uses web scraping to collect the latest discount information.

[0841] output:

[0842] Collected data (past project data, current market price information, latest discount information).

[0843] Step 3: Model Application Phase

[0844] Detailed explanation:

[0845] Based on the collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item.

[0846] input:

[0847] Past project data, current market price information, and the latest discount information.

[0848] Specific actions:

[0849] The server formats the data and inputs it into the generative AI model. The generative AI model analyzes this data and calculates efficient budget allocation results.

[0850] output:

[0851] Budget allocation results calculated by a generative AI model.

[0852] Step 4: Proposal Generation Phase

[0853] Detailed explanation:

[0854] The server generates cost reduction proposals based on budget allocation results obtained from the generated AI model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and incorporation of the latest discount information.

[0855] input:

[0856] Budget allocation results for generative AI models.

[0857] Specific actions:

[0858] The server generates cost reduction proposals based on the budget allocation results. This includes comparing prices with market prices, recommending alternatives, and applying the latest discount information.

[0859] output:

[0860] The generated cost reduction proposals.

[0861] Step 5: Proposal Review Phase

[0862] Detailed explanation:

[0863] Users review the proposals displayed on their devices. If they are dissatisfied with the proposals or have additional requests or changes to the conditions, they enter them into their devices and send them to the server.

[0864] input:

[0865] The generated cost reduction proposals.

[0866] Specific actions:

[0867] The user reviews the proposal on their device, enters any necessary feedback or changes to the conditions, and submits it.

[0868] output:

[0869] User feedback.

[0870] Step 6: Feedback and Re-evaluation Phase

[0871] Detailed explanation:

[0872] The server receives feedback from the user, re-inputs it into the generated AI model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user.

[0873] input:

[0874] User feedback.

[0875] Specific actions:

[0876] The server analyzes the feedback and inputs it back into the generating AI model to generate new suggestions.

[0877] output:

[0878] A re-evaluated new proposal.

[0879] ---

[0880] By sequentially executing the specific processing steps described above, the system of the present invention proposes the optimal renovation plan within the user's budget and, if necessary, re-evaluates it based on user feedback.

[0881] (Application Example 1)

[0882] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0883] Conventional budget optimization systems for renovation projects could only perform partial optimizations based solely on user-provided information, making it difficult to reflect specific market trends and cost-reduction suggestions in store renovation projects. Furthermore, they lacked sufficient capabilities to incorporate user feedback in real time and re-evaluate using generative AI models. This resulted in problems such as budget overruns or underruns in store renovation projects.

[0884] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0885] This invention includes a server comprising: a device for inputting user project information; a device including a terminal for transmitting the input information to an information processing device; a device including an information processing device for collecting past project data and market price data; a device including an information processing device for calculating budget allocation using a generated AI model based on the collected data; a device including an information processing device for generating cost reduction proposals based on the calculation results and transmitting them to the terminal; and a device including a terminal for displaying the transmitted proposals to the user; and a system characterized by being designed to optimize budget allocation in store renovation projects. This makes it possible to accurately reflect market trends and cost reduction proposals in store renovation projects and to incorporate user feedback in real time.

[0886] A "device for inputting user project information" refers to a terminal or device used by users to input basic information about renovation or store remodeling projects.

[0887] "Devices including terminals that transmit to information processing devices" refers to terminals used to transmit information entered by users to information processing devices in servers or cloud systems.

[0888] "Device including an information processing device for collecting past project data and market price data" refers to a device used to collect past data and current market price information related to renovations and store remodeling.

[0889] "An information processing device including an information processing device that calculates budget allocation using a generative AI model" refers to an information processing device that uses an AI model to calculate budget allocation based on collected data.

[0890] "An information processing device that generates cost reduction proposals and transmits them to the terminal" refers to an information processing device that creates cost reduction proposals based on the generated budget allocation results and transmits that information to the user's terminal.

[0891] "Device including a terminal that displays the transmitted proposal to the user" refers to a terminal that displays cost reduction proposals transmitted from the server to the user.

[0892] A "system characterized by being designed to optimize budget allocation in store renovation projects" refers to a system specifically designed to optimize the budget for store renovation projects.

[0893] This invention is a system for optimizing the budget in store renovation projects. The specific details of implementing this system are described below.

[0894] User input phase

[0895] The user enters basic information about the store renovation project into a dedicated terminal. This information includes the area to be renovated, the number of rooms, desired materials (e.g., flooring, countertops), required equipment (e.g., a new kitchen and bathroom), and a budget limit. The user enters the information and sends it to the server via the terminal.

[0896] Data collection phase

[0897] The server collects data on past store renovation projects from a database. It also retrieves current market price information from a market price database. Furthermore, it uses scraping techniques to collect the latest discount information from the internet. This data is used to optimize the budget.

[0898] Model Application Phase

[0899] Based on project data and market price information collected on the server, a generative AI model is used to calculate the budget allocation for each item. The generative AI model analyzes historical data and market trends to provide efficient budget allocation results. Specifically, it uses the Python Scikit-learn library and leverages algorithms such as RandomForestRegressor.

[0900] Proposal generation phase

[0901] The server generates cost reduction proposals based on budget allocation results obtained from the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[0902] Proposal review phase

[0903] The user reviews the suggestions displayed on their device. If they are dissatisfied with the suggestions, or have additional requests or changes to the conditions, they enter them on their device. The user's feedback is sent to the server.

[0904] Feedback and re-evaluation phase

[0905] The server receives feedback from the user and, if necessary, re-inputs it into the generated AI model for re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. By repeating this process, it is possible to provide the most suitable optimized budget for the user's needs.

[0906] Specific example

[0907] For example, if a user enters information such as "area 100 square meters, 3 rooms, desired flooring, budget 5 million yen," the server retrieves similar past project data and gathers market price data and the latest discount information. A generative AI model analyzes this data and displays budget allocation and cost reduction suggestions like the following:

[0908] High-quality flooring costs 1.5 million yen, but using an alternative can reduce the cost to 1.2 million yen.

[0909] A marble countertop costs 500,000 yen, but this can be reduced to 400,000 yen by using reusable materials.

[0910] Kitchen equipment costs 1.2 million yen, and bathroom equipment costs 800,000 yen, but after applying discount information, these can be reduced to 1.1 million yen and 700,000 yen respectively.

[0911] Other 1 million yen

[0912] In this way, users can obtain a concrete plan optimized for their budget. Furthermore, by incorporating user feedback and repeatedly providing even more optimal suggestions, it becomes possible to execute an optimized store renovation project.

[0913] Example of a prompt

[0914] "Users, please enter your store renovation plan:"

[0915] Area: 100 square meters

[0916] Number of rooms: 3

[0917] Desired material: Flooring

[0918] Budget: 5 million yen

[0919] As described above, the present invention is a system that optimizes the budget for store renovation projects and provides optimal proposals tailored to the user's needs.

[0920] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0921] Step 1:

[0922] The user uses a terminal to input basic information about the store renovation project. This information includes area, number of rooms, desired materials, required equipment, and budget limit. Once input is complete, the information is sent to the server. For example, input data might include "Area: 100 square meters, Number of rooms: 3, Flooring desired, Budget: 5 million yen."

[0923] Step 2:

[0924] The server collects past similar project data and market price data based on the project information received from the user. Past project data is obtained from a database, and current market price information is obtained from a market price database. In addition, the server collects the latest discount information from the internet using scraping techniques. As a result, a large amount of reference data is accumulated on the server along with the user's input information.

[0925] Step 3:

[0926] The server uses a generative AI model to calculate budget allocation based on the collected data. This model is implemented using the Python Scikit-learn library and employs algorithms such as RandomForestRegressor. The server provides the model with the user's project information and collected data as input and outputs the budget allocation results. For example, the budget allocation results might include 1.5 million yen for high-quality flooring, 500,000 yen for marble countertops, 1.2 million yen for kitchen equipment, and 800,000 yen for bathroom equipment.

[0927] Step 4:

[0928] The server generates cost reduction proposals based on the budget allocation results obtained by the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. Specifically, it creates proposals to reduce the cost of high-quality flooring to 1.2 million yen, marble countertops to 400,000 yen, kitchen equipment to 1.1 million yen, and bathroom equipment to 700,000 yen. These proposals are then sent to the terminal.

[0929] Step 5:

[0930] The user reviews the suggestions displayed on their device. If the user is dissatisfied with the content or has additional requests or changes to the conditions, they enter them into the device. For example, feedback such as "I don't want a flooring alternative" is possible. This feedback is sent to the server.

[0931] Step 6:

[0932] The server receives feedback from the user and, if necessary, re-inputs it into the generated AI model for re-evaluation. This generates new suggestions, which are then sent back to the terminal. By repeating this process, it is possible to provide an optimized budget that best suits the user's needs.

[0933] By following these steps, efficient and cost-effective budget allocation can be achieved even in store renovation projects. Furthermore, it becomes possible to incorporate user feedback in real time and provide the optimal renovation plan.

[0934] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0935] This invention provides a system that enables more personalized proposals by combining a system for optimizing renovation project budgets with an emotion engine that recognizes user emotions. The system includes a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, a feedback and re-evaluation phase, and an emotion analysis phase. Its detailed operation is described below.

[0936] User input phase

[0937] First, the user uses a terminal to input basic information about the renovation project. This includes details such as area, number of rooms, desired materials and equipment, and budget limit. In addition, the input interface on the terminal incorporates an emotion engine that recognizes the user's emotions through their facial expressions and voice.

[0938] Data collection phase

[0939] The terminal transmits project information and sentiment information entered by the user to the server. The server searches a database of past projects and collects data on similar renovation projects. In addition, it obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[0940] Model Application Phase

[0941] Based on collected project data and market price information, the server uses a generative AI model to calculate budget allocation for each item. Furthermore, by incorporating user emotional information from an emotion engine, the user's psychological state is reflected in the optimization of budget allocation.

[0942] Proposal generation phase

[0943] The server generates cost reduction suggestions based on calculation results from the generated AI model. These suggestions include comparisons with market prices adjusted based on user sentiment information, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information.

[0944] Proposal review phase

[0945] The server sends the generated proposal to the terminal in a data format such as JSON. The terminal displays the received proposal to the user. The user reviews the proposed plan. At this point, they also check whether the proposal aligns with their feelings.

[0946] Feedback and re-evaluation phase

[0947] The user provides feedback on the proposed plan. The terminal receiving the feedback sends it to the server. The server receives the user's feedback and re-enters it into the model as needed for re-evaluation. The re-evaluation generates a new proposal. This process is repeated to provide the optimized budget and proposal that best suits the user's needs.

[0948] Emotion analysis phase

[0949] The emotion engine also plays a crucial role when users provide feedback. While users are entering their feedback, it continuously monitors their emotions and uses that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify its approach to certain items.

[0950] Specific example

[0951] For example, if a user plans to renovate a 100-square-meter home, desires high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and has a budget limit of 5 million yen, the emotion engine analyzes the user's emotions regarding these requests from their facial expressions and voice. The server retrieves similar past project data and, based on market price data, the latest discount information obtained through scraping, and the user's emotion information, suggests the optimal budget allocation and generates cost-saving proposals. If the user expresses dissatisfaction with the proposal, the emotion engine detects this, and the server incorporates this information into a new proposal, which is then presented to the user again. Through this process, the user can obtain an optimized renovation plan while minimizing unnecessary spending.

[0952] This series of processes allows users to execute renovation projects that efficiently utilize their budget while also increasing emotional satisfaction.

[0953] The following describes the processing flow.

[0954] Step 1:

[0955] The user uses a terminal to input basic information about their renovation project. This information includes area, number of rooms, desired materials, equipment, and budget limit. The terminal also has an emotion engine that recognizes the user's emotions through their facial expressions and voice while they are inputting information.

[0956] Step 2:

[0957] The terminal sends emotional information along with project information entered by the user to the server.

[0958] Step 3:

[0959] The server receives the submitted project information and searches the past project database. It also retrieves current market price information from the market price database and collects the latest discount information from the internet using scraping techniques.

[0960] Step 4:

[0961] The server analyzes collected historical project data, market price information, scraped data, and sentiment information, and inputs this into a generative AI model.

[0962] Step 5:

[0963] The server uses a generated AI model to analyze input data, calculates appropriate budget allocations for each item in the renovation project, and adjusts the budget allocation to match the user's psychological state based on emotional information.

[0964] Step 6:

[0965] The server generates further cost-reduction suggestions based on the AI ​​model's calculation results. These suggestions include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The suggestions are optimized by taking sentiment into account.

[0966] Step 7:

[0967] The server converts the budget allocation and cost reduction proposals it generates into a data format such as JSON and sends it to the terminal.

[0968] Step 8:

[0969] The device displays suggestions received from the server to the user. The user reviews and examines the suggested plans. While viewing the suggestions, the emotion engine analyzes the user's facial expressions and reactions to collect emotional information.

[0970] Step 9:

[0971] Users provide feedback on the proposed plan. This feedback can include additional requests, changes to conditions, and emotional responses.

[0972] Step 10:

[0973] The device sends user feedback and sentiment information to the server.

[0974] Step 11:

[0975] The server receives user feedback and, if necessary, re-enters it into the model for re-evaluation. This re-evaluation generates new suggestions. During this process, the suggestions are adjusted based on the acquired sentiment information.

[0976] Step 12:

[0977] The server sends the newly generated suggestion back to the terminal, which then displays it to the user. The sentiment engine continues to monitor the user's emotions and collects new sentiment information as needed. This process is repeated until the optimal plan that best satisfies the user is determined.

[0978] (Example 2)

[0979] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0980] Conventional budget optimization systems for renovation projects often fail to adequately address user satisfaction because they prioritize budget allocation and cost reduction proposals without considering user emotions. Furthermore, they lacked sufficient mechanisms for incorporating and re-evaluating user feedback. As a result, proposals sometimes failed to meet user expectations, leading to a lack of effective renovation plans.

[0981] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0982] In this invention, the server includes means for inputting the user's project information and the user's emotional information, means for collecting past project data, market price data, and the latest discount information from the internet, means for calculating budget allocation using a generated AI model based on the collected data, means for reflecting the user's emotional information in the budget allocation, and means for analyzing the user's emotions when the user provides feedback. This makes it possible to propose an optimal renovation plan that takes the user's emotions into consideration, thereby increasing user satisfaction and providing an effective renovation plan.

[0983] "User project information" refers to detailed information about the renovation project, such as the area, number of rooms, desired materials and equipment, and budget limit.

[0984] "User emotional information" refers to information that shows the psychological response of the user, analyzed through their facial expressions and voice.

[0985] A "terminal" refers to an electronic device used by a user to input information and communicate with a server.

[0986] "Past project data" refers to data that includes records and detailed information about previously carried out renovation projects.

[0987] "Market price data" refers to data that includes current price information for materials, equipment, and services related to home renovation.

[0988] "Latest discount information" refers to currently applicable discount information obtained by scraping from the internet.

[0989] A "generative AI model" is an artificial intelligence-based algorithm used to calculate budget allocation and cost reduction proposals based on collected data.

[0990] "Budget allocation" refers to the allocation of funds to each item in a renovation project.

[0991] A "cost reduction proposal" refers to specific suggestions for efficiently using a user's project budget and achieving maximum results with minimum cost.

[0992] "Feedback" refers to information that shows the user's evaluation and opinion on the proposed plan.

[0993] An "emotion engine" is a software or hardware system that analyzes a user's emotions through their facial expressions and voice.

[0994] This invention provides a system that enables more personalized proposals by combining a system for optimizing the budget of a renovation project with an emotion engine that recognizes the user's emotions. The system includes a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, a feedback and re-evaluation phase, and an emotion analysis phase.

[0995] First, the user uses a terminal to input basic information about the renovation project. This includes detailed information such as area, number of rooms, desired materials and equipment, and budget limit. Furthermore, the input interface on the terminal incorporates an emotion engine that recognizes the user's emotions through their facial expressions and voice. The emotion engine collects and analyzes the user's facial expressions and voice through a webcam and microphone while they are performing the input task.

[0996] Next, the terminal sends project information and sentiment information entered by the user to the server. The server searches the past project database and collects data on similar renovation projects. Furthermore, it obtains current market price information from the market price database and collects the latest discount information from the internet using scraping techniques.

[0997] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. User sentiment information is also incorporated to reflect the user's psychological state in optimizing the budget allocation. The generative AI model is an algorithm that optimizes budget allocation according to user requests, and it performs calculations based on prompt text input.

[0998] For example, if a user inputs information that they are planning a 100-square-meter home renovation, desire high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and have a budget limit of 5 million yen, the emotion engine will analyze the user's emotions regarding these requests from their facial expressions and voice. The server will retrieve similar past project data, and based on market price data, the latest discount information obtained through scraping, and the user's emotion information, it will suggest the optimal budget allocation and generate cost-saving proposals. An example of this prompt message would be: "The user has entered that they desire a 100-square-meter home renovation, requesting high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, with a budget limit of 5 million yen. Please optimize the budget allocation based on past project data and market price data. Also, please consider the user's emotion information regarding the proposed content."

[0999] In the proposal generation phase, the server generates cost reduction proposals based on the calculation results of the generation AI model. These proposals include a comparison with market prices adjusted based on the user's sentiment information, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The server sends the generated proposals to the terminal in a data format such as JSON. The terminal displays the received proposals to the user, who reviews the proposed plan. At this time, the user also checks whether the proposal content matches their sentiment.

[1000] In the feedback and re-evaluation phase, the user inputs feedback on the proposed plan. The terminal receiving the feedback sends it to the server. The server receives the user's feedback and, if necessary, re-inputs it into the generated AI model for re-evaluation. The re-evaluation generates a new proposal, and by repeating this process, the system provides the optimized budget and proposal that best suits the user's needs.

[1001] Finally, in the emotion analysis phase, the emotion engine also plays a crucial role during feedback, analyzing the user's facial expressions and voice, and using that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify the approach to specific items.

[1002] This series of processes allows users to execute renovation projects that efficiently utilize their budget while also increasing emotional satisfaction.

[1003] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1004] Step 1: User Input Phase

[1005] Specific operation: The user enters basic information about the renovation project through the terminal's input interface. This includes area, number of rooms, desired materials and equipment, and budget limit. The terminal also has an emotion engine built in, which collects facial expressions and voice via the webcam and microphone during the input process.

[1006] Input: Area, number of rooms, desired materials / equipment, budget limit, user's facial expression and voice.

[1007] Output: User project information and sentiment information

[1008] Data processing / calculations: None

[1009] Step 2: Data Collection Phase

[1010] Specific operation: The terminal converts the project information and sentiment information entered by the user into JSON format and sends it to the server. The server collects historical project data, market price data, and the latest discount information by scraping from the internet.

[1011] Input: User project information and sentiment information

[1012] Output: Historical project data, market price data, and the latest discount information.

[1013] Data processing and calculation: The server receives data in JSON format and collects related information from databases and the internet.

[1014] Step 3: Model Application Phase

[1015] Specific operation: The server uses a generated AI model based on the collected data to calculate the budget allocation for each item. At the same time, it incorporates user sentiment information to reflect psychological factors in the budget allocation.

[1016] Input: Historical project data, market price data, latest discount information, user sentiment information

[1017] Output: Optimized budget allocation

[1018] Data processing and calculation: The server sends prompt messages to the generated AI model to calculate budget allocation. During this process, user sentiment information is incorporated and adjusted.

[1019] Step 4: Proposal Generation Phase

[1020] Specific operation: The server generates cost reduction suggestions based on the calculation results of the generated AI model. These suggestions include comparison with market prices, recommendations for alternatives, suggestions for reusable materials, and incorporation of the latest discount information. The suggested results are sent to the terminal in JSON format.

[1021] Input: Optimized budget allocation

[1022] Output: Cost reduction proposals

[1023] Data processing and calculation: The server analyzes the budget allocation results and generates proposals. These are then sent to the terminal in JSON format.

[1024] Step 5: Proposal Review Phase

[1025] Specific operation: The server sends the generated proposal to the terminal, and the terminal displays the received proposal to the user. The user reviews the proposed plan. At this time, they also check whether the proposal matches their feelings.

[1026] Input: Cost reduction proposal

[1027] Output: User reviews and sentiment reactions

[1028] Data processing / calculations: None

[1029] Step 6: Feedback and Re-evaluation Phase

[1030] Specific operation: The user inputs feedback on the proposed content, and the device sends this to the server. The server analyzes the feedback and, if necessary, re-inputs it into the generating AI model for re-evaluation. A new proposal is generated and provided to the user again.

[1031] Input: User feedback and sentiment information

[1032] Output: New proposal

[1033] Data processing and calculation: The server analyzes the feedback and re-inputs it into the generating AI model to generate new suggestions.

[1034] Step 7: Emotional Analysis Phase

[1035] Specific operation: The emotion engine continuously monitors user emotions as they provide feedback and uses that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify its approach to certain items.

[1036] Input: User sentiment information

[1037] Output: Improved suggestions

[1038] Data Processing and Calculation: The emotion engine analyzes the emotion data during feedback, sends the results to the server, and incorporates them into the suggestions.

[1039] (Application Example 2)

[1040] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1041] In modern renovation projects, it's crucial to optimize the user's budget while providing proposals tailored to their individual needs. However, traditional systems simply perform mechanical calculations based on input information, failing to consider user emotions or real-time reactions. As a result, user satisfaction declined, and effective budget allocation became difficult.

[1042] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's project information, means including a terminal for transmitting the input information to the server, means including a server for collecting past project data and market price data, means including a server for calculating budget allocation using a generated AI model based on the collected data, means including an emotion engine for recognizing the user's emotions in real time and reflecting them in the proposed content, and means including a terminal for displaying the transmitted proposal to the user. This makes it possible to optimize the renovation budget and provide personalized proposals while taking emotions into consideration.

[1043] "Means for inputting user project information" refers to a device or software that provides an interface for users to input information related to a renovation project (e.g., area, number of rooms, desired materials / equipment, budget limit, etc.).

[1044] "Means including a terminal that transmits the input information to the server" refers to a device or apparatus equipped with the function of transmitting project information entered by a user to a remote server.

[1045] "Means including a server for collecting past project data and market price data" refers to a server that collects and stores data on past renovation projects and data on current market prices.

[1046] "Means including a server that calculates budget allocation using a generative AI model based on the collected data" refers to a server that uses collected project data and market price data to calculate the optimal budget allocation using a generative AI model.

[1047] "Means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal" refers to a server that creates cost reduction proposals based on budget allocations calculated by a generation AI model and transmits them to the user's terminal.

[1048] "Means including an emotion engine for recognizing user emotions in real time and reflecting them in proposals" refers to an emotion analysis engine that analyzes user emotions in real time from facial expressions and voice, and reflects the results in renovation proposals.

[1049] "Means including a terminal that displays the transmitted proposal to the user" refers to a terminal or device that has the function of displaying the renovation proposal transmitted from the server to the user.

[1050] This invention is a system that optimizes the budget for renovation projects while providing personalized suggestions that reflect the user's emotions. The system is designed to assist users in selecting renovation-related products in physical stores using smart glasses.

[1051] Hardware and software to be used

[1052] Hardware:

[1053] Smart glasses (e.g., Google Glass)

[1054] software:

[1055] Emotional engine (e.g., Affectiva)

[1056] Generative AI models (e.g., GPT models, or custom models)

[1057] Specific operation of the system

[1058] 1. User input phase:

[1059] A user wearing smart glasses inputs project information (e.g., size of the renovation area, desired design, budget, etc.) via voice. The smart glasses' camera and microphone capture the user's facial expressions and voice, and this data is transmitted to the server in real time.

[1060] 2. Data Collection Phase:

[1061] The server receives project and sentiment information submitted by users and collects relevant data from historical project data and market price databases. Furthermore, it uses scraping techniques to obtain the latest discount information from the internet.

[1062] 3. Model Application Phase:

[1063] The server uses a generative AI model based on the collected data to calculate budget allocation. It also incorporates user emotional information from an emotion engine to reflect the user's psychological state in the budget allocation process.

[1064] 4. Proposal generation phase:

[1065] The server generates cost-saving suggestions based on calculation results from a generative AI model and emotional information. These suggestions include recommendations for cost-effective alternatives, suggestions for reusable materials, and the incorporation of the latest discount information. The suggestions are sent from the server to the smart glasses and displayed to the user.

[1066] 5. Feedback and Re-evaluation Phase:

[1067] The user reviews the suggestions and provides feedback via voice input. The smart glasses simultaneously capture the user's facial expressions and send them to the server. The server then re-evaluates the feedback and generates new suggestions.

[1068] Specific example

[1069] For example, suppose a user wants a high-quality leather sofa and has a budget of 200,000 yen. Smart glasses analyze the user's preferences from their facial expressions and voice, and present a list of optimal products based on past purchase data and market prices. The system monitors the user's reactions in real time and adjusts its suggestions based on changes in their emotions.

[1070] Examples of prompts for generative AI models

[1071] "The user wants a high-quality leather sofa, and their budget is 200,000 yen. Please suggest the best option within that budget."

[1072] "The user is looking for a 50m² area for renovation." 2 I'm looking for furniture for my living room. Please provide optimized suggestions based on emotional analysis.

[1073] This system allows users to receive optimized proposals that are emotionally satisfying while minimizing unnecessary expenses in their renovation projects.

[1074] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1075] Step 1:

[1076] The user wears smart glasses and inputs basic information about their renovation project via voice. Specifically, they provide information such as the size of the renovation area, desired design, and budget. The smart glasses' camera and microphone capture the user's facial expressions and voice, and transmit this data to the server in real time. Input: User's voice data and facial expression data. Output: User's project information and emotion data.

[1077] Step 2:

[1078] The server receives project information and sentiment information submitted by users, and collects relevant data from historical project data and market price databases. It also uses scraping techniques to obtain the latest discount information from the internet. Input: User project information and sentiment data. Output: Historical project data, market price data, and latest discount information.

[1079] Step 3:

[1080] The server uses a generative AI model based on the collected data to calculate budget allocation. Specifically, project information is input to the generative AI model as prompts, and the optimal budget allocation is calculated. In addition, user emotion information from an emotion engine is incorporated to reflect the user's psychological state in the budget allocation. Input: Past project data, market price data, latest discount information, and user emotion data. Output: Budget allocation calculation results reflecting emotions.

[1081] Step 4:

[1082] The server generates cost reduction proposals based on calculation results from a generative AI model. These proposals include recommendations for cost-effective alternatives, suggestions for reusable materials, and the incorporation of the latest discount information. The generated proposals are sent from the server to the smart glasses. Input: Budget allocation calculation results reflecting emotions. Output: Cost reduction proposals.

[1083] Step 5:

[1084] The smart glasses display suggestions sent from the server to the user. The user reviews the suggestions and provides feedback via voice. The smart glasses also capture the user's facial expressions simultaneously with the feedback and send this data to the server. Input: Cost reduction suggestions and user feedback. Output: User reaction data and feedback data.

[1085] Step 6:

[1086] The server re-evaluates user feedback and generates new suggestions. Specifically, it inputs the sentiment data and feedback data again into the AI ​​model to create optimized new suggestions. The new suggestions are then sent back to the smart glasses and displayed to the user. Input: User reaction data and feedback data. Output: Re-evaluated suggestions.

[1087] 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.

[1088] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. 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 shown 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.

[1089] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1090] [Fourth Embodiment]

[1091] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1092] 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.

[1093] 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).

[1094] 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.

[1095] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[1096] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1097] 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.

[1098] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1099] 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.

[1100] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[1101] The 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.

[1102] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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.

[1103] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1104] This invention is a system that supports budget optimization in renovation projects and consists of a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, and a feedback / re-evaluation phase. Its detailed operation is described below.

[1105] User input phase

[1106] The user enters basic information about the renovation project into the terminal. This information includes the area to be renovated, the number of rooms, desired materials (e.g., high-quality flooring, marble countertops), required equipment (e.g., new kitchen and bathroom), and budget limit. The entered information is sent from the terminal to the server.

[1107] Data collection phase

[1108] The server collects data on similar renovation projects from a database of past projects. It also retrieves current market price information from a market price database. Furthermore, it uses scraping techniques to collect the latest discount information from the internet.

[1109] Model Application Phase

[1110] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. This model analyzes historical data and market trends to provide efficient allocation results.

[1111] Proposal generation phase

[1112] The server generates cost reduction proposals based on budget allocation results obtained from the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and incorporation of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[1113] Proposal review phase

[1114] The user reviews the proposal displayed on the device. If they are dissatisfied with the proposal, or have additional requests or changes to the conditions, they enter them into the device. The device then sends the user's feedback to the server.

[1115] Feedback and re-evaluation phase

[1116] The server receives feedback from the user, re-inputs it into the model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. By repeating this process, the system can provide the most suitable optimization budget for the user's needs.

[1117] Specific example

[1118] For example, suppose a user is planning a renovation of a 100-square-meter home, desires high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and has a budget limit of 5 million yen. The server retrieves data from similar past projects, gathers market price data, and collects the latest discount information through web scraping. The AI ​​model analyzes this data and presents budget allocation and cost reduction suggestions as follows:

[1119] High-quality flooring costs 1.5 million yen, but using an alternative could reduce the cost to 1.2 million yen.

[1120] A marble countertop costs 500,000 yen, but by using recycled materials, the cost can be reduced to 400,000 yen.

[1121] Kitchen equipment can be reduced by 1.2 million yen, bathroom equipment by 800,000 yen, and after applying discount information, these can be reduced to 1.1 million yen and 700,000 yen respectively.

[1122] Other 1 million yen

[1123] In this way, users can obtain a concrete plan optimized for their budget. Throughout this process, user feedback is incorporated, and even more optimal suggestions are repeatedly provided, enabling the successful execution of an optimized renovation project.

[1124] The following describes the processing flow.

[1125] Step 1:

[1126] The user uses a device to enter basic information about the renovation project. This information includes the area to be renovated, the number of rooms, desired materials and equipment, and the budget limit.

[1127] Step 2:

[1128] The terminal sends project information entered by the user to the server. The information sent includes all the project details entered.

[1129] Step 3:

[1130] The server receives the submitted project information and searches the past project database. Simultaneously, it retrieves current market price information from the market price database. It also collects the latest discount information from the internet using scraping techniques.

[1131] Step 4:

[1132] The server analyzes collected historical project data and market price information, and inputs this into a generating AI model.

[1133] Step 5:

[1134] The server uses a generated AI model to analyze the input data and calculate the appropriate budget allocation for each item in the renovation project. This calculation includes the optimal cost for each material and equipment.

[1135] Step 6:

[1136] The server generates further cost-reduction suggestions based on the AI ​​model's calculation results. These suggestions include comparisons with market prices based on user preferences, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information.

[1137] Step 7:

[1138] The server converts the budget allocation and cost reduction proposals it generates into a data format such as JSON and sends it to the terminal.

[1139] Step 8:

[1140] The terminal displays the suggestions received from the server to the user. The user reviews and confirms the suggested plan.

[1141] Step 9:

[1142] The user enters feedback on the proposed plan. This feedback may include additional requests or changes to the terms and conditions.

[1143] Step 10:

[1144] The device sends user feedback to the server.

[1145] Step 11:

[1146] The server receives user feedback and, if necessary, re-inputs it into the model for re-evaluation. This re-evaluation generates new suggestions.

[1147] Step 12:

[1148] The server sends the newly generated proposal back to the terminal, which then displays it to the user. This process is repeated until the optimal plan that best satisfies the user is determined.

[1149] (Example 1)

[1150] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1151] Budgeting for renovation projects is complex and requires considering many factors. Therefore, manually determining the optimal budget allocation requires a tremendous amount of time and effort from the user. Furthermore, constantly checking market price fluctuations and discount information is time-consuming, making it difficult to obtain optimal cost-saving proposals. To address these challenges, there is a need for a user-friendly system that efficiently optimizes budgets.

[1152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1153] In this invention, the server includes means for inputting user project information, means including a terminal for transmitting the input information to the server, means including a server for collecting past project data and market price data, means including a server for calculating budget allocation using a generation AI model based on the collected data, means including a server for generating cost reduction proposals based on the calculation results and transmitting them to the terminal, means including a terminal for displaying the transmitted proposals to the user, means including a server for receiving user feedback and re-inputting data into the generation AI model for re-evaluation, and means including a server for obtaining the latest discount information from the internet using a scraping technique based on the collected data. This enables the user to obtain the optimal budget allocation efficiently and quickly. Furthermore, since re-evaluation reflecting feedback is possible, flexible proposals tailored to the user's needs can be made.

[1154] "User project information" refers to detailed information about the renovation project, such as the area, number of rooms, desired materials, necessary equipment, and budget limit.

[1155] A "terminal" is an electronic device used by users to input information and communicate with a server. Specifically, this includes personal computers, tablets, and smartphones.

[1156] A "server" is a computing system used for data collection, analysis, generation, budget allocation calculations using AI models, generation of cost reduction proposals, and processing user feedback.

[1157] "Past project data" refers to data related to previously carried out renovation projects, including budget, materials used, construction details, and duration.

[1158] "Market price data" refers to information about the current market value of materials and equipment needed for home renovations. This data is used to understand price fluctuations and trends.

[1159] A "generative AI model" is an artificial intelligence algorithm that automatically calculates and generates budget allocation and cost reduction proposals based on collected data.

[1160] "Cost reduction suggestions" are proposals for efficiently using the user's budget, and include recommendations for alternative materials, comparisons of market prices, and incorporation of the latest discount information.

[1161] "Web scraping" is a technique for automatically collecting specific data from publicly available information on the internet.

[1162] "Feedback" refers to opinions, additional requests, and information regarding changes to terms and conditions provided by users in response to suggestions.

[1163] "Re-evaluation" is the process of running the generated AI model again based on user feedback to generate new suggestions.

[1164] This invention is a system that supports budget optimization in renovation projects. The system consists of the following phases: user input phase, data collection phase, model application phase, proposal generation phase, proposal confirmation phase, and feedback / re-evaluation phase. The specific implementation methods for each phase are described below.

[1165] User input phase

[1166] The user enters basic information about the renovation project via a terminal. This information includes the area to be renovated, the number of rooms, desired materials, necessary equipment, and budget limit. For example, the user might enter "100 square meter residence, 3 rooms, high-quality flooring, marble countertops, new kitchen and bathroom, budget limit of 5 million yen." The terminal then sends this information to the server.

[1167] Data collection phase

[1168] The server collects data on similar renovation projects from a database of past projects. It also obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[1169] Model Application Phase

[1170] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. This model analyzes historical data and market trends to provide efficient allocation results. The generative AI model is input with historical project data and market price information, and outputs a budget allocation result such as "1.5 million yen for high-quality flooring, 500,000 yen for marble countertops, 1.2 million yen for kitchen equipment, 800,000 yen for bathroom equipment, and 1 million yen for other items."

[1171] Proposal generation phase

[1172] The server generates cost reduction proposals based on budget allocation results obtained from the generated AI model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[1173] Proposal review phase

[1174] Users review the proposals displayed on their devices. If they are dissatisfied with the proposals or have additional requests or changes to the conditions, they enter them into their devices and send them to the server.

[1175] Feedback and re-evaluation phase

[1176] The server receives user feedback, re-inputs it into the generated AI model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. This ensures that the user receives an optimized renovation plan that best suits their needs.

[1177] Example of a prompt

[1178] "We are planning a renovation of a 100-square-meter residence. We would like high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, with a budget limit of 5 million yen. Please propose a budget allocation based on similar past project data and market price information."

[1179] This system utilizes AI models generated from user input to analyze historical data and market trends, providing efficient and optimal allocation of renovation budgets. By incorporating user feedback and re-evaluating the system, it can flexibly respond to user needs and provide the best possible proposals.

[1180] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1181] Step 1: User Input Phase

[1182] Detailed explanation:

[1183] The user uses a terminal to enter basic information about the renovation project. This information includes the area to be renovated, the number of rooms, desired materials, necessary equipment, and budget limit.

[1184] input:

[1185] Information on a "100 square meter residence, 3 rooms, high-quality flooring, marble countertops, new kitchen and bathroom, budget limit of 5 million yen."

[1186] Specific actions:

[1187] The user enters the required information on their device and clicks the submit button.

[1188] output:

[1189] The device sends this information to the server.

[1190] Step 2: Data Collection Phase

[1191] Detailed explanation:

[1192] The server collects data on similar renovation projects from a database of past projects. It also obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[1193] input:

[1194] User project information.

[1195] Specific actions:

[1196] The server queries a database of past projects to retrieve similar project data. Similarly, the server retrieves current market price information from a market price database and uses web scraping to collect the latest discount information.

[1197] output:

[1198] Collected data (past project data, current market price information, latest discount information).

[1199] Step 3: Model Application Phase

[1200] Detailed explanation:

[1201] Based on the collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item.

[1202] input:

[1203] Past project data, current market price information, and the latest discount information.

[1204] Specific actions:

[1205] The server formats the data and inputs it into the generative AI model. The generative AI model analyzes this data and calculates efficient budget allocation results.

[1206] output:

[1207] Budget allocation results calculated by a generative AI model.

[1208] Step 4: Proposal Generation Phase

[1209] Detailed explanation:

[1210] The server generates cost reduction proposals based on budget allocation results obtained from the generated AI model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and incorporation of the latest discount information.

[1211] input:

[1212] Budget allocation results for generative AI models.

[1213] Specific actions:

[1214] The server generates cost reduction proposals based on the budget allocation results. This includes comparing prices with market prices, recommending alternatives, and applying the latest discount information.

[1215] output:

[1216] The generated cost reduction proposals.

[1217] Step 5: Proposal Review Phase

[1218] Detailed explanation:

[1219] Users review the proposals displayed on their devices. If they are dissatisfied with the proposals or have additional requests or changes to the conditions, they enter them into their devices and send them to the server.

[1220] input:

[1221] The generated cost reduction proposals.

[1222] Specific actions:

[1223] The user reviews the proposal on their device, enters any necessary feedback or changes to the conditions, and submits it.

[1224] output:

[1225] User feedback.

[1226] Step 6: Feedback and Re-evaluation Phase

[1227] Detailed explanation:

[1228] The server receives feedback from the user, re-inputs it into the generated AI model as needed, and performs a re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user.

[1229] input:

[1230] User feedback.

[1231] Specific actions:

[1232] The server analyzes the feedback and inputs it back into the generating AI model to generate new suggestions.

[1233] output:

[1234] A re-evaluated new proposal.

[1235] ---

[1236] By sequentially executing the specific processing steps described above, the system of the present invention proposes the optimal renovation plan within the user's budget and, if necessary, re-evaluates it based on user feedback.

[1237] (Application Example 1)

[1238] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1239] Conventional budget optimization systems for renovation projects could only perform partial optimizations based solely on user-provided information, making it difficult to reflect specific market trends and cost-reduction suggestions in store renovation projects. Furthermore, they lacked sufficient capabilities to incorporate user feedback in real time and re-evaluate using generative AI models. This resulted in problems such as budget overruns or underruns in store renovation projects.

[1240] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1241] This invention includes a server comprising: a device for inputting user project information; a device including a terminal for transmitting the input information to an information processing device; a device including an information processing device for collecting past project data and market price data; a device including an information processing device for calculating budget allocation using a generated AI model based on the collected data; a device including an information processing device for generating cost reduction proposals based on the calculation results and transmitting them to the terminal; and a device including a terminal for displaying the transmitted proposals to the user; and a system characterized by being designed to optimize budget allocation in store renovation projects. This makes it possible to accurately reflect market trends and cost reduction proposals in store renovation projects and to incorporate user feedback in real time.

[1242] A "device for inputting user project information" refers to a terminal or device used by users to input basic information about renovation or store remodeling projects.

[1243] "Devices including terminals that transmit to information processing devices" refers to terminals used to transmit information entered by users to information processing devices in servers or cloud systems.

[1244] "Device including an information processing device for collecting past project data and market price data" refers to a device used to collect past data and current market price information related to renovations and store remodeling.

[1245] "An information processing device including an information processing device that calculates budget allocation using a generative AI model" refers to an information processing device that uses an AI model to calculate budget allocation based on collected data.

[1246] "An information processing device that generates cost reduction proposals and transmits them to the terminal" refers to an information processing device that creates cost reduction proposals based on the generated budget allocation results and transmits that information to the user's terminal.

[1247] "Device including a terminal that displays the transmitted proposal to the user" refers to a terminal that displays cost reduction proposals transmitted from the server to the user.

[1248] A "system characterized by being designed to optimize budget allocation in store renovation projects" refers to a system specifically designed to optimize the budget for store renovation projects.

[1249] This invention is a system for optimizing the budget in store renovation projects. The specific details of implementing this system are described below.

[1250] User input phase

[1251] The user enters basic information about the store renovation project into a dedicated terminal. This information includes the area to be renovated, the number of rooms, desired materials (e.g., flooring, countertops), required equipment (e.g., a new kitchen and bathroom), and a budget limit. The user enters the information and sends it to the server via the terminal.

[1252] Data collection phase

[1253] The server collects data on past store renovation projects from a database. It also retrieves current market price information from a market price database. Furthermore, it uses scraping techniques to collect the latest discount information from the internet. This data is used to optimize the budget.

[1254] Model Application Phase

[1255] Based on project data and market price information collected on the server, a generative AI model is used to calculate the budget allocation for each item. The generative AI model analyzes historical data and market trends to provide efficient budget allocation results. Specifically, it uses the Python Scikit-learn library and leverages algorithms such as RandomForestRegressor.

[1256] Proposal generation phase

[1257] The server generates cost reduction proposals based on budget allocation results obtained from the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The generated proposals are sent to the terminal and displayed to the user.

[1258] Proposal review phase

[1259] The user reviews the suggestions displayed on their device. If they are dissatisfied with the suggestions, or have additional requests or changes to the conditions, they enter them on their device. The user's feedback is sent to the server.

[1260] Feedback and re-evaluation phase

[1261] The server receives feedback from the user and, if necessary, re-inputs it into the generated AI model for re-evaluation. This re-evaluation generates new suggestions, which are then sent back to the user. By repeating this process, it is possible to provide the most suitable optimized budget for the user's needs.

[1262] Specific example

[1263] For example, if a user enters information such as "area 100 square meters, 3 rooms, desired flooring, budget 5 million yen," the server retrieves similar past project data and gathers market price data and the latest discount information. A generative AI model analyzes this data and displays budget allocation and cost reduction suggestions like the following:

[1264] High-quality flooring costs 1.5 million yen, but using an alternative can reduce the cost to 1.2 million yen.

[1265] A marble countertop costs 500,000 yen, but this can be reduced to 400,000 yen by using reusable materials.

[1266] Kitchen equipment costs 1.2 million yen, and bathroom equipment costs 800,000 yen, but after applying discount information, these can be reduced to 1.1 million yen and 700,000 yen respectively.

[1267] Other 1 million yen

[1268] In this way, users can obtain a concrete plan optimized for their budget. Furthermore, by incorporating user feedback and repeatedly providing even more optimal suggestions, it becomes possible to execute an optimized store renovation project.

[1269] Example of a prompt

[1270] "Users, please enter your store renovation plan:"

[1271] Area: 100 square meters

[1272] Number of rooms: 3

[1273] Desired material: Flooring

[1274] Budget: 5 million yen

[1275] As described above, the present invention is a system that optimizes the budget for store renovation projects and provides optimal proposals tailored to the user's needs.

[1276] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1277] Step 1:

[1278] The user uses a terminal to input basic information about the store renovation project. This information includes area, number of rooms, desired materials, required equipment, and budget limit. Once input is complete, the information is sent to the server. For example, input data might include "Area: 100 square meters, Number of rooms: 3, Flooring desired, Budget: 5 million yen."

[1279] Step 2:

[1280] The server collects past similar project data and market price data based on the project information received from the user. Past project data is obtained from a database, and current market price information is obtained from a market price database. In addition, the server collects the latest discount information from the internet using scraping techniques. As a result, a large amount of reference data is accumulated on the server along with the user's input information.

[1281] Step 3:

[1282] The server uses a generative AI model to calculate budget allocation based on the collected data. This model is implemented using the Python Scikit-learn library and employs algorithms such as RandomForestRegressor. The server provides the model with the user's project information and collected data as input and outputs the budget allocation results. For example, the budget allocation results might include 1.5 million yen for high-quality flooring, 500,000 yen for marble countertops, 1.2 million yen for kitchen equipment, and 800,000 yen for bathroom equipment.

[1283] Step 4:

[1284] The server generates cost reduction proposals based on the budget allocation results obtained by the AI ​​model. These proposals include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. Specifically, it creates proposals to reduce the cost of high-quality flooring to 1.2 million yen, marble countertops to 400,000 yen, kitchen equipment to 1.1 million yen, and bathroom equipment to 700,000 yen. These proposals are then sent to the terminal.

[1285] Step 5:

[1286] The user reviews the suggestions displayed on their device. If the user is dissatisfied with the content or has additional requests or changes to the conditions, they enter them into the device. For example, feedback such as "I don't want a flooring alternative" is possible. This feedback is sent to the server.

[1287] Step 6:

[1288] The server receives feedback from the user and, if necessary, re-inputs it into the generated AI model for re-evaluation. This generates new suggestions, which are then sent back to the terminal. By repeating this process, it is possible to provide an optimized budget that best suits the user's needs.

[1289] By following these steps, efficient and cost-effective budget allocation can be achieved even in store renovation projects. Furthermore, it becomes possible to incorporate user feedback in real time and provide the optimal renovation plan.

[1290] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1291] This invention provides a system that enables more personalized proposals by combining a system for optimizing renovation project budgets with an emotion engine that recognizes user emotions. The system includes a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, a feedback and re-evaluation phase, and an emotion analysis phase. Its detailed operation is described below.

[1292] User input phase

[1293] First, the user uses a terminal to input basic information about the renovation project. This includes details such as area, number of rooms, desired materials and equipment, and budget limit. In addition, the input interface on the terminal incorporates an emotion engine that recognizes the user's emotions through their facial expressions and voice.

[1294] Data collection phase

[1295] The terminal transmits project information and sentiment information entered by the user to the server. The server searches a database of past projects and collects data on similar renovation projects. In addition, it obtains current market price information from a market price database and collects the latest discount information from the internet using web scraping techniques.

[1296] Model Application Phase

[1297] Based on collected project data and market price information, the server uses a generative AI model to calculate budget allocation for each item. Furthermore, by incorporating user emotional information from an emotion engine, the user's psychological state is reflected in the optimization of budget allocation.

[1298] Proposal generation phase

[1299] The server generates cost reduction suggestions based on calculation results from the generated AI model. These suggestions include comparisons with market prices adjusted based on user sentiment information, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information.

[1300] Proposal review phase

[1301] The server sends the generated proposal to the terminal in a data format such as JSON. The terminal displays the received proposal to the user. The user reviews the proposed plan. At this point, they also check whether the proposal aligns with their feelings.

[1302] Feedback and re-evaluation phase

[1303] The user provides feedback on the proposed plan. The terminal receiving the feedback sends it to the server. The server receives the user's feedback and re-enters it into the model as needed for re-evaluation. The re-evaluation generates a new proposal. This process is repeated to provide the optimized budget and proposal that best suits the user's needs.

[1304] Emotion analysis phase

[1305] The emotion engine also plays a crucial role when users provide feedback. While users are entering their feedback, it continuously monitors their emotions and uses that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify its approach to certain items.

[1306] Specific example

[1307] For example, if a user plans to renovate a 100-square-meter home, desires high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and has a budget limit of 5 million yen, the emotion engine analyzes the user's emotions regarding these requests from their facial expressions and voice. The server retrieves similar past project data and, based on market price data, the latest discount information obtained through scraping, and the user's emotion information, suggests the optimal budget allocation and generates cost-saving proposals. If the user expresses dissatisfaction with the proposal, the emotion engine detects this, and the server incorporates this information into a new proposal, which is then presented to the user again. Through this process, the user can obtain an optimized renovation plan while minimizing unnecessary spending.

[1308] This series of processes allows users to execute renovation projects that efficiently utilize their budget while also increasing emotional satisfaction.

[1309] The following describes the processing flow.

[1310] Step 1:

[1311] The user uses a terminal to input basic information about their renovation project. This information includes area, number of rooms, desired materials, equipment, and budget limit. The terminal also has an emotion engine that recognizes the user's emotions through their facial expressions and voice while they are inputting information.

[1312] Step 2:

[1313] The terminal sends emotional information along with project information entered by the user to the server.

[1314] Step 3:

[1315] The server receives the submitted project information and searches the past project database. It also retrieves current market price information from the market price database and collects the latest discount information from the internet using scraping techniques.

[1316] Step 4:

[1317] The server analyzes collected historical project data, market price information, scraped data, and sentiment information, and inputs this into a generative AI model.

[1318] Step 5:

[1319] The server uses a generated AI model to analyze input data, calculates appropriate budget allocations for each item in the renovation project, and adjusts the budget allocation to match the user's psychological state based on emotional information.

[1320] Step 6:

[1321] The server generates further cost-reduction suggestions based on the AI ​​model's calculation results. These suggestions include comparisons with market prices, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The suggestions are optimized by taking sentiment into account.

[1322] Step 7:

[1323] The server converts the budget allocation and cost reduction proposals it generates into a data format such as JSON and sends it to the terminal.

[1324] Step 8:

[1325] The device displays suggestions received from the server to the user. The user reviews and examines the suggested plans. While viewing the suggestions, the emotion engine analyzes the user's facial expressions and reactions to collect emotional information.

[1326] Step 9:

[1327] Users provide feedback on the proposed plan. This feedback can include additional requests, changes to conditions, and emotional responses.

[1328] Step 10:

[1329] The device sends user feedback and sentiment information to the server.

[1330] Step 11:

[1331] The server receives user feedback and, if necessary, re-enters it into the model for re-evaluation. This re-evaluation generates new suggestions. During this process, the suggestions are adjusted based on the acquired sentiment information.

[1332] Step 12:

[1333] The server sends the newly generated suggestion back to the terminal, which then displays it to the user. The sentiment engine continues to monitor the user's emotions and collects new sentiment information as needed. This process is repeated until the optimal plan that best satisfies the user is determined.

[1334] (Example 2)

[1335] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1336] Conventional budget optimization systems for renovation projects often fail to adequately address user satisfaction because they prioritize budget allocation and cost reduction proposals without considering user emotions. Furthermore, they lacked sufficient mechanisms for incorporating and re-evaluating user feedback. As a result, proposals sometimes failed to meet user expectations, leading to a lack of effective renovation plans.

[1337] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1338] In this invention, the server includes means for inputting the user's project information and the user's emotional information, means for collecting past project data, market price data, and the latest discount information from the internet, means for calculating budget allocation using a generated AI model based on the collected data, means for reflecting the user's emotional information in the budget allocation, and means for analyzing the user's emotions when the user provides feedback. This makes it possible to propose an optimal renovation plan that takes the user's emotions into consideration, thereby increasing user satisfaction and providing an effective renovation plan.

[1339] "User project information" refers to detailed information about the renovation project, such as the area, number of rooms, desired materials and equipment, and budget limit.

[1340] "User emotional information" refers to information that shows the psychological response of the user, analyzed through their facial expressions and voice.

[1341] A "terminal" refers to an electronic device used by a user to input information and communicate with a server.

[1342] "Past project data" refers to data that includes records and detailed information about previously carried out renovation projects.

[1343] "Market price data" refers to data that includes current price information for materials, equipment, and services related to home renovation.

[1344] "Latest discount information" refers to currently applicable discount information obtained by scraping from the internet.

[1345] A "generative AI model" is an artificial intelligence-based algorithm used to calculate budget allocation and cost reduction proposals based on collected data.

[1346] "Budget allocation" refers to the allocation of funds to each item in a renovation project.

[1347] A "cost reduction proposal" refers to specific suggestions for efficiently using a user's project budget and achieving maximum results with minimum cost.

[1348] "Feedback" refers to information that shows the user's evaluation and opinion on the proposed plan.

[1349] An "emotion engine" is a software or hardware system that analyzes a user's emotions through their facial expressions and voice.

[1350] This invention provides a system that enables more personalized proposals by combining a system for optimizing the budget of a renovation project with an emotion engine that recognizes the user's emotions. The system includes a user input phase, a data collection phase, a model application phase, a proposal generation phase, a proposal confirmation phase, a feedback and re-evaluation phase, and an emotion analysis phase.

[1351] First, the user uses a terminal to input basic information about the renovation project. This includes detailed information such as area, number of rooms, desired materials and equipment, and budget limit. Furthermore, the input interface on the terminal incorporates an emotion engine that recognizes the user's emotions through their facial expressions and voice. The emotion engine collects and analyzes the user's facial expressions and voice through a webcam and microphone while they are performing the input task.

[1352] Next, the terminal sends project information and sentiment information entered by the user to the server. The server searches the past project database and collects data on similar renovation projects. Furthermore, it obtains current market price information from the market price database and collects the latest discount information from the internet using scraping techniques.

[1353] Based on collected project data and market price information, the server uses a generative AI model to calculate the budget allocation for each item. User sentiment information is also incorporated to reflect the user's psychological state in optimizing the budget allocation. The generative AI model is an algorithm that optimizes budget allocation according to user requests, and it performs calculations based on prompt text input.

[1354] For example, if a user inputs information that they are planning a 100-square-meter home renovation, desire high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, and have a budget limit of 5 million yen, the emotion engine will analyze the user's emotions regarding these requests from their facial expressions and voice. The server will retrieve similar past project data, and based on market price data, the latest discount information obtained through scraping, and the user's emotion information, it will suggest the optimal budget allocation and generate cost-saving proposals. An example of this prompt message would be: "The user has entered that they desire a 100-square-meter home renovation, requesting high-quality flooring, marble countertops, and new kitchen and bathroom fixtures, with a budget limit of 5 million yen. Please optimize the budget allocation based on past project data and market price data. Also, please consider the user's emotion information regarding the proposed content."

[1355] In the proposal generation phase, the server generates cost reduction proposals based on the calculation results of the generation AI model. These proposals include a comparison with market prices adjusted based on the user's sentiment information, recommendations for cost-effective alternatives, suggestions for reusable materials, and reflections of the latest discount information. The server sends the generated proposals to the terminal in a data format such as JSON. The terminal displays the received proposals to the user, who reviews the proposed plan. At this time, the user also checks whether the proposal content matches their sentiment.

[1356] In the feedback and re-evaluation phase, the user inputs feedback on the proposed plan. The terminal receiving the feedback sends it to the server. The server receives the user's feedback and, if necessary, re-inputs it into the generated AI model for re-evaluation. The re-evaluation generates a new proposal, and by repeating this process, the system provides the optimized budget and proposal that best suits the user's needs.

[1357] Finally, in the emotion analysis phase, the emotion engine also plays a crucial role during feedback, analyzing the user's facial expressions and voice, and using that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify the approach to specific items.

[1358] This series of processes allows users to execute renovation projects that efficiently utilize their budget while also increasing emotional satisfaction.

[1359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1360] Step 1: User Input Phase

[1361] Specific operation: The user enters basic information about the renovation project through the terminal's input interface. This includes area, number of rooms, desired materials and equipment, and budget limit. The terminal also has an emotion engine built in, which collects facial expressions and voice via the webcam and microphone during the input process.

[1362] Input: Area, number of rooms, desired materials / equipment, budget limit, user's facial expression and voice.

[1363] Output: User project information and sentiment information

[1364] Data processing / calculations: None

[1365] Step 2: Data Collection Phase

[1366] Specific operation: The terminal converts the project information and sentiment information entered by the user into JSON format and sends it to the server. The server collects historical project data, market price data, and the latest discount information by scraping from the internet.

[1367] Input: User project information and sentiment information

[1368] Output: Historical project data, market price data, and the latest discount information.

[1369] Data processing and calculation: The server receives data in JSON format and collects related information from databases and the internet.

[1370] Step 3: Model Application Phase

[1371] Specific operation: The server uses a generated AI model based on the collected data to calculate the budget allocation for each item. At the same time, it incorporates user sentiment information to reflect psychological factors in the budget allocation.

[1372] Input: Historical project data, market price data, latest discount information, user sentiment information

[1373] Output: Optimized budget allocation

[1374] Data processing and calculation: The server sends prompt messages to the generated AI model to calculate budget allocation. During this process, user sentiment information is incorporated and adjusted.

[1375] Step 4: Proposal Generation Phase

[1376] Specific operation: The server generates cost reduction suggestions based on the calculation results of the generated AI model. These suggestions include comparison with market prices, recommendations for alternatives, suggestions for reusable materials, and incorporation of the latest discount information. The suggested results are sent to the terminal in JSON format.

[1377] Input: Optimized budget allocation

[1378] Output: Cost reduction proposals

[1379] Data processing and calculation: The server analyzes the budget allocation results and generates proposals. These are then sent to the terminal in JSON format.

[1380] Step 5: Proposal Review Phase

[1381] Specific operation: The server sends the generated proposal to the terminal, and the terminal displays the received proposal to the user. The user reviews the proposed plan. At this time, they also check whether the proposal matches their feelings.

[1382] Input: Cost reduction proposal

[1383] Output: User reviews and sentiment reactions

[1384] Data processing / calculations: None

[1385] Step 6: Feedback and Re-evaluation Phase

[1386] Specific operation: The user inputs feedback on the proposed content, and the device sends this to the server. The server analyzes the feedback and, if necessary, re-inputs it into the generating AI model for re-evaluation. A new proposal is generated and provided to the user again.

[1387] Input: User feedback and sentiment information

[1388] Output: New proposal

[1389] Data processing and calculation: The server analyzes the feedback and re-inputs it into the generating AI model to generate new suggestions.

[1390] Step 7: Emotional Analysis Phase

[1391] Specific operation: The emotion engine continuously monitors user emotions as they provide feedback and uses that information to further improve the suggestions. For example, if a user expresses dissatisfaction with a suggestion, the new suggestion will take the user's emotions into account and modify its approach to certain items.

[1392] Input: User sentiment information

[1393] Output: Improved suggestions

[1394] Data Processing and Calculation: The emotion engine analyzes the emotion data during feedback, sends the results to the server, and incorporates them into the suggestions.

[1395] (Application Example 2)

[1396] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1397] In modern renovation projects, it's crucial to optimize the user's budget while providing proposals tailored to their individual needs. However, traditional systems simply perform mechanical calculations based on input information, failing to consider user emotions or real-time reactions. As a result, user satisfaction declined, and effective budget allocation became difficult.

[1398] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the user's project information, means including a terminal for transmitting the input information to the server, means including a server for collecting past project data and market price data, means including a server for calculating budget allocation using a generated AI model based on the collected data, means including an emotion engine for recognizing the user's emotions in real time and reflecting them in the proposed content, and means including a terminal for displaying the transmitted proposal to the user. This makes it possible to optimize the renovation budget and provide personalized proposals while taking emotions into consideration.

[1399] "Means for inputting user project information" refers to a device or software that provides an interface for users to input information related to a renovation project (e.g., area, number of rooms, desired materials / equipment, budget limit, etc.).

[1400] "Means including a terminal that transmits the input information to the server" refers to a device or apparatus equipped with the function of transmitting project information entered by a user to a remote server.

[1401] "Means including a server for collecting past project data and market price data" refers to a server that collects and stores data on past renovation projects and data on current market prices.

[1402] "Means including a server that calculates budget allocation using a generative AI model based on the collected data" refers to a server that uses collected project data and market price data to calculate the optimal budget allocation using a generative AI model.

[1403] "Means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal" refers to a server that creates cost reduction proposals based on budget allocations calculated by a generation AI model and transmits them to the user's terminal.

[1404] "Means including an emotion engine for recognizing user emotions in real time and reflecting them in proposals" refers to an emotion analysis engine that analyzes user emotions in real time from facial expressions and voice, and reflects the results in renovation proposals.

[1405] "Means including a terminal that displays the transmitted proposal to the user" refers to a terminal or device that has the function of displaying the renovation proposal transmitted from the server to the user.

[1406] This invention is a system that optimizes the budget for renovation projects while providing personalized suggestions that reflect the user's emotions. The system is designed to assist users in selecting renovation-related products in physical stores using smart glasses.

[1407] Hardware and software to be used

[1408] Hardware:

[1409] Smart glasses (e.g., Google Glass)

[1410] software:

[1411] Emotional engine (e.g., Affectiva)

[1412] Generative AI models (e.g., GPT models, or custom models)

[1413] Specific operation of the system

[1414] 1. User input phase:

[1415] A user wearing smart glasses inputs project information (e.g., size of the renovation area, desired design, budget, etc.) via voice. The smart glasses' camera and microphone capture the user's facial expressions and voice, and this data is transmitted to the server in real time.

[1416] 2. Data Collection Phase:

[1417] The server receives project and sentiment information submitted by users and collects relevant data from historical project data and market price databases. Furthermore, it uses scraping techniques to obtain the latest discount information from the internet.

[1418] 3. Model Application Phase:

[1419] The server uses a generative AI model based on the collected data to calculate budget allocation. It also incorporates user emotional information from an emotion engine to reflect the user's psychological state in the budget allocation process.

[1420] 4. Proposal generation phase:

[1421] The server generates cost-saving suggestions based on calculation results from a generative AI model and emotional information. These suggestions include recommendations for cost-effective alternatives, suggestions for reusable materials, and the incorporation of the latest discount information. The suggestions are sent from the server to the smart glasses and displayed to the user.

[1422] 5. Feedback and Re-evaluation Phase:

[1423] The user reviews the suggestions and provides feedback via voice input. The smart glasses simultaneously capture the user's facial expressions and send them to the server. The server then re-evaluates the feedback and generates new suggestions.

[1424] Specific example

[1425] For example, suppose a user wants a high-quality leather sofa and has a budget of 200,000 yen. Smart glasses analyze the user's preferences from their facial expressions and voice, and present a list of optimal products based on past purchase data and market prices. The system monitors the user's reactions in real time and adjusts its suggestions based on changes in their emotions.

[1426] Examples of prompts for generative AI models

[1427] "The user wants a high-quality leather sofa, and their budget is 200,000 yen. Please suggest the best option within that budget."

[1428] "The user is looking for a 50m² area for renovation." 2 I'm looking for furniture for my living room. Please provide optimized suggestions based on emotional analysis.

[1429] This system allows users to receive optimized proposals that are emotionally satisfying while minimizing unnecessary expenses in their renovation projects.

[1430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1431] Step 1:

[1432] The user wears smart glasses and inputs basic information about their renovation project via voice. Specifically, they provide information such as the size of the renovation area, desired design, and budget. The smart glasses' camera and microphone capture the user's facial expressions and voice, and transmit this data to the server in real time. Input: User's voice data and facial expression data. Output: User's project information and emotion data.

[1433] Step 2:

[1434] The server receives project information and sentiment information submitted by users, and collects relevant data from historical project data and market price databases. It also uses scraping techniques to obtain the latest discount information from the internet. Input: User project information and sentiment data. Output: Historical project data, market price data, and latest discount information.

[1435] Step 3:

[1436] The server uses a generative AI model based on the collected data to calculate budget allocation. Specifically, project information is input to the generative AI model as prompts, and the optimal budget allocation is calculated. In addition, user emotion information from an emotion engine is incorporated to reflect the user's psychological state in the budget allocation. Input: Past project data, market price data, latest discount information, and user emotion data. Output: Budget allocation calculation results reflecting emotions.

[1437] Step 4:

[1438] The server generates cost reduction proposals based on calculation results from a generative AI model. These proposals include recommendations for cost-effective alternatives, suggestions for reusable materials, and the incorporation of the latest discount information. The generated proposals are sent from the server to the smart glasses. Input: Budget allocation calculation results reflecting emotions. Output: Cost reduction proposals.

[1439] Step 5:

[1440] The smart glasses display suggestions sent from the server to the user. The user reviews the suggestions and provides feedback via voice. The smart glasses also capture the user's facial expressions simultaneously with the feedback and send this data to the server. Input: Cost reduction suggestions and user feedback. Output: User reaction data and feedback data.

[1441] Step 6:

[1442] The server re-evaluates user feedback and generates new suggestions. Specifically, it inputs the sentiment data and feedback data again into the AI ​​model to create optimized new suggestions. The new suggestions are then sent back to the smart glasses and displayed to the user. Input: User reaction data and feedback data. Output: Re-evaluated suggestions.

[1443] 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.

[1444] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. 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 shown 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.

[1445] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1446] 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.

[1447] Figure 9 shows an 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[1448] 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.

[1449] 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.

[1450] 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.

[1451] 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."

[1452] 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.

[1453] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, 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. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1454] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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.

[1463] 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.

[1464] The following is further disclosed regarding the embodiments described above.

[1465] (Claim 1)

[1466] A system for optimizing the budget of a renovation project.

[1467] A means of inputting user project information,

[1468] Means including a terminal that transmits the input information to a server,

[1469] Means including a server for collecting past project data and market price data,

[1470] A means including a server that calculates budget allocation using an AI model generated based on the collected data,

[1471] A means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal,

[1472] Means including a terminal that displays the transmitted proposal to the user,

[1473] A system that includes this.

[1474] (Claim 2)

[1475] The system according to claim 1, which receives user feedback and re-inputs the data into the AI ​​model for re-evaluation.

[1476] (Claim 3)

[1477] The system according to claim 1, comprising a server that uses a scraping technique to obtain the latest discount information from the internet based on the aforementioned collected data.

[1478] "Example 1"

[1479] (Claim 1)

[1480] A means of inputting user project information,

[1481] Means including a terminal that transmits the input information to a server,

[1482] Means including a server for collecting past project data and market price data,

[1483] A means including a server that calculates budget allocation using an AI model generated based on the collected data,

[1484] A means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal,

[1485] Means including a terminal that displays the transmitted proposal to the user,

[1486] A means including a server that receives user feedback and re-inputs the data into the generated AI model for re-evaluation,

[1487] A means including a server that uses scraping techniques to obtain the latest discount information from the internet based on the aforementioned collected data,

[1488] A system that includes this.

[1489] (Claim 2)

[1490] The system according to claim 1, comprising means for analyzing user-provided feedback information and re-inputting it into a generating AI model to generate new suggestions.

[1491] (Claim 3)

[1492] The system according to claim 1, comprising means for generating prompt sentences based on information provided by the user and collected data, and inputting them into a generating AI model.

[1493] "Application Example 1"

[1494] (Claim 1)

[1495] A device for inputting user project information,

[1496] A device including a terminal that transmits the input information to an information processing device,

[1497] A device including an information processing device that collects past project data and market price data,

[1498] An apparatus including an information processing device that calculates budget allocation using a generated AI model based on the collected data,

[1499] An apparatus including an information processing device that generates cost reduction proposals based on the calculation results and transmits them to the terminal,

[1500] A device including a terminal that displays the transmitted proposal to the user,

[1501] A system characterized by its design to optimize budget allocation in store renovation projects.

[1502] (Claim 2)

[1503] The system according to claim 1, which receives user feedback and re-inputs the data into the AI ​​model for re-evaluation.

[1504] (Claim 3)

[1505] The system according to claim 1, comprising an information processing device that obtains the latest discount information from the internet using a scraping technique based on the aforementioned collected data.

[1506] "Example 2 of combining an emotion engine"

[1507] (Claim 1)

[1508] A means for inputting user project information and user sentiment information,

[1509] Means including a terminal that transmits the input information to a server,

[1510] Means for collecting past project data, market price data, and the latest discount information from the internet,

[1511] A means for calculating budget allocation using a generated AI model based on the collected data,

[1512] A means of reflecting user sentiment information in budget allocation,

[1513] A means for generating cost reduction proposals based on the calculation results and transmitting them to the terminal,

[1514] Means including a terminal that displays the transmitted proposal to the user,

[1515] A means of analyzing user emotions when providing user feedback,

[1516] A system that includes this.

[1517] (Claim 2)

[1518] The system according to claim 1, which receives user feedback and re-inputs the data into a regenerating AI model based on emotional information to perform a re-evaluation.

[1519] (Claim 3)

[1520] The system according to claim 1, comprising means for obtaining the latest discount information from the internet using a scraping technique based on the aforementioned collected data.

[1521] "Application example 2 when combining with an emotional engine"

[1522] (Claim 1)

[1523] A system for optimizing the budget of a renovation project.

[1524] A means of inputting user project information,

[1525] Means including a terminal that transmits the input information to a server,

[1526] Means including a server for collecting past project data and market price data,

[1527] A means including a server that calculates budget allocation using an AI model generated based on the collected data,

[1528] A means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal,

[1529] A means including an emotion engine to recognize user emotions in real time and reflect them in the suggested content,

[1530] Means including a terminal that displays the transmitted proposal to the user,

[1531] A system that includes this.

[1532] (Claim 2)

[1533] The system according to claim 1, which receives user feedback and re-inputs the data into the AI ​​model for re-evaluation.

[1534] (Claim 3)

[1535] The system according to claim 1, comprising a server that uses a scraping technique to obtain the latest discount information from the internet based on the aforementioned collected data. [Explanation of Symbols]

[1536] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A system for optimizing the budget of a renovation project. A means of inputting user project information, Means including a terminal that transmits the input information to a server, Means including a server for collecting past project data and market price data, A means including a server that calculates budget allocation using an AI model generated based on the collected data, A means including a server that generates cost reduction proposals based on the calculation results and transmits them to the terminal, Means including a terminal that displays the transmitted proposal to the user, A system that includes this.

2. The system according to claim 1, which receives user feedback and re-inputs the data into the AI ​​model for re-evaluation.

3. The system according to claim 1, comprising a server that uses a scraping technique to obtain the latest discount information from the internet based on the collected data.

Images