System

Abstract

A system is provided.SOLUTION: A system includes a means for collecting questionnaire data from residents, a means for collecting behavior data from the residents, a means for training and operating a generation AI for generating an avatar imitating the thinking of the residents based on the collected questionnaire data and behavior data, a means for simulating the generated avatar in a digital twin environment, and a means for automatically generating a city planning based on a simulation result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Many modern urban plans are formulated with limited information and resources, and one of the challenges is that they do not adequately reflect the diverse needs and opinions of residents. In particular, feedback on improving residents' living environments and optimizing public services is not effectively collected, resulting in the creation of cities that are attractive and comfortable for residents. In addition, the process for reflecting residents' opinions is cumbersome, and there is a lack of incentives to promote resident participation. [Means for solving the problem]

[0005] This invention provides a system that generates avatars that mimic residents' thinking by collecting data from residents through surveys and IoT sensors and training a generation AI based on that data. These avatars are simulated in a digital twin environment, and residents' needs are aggregated and analyzed from the simulation results, automatically generating urban plans tailored to individual preferences. The system also includes a means for obtaining consent to provide data and offering local currency as an incentive to residents who consent. This invention makes it possible to realize urban plans that effectively reflect the diverse needs of residents, promoting resident participation and creating attractive, comfortable cities.

[0006] "Residents" refers to people who live in the city or region where the system is installed.

[0007] "Survey data" refers to information collected through questionnaires or online forms completed by residents, including information on their opinions about their living environment and the facilities they use.

[0008] "Behavioral data" refers to information about residents' daily activities, including data collected by IoT sensors, such as GPS data and records of public facility use.

[0009] "Generative AI" refers to artificial intelligence that mimics the thinking and behavioral patterns of residents based on collected survey data and behavioral data.

[0010] "Avatar" refers to a virtual human model created by generative AI that mimics the thinking and behavior patterns of residents.

[0011] "Digital twin" refers to a simulated environment that recreates a real urban environment in a virtual space, where avatar activities can be simulated.

[0012] "Simulation results" refers to the data recorded by observing the avatar's activities and reactions in the digital twin environment.

[0013] "Urban planning" refers to specific plans and policies formulated with the aim of optimizing urban development and public services.

[0014] "Incentives" refer to rewards or benefits given to residents to encourage them to provide data. In this case, this mainly refers to local currency. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a 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.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0029] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention automatically generates urban plans tailored to individual preferences by collecting data on residents, using generative AI to generate avatars that mimic the residents' thoughts, and conducting simulations in a digital twin environment. This system is specifically implemented as follows.

[0037] Data collection

[0038] First, users answer a questionnaire using their smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, etc. This allows the collection of survey data.

[0039] Next, the device collects behavioral data about the resident's daily life. For example, GPS data from a smartwatch or smartphone is used to obtain data on the commute route and facilities used. This behavioral data is then sent to a server.

[0040] Consent confirmation and incentive provision

[0041] The server sends a confirmation message to the device to obtain consent for data provision. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is accepted.

[0042] The server will provide local currency as an incentive to users who agree to participate, encouraging them to actively participate in providing data.

[0043] Training generative AI models

[0044] The server then preprocesses the collected survey and behavioral data, cleansing and formatting it, and uses it to train a generative AI model.

[0045] Avatar generation

[0046] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts, based on the user's attributes and behavioral patterns.

[0047] Simulation on a digital twin

[0048] The server then introduces the generated avatar into the digital twin environment and runs a simulation, observing the avatar's reactions and behavior and collecting data.

[0049] Urban planning proposals

[0050] The server analyzes the simulation results and collects the opinions and preferences of residents. Based on this, an urban plan that meets the needs of residents is automatically generated. The generated urban plan is then presented to local government officials.

[0051] Specific examples

[0052] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents fill out a survey and GPS data is collected to identify their behavioral patterns, such as the routes they usually take and the facilities they use. Next, generative AI is used to create avatars that mimic each resident's behavioral patterns and park preferences, and a simulation of the park's establishment is run on the digital twin.

[0053] The simulation results showed that many residents use parks on weekends and that certain areas are more frequently used, and based on this, the system proposed the location and design of new parks to meet the needs of residents. This concrete example will realize attractive urban planning that reflects the opinions of residents.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] Users answer the questionnaire using their smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, etc. Once the answers are completed, the questionnaire data is sent to the server.

[0057] Step 2:

[0058] The device collects behavioral data related to the user's daily life. Specifically, it acquires GPS data from smartwatches and smartphones, and collects data on the user's commute route and the public facilities they use. The collected behavioral data is sent to a server.

[0059] Step 3:

[0060] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message, consent is obtained. The information for which consent has been obtained is stored on the server.

[0061] Step 4:

[0062] The server will grant local currency as an incentive to users who agree. The server will grant local currency by checking the user's data provision history and adding the necessary local currency to the user's account.

[0063] Step 5:

[0064] The server preprocesses the collected survey and behavioral data, cleansing and formatting the data, and uses the preprocessed data as training data for the generative AI model.

[0065] Step 6:

[0066] The server trains a generative AI model based on the preprocessed data, which is then used to mimic the thinking and behavior patterns of residents.

[0067] Step 7:

[0068] The server uses a trained generative AI model to generate an avatar based on the user's attributes and behavioral patterns. This avatar is a virtual human model that mimics the thoughts and behavior of the resident.

[0069] Step 8:

[0070] The server then introduces the generated avatar into the digital twin environment and performs a simulation, observing the avatar's reactions and behavior and collecting the simulation results as data.

[0071] Step 9:

[0072] The server analyzes the simulation results, aggregates residents' opinions and preferences using statistical methods, and extracts residents' needs based on the analyzed data.

[0073] Step 10:

[0074] The server automatically generates an urban plan based on the needs extracted and in line with the opinions of residents. The generated urban plan is then presented to local government officials for final review and adjustment.

[0075] Example 1

[0076] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0077] Conventional urban planning often fails to adequately reflect residents' opinions and preferences. Furthermore, there is a lack of methods for integrating and utilizing residents' behavioral patterns and daily mobility data, resulting in plans that often deviate from residents' actual needs. To solve this problem, a method is needed to efficiently collect survey data and behavioral data, use generative AI to generate avatars that mimic residents' thoughts, and simulate them in a digital twin environment.

[0078] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0079] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for cleansing and formatting the collected survey data and behavioral data, and means for training and operating a generation AI that generates avatars that mimic the thinking of residents, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, and means for presenting the urban plans to local government officials. This enables the automatic generation of advanced urban plans that reflect the opinions and behavioral patterns of residents.

[0080] "Residents" refers to ordinary people who live in a city or region.

[0081] "Survey data" refers to response data collected from residents regarding their living environment, means of transportation, and facility usage.

[0082] "Behavioral data" refers to location and behavioral information collected from devices such as smartphones and smartwatches, such as residents' routes and destinations in their daily lives.

[0083] "Generative AI" refers to artificial intelligence that generates avatars that mimic the thinking and behavior patterns of residents based on collected data.

[0084] "Cleansing" is a data preprocessing process that removes inaccurate or missing data and improves data quality.

[0085] "Format conversion" refers to the process of converting collected data into a format that can be used by generative AI models.

[0086] An "avatar" is a digital representative that mimics the characteristics and behavioral patterns of a resident.

[0087] A "digital twin environment" refers to a virtual environment that digitally recreates a specific location or system in the real world.

[0088] "Simulation" refers to a method of conducting virtual experiments in a digital twin environment using a generated avatar and analyzing the results.

[0089] "Urban planning" refers to the act or content of designing and planning the layout of infrastructure and facilities in a local community to improve the living environment of residents.

[0090] "Municipal officials" refer to local government officials in charge of urban planning and local resident services.

[0091] "Incentives" refers to incentives, particularly rewards such as local currency, given to encourage residents to provide data.

[0092] The present invention automatically generates urban plans tailored to individual preferences by collecting data on residents, using generative AI to generate avatars that mimic the residents' thoughts, and conducting simulations in a digital twin environment. This invention is specifically implemented as follows.

[0093] First, the user answers a questionnaire using a smartphone or PC about their living environment, transportation, favorite parks and facilities, etc. This collects the survey data. Next, the device uses GPS data from the smartwatch or smartphone to collect behavioral data about the user's daily life and sends it to the server.

[0094] Next, the server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in the consent confirmation message, consent is accepted. The server awards local currency as an incentive to users who consent. This encourages residents to actively participate in data provision.

[0095] The server then preprocesses the collected survey and behavioral data. This preprocessing step involves data cleansing and formatting. Cleansing removes inaccurate or missing data, while formatting converts the data into a format suitable for AI models.

[0096] The server then uses the pre-processed data to train a generative AI model, which uses state-of-the-art neural network technology to learn residents' behavioral patterns and preferences.

[0097] Once training is complete, the server uses the generative AI model to generate an avatar that mimics the user's thoughts and behaviors, creating a digital representation of the user's characteristics.

[0098] Next, the avatar generated by the server is introduced into the digital twin environment, and simulations such as urban planning are carried out. Through this simulation, the avatar's behavior and reactions are observed, and the simulation results are collected as data.

[0099] Finally, the server automatically generates an urban plan based on the simulation results. The simulation results are statistically analyzed and residents' needs are summarized based on this. The generated urban plan is presented to local government officials and developed into a concrete plan.

[0100] Specific examples

[0101] For example, this system can be used when considering the establishment of a new public park in a certain area. Users respond to a questionnaire and GPS data is collected, revealing behavioral patterns such as the routes residents usually take and the facilities they use. Next, generative AI is used to create avatars that mimic each resident's behavioral patterns and preferences for parks, and a simulation of the park's establishment is carried out in a digital twin environment. The simulation results show that many residents use the park on weekends and that certain areas are used frequently, and based on this, the system proposes the location and design of the park.

[0102] Prompt Sentence Examples

[0103] "Based on user survey data and GPS data, use a generative AI model to generate avatars that mimic the thoughts of residents, and simulate the installation of a new public park in a digital twin environment."

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1: Conduct a survey

[0106] Users use their smartphones or PCs to answer a questionnaire about their living environment, transportation, and favorite parks and facilities. Based on the survey questions they input (e.g., "Which is the nearest park?" and "What is your usual mode of transportation?"), the system outputs the user's response data. Specifically, data such as "Most favorite park: Central Park" and "Method of commuting: Bicycle" are collected.

[0107] Step 2: Collect behavioral data

[0108] The device uses GPS data from a smartwatch or smartphone to record the user's daily travel routes, visited destinations, and other behavioral data. The user's travel patterns are output based on input location information (e.g., GPS data with time stamps). For example, data such as "Leaving home (location information) at 8 a.m. and arriving at office (location information) at 9 a.m." is collected.

[0109] Step 3: Confirm consent

[0110] The server sends a consent confirmation message regarding data provision to the terminal. Based on the input consent confirmation message (e.g., information about the purpose of data use and privacy protection), the user's response data is output. Specifically, consent is accepted when the user presses the "Agree" button on the displayed consent confirmation message.

[0111] Step 4: Offer incentives

[0112] The server will award local currency as an incentive to users who agree. Based on the consent confirmation result as input, points will be added to the user's account. As a result, "Points awarded: 100 local currency points" or similar will be output.

[0113] Step 5: Preprocessing the data

[0114] The server preprocesses the collected survey and behavioral data. Based on the raw data (survey data and behavioral data) as input, data cleansing and format conversion are performed, and a clean dataset is output. Specifically, this includes operations such as "removing invalid location records."

[0115] Step 6: Training the AI ​​model

[0116] The server trains a generative AI model based on the preprocessed data. Based on the clean data set as input, the AI ​​model is trained using algorithms such as neural networks. The result is a generative AI model that has learned specific patterns and tendencies.

[0117] Step 7: Avatar generation

[0118] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. Based on the generative AI model and the user's attribute data as input, an avatar with the user's unique behavioral patterns is output. Specifically, an avatar named "Office Worker A" is generated.

[0119] Step 8: Run the simulation

[0120] The server introduces the generated avatar into the digital twin environment and performs urban planning simulations. Specific urban planning scenarios are simulated based on the avatar and digital twin environment as input. Simulation data and the avatar's reactions are output as the result. For example, "usage patterns based on a new park installation scenario" are obtained.

[0121] Step 9: Analyze the simulation results

[0122] The server analyzes the simulation results and aggregates the needs of residents. Statistical analysis is performed based on the input simulation data, and aggregated needs data is output. Specifically, insights such as "parks in specific areas are frequently used" can be obtained.

[0123] Step 10: Urban Planning Proposal

[0124] Based on the analysis results, the server automatically generates an urban plan that meets the needs of residents and presents it to local government officials. Based on the analysis results as input, specific urban plans (e.g., the design and location of a new park) are output. As a result, a "proposal for the establishment of a central park" is provided to local government officials.

[0125] (Application example 1)

[0126] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0127] In modern urban planning and store management, it is important to create optimal plans that reflect the specific needs and behavioral patterns of residents and customers. However, traditional methods have difficulty fully incorporating the voices of residents and customers, and optimization of urban planning and store management has not reached a reasonable level. For this reason, there is a need for a system that can automatically generate plans and proposals that accurately reflect individual preferences and behavioral patterns based on resident and customer data.

[0128] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0129] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for training and operating a generation AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, and means for optimizing store layouts and product configurations. This enables optimal urban planning and store operations that reflect the specific needs and behavioral patterns of residents and customers.

[0130] "Resident" refers to an individual who resides in a particular area or city.

[0131] "Survey data" refers to data containing responses collected from residents and customers. The surveys include questions about living environments and product preferences.

[0132] "Behavioral data" refers to data that shows the behavioral patterns of residents and customers, such as GPS information, purchase history, and frequency of store visits.

[0133] "Generative AI" refers to an AI model that mimics a user's thoughts and actions based on collected data.

[0134] "Avatars" refer to virtual characters created by generative AI that mimic the characteristics of residents or customers.

[0135] A "digital twin" is a virtual reproduction of the physical world, used for simulation and prediction.

[0136] "Simulation" refers to the process of operating the generated avatar in a digital twin environment and observing its reactions and behavior under various conditions.

[0137] "Urban planning" refers to a plan to design the structure and functions of an entire city in order to improve the lives of its residents.

[0138] "Store layout" refers to the design of product placement and traffic flow within a physical store.

[0139] "Product mix" refers to determining the types and quantities of products to be sold in physical stores.

[0140] "Incentives" refers to rewards or benefits for providing data, including local currency and discount coupons.

[0141] "Statistical analysis" refers to analyzing collected data using statistical methods to extract meaningful information.

[0142] "Optimization" refers to adjusting a system or process to its optimum state in order to achieve a specific goal.

[0143] This invention automatically generates urban plans and store layouts tailored to individual preferences by collecting data on residents and customers, using generative AI to generate avatars that mimic the thoughts of residents and customers, and conducting simulations in a digital twin environment. This system is specifically implemented as follows.

[0144] Data collection

[0145] Users answer a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, product preferences, and store layout. This allows the collection of survey data.

[0146] Next, the device collects behavioral data about the daily lives of residents and customers, such as GPS data from smartwatches and smartphones, store visit history, purchase history, and product browsing history. This behavioral data is then sent to a server.

[0147] Consent confirmation and incentive provision

[0148] The server sends a confirmation message to the device to obtain consent for data provision. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is accepted.

[0149] The server will provide local currency or discount coupons as incentives to residents and customers who agree to participate in the data provision.

[0150] Training generative AI models

[0151] The server preprocesses the collected survey data and behavioral data. It cleans and formats the data and trains a generative AI model based on it. Specifically, it uses GPT-4 (registered trademark) as the generative AI model to learn user behavioral patterns and preferences.

[0152] Avatar generation

[0153] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. This avatar is created based on the user's attributes and behavioral patterns. For example, the server can input a prompt such as, "Customer A likes electronic devices and gadgets, and is particularly interested in the latest smartphone accessories. He frequently visits stores on weekends and enjoys looking at the new product display area."

[0154] Simulation on a digital twin

[0155] The server then introduces the generated avatar into the digital twin environment and performs a simulation. During the simulation, the avatar's reactions and behavior are observed and data is collected. Unity and Siemens' MindSphere are used as digital twin platforms.

[0156] Proposals for optimizing urban planning and store operations

[0157] The server analyzes the simulation results and aggregates the opinions and preferences of residents and customers. Based on this, the system automatically generates urban plans and store layouts that meet the needs of residents and customers. For example, it proposes optimal layouts and product configurations to store operators, so that the latest smartphone accessories are displayed in prominent locations.

[0158] Specific examples

[0159] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents fill out a survey and collect GPS data, revealing behavioral patterns such as the routes they usually take and which facilities they use. Next, generative AI is used to generate avatars that mimic each resident's behavioral patterns and preferences for parks, and a simulation of the park's establishment is carried out on the digital twin. The system can also be applied to store customization; for example, customer behavior can be simulated based on survey results and behavioral data to propose optimal store layouts. This specific example will enable attractive urban planning and store management that reflects the opinions of residents and customers.

[0160] This will enable optimal urban planning and store management that reflects the specific needs and behavioral patterns of residents and customers.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] Users answer the questionnaire using a smartphone or PC. The input is the user's questionnaire response, and the output is the collected questionnaire data. The questionnaire includes questions about living environment, product preferences, and store layout. The device sends this data to the server.

[0164] Step 2:

[0165] The device collects behavioral data about the user's daily life through a smartwatch or smartphone. Specifically, this includes GPS data, store visit history, purchase history, and product browsing history. This behavioral data is sent to a server. The input is the user's behavioral data, and the output is the collected behavioral data.

[0166] Step 3:

[0167] The server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in response to the consent confirmation message displayed on the terminal, consent is accepted. The input is the consent confirmation message, and the output is the user's consent status. If consent is given, the server grants the user local currency or discount coupons as an incentive.

[0168] Step 4:

[0169] The server preprocesses the collected survey and behavioral data, cleansing and formatting the data. The input is the survey and behavioral data, and the output is the preprocessed data. Based on this preprocessed data, the server trains a generative AI model (e.g., GPT-4).

[0170] Step 5:

[0171] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. The input is preprocessed data, and the output is the generated avatar. The server generates an avatar based on a prompt statement, such as, "Customer A likes electronic devices and gadgets, and is particularly interested in the latest smartphone accessories. He frequently visits stores on weekends and enjoys looking at the new product display area."

[0172] Step 6:

[0173] The server introduces the generated avatar into the digital twin environment and performs a simulation. Specific behaviors include how the avatar moves around the store and which areas it shows interest in. The input is the generated avatar, and the output is the simulation results. Unity and Siemens' MindSphere are used as digital twin platforms.

[0174] Step 7:

[0175] The server performs analysis based on the simulation results. Statistical methods are used to analyze the simulation results and aggregate the needs of residents and customers. The input is the simulation results, and the output is the analysis results. Based on these analysis results, the server proposes optimal layouts and product configurations to store operators.

[0176] Step 8:

[0177] The server automatically generates specific city planning and store operation optimization plans based on the analysis and simulation results. The input is the analysis results, and the output is an optimized city planning and store layout proposal. For example, it can propose a layout in which the latest smartphone accessories are placed in a prominent location.

[0178] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0179] This invention collects data on residents, generates avatars that mimic the thoughts and emotions of residents using generative AI and an emotion engine, and then performs simulations in a digital twin environment to automatically generate urban plans that are tailored to individual emotions and preferences. This system is specifically implemented as follows.

[0180] Data collection

[0181] First, the user answers a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and emotional changes in daily life. Once the answers are complete, the questionnaire data is sent to the server.

[0182] Next, the device collects behavioral data related to the user's daily life. For example, GPS data from a smartwatch or smartphone is used to collect data on the user's commute route and the facilities they use. Sensors installed in the smartphone or wearable device are also used to monitor the user's heart rate and facial expressions, collecting emotional data. This behavioral data and emotional data are then sent to a server.

[0183] Consent confirmation and incentive provision

[0184] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information for which consent has been obtained is stored on the server.

[0185] The server will provide local currency as an incentive to users who agree. The server will check the user's data provision history and add the necessary local currency to the user's account.

[0186] Training generative AI models and emotion engines

[0187] The server then preprocesses the collected survey data, behavioral data, and emotional data. The data is cleansed and formatted, and then used to train a generative AI model and an emotional engine. The generative AI model is used to mimic residents' thinking and behavior patterns, and the emotional engine is used to evaluate the user's emotional state.

[0188] Avatar generation

[0189] The server uses a trained generative AI model and emotion engine to generate an avatar based on the user's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the thoughts, actions, and emotions of the resident.

[0190] Simulation on a digital twin

[0191] The server then introduces the generated avatar into the digital twin environment and conducts a simulation, observing the avatar's reactions, behavior, and emotional changes, and collecting the simulation results as data.

[0192] Urban planning proposals

[0193] The server performs an analysis based on the simulation results. Statistical methods are used to aggregate residents' opinions, preferences, and emotional states, and the analyzed data is used to identify residents' needs. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0194] Specific examples

[0195] For example, this system could be used when considering the establishment of a new public park. Residents fill out a survey and GPS and emotional data are collected to determine the routes they typically take, the facilities they use, and the emotions they feel when they do. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, and a simulation of the park's construction is run on the digital twin.

[0196] The simulation results showed that many residents use parks on weekends and feel positive emotions in the process, and that certain areas are used frequently and have high emotional satisfaction. Based on this, the system proposes new park locations and designs that match the needs and emotions of residents. This specific example will realize livable urban planning that reflects the opinions and emotions of residents.

[0197] The processing flow will be explained below.

[0198] Step 1:

[0199] Users answer a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and emotional changes in daily life. Once the questionnaire is completed, the data is sent to the server.

[0200] Step 2:

[0201] The device collects behavioral data related to the user's daily life. For example, GPS data from a smartwatch or smartphone is used to collect data on the user's commute route and the facilities they use. Sensors installed in the smartphone or wearable device are also used to monitor the user's heart rate and facial expressions, and to collect emotional data. The collected behavioral and emotional data is sent to a server.

[0202] Step 3:

[0203] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information for which consent has been obtained is stored on the server.

[0204] Step 4:

[0205] The server will grant local currency as an incentive to users who agree. The server will grant local currency by checking the user's data provision history and adding the necessary local currency to the user's account.

[0206] Step 5:

[0207] The server preprocesses the collected survey data, behavioral data, and sentiment data. Data cleansing and format conversion are performed. The preprocessed data is used as training data for the generative AI model and sentiment engine.

[0208] Step 6:

[0209] The server trains the generative AI model and emotion engine based on the preprocessed data. The generative AI model imitates the residents' thought patterns and behavior patterns, and the emotion engine evaluates the user's emotional state.

[0210] Step 7:

[0211] The server uses the trained generative AI model and emotion engine to generate an avatar based on the user's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the thoughts, actions, and emotions of the resident.

[0212] Step 8:

[0213] The server then introduces the generated avatar into the digital twin environment and conducts a simulation, during which the avatar's reactions, behavior, and emotional changes are observed and collected.

[0214] Step 9:

[0215] The server analyzes the simulation results, using statistical methods to aggregate residents' opinions, preferences, and emotional states, and extracts residents' needs based on the analyzed data.

[0216] Step 10:

[0217] The server automatically generates an urban plan that is in line with the residents' opinions and emotions based on the extracted needs and emotional states. The generated urban plan is then presented to local government officials for final review and adjustment.

[0218] Specific examples

[0219] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents respond to a survey and GPS and emotional data are collected to determine the routes they take, the facilities they use, and the emotions they feel when doing so. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, and a simulation of the park's establishment is run on the digital twin. The simulation results show that many residents use the park on weekends and experience positive emotions while doing so, and that certain areas are frequently used and provide high emotional satisfaction. Based on this, the system can propose the location and design of the new park to match the residents' needs and emotions. This specific example will realize livable urban planning that reflects the opinions and emotions of residents.

[0220] Example 2

[0221] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0222] In modern urban planning, it is extremely important to effectively reflect the opinions and feelings of residents. However, conventional methods often rely on one-sided approaches based on quantitative data, which have the problem of not fully reflecting the diverse thoughts and feelings of residents. Furthermore, when it comes to collecting data from residents, there is a lack of motivation for them to actively provide it, making it difficult to collect accurate and abundant data. There is a need for a system that can solve these issues and realize urban planning that effectively reflects the opinions and feelings of residents.

[0223] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting questionnaire data from residents, means for collecting behavioral data and emotional data from residents, and means for training and operating a generation AI and emotion engine that generates avatars that mimic the thoughts and emotions of residents based on the collected questionnaire data, behavioral data, and emotional data. This makes it possible to effectively collect and analyze data including the diverse opinions and emotions of residents and automatically generate urban plans that match the emotions and preferences of each resident.

[0224] "Survey data" refers to data containing the contents of questionnaires answered by residents, including information on living environment, means of transportation, favorite parks and facilities, and emotional changes in daily life.

[0225] "Behavioral data" refers to data that shows residents' daily activities, including GPS data from smartwatches and smartphones, commuting routes, and usage of facilities.

[0226] "Emotion data" is data that indicates the emotional state of the resident, and includes heart rate data and facial expression recognition data.

[0227] "Generative AI" refers to an artificial intelligence model that mimics the thought and behavior patterns of residents based on collected data.

[0228] An "emotion engine" is a processing device or algorithm that evaluates the emotional state of residents based on collected emotional data.

[0229] "Avatars" are virtual human models that use generative AI and emotion engines to mimic the attributes, behavioral patterns, and emotional states of residents.

[0230] A "digital twin" is a simulated environment that virtually recreates a real urban environment and is used to observe the reactions and behavior of avatars.

[0231] "Simulation results" are data that show the results of observing and analyzing changes in the behavior and emotions of avatars in a digital twin environment.

[0232] "Means for automatically generating urban plans" refers to devices or software that aggregate residents' opinions, preferences, and emotional states based on simulation results, and then generate urban plans that meet the residents' needs based on the analyzed data.

[0233] "Confirmation means for obtaining consent to data provision" refers to the interface and process for confirming whether residents agree to provide their data, and may include consent confirmation messages and "Agree" buttons.

[0234] "Means for granting local currency" refers to a system that electronically grants local currency as an incentive to consenting residents.

[0235] "Statistical analysis means" refers to the process and algorithms for analyzing the simulation results using statistical methods and aggregating the opinions and emotional states of residents.

[0236] "Means of aggregating residents' needs" refers to systems and processes for organizing the diverse opinions and feelings of residents based on the results of statistical analysis and aggregating them into centralized data.

[0237] MODE FOR CARRYING OUT THE INVENTION

[0238] The present invention is a system that automatically generates urban plans tailored to individual emotions and preferences by collecting data on residents, generating avatars that mimic the residents' thoughts and emotions using a generative AI model and an emotion engine, and running simulations in a digital twin environment. This system is specifically implemented as follows.

[0239] Data collection

[0240] Users answer a questionnaire using a smartphone or personal computer (PC). The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and daily emotional changes. Once the user completes the questionnaire, the data is sent to the server.

[0241] The device collects behavioral data related to the user's daily life using the GPS of the smartwatch or smartphone, and collects emotional data using sensors installed in the smartphone or wearable device to monitor heart rate and facial expressions, which are also transmitted to the server.

[0242] Consent confirmation and incentive provision

[0243] The server sends a consent confirmation message regarding data provision to the terminal, and the user obtains consent by pressing the "Agree" button in response to the consent confirmation message. The consent information is stored on the server. The server grants local currency as an incentive to users who agree to data provision. The procedure for granting local currency is carried out by the server checking the user's data provision history and adding the required local currency to the user's account.

[0244] Training generative AI models and emotion engines

[0245] The server preprocesses the collected survey data, behavioral data, and emotional data. It cleanses the data, fills in missing data, and converts the data format. It then trains a generative AI model and an emotion engine based on the preprocessed data. The generative AI model is used to mimic residents' thinking and behavioral patterns, and the emotion engine is used to evaluate the user's emotional state.

[0246] Avatar generation

[0247] The server uses a trained generative AI model and emotion engine to generate an avatar based on each user's attributes, behavioral patterns, and emotional state. This avatar is a virtual person model that mimics the thoughts, actions, and even emotions of the resident.

[0248] Simulation in a digital twin environment

[0249] The server then introduces the generated avatar into a digital twin environment and conducts a simulation. The digital twin environment is a virtual reproduction of an actual urban environment, allowing users to observe the avatar's reactions, behavior, and emotional changes. The server then collects and analyzes the data obtained from this simulation.

[0250] Urban planning proposals

[0251] Based on the simulation results, the server uses statistical methods to aggregate residents' opinions, preferences, and emotional states, and extracts residents' needs from the analyzed data. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0252] Specific examples

[0253] For example, this system can be used when considering the establishment of a new public park. Residents respond to a survey and GPS and emotional data are collected, revealing the routes they take, the facilities they use, and the emotions they feel when they do. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, allowing simulations of park establishment to be conducted on the digital twin. If the simulation results show that a particular area is frequently used and emotionally satisfying, a proposal to establish a new park in that area can be made.

[0254] Prompt Sentence Examples

[0255] For example, a prompt to suggest the best location for a new public facility might look like this:

[0256] Based on the following data, suggest the best location and design for a new public park.

[0257] 1. Resident survey response data

[0258] 2. GPS-based behavioral data

[0259] 3. Collected emotional data

[0260] Based on the above data, please simulate and propose the location and design of the park that will most satisfy the residents.

[0261] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0262] Step 1:

[0263] Users answer a questionnaire using a smartphone or personal computer (PC). The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and daily emotional changes. Once the user completes the questionnaire, the data is sent from the device to the server.

[0264] Input: User survey response data

[0265] Output: Survey data sent to the server

[0266] Step 2:

[0267] The device collects behavioral data related to the user's daily life using the GPS of the smartwatch or smartphone, and collects emotional data using sensors installed in the smartphone or wearable device to monitor heart rate and facial expressions, which are also transmitted to the server.

[0268] Input: Behavioral and emotional data from smartwatches, smartphones, and wearable devices

[0269] Output: Behavioral and emotional data sent to the server

[0270] Step 3:

[0271] The server sends a consent confirmation message regarding data provision to the terminal, and the user consents by pressing the "Agree" button in response to the displayed consent confirmation message. The consent information is stored on the server.

[0272] Input: Consent confirmation message

[0273] Output: The consent information is saved on the server.

[0274] Step 4:

[0275] The server will grant local currency as an incentive to users who agree. The procedure for granting local currency is carried out by the server checking the user's data provision history and adding the necessary local currency to the user's account.

[0276] Input: User data provision history, consent information

[0277] Output: The local currency is added to the user's account

[0278] Step 5:

[0279] The server preprocesses the collected survey data, behavioral data, and sentiment data, cleansing the data, filling in missing data, and converting formats, and then trains the generative AI model and sentiment engine based on the preprocessed data.

[0280] Input: Survey data, behavioral data, emotional data

[0281] Output: Pre-processed data, trained generative AI model and emotion engine

[0282] Step 6:

[0283] The server uses a trained generative AI model and emotion engine to generate an avatar based on each user's attributes, behavioral patterns, and emotional state. This avatar is a virtual person model that mimics the thoughts, actions, and even emotions of the resident.

[0284] Input: Trained generative AI model and emotion engine, pre-processed data

[0285] Output: An avatar that mimics the user's attributes, behavioral patterns, and emotional state

[0286] Step 7:

[0287] The server then introduces the generated avatar into a digital twin environment and conducts a simulation. The digital twin environment is a virtual reproduction of an actual urban environment, allowing users to observe the avatar's reactions, behavior, and emotional changes. The server then collects and analyzes the data obtained from this simulation.

[0288] Input: Generated avatar

[0289] Output: Simulation result data

[0290] Step 8:

[0291] The server uses statistical methods to analyze residents' opinions, preferences, and emotional states based on the simulation results, and extracts residents' needs from the analyzed data. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0292] Input: Simulation result data

[0293] Output: Proposal of urban planning that reflects the needs of residents

[0294] (Application example 2)

[0295] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0296] In modern logistics facilities, work efficiency and worker satisfaction are important factors that directly affect facility productivity and worker safety. However, methods for optimizing these have not yet been established, and in particular, there is no system that reflects worker emotions and behavioral patterns. Therefore, there is a need to achieve both an efficient work environment and worker satisfaction in logistics facilities.

[0297] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0298] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for training and operating a generation AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, means for generating avatars that mimic the behavioral patterns and emotional states of workers and evaluating the optimization of work efficiency and work satisfaction at logistics facilities, means for analyzing the avatars' responses and behavioral patterns and generating proposals to support efficiency improvements at logistics facilities, and means for making proposals to improve the work environment based on the avatar simulation results.This makes it possible to maximize work efficiency in logistics facilities and create an optimal work environment that takes into account the emotions and satisfaction of workers.

[0299] "Survey data" refers to data containing subjective information provided by users about their living environment, means of transportation, daily activities, etc.

[0300] "Behavioral data" refers to objectively observed data that includes a user's daily behavior, location information, and physiological data such as heart rate and facial expressions.

[0301] "Generative AI" is artificial intelligence that generates avatars that mimic the user's thought and behavior patterns based on collected survey data and behavioral data.

[0302] A "digital twin" is a digital model that recreates physical world objects or systems in a virtual environment and is used for simulation and analysis.

[0303] The "simulation results" are the data collected by observing the behavior and reactions of avatars created in a digital twin environment.

[0304] "Urban planning" involves proposing the optimal layout and design of living spaces and infrastructure based on resident survey data, behavioral data, and simulation results.

[0305] "Worker" means a person engaged in work within a logistics facility.

[0306] "Work efficiency" is an indicator of how effectively and quickly work is carried out within a logistics facility.

[0307] "Labor satisfaction" is an indicator that shows how satisfied a worker is with their working environment and work content.

[0308] "Efficiency proposals" are specific proposals based on simulation results to improve work efficiency within logistics facilities.

[0309] "Improvement proposals" are proposals based on the simulation results with the aim of improving the working environment.

[0310] The present invention is a system for improving work efficiency and worker satisfaction within a logistics facility. This system is composed of multiple components, each of which works together to optimize the work environment.

[0311] Data collection

[0312] First, a device (such as a smartphone or robot) collects survey data from the user. The survey includes questions about the user's work environment, transportation, and daily activities. The collected data is then sent to a server.

[0313] Next, the device collects behavioral data related to the worker's daily work. For example, GPS data from smartphones and data from sensors installed in logistics facilities are used to collect data on the worker's location and movements. Sensors in smartwatches and smartphones are also used to collect emotional data such as heart rate and facial expressions. This data is also sent to the server.

[0314] Consent confirmation and incentive provision

[0315] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information regarding consent is stored on the server. The server grants local currency as an incentive to users who consent. This local currency is granted by the server by checking the user's data provision history and adding the appropriate amount to the user's account.

[0316] Training generative AI models and emotion engines

[0317] Next, the server preprocesses the collected survey data, behavioral data, and emotion data. Data cleansing and formatting are performed using Python. Based on the preprocessed data, a generative AI model and emotion engine are trained using TENSORFLOW (registered trademark) and Keras. The generative AI model is used to imitate the worker's thought patterns and behavioral patterns, and the emotion engine is used to evaluate the worker's emotional state.

[0318] Avatar generation

[0319] The server uses a trained generative AI model and emotion engine to generate an avatar based on the worker's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the worker's thoughts, actions, and emotions. Blender is used to generate a detailed model of the avatar.

[0320] Simulation on a digital twin

[0321] The server then introduces the generated avatar into the digital twin environment and runs a simulation using a Python program. During the simulation, the avatar's reactions, behavior, and emotional changes are observed, and the simulation results are collected as data.

[0322] Efficiency and improvement proposals

[0323] Based on the simulation results, the server automatically generates improvement proposals to maximize work efficiency and worker satisfaction at the logistics facility. Statistical methods are used to analyze the simulation results, and suggestions for improving the work environment are made based on data that aggregates the needs and emotional states of workers. These suggestions are then presented to the logistics facility's management for final review and adjustment.

[0324] Specific examples

[0325] For example, this system can be used when introducing a new logistics system. Workers fill out a questionnaire and GPS data, heart rate data, and facial expression data are collected to identify which work areas are most stressful and where work flow needs to be optimized. Next, generative AI and an emotion engine are used to generate avatars that mimic each worker's behavioral patterns and emotions, and simulations are run on the digital twin.

[0326] The simulation results show that many workers feel stressed in certain work areas and that improvements to traffic flow are necessary. Based on this, it is possible to propose improvements to the work environment of logistics facilities that are tailored to the needs and emotions of workers.

[0327] Example prompt sentence:

[0328] "Based on your work patterns and emotional data from the past week, we suggest the most efficient and least stressful work flow."

[0329] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0330] Step 1:

[0331] The server collects survey data from users. Users answer the survey using their smartphones or PCs and send the results to the server. The survey includes questions about living environment, transportation, and daily activities. The input is the survey response data from the users, and the output is the survey data stored on the server.

[0332] Step 2:

[0333] The device collects behavioral and emotional data related to the worker's daily work. It collects location information and movement data from the smartphone's GPS data and sensors installed in the logistics facility, and also obtains data such as the user's heart rate and facial expression. This data is sent to a server. The input is the user's behavioral and emotional data, and the output is the behavioral and emotional data stored on the server.

[0334] Step 3:

[0335] The server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in response to the consent confirmation message displayed on the terminal screen, consent is obtained and stored on the server. The server grants local currency as an incentive to users who consent. The input is the user's consent data, and the output is the consent data stored on the server and the granted local currency.

[0336] Step 4:

[0337] The server preprocesses the collected survey data, behavioral data, and sentiment data. It uses Python to cleanse and format the data, making it suitable for machine learning. The input is the collected raw data, and the output is the preprocessed dataset.

[0338] Step 5:

[0339] The server uses the preprocessed data to train a generative AI model and emotion engine using TensorFlow and Keras. The generative AI model imitates the worker's thought patterns and behavior patterns, and the emotion engine evaluates the worker's emotional state. The input is the preprocessed dataset, and the output is the trained generative AI model and emotion engine.

[0340] Step 6:

[0341] The server uses a trained generative AI model and an emotion engine to generate an avatar based on the worker's attributes, behavioral patterns, and emotional state. Blender is used to create detailed avatar models. The input is the trained generative AI model and the emotion engine, and the output is the generated avatar.

[0342] Step 7:

[0343] The server introduces the generated avatar into the digital twin environment and performs a simulation. A Python program is used to check the avatar's behavior and emotional changes, and the results are collected as data. The input is the generated avatar, and the output is the simulation results.

[0344] Step 8:

[0345] The server statistically analyzes the simulation results and automatically generates improvement proposals to maximize work efficiency and labor satisfaction at logistics facilities. Based on the simulation results, it aggregates the needs and emotional states of workers and proposes improvements to the work environment. The input is the simulation result data, and the output is an improvement proposal.

[0346] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0347] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0348] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0349] [Second embodiment]

[0350] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0351] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0352] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0353] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0354] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0355] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0356] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0357] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0358] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0359] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0360] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0361] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0362] The present invention automatically generates urban plans tailored to individual preferences by collecting data on residents, using generative AI to generate avatars that mimic the residents' thoughts, and conducting simulations in a digital twin environment. This system is specifically implemented as follows.

[0363] Data collection

[0364] First, users answer a questionnaire using their smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, etc. This allows the collection of survey data.

[0365] Next, the device collects behavioral data about the resident's daily life. For example, GPS data from a smartwatch or smartphone is used to obtain data on the commute route and facilities used. This behavioral data is then sent to a server.

[0366] Consent confirmation and incentive provision

[0367] The server sends a confirmation message to the device to obtain consent for data provision. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is accepted.

[0368] The server will provide local currency as an incentive to users who agree to participate, encouraging them to actively participate in providing data.

[0369] Training generative AI models

[0370] The server then preprocesses the collected survey and behavioral data, cleansing and formatting it, and uses it to train a generative AI model.

[0371] Avatar generation

[0372] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts, based on the user's attributes and behavioral patterns.

[0373] Simulation on a digital twin

[0374] The server then introduces the generated avatar into the digital twin environment and runs a simulation, observing the avatar's reactions and behavior and collecting data.

[0375] Urban planning proposals

[0376] The server analyzes the simulation results and collects the opinions and preferences of residents. Based on this, an urban plan that meets the needs of residents is automatically generated. The generated urban plan is then presented to local government officials.

[0377] Specific examples

[0378] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents fill out a survey and GPS data is collected to identify their behavioral patterns, such as the routes they usually take and the facilities they use. Next, generative AI is used to create avatars that mimic each resident's behavioral patterns and park preferences, and a simulation of the park's establishment is run on the digital twin.

[0379] The simulation results showed that many residents use parks on weekends and that certain areas are more frequently used, and based on this, the system proposed the location and design of new parks to meet the needs of residents. This concrete example will realize attractive urban planning that reflects the opinions of residents.

[0380] The processing flow will be explained below.

[0381] Step 1:

[0382] Users answer the questionnaire using their smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, etc. Once the answers are completed, the questionnaire data is sent to the server.

[0383] Step 2:

[0384] The device collects behavioral data related to the user's daily life. Specifically, it acquires GPS data from smartwatches and smartphones, and collects data on the user's commute route and the public facilities they use. The collected behavioral data is sent to a server.

[0385] Step 3:

[0386] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message, consent is obtained. The information for which consent has been obtained is stored on the server.

[0387] Step 4:

[0388] The server will grant local currency as an incentive to users who agree. The server will grant local currency by checking the user's data provision history and adding the necessary local currency to the user's account.

[0389] Step 5:

[0390] The server preprocesses the collected survey and behavioral data, cleansing and formatting the data, and uses the preprocessed data as training data for the generative AI model.

[0391] Step 6:

[0392] The server trains a generative AI model based on the preprocessed data, which is then used to mimic the thinking and behavior patterns of residents.

[0393] Step 7:

[0394] The server uses a trained generative AI model to generate an avatar based on the user's attributes and behavioral patterns. This avatar is a virtual human model that mimics the thoughts and behavior of the resident.

[0395] Step 8:

[0396] The server then introduces the generated avatar into the digital twin environment and performs a simulation, observing the avatar's reactions and behavior and collecting the simulation results as data.

[0397] Step 9:

[0398] The server analyzes the simulation results, aggregates residents' opinions and preferences using statistical methods, and extracts residents' needs based on the analyzed data.

[0399] Step 10:

[0400] The server automatically generates an urban plan based on the needs extracted and in line with the opinions of residents. The generated urban plan is then presented to local government officials for final review and adjustment.

[0401] Example 1

[0402] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0403] Conventional urban planning often fails to adequately reflect residents' opinions and preferences. Furthermore, there is a lack of methods for integrating and utilizing residents' behavioral patterns and daily mobility data, resulting in plans that often deviate from residents' actual needs. To solve this problem, a method is needed to efficiently collect survey data and behavioral data, use generative AI to generate avatars that mimic residents' thoughts, and simulate them in a digital twin environment.

[0404] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0405] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for cleansing and formatting the collected survey data and behavioral data, and means for training and operating a generation AI that generates avatars that mimic the thinking of residents, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, and means for presenting the urban plans to local government officials. This enables the automatic generation of advanced urban plans that reflect the opinions and behavioral patterns of residents.

[0406] "Residents" refers to ordinary people who live in a city or region.

[0407] "Survey data" refers to response data collected from residents regarding their living environment, means of transportation, and facility usage.

[0408] "Behavioral data" refers to location and behavioral information collected from devices such as smartphones and smartwatches, such as residents' routes and destinations in their daily lives.

[0409] "Generative AI" refers to artificial intelligence that generates avatars that mimic the thinking and behavior patterns of residents based on collected data.

[0410] "Cleansing" is a data preprocessing process that removes inaccurate or missing data and improves data quality.

[0411] "Format conversion" refers to the process of converting collected data into a format that can be used by generative AI models.

[0412] An "avatar" is a digital representative that mimics the characteristics and behavioral patterns of a resident.

[0413] A "digital twin environment" refers to a virtual environment that digitally recreates a specific location or system in the real world.

[0414] "Simulation" refers to a method of conducting virtual experiments in a digital twin environment using a generated avatar and analyzing the results.

[0415] "Urban planning" refers to the act or content of designing and planning the layout of infrastructure and facilities in a local community to improve the living environment of residents.

[0416] "Municipal officials" refer to local government officials in charge of urban planning and local resident services.

[0417] "Incentives" refers to incentives, particularly rewards such as local currency, given to encourage residents to provide data.

[0418] The present invention automatically generates urban plans tailored to individual preferences by collecting data on residents, using generative AI to generate avatars that mimic the residents' thoughts, and conducting simulations in a digital twin environment. This invention is specifically implemented as follows.

[0419] First, the user answers a questionnaire using a smartphone or PC about their living environment, transportation, favorite parks and facilities, etc. This collects the survey data. Next, the device uses GPS data from the smartwatch or smartphone to collect behavioral data about the user's daily life and sends it to the server.

[0420] Next, the server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in the consent confirmation message, consent is accepted. The server awards local currency as an incentive to users who consent. This encourages residents to actively participate in data provision.

[0421] The server then preprocesses the collected survey and behavioral data. This preprocessing step involves data cleansing and formatting. Cleansing removes inaccurate or missing data, while formatting converts the data into a format suitable for AI models.

[0422] The server then uses the pre-processed data to train a generative AI model, which uses state-of-the-art neural network technology to learn residents' behavioral patterns and preferences.

[0423] Once training is complete, the server uses the generative AI model to generate an avatar that mimics the user's thoughts and behaviors, creating a digital representation of the user's characteristics.

[0424] Next, the avatar generated by the server is introduced into the digital twin environment, and simulations such as urban planning are carried out. Through this simulation, the avatar's behavior and reactions are observed, and the simulation results are collected as data.

[0425] Finally, the server automatically generates an urban plan based on the simulation results. The simulation results are statistically analyzed and residents' needs are summarized based on this. The generated urban plan is presented to local government officials and developed into a concrete plan.

[0426] Specific examples

[0427] For example, this system can be used when considering the establishment of a new public park in a certain area. Users respond to a questionnaire and GPS data is collected, revealing behavioral patterns such as the routes residents usually take and the facilities they use. Next, generative AI is used to create avatars that mimic each resident's behavioral patterns and preferences for parks, and a simulation of the park's establishment is carried out in a digital twin environment. The simulation results show that many residents use the park on weekends and that certain areas are used frequently, and based on this, the system proposes the location and design of the park.

[0428] Prompt Sentence Examples

[0429] "Based on user survey data and GPS data, use a generative AI model to generate avatars that mimic the thoughts of residents, and simulate the installation of a new public park in a digital twin environment."

[0430] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0431] Step 1: Conduct a survey

[0432] Users use their smartphones or PCs to answer a questionnaire about their living environment, transportation, and favorite parks and facilities. Based on the survey questions they input (e.g., "Which is the nearest park?" and "What is your usual mode of transportation?"), the system outputs the user's response data. Specifically, data such as "Most favorite park: Central Park" and "Method of commuting: Bicycle" are collected.

[0433] Step 2: Collect behavioral data

[0434] The device uses GPS data from a smartwatch or smartphone to record the user's daily travel routes, visited destinations, and other behavioral data. The user's travel patterns are output based on input location information (e.g., GPS data with time stamps). For example, data such as "Leaving home (location information) at 8 a.m. and arriving at office (location information) at 9 a.m." is collected.

[0435] Step 3: Confirm consent

[0436] The server sends a consent confirmation message regarding data provision to the terminal. Based on the input consent confirmation message (e.g., information about the purpose of data use and privacy protection), the user's response data is output. Specifically, consent is accepted when the user presses the "Agree" button on the displayed consent confirmation message.

[0437] Step 4: Offer incentives

[0438] The server will award local currency as an incentive to users who agree. Based on the consent confirmation result as input, points will be added to the user's account. As a result, "Points awarded: 100 local currency points" or similar will be output.

[0439] Step 5: Preprocessing the data

[0440] The server preprocesses the collected survey and behavioral data. Based on the raw data (survey data and behavioral data) as input, data cleansing and format conversion are performed, and a clean dataset is output. Specifically, this includes operations such as "removing invalid location records."

[0441] Step 6: Training the AI ​​model

[0442] The server trains a generative AI model based on the preprocessed data. Based on the clean data set as input, the AI ​​model is trained using algorithms such as neural networks. The result is a generative AI model that has learned specific patterns and tendencies.

[0443] Step 7: Avatar generation

[0444] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. Based on the generative AI model and the user's attribute data as input, an avatar with the user's unique behavioral patterns is output. Specifically, an avatar named "Office Worker A" is generated.

[0445] Step 8: Run the simulation

[0446] The server introduces the generated avatar into the digital twin environment and performs urban planning simulations. Specific urban planning scenarios are simulated based on the avatar and digital twin environment as input. Simulation data and the avatar's reactions are output as the result. For example, "usage patterns based on a new park installation scenario" are obtained.

[0447] Step 9: Analyze the simulation results

[0448] The server analyzes the simulation results and aggregates the needs of residents. Statistical analysis is performed based on the input simulation data, and aggregated needs data is output. Specifically, insights such as "parks in specific areas are frequently used" can be obtained.

[0449] Step 10: Urban Planning Proposal

[0450] Based on the analysis results, the server automatically generates an urban plan that meets the needs of residents and presents it to local government officials. Based on the analysis results as input, specific urban plans (e.g., the design and location of a new park) are output. As a result, a "proposal for the establishment of a central park" is provided to local government officials.

[0451] (Application example 1)

[0452] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0453] In modern urban planning and store management, it is important to create optimal plans that reflect the specific needs and behavioral patterns of residents and customers. However, traditional methods have difficulty fully incorporating the voices of residents and customers, and optimization of urban planning and store management has not reached a reasonable level. For this reason, there is a need for a system that can automatically generate plans and proposals that accurately reflect individual preferences and behavioral patterns based on resident and customer data.

[0454] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0455] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for training and operating a generation AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, and means for optimizing store layouts and product configurations. This enables optimal urban planning and store operations that reflect the specific needs and behavioral patterns of residents and customers.

[0456] "Resident" refers to an individual who resides in a particular area or city.

[0457] "Survey data" refers to data containing responses collected from residents and customers. The surveys include questions about living environments and product preferences.

[0458] "Behavioral data" refers to data that shows the behavioral patterns of residents and customers, such as GPS information, purchase history, and frequency of store visits.

[0459] "Generative AI" refers to an AI model that mimics a user's thoughts and actions based on collected data.

[0460] "Avatars" refer to virtual characters created by generative AI that mimic the characteristics of residents or customers.

[0461] A "digital twin" is a virtual reproduction of the physical world, used for simulation and prediction.

[0462] "Simulation" refers to the process of operating the generated avatar in a digital twin environment and observing its reactions and behavior under various conditions.

[0463] "Urban planning" refers to a plan to design the structure and functions of an entire city in order to improve the lives of its residents.

[0464] "Store layout" refers to the design of product placement and traffic flow within a physical store.

[0465] "Product mix" refers to determining the types and quantities of products to be sold in physical stores.

[0466] "Incentives" refers to rewards or benefits for providing data, including local currency and discount coupons.

[0467] "Statistical analysis" refers to analyzing collected data using statistical methods to extract meaningful information.

[0468] "Optimization" refers to adjusting a system or process to its optimum state in order to achieve a specific goal.

[0469] This invention automatically generates urban plans and store layouts tailored to individual preferences by collecting data on residents and customers, using generative AI to generate avatars that mimic the thoughts of residents and customers, and conducting simulations in a digital twin environment. This system is specifically implemented as follows.

[0470] Data collection

[0471] Users answer a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, product preferences, and store layout. This allows the collection of survey data.

[0472] Next, the device collects behavioral data about the daily lives of residents and customers, such as GPS data from smartwatches and smartphones, store visit history, purchase history, and product browsing history. This behavioral data is then sent to a server.

[0473] Consent confirmation and incentive provision

[0474] The server sends a confirmation message to the device to obtain consent for data provision. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is accepted.

[0475] The server will provide local currency or discount coupons as incentives to residents and customers who agree to participate in the data provision.

[0476] Training generative AI models

[0477] The server preprocesses the collected survey data and behavioral data, cleansing and formatting the data, and then trains a generative AI model based on this data. Specifically, GPT-4 is used as the generative AI model, and it learns user behavioral patterns and preferences.

[0478] Avatar generation

[0479] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. This avatar is created based on the user's attributes and behavioral patterns. For example, the server can input a prompt such as, "Customer A likes electronic devices and gadgets, and is particularly interested in the latest smartphone accessories. He frequently visits stores on weekends and enjoys looking at the new product display area."

[0480] Simulation on a digital twin

[0481] The server then introduces the generated avatar into the digital twin environment and performs a simulation. During the simulation, the avatar's reactions and behavior are observed and data is collected. Unity and Siemens' MindSphere are used as digital twin platforms.

[0482] Proposals for optimizing urban planning and store operations

[0483] The server analyzes the simulation results and aggregates the opinions and preferences of residents and customers. Based on this, the system automatically generates urban plans and store layouts that meet the needs of residents and customers. For example, it proposes optimal layouts and product configurations to store operators, so that the latest smartphone accessories are displayed in prominent locations.

[0484] Specific examples

[0485] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents fill out a survey and collect GPS data, revealing behavioral patterns such as the routes they usually take and which facilities they use. Next, generative AI is used to generate avatars that mimic each resident's behavioral patterns and preferences for parks, and a simulation of the park's establishment is carried out on the digital twin. The system can also be applied to store customization; for example, customer behavior can be simulated based on survey results and behavioral data to propose optimal store layouts. This specific example will enable attractive urban planning and store management that reflects the opinions of residents and customers.

[0486] This will enable optimal urban planning and store management that reflects the specific needs and behavioral patterns of residents and customers.

[0487] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0488] Step 1:

[0489] Users answer the questionnaire using a smartphone or PC. The input is the user's questionnaire response, and the output is the collected questionnaire data. The questionnaire includes questions about living environment, product preferences, and store layout. The device sends this data to the server.

[0490] Step 2:

[0491] The device collects behavioral data about the user's daily life through a smartwatch or smartphone. Specifically, this includes GPS data, store visit history, purchase history, and product browsing history. This behavioral data is sent to a server. The input is the user's behavioral data, and the output is the collected behavioral data.

[0492] Step 3:

[0493] The server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in response to the consent confirmation message displayed on the terminal, consent is accepted. The input is the consent confirmation message, and the output is the user's consent status. If consent is given, the server grants the user local currency or discount coupons as an incentive.

[0494] Step 4:

[0495] The server preprocesses the collected survey and behavioral data, cleansing and formatting the data. The input is the survey and behavioral data, and the output is the preprocessed data. Based on this preprocessed data, the server trains a generative AI model (e.g., GPT-4).

[0496] Step 5:

[0497] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. The input is preprocessed data, and the output is the generated avatar. The server generates an avatar based on a prompt statement, such as, "Customer A likes electronic devices and gadgets, and is particularly interested in the latest smartphone accessories. He frequently visits stores on weekends and enjoys looking at the new product display area."

[0498] Step 6:

[0499] The server introduces the generated avatar into the digital twin environment and performs a simulation. Specific behaviors include how the avatar moves around the store and which areas it shows interest in. The input is the generated avatar, and the output is the simulation results. Unity and Siemens' MindSphere are used as digital twin platforms.

[0500] Step 7:

[0501] The server performs analysis based on the simulation results. Statistical methods are used to analyze the simulation results and aggregate the needs of residents and customers. The input is the simulation results, and the output is the analysis results. Based on these analysis results, the server proposes optimal layouts and product configurations to store operators.

[0502] Step 8:

[0503] The server automatically generates specific city planning and store operation optimization plans based on the analysis and simulation results. The input is the analysis results, and the output is an optimized city planning and store layout proposal. For example, it can propose a layout in which the latest smartphone accessories are placed in a prominent location.

[0504] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0505] This invention collects data on residents, generates avatars that mimic the thoughts and emotions of residents using generative AI and an emotion engine, and then performs simulations in a digital twin environment to automatically generate urban plans that are tailored to individual emotions and preferences. This system is specifically implemented as follows.

[0506] Data collection

[0507] First, the user answers a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and emotional changes in daily life. Once the answers are complete, the questionnaire data is sent to the server.

[0508] Next, the device collects behavioral data related to the user's daily life. For example, GPS data from a smartwatch or smartphone is used to collect data on the user's commute route and the facilities they use. Sensors installed in the smartphone or wearable device are also used to monitor the user's heart rate and facial expressions, collecting emotional data. This behavioral data and emotional data are then sent to a server.

[0509] Consent confirmation and incentive provision

[0510] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information for which consent has been obtained is stored on the server.

[0511] The server will provide local currency as an incentive to users who agree. The server will check the user's data provision history and add the necessary local currency to the user's account.

[0512] Training generative AI models and emotion engines

[0513] The server then preprocesses the collected survey data, behavioral data, and emotional data. The data is cleansed and formatted, and then used to train a generative AI model and an emotional engine. The generative AI model is used to mimic residents' thinking and behavior patterns, and the emotional engine is used to evaluate the user's emotional state.

[0514] Avatar generation

[0515] The server uses a trained generative AI model and emotion engine to generate an avatar based on the user's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the thoughts, actions, and emotions of the resident.

[0516] Simulation on a digital twin

[0517] The server then introduces the generated avatar into the digital twin environment and conducts a simulation, observing the avatar's reactions, behavior, and emotional changes, and collecting the simulation results as data.

[0518] Urban planning proposals

[0519] The server performs an analysis based on the simulation results. Statistical methods are used to aggregate residents' opinions, preferences, and emotional states, and the analyzed data is used to identify residents' needs. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0520] Specific examples

[0521] For example, this system could be used when considering the establishment of a new public park. Residents fill out a survey and GPS and emotional data are collected to determine the routes they typically take, the facilities they use, and the emotions they feel when they do. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, and a simulation of the park's construction is run on the digital twin.

[0522] The simulation results showed that many residents use parks on weekends and feel positive emotions in the process, and that certain areas are used frequently and have high emotional satisfaction. Based on this, the system proposes new park locations and designs that match the needs and emotions of residents. This specific example will realize livable urban planning that reflects the opinions and emotions of residents.

[0523] The processing flow will be explained below.

[0524] Step 1:

[0525] Users answer a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and emotional changes in daily life. Once the questionnaire is completed, the data is sent to the server.

[0526] Step 2:

[0527] The device collects behavioral data related to the user's daily life. For example, GPS data from a smartwatch or smartphone is used to collect data on the user's commute route and the facilities they use. Sensors installed in the smartphone or wearable device are also used to monitor the user's heart rate and facial expressions, and to collect emotional data. The collected behavioral and emotional data is sent to a server.

[0528] Step 3:

[0529] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information for which consent has been obtained is stored on the server.

[0530] Step 4:

[0531] The server will grant local currency as an incentive to users who agree. The server will grant local currency by checking the user's data provision history and adding the necessary local currency to the user's account.

[0532] Step 5:

[0533] The server preprocesses the collected survey data, behavioral data, and sentiment data. Data cleansing and format conversion are performed. The preprocessed data is used as training data for the generative AI model and sentiment engine.

[0534] Step 6:

[0535] The server trains the generative AI model and emotion engine based on the preprocessed data. The generative AI model imitates the residents' thought patterns and behavior patterns, and the emotion engine evaluates the user's emotional state.

[0536] Step 7:

[0537] The server uses the trained generative AI model and emotion engine to generate an avatar based on the user's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the thoughts, actions, and emotions of the resident.

[0538] Step 8:

[0539] The server then introduces the generated avatar into the digital twin environment and conducts a simulation, during which the avatar's reactions, behavior, and emotional changes are observed and collected.

[0540] Step 9:

[0541] The server analyzes the simulation results, using statistical methods to aggregate residents' opinions, preferences, and emotional states, and extracts residents' needs based on the analyzed data.

[0542] Step 10:

[0543] The server automatically generates an urban plan that is in line with the residents' opinions and emotions based on the extracted needs and emotional states. The generated urban plan is then presented to local government officials for final review and adjustment.

[0544] Specific examples

[0545] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents respond to a survey and GPS and emotional data are collected to determine the routes they take, the facilities they use, and the emotions they feel when doing so. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, and a simulation of the park's establishment is run on the digital twin. The simulation results show that many residents use the park on weekends and experience positive emotions while doing so, and that certain areas are frequently used and provide high emotional satisfaction. Based on this, the system can propose the location and design of the new park to match the residents' needs and emotions. This specific example will realize livable urban planning that reflects the opinions and emotions of residents.

[0546] Example 2

[0547] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0548] In modern urban planning, it is extremely important to effectively reflect the opinions and feelings of residents. However, conventional methods often rely on one-sided approaches based on quantitative data, which have the problem of not fully reflecting the diverse thoughts and feelings of residents. Furthermore, when it comes to collecting data from residents, there is a lack of motivation for them to actively provide it, making it difficult to collect accurate and abundant data. There is a need for a system that can solve these issues and realize urban planning that effectively reflects the opinions and feelings of residents.

[0549] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting questionnaire data from residents, means for collecting behavioral data and emotional data from residents, and means for training and operating a generation AI and emotion engine that generates avatars that mimic the thoughts and emotions of residents based on the collected questionnaire data, behavioral data, and emotional data. This makes it possible to effectively collect and analyze data including the diverse opinions and emotions of residents and automatically generate urban plans that match the emotions and preferences of each resident.

[0550] "Survey data" refers to data containing the contents of questionnaires answered by residents, including information on living environment, means of transportation, favorite parks and facilities, and emotional changes in daily life.

[0551] "Behavioral data" refers to data that shows residents' daily activities, including GPS data from smartwatches and smartphones, commuting routes, and usage of facilities.

[0552] "Emotion data" is data that indicates the emotional state of the resident, and includes heart rate data and facial expression recognition data.

[0553] "Generative AI" refers to an artificial intelligence model that mimics the thought and behavior patterns of residents based on collected data.

[0554] An "emotion engine" is a processing device or algorithm that evaluates the emotional state of residents based on collected emotional data.

[0555] "Avatars" are virtual human models that use generative AI and emotion engines to mimic the attributes, behavioral patterns, and emotional states of residents.

[0556] A "digital twin" is a simulated environment that virtually recreates a real urban environment and is used to observe the reactions and behavior of avatars.

[0557] "Simulation results" are data that show the results of observing and analyzing changes in the behavior and emotions of avatars in a digital twin environment.

[0558] "Means for automatically generating urban plans" refers to devices or software that aggregate residents' opinions, preferences, and emotional states based on simulation results, and then generate urban plans that meet the residents' needs based on the analyzed data.

[0559] "Confirmation means for obtaining consent to data provision" refers to the interface and process for confirming whether residents agree to provide their data, and may include consent confirmation messages and "Agree" buttons.

[0560] "Means for granting local currency" refers to a system that electronically grants local currency as an incentive to consenting residents.

[0561] "Statistical analysis means" refers to the process and algorithms for analyzing the simulation results using statistical methods and aggregating the opinions and emotional states of residents.

[0562] "Means of aggregating residents' needs" refers to systems and processes for organizing the diverse opinions and feelings of residents based on the results of statistical analysis and aggregating them into centralized data.

[0563] MODE FOR CARRYING OUT THE INVENTION

[0564] The present invention is a system that automatically generates urban plans tailored to individual emotions and preferences by collecting data on residents, generating avatars that mimic the residents' thoughts and emotions using a generative AI model and an emotion engine, and running simulations in a digital twin environment. This system is specifically implemented as follows.

[0565] Data collection

[0566] Users answer a questionnaire using a smartphone or personal computer (PC). The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and daily emotional changes. Once the user completes the questionnaire, the data is sent to the server.

[0567] The device collects behavioral data related to the user's daily life using the GPS of the smartwatch or smartphone, and collects emotional data using sensors installed in the smartphone or wearable device to monitor heart rate and facial expressions, which are also transmitted to the server.

[0568] Consent confirmation and incentive provision

[0569] The server sends a consent confirmation message regarding data provision to the terminal, and the user obtains consent by pressing the "Agree" button in response to the consent confirmation message. The consent information is stored on the server. The server grants local currency as an incentive to users who agree to data provision. The procedure for granting local currency is carried out by the server checking the user's data provision history and adding the required local currency to the user's account.

[0570] Training generative AI models and emotion engines

[0571] The server preprocesses the collected survey data, behavioral data, and emotional data. It cleanses the data, fills in missing data, and converts the data format. It then trains a generative AI model and an emotion engine based on the preprocessed data. The generative AI model is used to mimic residents' thinking and behavioral patterns, and the emotion engine is used to evaluate the user's emotional state.

[0572] Avatar generation

[0573] The server uses a trained generative AI model and emotion engine to generate an avatar based on each user's attributes, behavioral patterns, and emotional state. This avatar is a virtual person model that mimics the thoughts, actions, and even emotions of the resident.

[0574] Simulation in a digital twin environment

[0575] The server then introduces the generated avatar into a digital twin environment and conducts a simulation. The digital twin environment is a virtual reproduction of an actual urban environment, allowing users to observe the avatar's reactions, behavior, and emotional changes. The server then collects and analyzes the data obtained from this simulation.

[0576] Urban planning proposals

[0577] Based on the simulation results, the server uses statistical methods to aggregate residents' opinions, preferences, and emotional states, and extracts residents' needs from the analyzed data. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0578] Specific examples

[0579] For example, this system can be used when considering the establishment of a new public park. Residents respond to a survey and GPS and emotional data are collected, revealing the routes they take, the facilities they use, and the emotions they feel when they do. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, allowing simulations of park establishment to be conducted on the digital twin. If the simulation results show that a particular area is frequently used and emotionally satisfying, a proposal to establish a new park in that area can be made.

[0580] Prompt Sentence Examples

[0581] For example, a prompt to suggest the best location for a new public facility might look like this:

[0582] Based on the following data, suggest the best location and design for a new public park.

[0583] 1. Resident survey response data

[0584] 2. GPS-based behavioral data

[0585] 3. Collected emotional data

[0586] Based on the above data, please simulate and propose the location and design of the park that will most satisfy the residents.

[0587] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0588] Step 1:

[0589] Users answer a questionnaire using a smartphone or personal computer (PC). The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and daily emotional changes. Once the user completes the questionnaire, the data is sent from the device to the server.

[0590] Input: User survey response data

[0591] Output: Survey data sent to the server

[0592] Step 2:

[0593] The device collects behavioral data related to the user's daily life using the GPS of the smartwatch or smartphone, and collects emotional data using sensors installed in the smartphone or wearable device to monitor heart rate and facial expressions, which are also transmitted to the server.

[0594] Input: Behavioral and emotional data from smartwatches, smartphones, and wearable devices

[0595] Output: Behavioral and emotional data sent to the server

[0596] Step 3:

[0597] The server sends a consent confirmation message regarding data provision to the terminal, and the user consents by pressing the "Agree" button in response to the displayed consent confirmation message. The consent information is stored on the server.

[0598] Input: Consent confirmation message

[0599] Output: The consent information is saved on the server.

[0600] Step 4:

[0601] The server will grant local currency as an incentive to users who agree. The procedure for granting local currency is carried out by the server checking the user's data provision history and adding the necessary local currency to the user's account.

[0602] Input: User data provision history, consent information

[0603] Output: The local currency is added to the user's account

[0604] Step 5:

[0605] The server preprocesses the collected survey data, behavioral data, and sentiment data, cleansing the data, filling in missing data, and converting formats, and then trains the generative AI model and sentiment engine based on the preprocessed data.

[0606] Input: Survey data, behavioral data, emotional data

[0607] Output: Pre-processed data, trained generative AI model and emotion engine

[0608] Step 6:

[0609] The server uses a trained generative AI model and emotion engine to generate an avatar based on each user's attributes, behavioral patterns, and emotional state. This avatar is a virtual person model that mimics the thoughts, actions, and even emotions of the resident.

[0610] Input: Trained generative AI model and emotion engine, pre-processed data

[0611] Output: An avatar that mimics the user's attributes, behavioral patterns, and emotional state

[0612] Step 7:

[0613] The server then introduces the generated avatar into a digital twin environment and conducts a simulation. The digital twin environment is a virtual reproduction of an actual urban environment, allowing users to observe the avatar's reactions, behavior, and emotional changes. The server then collects and analyzes the data obtained from this simulation.

[0614] Input: Generated avatar

[0615] Output: Simulation result data

[0616] Step 8:

[0617] The server uses statistical methods to analyze residents' opinions, preferences, and emotional states based on the simulation results, and extracts residents' needs from the analyzed data. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0618] Input: Simulation result data

[0619] Output: Proposal of urban planning that reflects the needs of residents

[0620] (Application example 2)

[0621] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0622] In modern logistics facilities, work efficiency and worker satisfaction are important factors that directly affect facility productivity and worker safety. However, methods for optimizing these have not yet been established, and in particular, there is no system that reflects worker emotions and behavioral patterns. Therefore, there is a need to achieve both an efficient work environment and worker satisfaction in logistics facilities.

[0623] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0624] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for training and operating a generation AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, means for generating avatars that mimic the behavioral patterns and emotional states of workers and evaluating the optimization of work efficiency and work satisfaction at logistics facilities, means for analyzing the avatars' responses and behavioral patterns and generating proposals to support efficiency improvements at logistics facilities, and means for making proposals to improve the work environment based on the avatar simulation results.This makes it possible to maximize work efficiency in logistics facilities and create an optimal work environment that takes into account the emotions and satisfaction of workers.

[0625] "Survey data" refers to data containing subjective information provided by users about their living environment, means of transportation, daily activities, etc.

[0626] "Behavioral data" refers to objectively observed data that includes a user's daily behavior, location information, and physiological data such as heart rate and facial expressions.

[0627] "Generative AI" is artificial intelligence that generates avatars that mimic the user's thought and behavior patterns based on collected survey data and behavioral data.

[0628] A "digital twin" is a digital model that recreates physical world objects or systems in a virtual environment and is used for simulation and analysis.

[0629] The "simulation results" are the data collected by observing the behavior and reactions of avatars created in a digital twin environment.

[0630] "Urban planning" involves proposing the optimal layout and design of living spaces and infrastructure based on resident survey data, behavioral data, and simulation results.

[0631] "Worker" means a person engaged in work within a logistics facility.

[0632] "Work efficiency" is an indicator of how effectively and quickly work is carried out within a logistics facility.

[0633] "Labor satisfaction" is an indicator that shows how satisfied a worker is with their working environment and work content.

[0634] "Efficiency proposals" are specific proposals based on simulation results to improve work efficiency within logistics facilities.

[0635] "Improvement proposals" are proposals based on the simulation results with the aim of improving the working environment.

[0636] The present invention is a system for improving work efficiency and worker satisfaction within a logistics facility. This system is composed of multiple components, each of which works together to optimize the work environment.

[0637] Data collection

[0638] First, a device (such as a smartphone or robot) collects survey data from the user. The survey includes questions about the user's work environment, transportation, and daily activities. The collected data is then sent to a server.

[0639] Next, the device collects behavioral data related to the worker's daily work. For example, GPS data from smartphones and data from sensors installed in logistics facilities are used to collect data on the worker's location and movements. Sensors in smartwatches and smartphones are also used to collect emotional data such as heart rate and facial expressions. This data is also sent to the server.

[0640] Consent confirmation and incentive provision

[0641] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information regarding consent is stored on the server. The server grants local currency as an incentive to users who consent. This local currency is granted by the server by checking the user's data provision history and adding the appropriate amount to the user's account.

[0642] Training generative AI models and emotion engines

[0643] Next, the server preprocesses the collected survey data, behavioral data, and emotion data. Python is used to cleanse and format the data. Based on the preprocessed data, a generative AI model and emotion engine are trained using TensorFlow and Keras. The generative AI model is used to imitate the worker's thought patterns and behavioral patterns, and the emotion engine is used to evaluate the worker's emotional state.

[0644] Avatar generation

[0645] The server uses a trained generative AI model and emotion engine to generate an avatar based on the worker's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the worker's thoughts, actions, and emotions. Blender is used to generate a detailed model of the avatar.

[0646] Simulation on a digital twin

[0647] The server then introduces the generated avatar into the digital twin environment and runs a simulation using a Python program. During the simulation, the avatar's reactions, behavior, and emotional changes are observed, and the simulation results are collected as data.

[0648] Efficiency and improvement proposals

[0649] Based on the simulation results, the server automatically generates improvement proposals to maximize work efficiency and worker satisfaction at the logistics facility. Statistical methods are used to analyze the simulation results, and suggestions for improving the work environment are made based on data that aggregates the needs and emotional states of workers. These suggestions are then presented to the logistics facility's management for final review and adjustment.

[0650] Specific examples

[0651] For example, this system can be used when introducing a new logistics system. Workers fill out a questionnaire and GPS data, heart rate data, and facial expression data are collected to identify which work areas are most stressful and where work flow needs to be optimized. Next, generative AI and an emotion engine are used to generate avatars that mimic each worker's behavioral patterns and emotions, and simulations are run on the digital twin.

[0652] The simulation results show that many workers feel stressed in certain work areas and that improvements to traffic flow are necessary. Based on this, it is possible to propose improvements to the work environment of logistics facilities that are tailored to the needs and emotions of workers.

[0653] Example prompt sentence:

[0654] "Based on your work patterns and emotional data from the past week, we suggest the most efficient and least stressful work flow."

[0655] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0656] Step 1:

[0657] The server collects survey data from users. Users answer the survey using their smartphones or PCs and send the results to the server. The survey includes questions about living environment, transportation, and daily activities. The input is the survey response data from the users, and the output is the survey data stored on the server.

[0658] Step 2:

[0659] The device collects behavioral and emotional data related to the worker's daily work. It collects location information and movement data from the smartphone's GPS data and sensors installed in the logistics facility, and also obtains data such as the user's heart rate and facial expression. This data is sent to a server. The input is the user's behavioral and emotional data, and the output is the behavioral and emotional data stored on the server.

[0660] Step 3:

[0661] The server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in response to the consent confirmation message displayed on the terminal screen, consent is obtained and stored on the server. The server grants local currency as an incentive to users who consent. The input is the user's consent data, and the output is the consent data stored on the server and the granted local currency.

[0662] Step 4:

[0663] The server preprocesses the collected survey data, behavioral data, and sentiment data. It uses Python to cleanse and format the data, making it suitable for machine learning. The input is the collected raw data, and the output is the preprocessed dataset.

[0664] Step 5:

[0665] The server uses the preprocessed data to train a generative AI model and emotion engine using TensorFlow and Keras. The generative AI model imitates the worker's thought patterns and behavior patterns, and the emotion engine evaluates the worker's emotional state. The input is the preprocessed dataset, and the output is the trained generative AI model and emotion engine.

[0666] Step 6:

[0667] The server uses a trained generative AI model and an emotion engine to generate an avatar based on the worker's attributes, behavioral patterns, and emotional state. Blender is used to create detailed avatar models. The input is the trained generative AI model and the emotion engine, and the output is the generated avatar.

[0668] Step 7:

[0669] The server introduces the generated avatar into the digital twin environment and performs a simulation. A Python program is used to check the avatar's behavior and emotional changes, and the results are collected as data. The input is the generated avatar, and the output is the simulation results.

[0670] Step 8:

[0671] The server statistically analyzes the simulation results and automatically generates improvement proposals to maximize work efficiency and labor satisfaction at logistics facilities. Based on the simulation results, it aggregates the needs and emotional states of workers and proposes improvements to the work environment. The input is the simulation result data, and the output is an improvement proposal.

[0672] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0673] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0674] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0675] [Third embodiment]

[0676] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0677] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0678] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0679] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0680] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0681] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0682] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0683] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0684] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0685] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0686] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0687] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0688] The present invention automatically generates urban plans tailored to individual preferences by collecting data on residents, using generative AI to generate avatars that mimic the residents' thoughts, and conducting simulations in a digital twin environment. This system is specifically implemented as follows.

[0689] Data collection

[0690] First, users answer a questionnaire using their smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, etc. This allows the collection of survey data.

[0691] Next, the device collects behavioral data about the resident's daily life. For example, GPS data from a smartwatch or smartphone is used to obtain data on the commute route and facilities used. This behavioral data is then sent to a server.

[0692] Consent confirmation and incentive provision

[0693] The server sends a confirmation message to the device to obtain consent for data provision. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is accepted.

[0694] The server will provide local currency as an incentive to users who agree to participate, encouraging them to actively participate in providing data.

[0695] Training generative AI models

[0696] The server then preprocesses the collected survey and behavioral data, cleansing and formatting it, and uses it to train a generative AI model.

[0697] Avatar generation

[0698] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts, based on the user's attributes and behavioral patterns.

[0699] Simulation on a digital twin

[0700] The server then introduces the generated avatar into the digital twin environment and runs a simulation, observing the avatar's reactions and behavior and collecting data.

[0701] Urban planning proposals

[0702] The server analyzes the simulation results and collects the opinions and preferences of residents. Based on this, an urban plan that meets the needs of residents is automatically generated. The generated urban plan is then presented to local government officials.

[0703] Specific examples

[0704] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents fill out a survey and GPS data is collected to identify their behavioral patterns, such as the routes they usually take and the facilities they use. Next, generative AI is used to create avatars that mimic each resident's behavioral patterns and park preferences, and a simulation of the park's establishment is run on the digital twin.

[0705] The simulation results showed that many residents use parks on weekends and that certain areas are more frequently used, and based on this, the system proposed the location and design of new parks to meet the needs of residents. This concrete example will realize attractive urban planning that reflects the opinions of residents.

[0706] The processing flow will be explained below.

[0707] Step 1:

[0708] Users answer the questionnaire using their smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, etc. Once the answers are completed, the questionnaire data is sent to the server.

[0709] Step 2:

[0710] The device collects behavioral data related to the user's daily life. Specifically, it acquires GPS data from smartwatches and smartphones, and collects data on the user's commute route and the public facilities they use. The collected behavioral data is sent to a server.

[0711] Step 3:

[0712] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message, consent is obtained. The information for which consent has been obtained is stored on the server.

[0713] Step 4:

[0714] The server will grant local currency as an incentive to users who agree. The server will grant local currency by checking the user's data provision history and adding the necessary local currency to the user's account.

[0715] Step 5:

[0716] The server preprocesses the collected survey and behavioral data, cleansing and formatting the data, and uses the preprocessed data as training data for the generative AI model.

[0717] Step 6:

[0718] The server trains a generative AI model based on the preprocessed data, which is then used to mimic the thinking and behavior patterns of residents.

[0719] Step 7:

[0720] The server uses a trained generative AI model to generate an avatar based on the user's attributes and behavioral patterns. This avatar is a virtual human model that mimics the thoughts and behavior of the resident.

[0721] Step 8:

[0722] The server then introduces the generated avatar into the digital twin environment and performs a simulation, observing the avatar's reactions and behavior and collecting the simulation results as data.

[0723] Step 9:

[0724] The server analyzes the simulation results, aggregates residents' opinions and preferences using statistical methods, and extracts residents' needs based on the analyzed data.

[0725] Step 10:

[0726] The server automatically generates an urban plan based on the needs extracted and in line with the opinions of residents. The generated urban plan is then presented to local government officials for final review and adjustment.

[0727] Example 1

[0728] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0729] Conventional urban planning often fails to adequately reflect residents' opinions and preferences. Furthermore, there is a lack of methods for integrating and utilizing residents' behavioral patterns and daily mobility data, resulting in plans that often deviate from residents' actual needs. To solve this problem, a method is needed to efficiently collect survey data and behavioral data, use generative AI to generate avatars that mimic residents' thoughts, and simulate them in a digital twin environment.

[0730] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0731] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for cleansing and formatting the collected survey data and behavioral data, and means for training and operating a generation AI that generates avatars that mimic the thinking of residents, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, and means for presenting the urban plans to local government officials. This enables the automatic generation of advanced urban plans that reflect the opinions and behavioral patterns of residents.

[0732] "Residents" refers to ordinary people who live in a city or region.

[0733] "Survey data" refers to response data collected from residents regarding their living environment, means of transportation, and facility usage.

[0734] "Behavioral data" refers to location and behavioral information collected from devices such as smartphones and smartwatches, such as residents' routes and destinations in their daily lives.

[0735] "Generative AI" refers to artificial intelligence that generates avatars that mimic the thinking and behavior patterns of residents based on collected data.

[0736] "Cleansing" is a data preprocessing process that removes inaccurate or missing data and improves data quality.

[0737] "Format conversion" refers to the process of converting collected data into a format that can be used by generative AI models.

[0738] An "avatar" is a digital representative that mimics the characteristics and behavioral patterns of a resident.

[0739] A "digital twin environment" refers to a virtual environment that digitally recreates a specific location or system in the real world.

[0740] "Simulation" refers to a method of conducting virtual experiments in a digital twin environment using a generated avatar and analyzing the results.

[0741] "Urban planning" refers to the act or content of designing and planning the layout of infrastructure and facilities in a local community to improve the living environment of residents.

[0742] "Municipal officials" refer to local government officials in charge of urban planning and local resident services.

[0743] "Incentives" refers to incentives, particularly rewards such as local currency, given to encourage residents to provide data.

[0744] The present invention automatically generates urban plans tailored to individual preferences by collecting data on residents, using generative AI to generate avatars that mimic the residents' thoughts, and conducting simulations in a digital twin environment. This invention is specifically implemented as follows.

[0745] First, the user answers a questionnaire using a smartphone or PC about their living environment, transportation, favorite parks and facilities, etc. This collects the survey data. Next, the device uses GPS data from the smartwatch or smartphone to collect behavioral data about the user's daily life and sends it to the server.

[0746] Next, the server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in the consent confirmation message, consent is accepted. The server awards local currency as an incentive to users who consent. This encourages residents to actively participate in data provision.

[0747] The server then preprocesses the collected survey and behavioral data. This preprocessing step involves data cleansing and formatting. Cleansing removes inaccurate or missing data, while formatting converts the data into a format suitable for AI models.

[0748] The server then uses the pre-processed data to train a generative AI model, which uses state-of-the-art neural network technology to learn residents' behavioral patterns and preferences.

[0749] Once training is complete, the server uses the generative AI model to generate an avatar that mimics the user's thoughts and behaviors, creating a digital representation of the user's characteristics.

[0750] Next, the avatar generated by the server is introduced into the digital twin environment, and simulations such as urban planning are carried out. Through this simulation, the avatar's behavior and reactions are observed, and the simulation results are collected as data.

[0751] Finally, the server automatically generates an urban plan based on the simulation results. The simulation results are statistically analyzed and residents' needs are summarized based on this. The generated urban plan is presented to local government officials and developed into a concrete plan.

[0752] Specific examples

[0753] For example, this system can be used when considering the establishment of a new public park in a certain area. Users respond to a questionnaire and GPS data is collected, revealing behavioral patterns such as the routes residents usually take and the facilities they use. Next, generative AI is used to create avatars that mimic each resident's behavioral patterns and preferences for parks, and a simulation of the park's establishment is carried out in a digital twin environment. The simulation results show that many residents use the park on weekends and that certain areas are used frequently, and based on this, the system proposes the location and design of the park.

[0754] Prompt Sentence Examples

[0755] "Based on user survey data and GPS data, use a generative AI model to generate avatars that mimic the thoughts of residents, and simulate the installation of a new public park in a digital twin environment."

[0756] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0757] Step 1: Conduct a survey

[0758] Users use their smartphones or PCs to answer a questionnaire about their living environment, transportation, and favorite parks and facilities. Based on the survey questions they input (e.g., "Which is the nearest park?" and "What is your usual mode of transportation?"), the system outputs the user's response data. Specifically, data such as "Most favorite park: Central Park" and "Method of commuting: Bicycle" are collected.

[0759] Step 2: Collect behavioral data

[0760] The device uses GPS data from a smartwatch or smartphone to record the user's daily travel routes, visited destinations, and other behavioral data. The user's travel patterns are output based on input location information (e.g., GPS data with time stamps). For example, data such as "Leaving home (location information) at 8 a.m. and arriving at office (location information) at 9 a.m." is collected.

[0761] Step 3: Confirm consent

[0762] The server sends a consent confirmation message regarding data provision to the terminal. Based on the input consent confirmation message (e.g., information about the purpose of data use and privacy protection), the user's response data is output. Specifically, consent is accepted when the user presses the "Agree" button on the displayed consent confirmation message.

[0763] Step 4: Offer incentives

[0764] The server will award local currency as an incentive to users who agree. Based on the consent confirmation result as input, points will be added to the user's account. As a result, "Points awarded: 100 local currency points" or similar will be output.

[0765] Step 5: Preprocessing the data

[0766] The server preprocesses the collected survey and behavioral data. Based on the raw data (survey data and behavioral data) as input, data cleansing and format conversion are performed, and a clean dataset is output. Specifically, this includes operations such as "removing invalid location records."

[0767] Step 6: Training the AI ​​model

[0768] The server trains a generative AI model based on the preprocessed data. Based on the clean data set as input, the AI ​​model is trained using algorithms such as neural networks. The result is a generative AI model that has learned specific patterns and tendencies.

[0769] Step 7: Avatar generation

[0770] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. Based on the generative AI model and the user's attribute data as input, an avatar with the user's unique behavioral patterns is output. Specifically, an avatar named "Office Worker A" is generated.

[0771] Step 8: Run the simulation

[0772] The server introduces the generated avatar into the digital twin environment and performs urban planning simulations. Specific urban planning scenarios are simulated based on the avatar and digital twin environment as input. Simulation data and the avatar's reactions are output as the result. For example, "usage patterns based on a new park installation scenario" are obtained.

[0773] Step 9: Analyze the simulation results

[0774] The server analyzes the simulation results and aggregates the needs of residents. Statistical analysis is performed based on the input simulation data, and aggregated needs data is output. Specifically, insights such as "parks in specific areas are frequently used" can be obtained.

[0775] Step 10: Urban Planning Proposal

[0776] Based on the analysis results, the server automatically generates an urban plan that meets the needs of residents and presents it to local government officials. Based on the analysis results as input, specific urban plans (e.g., the design and location of a new park) are output. As a result, a "proposal for the establishment of a central park" is provided to local government officials.

[0777] (Application example 1)

[0778] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0779] In modern urban planning and store management, it is important to create optimal plans that reflect the specific needs and behavioral patterns of residents and customers. However, traditional methods have difficulty fully incorporating the voices of residents and customers, and optimization of urban planning and store management has not reached a reasonable level. For this reason, there is a need for a system that can automatically generate plans and proposals that accurately reflect individual preferences and behavioral patterns based on resident and customer data.

[0780] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0781] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for training and operating a generation AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, and means for optimizing store layouts and product configurations. This enables optimal urban planning and store operations that reflect the specific needs and behavioral patterns of residents and customers.

[0782] "Resident" refers to an individual who resides in a particular area or city.

[0783] "Survey data" refers to data containing responses collected from residents and customers. The surveys include questions about living environments and product preferences.

[0784] "Behavioral data" refers to data that shows the behavioral patterns of residents and customers, such as GPS information, purchase history, and frequency of store visits.

[0785] "Generative AI" refers to an AI model that mimics a user's thoughts and actions based on collected data.

[0786] "Avatars" refer to virtual characters created by generative AI that mimic the characteristics of residents or customers.

[0787] A "digital twin" is a virtual reproduction of the physical world, used for simulation and prediction.

[0788] "Simulation" refers to the process of operating the generated avatar in a digital twin environment and observing its reactions and behavior under various conditions.

[0789] "Urban planning" refers to a plan to design the structure and functions of an entire city in order to improve the lives of its residents.

[0790] "Store layout" refers to the design of product placement and traffic flow within a physical store.

[0791] "Product mix" refers to determining the types and quantities of products to be sold in physical stores.

[0792] "Incentives" refers to rewards or benefits for providing data, including local currency and discount coupons.

[0793] "Statistical analysis" refers to analyzing collected data using statistical methods to extract meaningful information.

[0794] "Optimization" refers to adjusting a system or process to its optimum state in order to achieve a specific goal.

[0795] This invention automatically generates urban plans and store layouts tailored to individual preferences by collecting data on residents and customers, using generative AI to generate avatars that mimic the thoughts of residents and customers, and conducting simulations in a digital twin environment. This system is specifically implemented as follows.

[0796] Data collection

[0797] Users answer a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, product preferences, and store layout. This allows the collection of survey data.

[0798] Next, the device collects behavioral data about the daily lives of residents and customers, such as GPS data from smartwatches and smartphones, store visit history, purchase history, and product browsing history. This behavioral data is then sent to a server.

[0799] Consent confirmation and incentive provision

[0800] The server sends a confirmation message to the device to obtain consent for data provision. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is accepted.

[0801] The server will provide local currency or discount coupons as incentives to residents and customers who agree to participate in the data provision.

[0802] Training generative AI models

[0803] The server preprocesses the collected survey data and behavioral data, cleansing and formatting the data, and then trains a generative AI model based on this data. Specifically, GPT-4 is used as the generative AI model, and it learns user behavioral patterns and preferences.

[0804] Avatar generation

[0805] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. This avatar is created based on the user's attributes and behavioral patterns. For example, the server can input a prompt such as, "Customer A likes electronic devices and gadgets, and is particularly interested in the latest smartphone accessories. He frequently visits stores on weekends and enjoys looking at the new product display area."

[0806] Simulation on a digital twin

[0807] The server then introduces the generated avatar into the digital twin environment and performs a simulation. During the simulation, the avatar's reactions and behavior are observed and data is collected. Unity and Siemens' MindSphere are used as digital twin platforms.

[0808] Proposals for optimizing urban planning and store operations

[0809] The server analyzes the simulation results and aggregates the opinions and preferences of residents and customers. Based on this, the system automatically generates urban plans and store layouts that meet the needs of residents and customers. For example, it proposes optimal layouts and product configurations to store operators, so that the latest smartphone accessories are displayed in prominent locations.

[0810] Specific examples

[0811] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents fill out a survey and collect GPS data, revealing behavioral patterns such as the routes they usually take and which facilities they use. Next, generative AI is used to generate avatars that mimic each resident's behavioral patterns and preferences for parks, and a simulation of the park's establishment is carried out on the digital twin. The system can also be applied to store customization; for example, customer behavior can be simulated based on survey results and behavioral data to propose optimal store layouts. This specific example will enable attractive urban planning and store management that reflects the opinions of residents and customers.

[0812] This will enable optimal urban planning and store management that reflects the specific needs and behavioral patterns of residents and customers.

[0813] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0814] Step 1:

[0815] Users answer the questionnaire using a smartphone or PC. The input is the user's questionnaire response, and the output is the collected questionnaire data. The questionnaire includes questions about living environment, product preferences, and store layout. The device sends this data to the server.

[0816] Step 2:

[0817] The device collects behavioral data about the user's daily life through a smartwatch or smartphone. Specifically, this includes GPS data, store visit history, purchase history, and product browsing history. This behavioral data is sent to a server. The input is the user's behavioral data, and the output is the collected behavioral data.

[0818] Step 3:

[0819] The server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in response to the consent confirmation message displayed on the terminal, consent is accepted. The input is the consent confirmation message, and the output is the user's consent status. If consent is given, the server grants the user local currency or discount coupons as an incentive.

[0820] Step 4:

[0821] The server preprocesses the collected survey and behavioral data, cleansing and formatting the data. The input is the survey and behavioral data, and the output is the preprocessed data. Based on this preprocessed data, the server trains a generative AI model (e.g., GPT-4).

[0822] Step 5:

[0823] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. The input is preprocessed data, and the output is the generated avatar. The server generates an avatar based on a prompt statement, such as, "Customer A likes electronic devices and gadgets, and is particularly interested in the latest smartphone accessories. He frequently visits stores on weekends and enjoys looking at the new product display area."

[0824] Step 6:

[0825] The server introduces the generated avatar into the digital twin environment and performs a simulation. Specific behaviors include how the avatar moves around the store and which areas it shows interest in. The input is the generated avatar, and the output is the simulation results. Unity and Siemens' MindSphere are used as digital twin platforms.

[0826] Step 7:

[0827] The server performs analysis based on the simulation results. Statistical methods are used to analyze the simulation results and aggregate the needs of residents and customers. The input is the simulation results, and the output is the analysis results. Based on these analysis results, the server proposes optimal layouts and product configurations to store operators.

[0828] Step 8:

[0829] The server automatically generates specific city planning and store operation optimization plans based on the analysis and simulation results. The input is the analysis results, and the output is an optimized city planning and store layout proposal. For example, it can propose a layout in which the latest smartphone accessories are placed in a prominent location.

[0830] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0831] This invention collects data on residents, generates avatars that mimic the thoughts and emotions of residents using generative AI and an emotion engine, and then performs simulations in a digital twin environment to automatically generate urban plans that are tailored to individual emotions and preferences. This system is specifically implemented as follows.

[0832] Data collection

[0833] First, the user answers a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and emotional changes in daily life. Once the answers are complete, the questionnaire data is sent to the server.

[0834] Next, the device collects behavioral data related to the user's daily life. For example, GPS data from a smartwatch or smartphone is used to collect data on the user's commute route and the facilities they use. Sensors installed in the smartphone or wearable device are also used to monitor the user's heart rate and facial expressions, collecting emotional data. This behavioral data and emotional data are then sent to a server.

[0835] Consent confirmation and incentive provision

[0836] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information for which consent has been obtained is stored on the server.

[0837] The server will provide local currency as an incentive to users who agree. The server will check the user's data provision history and add the necessary local currency to the user's account.

[0838] Training generative AI models and emotion engines

[0839] The server then preprocesses the collected survey data, behavioral data, and emotional data. The data is cleansed and formatted, and then used to train a generative AI model and an emotional engine. The generative AI model is used to mimic residents' thinking and behavior patterns, and the emotional engine is used to evaluate the user's emotional state.

[0840] Avatar generation

[0841] The server uses a trained generative AI model and emotion engine to generate an avatar based on the user's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the thoughts, actions, and emotions of the resident.

[0842] Simulation on a digital twin

[0843] The server then introduces the generated avatar into the digital twin environment and conducts a simulation, observing the avatar's reactions, behavior, and emotional changes, and collecting the simulation results as data.

[0844] Urban planning proposals

[0845] The server performs an analysis based on the simulation results. Statistical methods are used to aggregate residents' opinions, preferences, and emotional states, and the analyzed data is used to identify residents' needs. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0846] Specific examples

[0847] For example, this system could be used when considering the establishment of a new public park. Residents fill out a survey and GPS and emotional data are collected to determine the routes they typically take, the facilities they use, and the emotions they feel when they do. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, and a simulation of the park's construction is run on the digital twin.

[0848] The simulation results showed that many residents use parks on weekends and feel positive emotions in the process, and that certain areas are used frequently and have high emotional satisfaction. Based on this, the system proposes new park locations and designs that match the needs and emotions of residents. This specific example will realize livable urban planning that reflects the opinions and emotions of residents.

[0849] The processing flow will be explained below.

[0850] Step 1:

[0851] Users answer a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and emotional changes in daily life. Once the questionnaire is completed, the data is sent to the server.

[0852] Step 2:

[0853] The device collects behavioral data related to the user's daily life. For example, GPS data from a smartwatch or smartphone is used to collect data on the user's commute route and the facilities they use. Sensors installed in the smartphone or wearable device are also used to monitor the user's heart rate and facial expressions, and to collect emotional data. The collected behavioral and emotional data is sent to a server.

[0854] Step 3:

[0855] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information for which consent has been obtained is stored on the server.

[0856] Step 4:

[0857] The server will grant local currency as an incentive to users who agree. The server will grant local currency by checking the user's data provision history and adding the necessary local currency to the user's account.

[0858] Step 5:

[0859] The server preprocesses the collected survey data, behavioral data, and sentiment data. Data cleansing and format conversion are performed. The preprocessed data is used as training data for the generative AI model and sentiment engine.

[0860] Step 6:

[0861] The server trains the generative AI model and emotion engine based on the preprocessed data. The generative AI model imitates the residents' thought patterns and behavior patterns, and the emotion engine evaluates the user's emotional state.

[0862] Step 7:

[0863] The server uses the trained generative AI model and emotion engine to generate an avatar based on the user's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the thoughts, actions, and emotions of the resident.

[0864] Step 8:

[0865] The server then introduces the generated avatar into the digital twin environment and conducts a simulation, during which the avatar's reactions, behavior, and emotional changes are observed and collected.

[0866] Step 9:

[0867] The server analyzes the simulation results, using statistical methods to aggregate residents' opinions, preferences, and emotional states, and extracts residents' needs based on the analyzed data.

[0868] Step 10:

[0869] The server automatically generates an urban plan that is in line with the residents' opinions and emotions based on the extracted needs and emotional states. The generated urban plan is then presented to local government officials for final review and adjustment.

[0870] Specific examples

[0871] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents respond to a survey and GPS and emotional data are collected to determine the routes they take, the facilities they use, and the emotions they feel when doing so. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, and a simulation of the park's establishment is run on the digital twin. The simulation results show that many residents use the park on weekends and experience positive emotions while doing so, and that certain areas are frequently used and provide high emotional satisfaction. Based on this, the system can propose the location and design of the new park to match the residents' needs and emotions. This specific example will realize livable urban planning that reflects the opinions and emotions of residents.

[0872] Example 2

[0873] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0874] In modern urban planning, it is extremely important to effectively reflect the opinions and feelings of residents. However, conventional methods often rely on one-sided approaches based on quantitative data, which have the problem of not fully reflecting the diverse thoughts and feelings of residents. Furthermore, when it comes to collecting data from residents, there is a lack of motivation for them to actively provide it, making it difficult to collect accurate and abundant data. There is a need for a system that can solve these issues and realize urban planning that effectively reflects the opinions and feelings of residents.

[0875] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting questionnaire data from residents, means for collecting behavioral data and emotional data from residents, and means for training and operating a generation AI and emotion engine that generates avatars that mimic the thoughts and emotions of residents based on the collected questionnaire data, behavioral data, and emotional data. This makes it possible to effectively collect and analyze data including the diverse opinions and emotions of residents and automatically generate urban plans that match the emotions and preferences of each resident.

[0876] "Survey data" refers to data containing the contents of questionnaires answered by residents, including information on living environment, means of transportation, favorite parks and facilities, and emotional changes in daily life.

[0877] "Behavioral data" refers to data that shows residents' daily activities, including GPS data from smartwatches and smartphones, commuting routes, and usage of facilities.

[0878] "Emotion data" is data that indicates the emotional state of the resident, and includes heart rate data and facial expression recognition data.

[0879] "Generative AI" refers to an artificial intelligence model that mimics the thought and behavior patterns of residents based on collected data.

[0880] An "emotion engine" is a processing device or algorithm that evaluates the emotional state of residents based on collected emotional data.

[0881] "Avatars" are virtual human models that use generative AI and emotion engines to mimic the attributes, behavioral patterns, and emotional states of residents.

[0882] A "digital twin" is a simulated environment that virtually recreates a real urban environment and is used to observe the reactions and behavior of avatars.

[0883] "Simulation results" are data that show the results of observing and analyzing changes in the behavior and emotions of avatars in a digital twin environment.

[0884] "Means for automatically generating urban plans" refers to devices or software that aggregate residents' opinions, preferences, and emotional states based on simulation results, and then generate urban plans that meet the residents' needs based on the analyzed data.

[0885] "Confirmation means for obtaining consent to data provision" refers to the interface and process for confirming whether residents agree to provide their data, and may include consent confirmation messages and "Agree" buttons.

[0886] "Means for granting local currency" refers to a system that electronically grants local currency as an incentive to consenting residents.

[0887] "Statistical analysis means" refers to the process and algorithms for analyzing the simulation results using statistical methods and aggregating the opinions and emotional states of residents.

[0888] "Means of aggregating residents' needs" refers to systems and processes for organizing the diverse opinions and feelings of residents based on the results of statistical analysis and aggregating them into centralized data.

[0889] MODE FOR CARRYING OUT THE INVENTION

[0890] The present invention is a system that automatically generates urban plans tailored to individual emotions and preferences by collecting data on residents, generating avatars that mimic the residents' thoughts and emotions using a generative AI model and an emotion engine, and running simulations in a digital twin environment. This system is specifically implemented as follows.

[0891] Data collection

[0892] Users answer a questionnaire using a smartphone or personal computer (PC). The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and daily emotional changes. Once the user completes the questionnaire, the data is sent to the server.

[0893] The device collects behavioral data related to the user's daily life using the GPS of the smartwatch or smartphone, and collects emotional data using sensors installed in the smartphone or wearable device to monitor heart rate and facial expressions, which are also transmitted to the server.

[0894] Consent confirmation and incentive provision

[0895] The server sends a consent confirmation message regarding data provision to the terminal, and the user obtains consent by pressing the "Agree" button in response to the consent confirmation message. The consent information is stored on the server. The server grants local currency as an incentive to users who agree to data provision. The procedure for granting local currency is carried out by the server checking the user's data provision history and adding the required local currency to the user's account.

[0896] Training generative AI models and emotion engines

[0897] The server preprocesses the collected survey data, behavioral data, and emotional data. It cleanses the data, fills in missing data, and converts the data format. It then trains a generative AI model and an emotion engine based on the preprocessed data. The generative AI model is used to mimic residents' thinking and behavioral patterns, and the emotion engine is used to evaluate the user's emotional state.

[0898] Avatar generation

[0899] The server uses a trained generative AI model and emotion engine to generate an avatar based on each user's attributes, behavioral patterns, and emotional state. This avatar is a virtual person model that mimics the thoughts, actions, and even emotions of the resident.

[0900] Simulation in a digital twin environment

[0901] The server then introduces the generated avatar into a digital twin environment and conducts a simulation. The digital twin environment is a virtual reproduction of an actual urban environment, allowing users to observe the avatar's reactions, behavior, and emotional changes. The server then collects and analyzes the data obtained from this simulation.

[0902] Urban planning proposals

[0903] Based on the simulation results, the server uses statistical methods to aggregate residents' opinions, preferences, and emotional states, and extracts residents' needs from the analyzed data. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0904] Specific examples

[0905] For example, this system can be used when considering the establishment of a new public park. Residents respond to a survey and GPS and emotional data are collected, revealing the routes they take, the facilities they use, and the emotions they feel when they do. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, allowing simulations of park establishment to be conducted on the digital twin. If the simulation results show that a particular area is frequently used and emotionally satisfying, a proposal to establish a new park in that area can be made.

[0906] Prompt Sentence Examples

[0907] For example, a prompt to suggest the best location for a new public facility might look like this:

[0908] Based on the following data, suggest the best location and design for a new public park.

[0909] 1. Resident survey response data

[0910] 2. GPS-based behavioral data

[0911] 3. Collected emotional data

[0912] Based on the above data, please simulate and propose the location and design of the park that will most satisfy the residents.

[0913] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0914] Step 1:

[0915] Users answer a questionnaire using a smartphone or personal computer (PC). The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and daily emotional changes. Once the user completes the questionnaire, the data is sent from the device to the server.

[0916] Input: User survey response data

[0917] Output: Survey data sent to the server

[0918] Step 2:

[0919] The device collects behavioral data related to the user's daily life using the GPS of the smartwatch or smartphone, and collects emotional data using sensors installed in the smartphone or wearable device to monitor heart rate and facial expressions, which are also transmitted to the server.

[0920] Input: Behavioral and emotional data from smartwatches, smartphones, and wearable devices

[0921] Output: Behavioral and emotional data sent to the server

[0922] Step 3:

[0923] The server sends a consent confirmation message regarding data provision to the terminal, and the user consents by pressing the "Agree" button in response to the displayed consent confirmation message. The consent information is stored on the server.

[0924] Input: Consent confirmation message

[0925] Output: The consent information is saved on the server.

[0926] Step 4:

[0927] The server will grant local currency as an incentive to users who agree. The procedure for granting local currency is carried out by the server checking the user's data provision history and adding the necessary local currency to the user's account.

[0928] Input: User data provision history, consent information

[0929] Output: The local currency is added to the user's account

[0930] Step 5:

[0931] The server preprocesses the collected survey data, behavioral data, and sentiment data, cleansing the data, filling in missing data, and converting formats, and then trains the generative AI model and sentiment engine based on the preprocessed data.

[0932] Input: Survey data, behavioral data, emotional data

[0933] Output: Pre-processed data, trained generative AI model and emotion engine

[0934] Step 6:

[0935] The server uses a trained generative AI model and emotion engine to generate an avatar based on each user's attributes, behavioral patterns, and emotional state. This avatar is a virtual person model that mimics the thoughts, actions, and even emotions of the resident.

[0936] Input: Trained generative AI model and emotion engine, pre-processed data

[0937] Output: An avatar that mimics the user's attributes, behavioral patterns, and emotional state

[0938] Step 7:

[0939] The server then introduces the generated avatar into a digital twin environment and conducts a simulation. The digital twin environment is a virtual reproduction of an actual urban environment, allowing users to observe the avatar's reactions, behavior, and emotional changes. The server then collects and analyzes the data obtained from this simulation.

[0940] Input: Generated avatar

[0941] Output: Simulation result data

[0942] Step 8:

[0943] The server uses statistical methods to analyze residents' opinions, preferences, and emotional states based on the simulation results, and extracts residents' needs from the analyzed data. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[0944] Input: Simulation result data

[0945] Output: Proposal of urban planning that reflects the needs of residents

[0946] (Application example 2)

[0947] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0948] In modern logistics facilities, work efficiency and worker satisfaction are important factors that directly affect facility productivity and worker safety. However, methods for optimizing these have not yet been established, and in particular, there is no system that reflects worker emotions and behavioral patterns. Therefore, there is a need to achieve both an efficient work environment and worker satisfaction in logistics facilities.

[0949] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0950] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for training and operating a generation AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, means for generating avatars that mimic the behavioral patterns and emotional states of workers and evaluating the optimization of work efficiency and work satisfaction at logistics facilities, means for analyzing the avatars' responses and behavioral patterns and generating proposals to support efficiency improvements at logistics facilities, and means for making proposals to improve the work environment based on the avatar simulation results.This makes it possible to maximize work efficiency in logistics facilities and create an optimal work environment that takes into account the emotions and satisfaction of workers.

[0951] "Survey data" refers to data containing subjective information provided by users about their living environment, means of transportation, daily activities, etc.

[0952] "Behavioral data" refers to objectively observed data that includes a user's daily behavior, location information, and physiological data such as heart rate and facial expressions.

[0953] "Generative AI" is artificial intelligence that generates avatars that mimic the user's thought and behavior patterns based on collected survey data and behavioral data.

[0954] A "digital twin" is a digital model that recreates physical world objects or systems in a virtual environment and is used for simulation and analysis.

[0955] The "simulation results" are the data collected by observing the behavior and reactions of avatars created in a digital twin environment.

[0956] "Urban planning" involves proposing the optimal layout and design of living spaces and infrastructure based on resident survey data, behavioral data, and simulation results.

[0957] "Worker" means a person engaged in work within a logistics facility.

[0958] "Work efficiency" is an indicator of how effectively and quickly work is carried out within a logistics facility.

[0959] "Labor satisfaction" is an indicator that shows how satisfied a worker is with their working environment and work content.

[0960] "Efficiency proposals" are specific proposals based on simulation results to improve work efficiency within logistics facilities.

[0961] "Improvement proposals" are proposals based on the simulation results with the aim of improving the working environment.

[0962] The present invention is a system for improving work efficiency and worker satisfaction within a logistics facility. This system is composed of multiple components, each of which works together to optimize the work environment.

[0963] Data collection

[0964] First, a device (such as a smartphone or robot) collects survey data from the user. The survey includes questions about the user's work environment, transportation, and daily activities. The collected data is then sent to a server.

[0965] Next, the device collects behavioral data related to the worker's daily work. For example, GPS data from smartphones and data from sensors installed in logistics facilities are used to collect data on the worker's location and movements. Sensors in smartwatches and smartphones are also used to collect emotional data such as heart rate and facial expressions. This data is also sent to the server.

[0966] Consent confirmation and incentive provision

[0967] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information regarding consent is stored on the server. The server grants local currency as an incentive to users who consent. This local currency is granted by the server by checking the user's data provision history and adding the appropriate amount to the user's account.

[0968] Training generative AI models and emotion engines

[0969] Next, the server preprocesses the collected survey data, behavioral data, and emotion data. Python is used to cleanse and format the data. Based on the preprocessed data, a generative AI model and emotion engine are trained using TensorFlow and Keras. The generative AI model is used to imitate the worker's thought patterns and behavioral patterns, and the emotion engine is used to evaluate the worker's emotional state.

[0970] Avatar generation

[0971] The server uses a trained generative AI model and emotion engine to generate an avatar based on the worker's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the worker's thoughts, actions, and emotions. Blender is used to generate a detailed model of the avatar.

[0972] Simulation on a digital twin

[0973] The server then introduces the generated avatar into the digital twin environment and runs a simulation using a Python program. During the simulation, the avatar's reactions, behavior, and emotional changes are observed, and the simulation results are collected as data.

[0974] Efficiency and improvement proposals

[0975] Based on the simulation results, the server automatically generates improvement proposals to maximize work efficiency and worker satisfaction at the logistics facility. Statistical methods are used to analyze the simulation results, and suggestions for improving the work environment are made based on data that aggregates the needs and emotional states of workers. These suggestions are then presented to the logistics facility's management for final review and adjustment.

[0976] Specific examples

[0977] For example, this system can be used when introducing a new logistics system. Workers fill out a questionnaire and GPS data, heart rate data, and facial expression data are collected to identify which work areas are most stressful and where work flow needs to be optimized. Next, generative AI and an emotion engine are used to generate avatars that mimic each worker's behavioral patterns and emotions, and simulations are run on the digital twin.

[0978] The simulation results show that many workers feel stressed in certain work areas and that improvements to traffic flow are necessary. Based on this, it is possible to propose improvements to the work environment of logistics facilities that are tailored to the needs and emotions of workers.

[0979] Example prompt sentence:

[0980] "Based on your work patterns and emotional data from the past week, we suggest the most efficient and least stressful work flow."

[0981] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0982] Step 1:

[0983] The server collects survey data from users. Users answer the survey using their smartphones or PCs and send the results to the server. The survey includes questions about living environment, transportation, and daily activities. The input is the survey response data from the users, and the output is the survey data stored on the server.

[0984] Step 2:

[0985] The device collects behavioral and emotional data related to the worker's daily work. It collects location information and movement data from the smartphone's GPS data and sensors installed in the logistics facility, and also obtains data such as the user's heart rate and facial expression. This data is sent to a server. The input is the user's behavioral and emotional data, and the output is the behavioral and emotional data stored on the server.

[0986] Step 3:

[0987] The server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in response to the consent confirmation message displayed on the terminal screen, consent is obtained and stored on the server. The server grants local currency as an incentive to users who consent. The input is the user's consent data, and the output is the consent data stored on the server and the granted local currency.

[0988] Step 4:

[0989] The server preprocesses the collected survey data, behavioral data, and sentiment data. It uses Python to cleanse and format the data, making it suitable for machine learning. The input is the collected raw data, and the output is the preprocessed dataset.

[0990] Step 5:

[0991] The server uses the preprocessed data to train a generative AI model and emotion engine using TensorFlow and Keras. The generative AI model imitates the worker's thought patterns and behavior patterns, and the emotion engine evaluates the worker's emotional state. The input is the preprocessed dataset, and the output is the trained generative AI model and emotion engine.

[0992] Step 6:

[0993] The server uses a trained generative AI model and an emotion engine to generate an avatar based on the worker's attributes, behavioral patterns, and emotional state. Blender is used to create detailed avatar models. The input is the trained generative AI model and the emotion engine, and the output is the generated avatar.

[0994] Step 7:

[0995] The server introduces the generated avatar into the digital twin environment and performs a simulation. A Python program is used to check the avatar's behavior and emotional changes, and the results are collected as data. The input is the generated avatar, and the output is the simulation results.

[0996] Step 8:

[0997] The server statistically analyzes the simulation results and automatically generates improvement proposals to maximize work efficiency and labor satisfaction at logistics facilities. Based on the simulation results, it aggregates the needs and emotional states of workers and proposes improvements to the work environment. The input is the simulation result data, and the output is an improvement proposal.

[0998] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0999] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1000] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1001] [Fourth embodiment]

[1002] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1003] 7, a 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.

[1004] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1005] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1006] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1007] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1008] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1009] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1010] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1011] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1012] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1013] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1014] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1015] The present invention automatically generates urban plans tailored to individual preferences by collecting data on residents, using generative AI to generate avatars that mimic the residents' thoughts, and conducting simulations in a digital twin environment. This system is specifically implemented as follows.

[1016] Data collection

[1017] First, users answer a questionnaire using their smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, etc. This allows the collection of survey data.

[1018] Next, the device collects behavioral data about the resident's daily life. For example, GPS data from a smartwatch or smartphone is used to obtain data on the commute route and facilities used. This behavioral data is then sent to a server.

[1019] Consent confirmation and incentive provision

[1020] The server sends a confirmation message to the device to obtain consent for data provision. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is accepted.

[1021] The server will provide local currency as an incentive to users who agree to participate, encouraging them to actively participate in providing data.

[1022] Training generative AI models

[1023] The server then preprocesses the collected survey and behavioral data, cleansing and formatting it, and uses it to train a generative AI model.

[1024] Avatar generation

[1025] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts, based on the user's attributes and behavioral patterns.

[1026] Simulation on a digital twin

[1027] The server then introduces the generated avatar into the digital twin environment and runs a simulation, observing the avatar's reactions and behavior and collecting data.

[1028] Urban planning proposals

[1029] The server analyzes the simulation results and collects the opinions and preferences of residents. Based on this, an urban plan that meets the needs of residents is automatically generated. The generated urban plan is then presented to local government officials.

[1030] Specific examples

[1031] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents fill out a survey and GPS data is collected to identify their behavioral patterns, such as the routes they usually take and the facilities they use. Next, generative AI is used to create avatars that mimic each resident's behavioral patterns and park preferences, and a simulation of the park's establishment is run on the digital twin.

[1032] The simulation results showed that many residents use parks on weekends and that certain areas are more frequently used, and based on this, the system proposed the location and design of new parks to meet the needs of residents. This concrete example will realize attractive urban planning that reflects the opinions of residents.

[1033] The processing flow will be explained below.

[1034] Step 1:

[1035] Users answer the questionnaire using their smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, etc. Once the answers are completed, the questionnaire data is sent to the server.

[1036] Step 2:

[1037] The device collects behavioral data related to the user's daily life. Specifically, it acquires GPS data from smartwatches and smartphones, and collects data on the user's commute route and the public facilities they use. The collected behavioral data is sent to a server.

[1038] Step 3:

[1039] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message, consent is obtained. The information for which consent has been obtained is stored on the server.

[1040] Step 4:

[1041] The server will grant local currency as an incentive to users who agree. The server will grant local currency by checking the user's data provision history and adding the necessary local currency to the user's account.

[1042] Step 5:

[1043] The server preprocesses the collected survey and behavioral data, cleansing and formatting the data, and uses the preprocessed data as training data for the generative AI model.

[1044] Step 6:

[1045] The server trains a generative AI model based on the preprocessed data, which is then used to mimic the thinking and behavior patterns of residents.

[1046] Step 7:

[1047] The server uses a trained generative AI model to generate an avatar based on the user's attributes and behavioral patterns. This avatar is a virtual human model that mimics the thoughts and behavior of the resident.

[1048] Step 8:

[1049] The server then introduces the generated avatar into the digital twin environment and performs a simulation, observing the avatar's reactions and behavior and collecting the simulation results as data.

[1050] Step 9:

[1051] The server analyzes the simulation results, aggregates residents' opinions and preferences using statistical methods, and extracts residents' needs based on the analyzed data.

[1052] Step 10:

[1053] The server automatically generates an urban plan based on the needs extracted and in line with the opinions of residents. The generated urban plan is then presented to local government officials for final review and adjustment.

[1054] Example 1

[1055] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1056] Conventional urban planning often fails to adequately reflect residents' opinions and preferences. Furthermore, there is a lack of methods for integrating and utilizing residents' behavioral patterns and daily mobility data, resulting in plans that often deviate from residents' actual needs. To solve this problem, a method is needed to efficiently collect survey data and behavioral data, use generative AI to generate avatars that mimic residents' thoughts, and simulate them in a digital twin environment.

[1057] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1058] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for cleansing and formatting the collected survey data and behavioral data, and means for training and operating a generation AI that generates avatars that mimic the thinking of residents, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, and means for presenting the urban plans to local government officials. This enables the automatic generation of advanced urban plans that reflect the opinions and behavioral patterns of residents.

[1059] "Residents" refers to ordinary people who live in a city or region.

[1060] "Survey data" refers to response data collected from residents regarding their living environment, means of transportation, and facility usage.

[1061] "Behavioral data" refers to location and behavioral information collected from devices such as smartphones and smartwatches, such as residents' routes and destinations in their daily lives.

[1062] "Generative AI" refers to artificial intelligence that generates avatars that mimic the thinking and behavior patterns of residents based on collected data.

[1063] "Cleansing" is a data preprocessing process that removes inaccurate or missing data and improves data quality.

[1064] "Format conversion" refers to the process of converting collected data into a format that can be used by generative AI models.

[1065] An "avatar" is a digital representative that mimics the characteristics and behavioral patterns of a resident.

[1066] A "digital twin environment" refers to a virtual environment that digitally recreates a specific location or system in the real world.

[1067] "Simulation" refers to a method of conducting virtual experiments in a digital twin environment using a generated avatar and analyzing the results.

[1068] "Urban planning" refers to the act or content of designing and planning the layout of infrastructure and facilities in a local community to improve the living environment of residents.

[1069] "Municipal officials" refer to local government officials in charge of urban planning and local resident services.

[1070] "Incentives" refers to incentives, particularly rewards such as local currency, given to encourage residents to provide data.

[1071] The present invention automatically generates urban plans tailored to individual preferences by collecting data on residents, using generative AI to generate avatars that mimic the residents' thoughts, and conducting simulations in a digital twin environment. This invention is specifically implemented as follows.

[1072] First, the user answers a questionnaire using a smartphone or PC about their living environment, transportation, favorite parks and facilities, etc. This collects the survey data. Next, the device uses GPS data from the smartwatch or smartphone to collect behavioral data about the user's daily life and sends it to the server.

[1073] Next, the server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in the consent confirmation message, consent is accepted. The server awards local currency as an incentive to users who consent. This encourages residents to actively participate in data provision.

[1074] The server then preprocesses the collected survey and behavioral data. This preprocessing step involves data cleansing and formatting. Cleansing removes inaccurate or missing data, while formatting converts the data into a format suitable for AI models.

[1075] The server then uses the pre-processed data to train a generative AI model, which uses state-of-the-art neural network technology to learn residents' behavioral patterns and preferences.

[1076] Once training is complete, the server uses the generative AI model to generate an avatar that mimics the user's thoughts and behaviors, creating a digital representation of the user's characteristics.

[1077] Next, the avatar generated by the server is introduced into the digital twin environment, and simulations such as urban planning are carried out. Through this simulation, the avatar's behavior and reactions are observed, and the simulation results are collected as data.

[1078] Finally, the server automatically generates an urban plan based on the simulation results. The simulation results are statistically analyzed and residents' needs are summarized based on this. The generated urban plan is presented to local government officials and developed into a concrete plan.

[1079] Specific examples

[1080] For example, this system can be used when considering the establishment of a new public park in a certain area. Users respond to a questionnaire and GPS data is collected, revealing behavioral patterns such as the routes residents usually take and the facilities they use. Next, generative AI is used to create avatars that mimic each resident's behavioral patterns and preferences for parks, and a simulation of the park's establishment is carried out in a digital twin environment. The simulation results show that many residents use the park on weekends and that certain areas are used frequently, and based on this, the system proposes the location and design of the park.

[1081] Prompt Sentence Examples

[1082] "Based on user survey data and GPS data, use a generative AI model to generate avatars that mimic the thoughts of residents, and simulate the installation of a new public park in a digital twin environment."

[1083] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1084] Step 1: Conduct a survey

[1085] Users use their smartphones or PCs to answer a questionnaire about their living environment, transportation, and favorite parks and facilities. Based on the survey questions they input (e.g., "Which is the nearest park?" and "What is your usual mode of transportation?"), the system outputs the user's response data. Specifically, data such as "Most favorite park: Central Park" and "Method of commuting: Bicycle" are collected.

[1086] Step 2: Collect behavioral data

[1087] The device uses GPS data from a smartwatch or smartphone to record the user's daily travel routes, visited destinations, and other behavioral data. The user's travel patterns are output based on input location information (e.g., GPS data with time stamps). For example, data such as "Leaving home (location information) at 8 a.m. and arriving at office (location information) at 9 a.m." is collected.

[1088] Step 3: Confirm consent

[1089] The server sends a consent confirmation message regarding data provision to the terminal. Based on the input consent confirmation message (e.g., information about the purpose of data use and privacy protection), the user's response data is output. Specifically, consent is accepted when the user presses the "Agree" button on the displayed consent confirmation message.

[1090] Step 4: Offer incentives

[1091] The server will award local currency as an incentive to users who agree. Based on the consent confirmation result as input, points will be added to the user's account. As a result, "Points awarded: 100 local currency points" or similar will be output.

[1092] Step 5: Preprocessing the data

[1093] The server preprocesses the collected survey and behavioral data. Based on the raw data (survey data and behavioral data) as input, data cleansing and format conversion are performed, and a clean dataset is output. Specifically, this includes operations such as "removing invalid location records."

[1094] Step 6: Training the AI ​​model

[1095] The server trains a generative AI model based on the preprocessed data. Based on the clean data set as input, the AI ​​model is trained using algorithms such as neural networks. The result is a generative AI model that has learned specific patterns and tendencies.

[1096] Step 7: Avatar generation

[1097] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. Based on the generative AI model and the user's attribute data as input, an avatar with the user's unique behavioral patterns is output. Specifically, an avatar named "Office Worker A" is generated.

[1098] Step 8: Run the simulation

[1099] The server introduces the generated avatar into the digital twin environment and performs urban planning simulations. Specific urban planning scenarios are simulated based on the avatar and digital twin environment as input. Simulation data and the avatar's reactions are output as the result. For example, "usage patterns based on a new park installation scenario" are obtained.

[1100] Step 9: Analyze the simulation results

[1101] The server analyzes the simulation results and aggregates the needs of residents. Statistical analysis is performed based on the input simulation data, and aggregated needs data is output. Specifically, insights such as "parks in specific areas are frequently used" can be obtained.

[1102] Step 10: Urban Planning Proposal

[1103] Based on the analysis results, the server automatically generates an urban plan that meets the needs of residents and presents it to local government officials. Based on the analysis results as input, specific urban plans (e.g., the design and location of a new park) are output. As a result, a "proposal for the establishment of a central park" is provided to local government officials.

[1104] (Application example 1)

[1105] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1106] In modern urban planning and store management, it is important to create optimal plans that reflect the specific needs and behavioral patterns of residents and customers. However, traditional methods have difficulty fully incorporating the voices of residents and customers, and optimization of urban planning and store management has not reached a reasonable level. For this reason, there is a need for a system that can automatically generate plans and proposals that accurately reflect individual preferences and behavioral patterns based on resident and customer data.

[1107] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1108] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for training and operating a generation AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, and means for optimizing store layouts and product configurations. This enables optimal urban planning and store operations that reflect the specific needs and behavioral patterns of residents and customers.

[1109] "Resident" refers to an individual who resides in a particular area or city.

[1110] "Survey data" refers to data containing responses collected from residents and customers. The surveys include questions about living environments and product preferences.

[1111] "Behavioral data" refers to data that shows the behavioral patterns of residents and customers, such as GPS information, purchase history, and frequency of store visits.

[1112] "Generative AI" refers to an AI model that mimics a user's thoughts and actions based on collected data.

[1113] "Avatars" refer to virtual characters created by generative AI that mimic the characteristics of residents or customers.

[1114] A "digital twin" is a virtual reproduction of the physical world, used for simulation and prediction.

[1115] "Simulation" refers to the process of operating the generated avatar in a digital twin environment and observing its reactions and behavior under various conditions.

[1116] "Urban planning" refers to a plan to design the structure and functions of an entire city in order to improve the lives of its residents.

[1117] "Store layout" refers to the design of product placement and traffic flow within a physical store.

[1118] "Product mix" refers to determining the types and quantities of products to be sold in physical stores.

[1119] "Incentives" refers to rewards or benefits for providing data, including local currency and discount coupons.

[1120] "Statistical analysis" refers to analyzing collected data using statistical methods to extract meaningful information.

[1121] "Optimization" refers to adjusting a system or process to its optimum state in order to achieve a specific goal.

[1122] This invention automatically generates urban plans and store layouts tailored to individual preferences by collecting data on residents and customers, using generative AI to generate avatars that mimic the thoughts of residents and customers, and conducting simulations in a digital twin environment. This system is specifically implemented as follows.

[1123] Data collection

[1124] Users answer a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, product preferences, and store layout. This allows the collection of survey data.

[1125] Next, the device collects behavioral data about the daily lives of residents and customers, such as GPS data from smartwatches and smartphones, store visit history, purchase history, and product browsing history. This behavioral data is then sent to a server.

[1126] Consent confirmation and incentive provision

[1127] The server sends a confirmation message to the device to obtain consent for data provision. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is accepted.

[1128] The server will provide local currency or discount coupons as incentives to residents and customers who agree to participate in the data provision.

[1129] Training generative AI models

[1130] The server preprocesses the collected survey data and behavioral data, cleansing and formatting the data, and then trains a generative AI model based on this data. Specifically, GPT-4 is used as the generative AI model, and it learns user behavioral patterns and preferences.

[1131] Avatar generation

[1132] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. This avatar is created based on the user's attributes and behavioral patterns. For example, the server can input a prompt such as, "Customer A likes electronic devices and gadgets, and is particularly interested in the latest smartphone accessories. He frequently visits stores on weekends and enjoys looking at the new product display area."

[1133] Simulation on a digital twin

[1134] The server then introduces the generated avatar into the digital twin environment and performs a simulation. During the simulation, the avatar's reactions and behavior are observed and data is collected. Unity and Siemens' MindSphere are used as digital twin platforms.

[1135] Proposals for optimizing urban planning and store operations

[1136] The server analyzes the simulation results and aggregates the opinions and preferences of residents and customers. Based on this, the system automatically generates urban plans and store layouts that meet the needs of residents and customers. For example, it proposes optimal layouts and product configurations to store operators, so that the latest smartphone accessories are displayed in prominent locations.

[1137] Specific examples

[1138] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents fill out a survey and collect GPS data, revealing behavioral patterns such as the routes they usually take and which facilities they use. Next, generative AI is used to generate avatars that mimic each resident's behavioral patterns and preferences for parks, and a simulation of the park's establishment is carried out on the digital twin. The system can also be applied to store customization; for example, customer behavior can be simulated based on survey results and behavioral data to propose optimal store layouts. This specific example will enable attractive urban planning and store management that reflects the opinions of residents and customers.

[1139] This will enable optimal urban planning and store management that reflects the specific needs and behavioral patterns of residents and customers.

[1140] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1141] Step 1:

[1142] Users answer the questionnaire using a smartphone or PC. The input is the user's questionnaire response, and the output is the collected questionnaire data. The questionnaire includes questions about living environment, product preferences, and store layout. The device sends this data to the server.

[1143] Step 2:

[1144] The device collects behavioral data about the user's daily life through a smartwatch or smartphone. Specifically, this includes GPS data, store visit history, purchase history, and product browsing history. This behavioral data is sent to a server. The input is the user's behavioral data, and the output is the collected behavioral data.

[1145] Step 3:

[1146] The server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in response to the consent confirmation message displayed on the terminal, consent is accepted. The input is the consent confirmation message, and the output is the user's consent status. If consent is given, the server grants the user local currency or discount coupons as an incentive.

[1147] Step 4:

[1148] The server preprocesses the collected survey and behavioral data, cleansing and formatting the data. The input is the survey and behavioral data, and the output is the preprocessed data. Based on this preprocessed data, the server trains a generative AI model (e.g., GPT-4).

[1149] Step 5:

[1150] The server uses a trained generative AI model to generate an avatar that mimics the user's thoughts. The input is preprocessed data, and the output is the generated avatar. The server generates an avatar based on a prompt statement, such as, "Customer A likes electronic devices and gadgets, and is particularly interested in the latest smartphone accessories. He frequently visits stores on weekends and enjoys looking at the new product display area."

[1151] Step 6:

[1152] The server introduces the generated avatar into the digital twin environment and performs a simulation. Specific behaviors include how the avatar moves around the store and which areas it shows interest in. The input is the generated avatar, and the output is the simulation results. Unity and Siemens' MindSphere are used as digital twin platforms.

[1153] Step 7:

[1154] The server performs analysis based on the simulation results. Statistical methods are used to analyze the simulation results and aggregate the needs of residents and customers. The input is the simulation results, and the output is the analysis results. Based on these analysis results, the server proposes optimal layouts and product configurations to store operators.

[1155] Step 8:

[1156] The server automatically generates specific city planning and store operation optimization plans based on the analysis and simulation results. The input is the analysis results, and the output is an optimized city planning and store layout proposal. For example, it can propose a layout in which the latest smartphone accessories are placed in a prominent location.

[1157] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1158] This invention collects data on residents, generates avatars that mimic the thoughts and emotions of residents using generative AI and an emotion engine, and then performs simulations in a digital twin environment to automatically generate urban plans that are tailored to individual emotions and preferences. This system is specifically implemented as follows.

[1159] Data collection

[1160] First, the user answers a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and emotional changes in daily life. Once the answers are complete, the questionnaire data is sent to the server.

[1161] Next, the device collects behavioral data related to the user's daily life. For example, GPS data from a smartwatch or smartphone is used to collect data on the user's commute route and the facilities they use. Sensors installed in the smartphone or wearable device are also used to monitor the user's heart rate and facial expressions, collecting emotional data. This behavioral data and emotional data are then sent to a server.

[1162] Consent confirmation and incentive provision

[1163] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information for which consent has been obtained is stored on the server.

[1164] The server will provide local currency as an incentive to users who agree. The server will check the user's data provision history and add the necessary local currency to the user's account.

[1165] Training generative AI models and emotion engines

[1166] The server then preprocesses the collected survey data, behavioral data, and emotional data. The data is cleansed and formatted, and then used to train a generative AI model and an emotional engine. The generative AI model is used to mimic residents' thinking and behavior patterns, and the emotional engine is used to evaluate the user's emotional state.

[1167] Avatar generation

[1168] The server uses a trained generative AI model and emotion engine to generate an avatar based on the user's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the thoughts, actions, and emotions of the resident.

[1169] Simulation on a digital twin

[1170] The server then introduces the generated avatar into the digital twin environment and conducts a simulation, observing the avatar's reactions, behavior, and emotional changes, and collecting the simulation results as data.

[1171] Urban planning proposals

[1172] The server performs an analysis based on the simulation results. Statistical methods are used to aggregate residents' opinions, preferences, and emotional states, and the analyzed data is used to identify residents' needs. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[1173] Specific examples

[1174] For example, this system could be used when considering the establishment of a new public park. Residents fill out a survey and GPS and emotional data are collected to determine the routes they typically take, the facilities they use, and the emotions they feel when they do. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, and a simulation of the park's construction is run on the digital twin.

[1175] The simulation results showed that many residents use parks on weekends and feel positive emotions in the process, and that certain areas are used frequently and have high emotional satisfaction. Based on this, the system proposes new park locations and designs that match the needs and emotions of residents. This specific example will realize livable urban planning that reflects the opinions and emotions of residents.

[1176] The processing flow will be explained below.

[1177] Step 1:

[1178] Users answer a questionnaire using a smartphone or PC. The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and emotional changes in daily life. Once the questionnaire is completed, the data is sent to the server.

[1179] Step 2:

[1180] The device collects behavioral data related to the user's daily life. For example, GPS data from a smartwatch or smartphone is used to collect data on the user's commute route and the facilities they use. Sensors installed in the smartphone or wearable device are also used to monitor the user's heart rate and facial expressions, and to collect emotional data. The collected behavioral and emotional data is sent to a server.

[1181] Step 3:

[1182] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information for which consent has been obtained is stored on the server.

[1183] Step 4:

[1184] The server will grant local currency as an incentive to users who agree. The server will grant local currency by checking the user's data provision history and adding the necessary local currency to the user's account.

[1185] Step 5:

[1186] The server preprocesses the collected survey data, behavioral data, and sentiment data. Data cleansing and format conversion are performed. The preprocessed data is used as training data for the generative AI model and sentiment engine.

[1187] Step 6:

[1188] The server trains the generative AI model and emotion engine based on the preprocessed data. The generative AI model imitates the residents' thought patterns and behavior patterns, and the emotion engine evaluates the user's emotional state.

[1189] Step 7:

[1190] The server uses the trained generative AI model and emotion engine to generate an avatar based on the user's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the thoughts, actions, and emotions of the resident.

[1191] Step 8:

[1192] The server then introduces the generated avatar into the digital twin environment and conducts a simulation, during which the avatar's reactions, behavior, and emotional changes are observed and collected.

[1193] Step 9:

[1194] The server analyzes the simulation results, using statistical methods to aggregate residents' opinions, preferences, and emotional states, and extracts residents' needs based on the analyzed data.

[1195] Step 10:

[1196] The server automatically generates an urban plan that is in line with the residents' opinions and emotions based on the extracted needs and emotional states. The generated urban plan is then presented to local government officials for final review and adjustment.

[1197] Specific examples

[1198] For example, this system can be used when considering the establishment of a new public park in a certain area. Residents respond to a survey and GPS and emotional data are collected to determine the routes they take, the facilities they use, and the emotions they feel when doing so. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, and a simulation of the park's establishment is run on the digital twin. The simulation results show that many residents use the park on weekends and experience positive emotions while doing so, and that certain areas are frequently used and provide high emotional satisfaction. Based on this, the system can propose the location and design of the new park to match the residents' needs and emotions. This specific example will realize livable urban planning that reflects the opinions and emotions of residents.

[1199] Example 2

[1200] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1201] In modern urban planning, it is extremely important to effectively reflect the opinions and feelings of residents. However, conventional methods often rely on one-sided approaches based on quantitative data, which have the problem of not fully reflecting the diverse thoughts and feelings of residents. Furthermore, when it comes to collecting data from residents, there is a lack of motivation for them to actively provide it, making it difficult to collect accurate and abundant data. There is a need for a system that can solve these issues and realize urban planning that effectively reflects the opinions and feelings of residents.

[1202] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting questionnaire data from residents, means for collecting behavioral data and emotional data from residents, and means for training and operating a generation AI and emotion engine that generates avatars that mimic the thoughts and emotions of residents based on the collected questionnaire data, behavioral data, and emotional data. This makes it possible to effectively collect and analyze data including the diverse opinions and emotions of residents and automatically generate urban plans that match the emotions and preferences of each resident.

[1203] "Survey data" refers to data containing the contents of questionnaires answered by residents, including information on living environment, means of transportation, favorite parks and facilities, and emotional changes in daily life.

[1204] "Behavioral data" refers to data that shows residents' daily activities, including GPS data from smartwatches and smartphones, commuting routes, and usage of facilities.

[1205] "Emotion data" is data that indicates the emotional state of the resident, and includes heart rate data and facial expression recognition data.

[1206] "Generative AI" refers to an artificial intelligence model that mimics the thought and behavior patterns of residents based on collected data.

[1207] An "emotion engine" is a processing device or algorithm that evaluates the emotional state of residents based on collected emotional data.

[1208] "Avatars" are virtual human models that use generative AI and emotion engines to mimic the attributes, behavioral patterns, and emotional states of residents.

[1209] A "digital twin" is a simulated environment that virtually recreates a real urban environment and is used to observe the reactions and behavior of avatars.

[1210] "Simulation results" are data that show the results of observing and analyzing changes in the behavior and emotions of avatars in a digital twin environment.

[1211] "Means for automatically generating urban plans" refers to devices or software that aggregate residents' opinions, preferences, and emotional states based on simulation results, and then generate urban plans that meet the residents' needs based on the analyzed data.

[1212] "Confirmation means for obtaining consent to data provision" refers to the interface and process for confirming whether residents agree to provide their data, and may include consent confirmation messages and "Agree" buttons.

[1213] "Means for granting local currency" refers to a system that electronically grants local currency as an incentive to consenting residents.

[1214] "Statistical analysis means" refers to the process and algorithms for analyzing the simulation results using statistical methods and aggregating the opinions and emotional states of residents.

[1215] "Means of aggregating residents' needs" refers to systems and processes for organizing the diverse opinions and feelings of residents based on the results of statistical analysis and aggregating them into centralized data.

[1216] MODE FOR CARRYING OUT THE INVENTION

[1217] The present invention is a system that automatically generates urban plans tailored to individual emotions and preferences by collecting data on residents, generating avatars that mimic the residents' thoughts and emotions using a generative AI model and an emotion engine, and running simulations in a digital twin environment. This system is specifically implemented as follows.

[1218] Data collection

[1219] Users answer a questionnaire using a smartphone or personal computer (PC). The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and daily emotional changes. Once the user completes the questionnaire, the data is sent to the server.

[1220] The device collects behavioral data related to the user's daily life using the GPS of the smartwatch or smartphone, and collects emotional data using sensors installed in the smartphone or wearable device to monitor heart rate and facial expressions, which are also transmitted to the server.

[1221] Consent confirmation and incentive provision

[1222] The server sends a consent confirmation message regarding data provision to the terminal, and the user obtains consent by pressing the "Agree" button in response to the consent confirmation message. The consent information is stored on the server. The server grants local currency as an incentive to users who agree to data provision. The procedure for granting local currency is carried out by the server checking the user's data provision history and adding the required local currency to the user's account.

[1223] Training generative AI models and emotion engines

[1224] The server preprocesses the collected survey data, behavioral data, and emotional data. It cleanses the data, fills in missing data, and converts the data format. It then trains a generative AI model and an emotion engine based on the preprocessed data. The generative AI model is used to mimic residents' thinking and behavioral patterns, and the emotion engine is used to evaluate the user's emotional state.

[1225] Avatar generation

[1226] The server uses a trained generative AI model and emotion engine to generate an avatar based on each user's attributes, behavioral patterns, and emotional state. This avatar is a virtual person model that mimics the thoughts, actions, and even emotions of the resident.

[1227] Simulation in a digital twin environment

[1228] The server then introduces the generated avatar into a digital twin environment and conducts a simulation. The digital twin environment is a virtual reproduction of an actual urban environment, allowing users to observe the avatar's reactions, behavior, and emotional changes. The server then collects and analyzes the data obtained from this simulation.

[1229] Urban planning proposals

[1230] Based on the simulation results, the server uses statistical methods to aggregate residents' opinions, preferences, and emotional states, and extracts residents' needs from the analyzed data. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[1231] Specific examples

[1232] For example, this system can be used when considering the establishment of a new public park. Residents respond to a survey and GPS and emotional data are collected, revealing the routes they take, the facilities they use, and the emotions they feel when they do. Next, generative AI and an emotion engine are used to generate avatars that mimic each resident's behavioral patterns and emotions, allowing simulations of park establishment to be conducted on the digital twin. If the simulation results show that a particular area is frequently used and emotionally satisfying, a proposal to establish a new park in that area can be made.

[1233] Prompt Sentence Examples

[1234] For example, a prompt to suggest the best location for a new public facility might look like this:

[1235] Based on the following data, suggest the best location and design for a new public park.

[1236] 1. Resident survey response data

[1237] 2. GPS-based behavioral data

[1238] 3. Collected emotional data

[1239] Based on the above data, please simulate and propose the location and design of the park that will most satisfy the residents.

[1240] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1241] Step 1:

[1242] Users answer a questionnaire using a smartphone or personal computer (PC). The questionnaire includes questions about their living environment, transportation, favorite parks and facilities, and daily emotional changes. Once the user completes the questionnaire, the data is sent from the device to the server.

[1243] Input: User survey response data

[1244] Output: Survey data sent to the server

[1245] Step 2:

[1246] The device collects behavioral data related to the user's daily life using the GPS of the smartwatch or smartphone, and collects emotional data using sensors installed in the smartphone or wearable device to monitor heart rate and facial expressions, which are also transmitted to the server.

[1247] Input: Behavioral and emotional data from smartwatches, smartphones, and wearable devices

[1248] Output: Behavioral and emotional data sent to the server

[1249] Step 3:

[1250] The server sends a consent confirmation message regarding data provision to the terminal, and the user consents by pressing the "Agree" button in response to the displayed consent confirmation message. The consent information is stored on the server.

[1251] Input: Consent confirmation message

[1252] Output: The consent information is saved on the server.

[1253] Step 4:

[1254] The server will grant local currency as an incentive to users who agree. The procedure for granting local currency is carried out by the server checking the user's data provision history and adding the necessary local currency to the user's account.

[1255] Input: User data provision history, consent information

[1256] Output: The local currency is added to the user's account

[1257] Step 5:

[1258] The server preprocesses the collected survey data, behavioral data, and sentiment data, cleansing the data, filling in missing data, and converting formats, and then trains the generative AI model and sentiment engine based on the preprocessed data.

[1259] Input: Survey data, behavioral data, emotional data

[1260] Output: Pre-processed data, trained generative AI model and emotion engine

[1261] Step 6:

[1262] The server uses a trained generative AI model and emotion engine to generate an avatar based on each user's attributes, behavioral patterns, and emotional state. This avatar is a virtual person model that mimics the thoughts, actions, and even emotions of the resident.

[1263] Input: Trained generative AI model and emotion engine, pre-processed data

[1264] Output: An avatar that mimics the user's attributes, behavioral patterns, and emotional state

[1265] Step 7:

[1266] The server then introduces the generated avatar into a digital twin environment and conducts a simulation. The digital twin environment is a virtual reproduction of an actual urban environment, allowing users to observe the avatar's reactions, behavior, and emotional changes. The server then collects and analyzes the data obtained from this simulation.

[1267] Input: Generated avatar

[1268] Output: Simulation result data

[1269] Step 8:

[1270] The server uses statistical methods to analyze residents' opinions, preferences, and emotional states based on the simulation results, and extracts residents' needs from the analyzed data. Based on this, an urban plan that is in line with residents' opinions and emotions is automatically generated. The generated urban plan is then presented to local government officials for final review and adjustment.

[1271] Input: Simulation result data

[1272] Output: Proposal of urban planning that reflects the needs of residents

[1273] (Application example 2)

[1274] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1275] In modern logistics facilities, work efficiency and worker satisfaction are important factors that directly affect facility productivity and worker safety. However, methods for optimizing these have not yet been established, and in particular, there is no system that reflects worker emotions and behavioral patterns. Therefore, there is a need to achieve both an efficient work environment and worker satisfaction in logistics facilities.

[1276] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1277] In this invention, the server includes means for collecting survey data from residents, means for collecting behavioral data from residents, means for training and operating a generation AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data, means for simulating the generated avatars in a digital twin environment, means for automatically generating urban plans based on the simulation results, means for generating avatars that mimic the behavioral patterns and emotional states of workers and evaluating the optimization of work efficiency and work satisfaction at logistics facilities, means for analyzing the avatars' responses and behavioral patterns and generating proposals to support efficiency improvements at logistics facilities, and means for making proposals to improve the work environment based on the avatar simulation results.This makes it possible to maximize work efficiency in logistics facilities and create an optimal work environment that takes into account the emotions and satisfaction of workers.

[1278] "Survey data" refers to data containing subjective information provided by users about their living environment, means of transportation, daily activities, etc.

[1279] "Behavioral data" refers to objectively observed data that includes a user's daily behavior, location information, and physiological data such as heart rate and facial expressions.

[1280] "Generative AI" is artificial intelligence that generates avatars that mimic the user's thought and behavior patterns based on collected survey data and behavioral data.

[1281] A "digital twin" is a digital model that recreates physical world objects or systems in a virtual environment and is used for simulation and analysis.

[1282] The "simulation results" are the data collected by observing the behavior and reactions of avatars created in a digital twin environment.

[1283] "Urban planning" involves proposing the optimal layout and design of living spaces and infrastructure based on resident survey data, behavioral data, and simulation results.

[1284] "Worker" means a person engaged in work within a logistics facility.

[1285] "Work efficiency" is an indicator of how effectively and quickly work is carried out within a logistics facility.

[1286] "Labor satisfaction" is an indicator that shows how satisfied a worker is with their working environment and work content.

[1287] "Efficiency proposals" are specific proposals based on simulation results to improve work efficiency within logistics facilities.

[1288] "Improvement proposals" are proposals based on the simulation results with the aim of improving the working environment.

[1289] The present invention is a system for improving work efficiency and worker satisfaction within a logistics facility. This system is composed of multiple components, each of which works together to optimize the work environment.

[1290] Data collection

[1291] First, a device (such as a smartphone or robot) collects survey data from the user. The survey includes questions about the user's work environment, transportation, and daily activities. The collected data is then sent to a server.

[1292] Next, the device collects behavioral data related to the worker's daily work. For example, GPS data from smartphones and data from sensors installed in logistics facilities are used to collect data on the worker's location and movements. Sensors in smartwatches and smartphones are also used to collect emotional data such as heart rate and facial expressions. This data is also sent to the server.

[1293] Consent confirmation and incentive provision

[1294] The server sends a consent confirmation message regarding data provision to the device. When the user presses the "Agree" button in response to the consent confirmation message displayed on the device, consent is obtained. The information regarding consent is stored on the server. The server grants local currency as an incentive to users who consent. This local currency is granted by the server by checking the user's data provision history and adding the appropriate amount to the user's account.

[1295] Training generative AI models and emotion engines

[1296] Next, the server preprocesses the collected survey data, behavioral data, and emotion data. Python is used to cleanse and format the data. Based on the preprocessed data, a generative AI model and emotion engine are trained using TensorFlow and Keras. The generative AI model is used to imitate the worker's thought patterns and behavioral patterns, and the emotion engine is used to evaluate the worker's emotional state.

[1297] Avatar generation

[1298] The server uses a trained generative AI model and emotion engine to generate an avatar based on the worker's attributes, behavioral patterns, and emotional state. This avatar is a virtual human model that mimics the worker's thoughts, actions, and emotions. Blender is used to generate a detailed model of the avatar.

[1299] Simulation on a digital twin

[1300] The server then introduces the generated avatar into the digital twin environment and runs a simulation using a Python program. During the simulation, the avatar's reactions, behavior, and emotional changes are observed, and the simulation results are collected as data.

[1301] Efficiency and improvement proposals

[1302] Based on the simulation results, the server automatically generates improvement proposals to maximize work efficiency and worker satisfaction at the logistics facility. Statistical methods are used to analyze the simulation results, and suggestions for improving the work environment are made based on data that aggregates the needs and emotional states of workers. These suggestions are then presented to the logistics facility's management for final review and adjustment.

[1303] Specific examples

[1304] For example, this system can be used when introducing a new logistics system. Workers fill out a questionnaire and GPS data, heart rate data, and facial expression data are collected to identify which work areas are most stressful and where work flow needs to be optimized. Next, generative AI and an emotion engine are used to generate avatars that mimic each worker's behavioral patterns and emotions, and simulations are run on the digital twin.

[1305] The simulation results show that many workers feel stressed in certain work areas and that improvements to traffic flow are necessary. Based on this, it is possible to propose improvements to the work environment of logistics facilities that are tailored to the needs and emotions of workers.

[1306] Example prompt sentence:

[1307] "Based on your work patterns and emotional data from the past week, we suggest the most efficient and least stressful work flow."

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Step 1:

[1310] The server collects survey data from users. Users answer the survey using their smartphones or PCs and send the results to the server. The survey includes questions about living environment, transportation, and daily activities. The input is the survey response data from the users, and the output is the survey data stored on the server.

[1311] Step 2:

[1312] The device collects behavioral and emotional data related to the worker's daily work. It collects location information and movement data from the smartphone's GPS data and sensors installed in the logistics facility, and also obtains data such as the user's heart rate and facial expression. This data is sent to a server. The input is the user's behavioral and emotional data, and the output is the behavioral and emotional data stored on the server.

[1313] Step 3:

[1314] The server sends a consent confirmation message regarding data provision to the terminal. When the user presses the "Agree" button in response to the consent confirmation message displayed on the terminal screen, consent is obtained and stored on the server. The server grants local currency as an incentive to users who consent. The input is the user's consent data, and the output is the consent data stored on the server and the granted local currency.

[1315] Step 4:

[1316] The server preprocesses the collected survey data, behavioral data, and sentiment data. It uses Python to cleanse and format the data, making it suitable for machine learning. The input is the collected raw data, and the output is the preprocessed dataset.

[1317] Step 5:

[1318] The server uses the preprocessed data to train a generative AI model and emotion engine using TensorFlow and Keras. The generative AI model imitates the worker's thought patterns and behavior patterns, and the emotion engine evaluates the worker's emotional state. The input is the preprocessed dataset, and the output is the trained generative AI model and emotion engine.

[1319] Step 6:

[1320] The server uses a trained generative AI model and an emotion engine to generate an avatar based on the worker's attributes, behavioral patterns, and emotional state. Blender is used to create detailed avatar models. The input is the trained generative AI model and the emotion engine, and the output is the generated avatar.

[1321] Step 7:

[1322] The server introduces the generated avatar into the digital twin environment and performs a simulation. A Python program is used to check the avatar's behavior and emotional changes, and the results are collected as data. The input is the generated avatar, and the output is the simulation results.

[1323] Step 8:

[1324] The server statistically analyzes the simulation results and automatically generates improvement proposals to maximize work efficiency and labor satisfaction at logistics facilities. Based on the simulation results, it aggregates the needs and emotional states of workers and proposes improvements to the work environment. The input is the simulation result data, and the output is an improvement proposal.

[1325] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1326] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1327] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1328] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1329] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1330] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1331] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1332] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1333] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1334] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1335] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1336] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1337] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1338] 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.

[1339] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1340] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1341] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1342] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1343] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1344] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1345] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1346] The following is further disclosed regarding the above embodiment.

[1347] (Claim 1)

[1348] a means of collecting survey data from residents;

[1349] a means of collecting behavioral data from residents;

[1350] A means for training and operating a generative AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data; and

[1351] A means for simulating the generated avatar in a digital twin environment;

[1352] A means for automatically generating urban plans based on the simulation results,

[1353] A system including:

[1354] (Claim 2)

[1355] A means of verifying consent from residents to provide data;

[1356] A means of providing local currency as an incentive to residents who agree,

[1357] The system of claim 1 further comprising:

[1358] (Claim 3)

[1359] a means for statistically analyzing the simulation results;

[1360] A means of summarizing residents' needs based on the analysis results, and

[1361] The system of claim 1 further comprising:

[1362] "Example 1"

[1363] (Claim 1)

[1364] a means of collecting survey data from residents;

[1365] a means of collecting behavioral data from residents;

[1366] A means for training and operating a generative AI that cleanses and converts data based on collected survey data and behavioral data, and generates avatars that mimic the thoughts of residents; and

[1367] A means for simulating the generated avatar in a digital twin environment;

[1368] A means for automatically generating urban plans based on the simulation results,

[1369] A means of presenting urban plans to local government officials;

[1370] A system including:

[1371] (Claim 2)

[1372] A means of verifying consent from residents to provide data;

[1373] A means of providing local currency as an incentive to residents who agree,

[1374] The system of claim 1 further comprising:

[1375] (Claim 3)

[1376] a means for statistically analyzing the simulation results;

[1377] A means of summarizing residents' needs based on the analysis results, and

[1378] The system of claim 1 further comprising:

[1379] "Application Example 1"

[1380] (Claim 1)

[1381] a means of collecting survey data from residents;

[1382] a means of collecting behavioral data from residents;

[1383] A means for training and operating a generative AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data; and

[1384] A means for simulating the generated avatar in a digital twin environment;

[1385] A means for automatically generating urban plans based on the simulation results,

[1386] Measures to optimize store layout and product mix,

[1387] A system including:

[1388] (Claim 2)

[1389] A means of verifying consent from residents to provide data;

[1390] A means of providing local currency as an incentive to residents who agree,

[1391] The system of claim 1 further comprising:

[1392] (Claim 3)

[1393] a means for statistically analyzing the simulation results;

[1394] A means of summarizing residents' needs based on the analysis results, and

[1395] A means to propose optimal layouts and product configurations to store operators,

[1396] The system of claim 1 further comprising:

[1397] "Example 2: Combining Emotion Engines"

[1398] (Claim 1)

[1399] a means of collecting survey data from residents;

[1400] a means for collecting behavioral and emotional data from residents;

[1401] a means for training and operating a generative AI and emotion engine that generates avatars that mimic the thoughts and emotions of residents based on the collected survey data, behavioral data, and emotion data; and

[1402] A means for simulating the generated avatar in a digital twin environment;

[1403] A means for automatically generating urban plans based on the simulation results,

[1404] A system including:

[1405] (Claim 2)

[1406] A means of verifying consent from residents to provide data;

[1407] A means of providing local currency as an incentive to residents who agree,

[1408] The system of claim 1 further comprising:

[1409] (Claim 3)

[1410] a means for statistically analyzing the simulation results;

[1411] A means of summarizing residents' needs based on the analysis results, and

[1412] The system of claim 1 further comprising:

[1413] "Application example 2 when combining emotion engines"

[1414] (Claim 1)

[1415] a means of collecting survey data from residents;

[1416] a means of collecting behavioral data from residents;

[1417] A means for training and operating a generative AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data; and

[1418] A means for simulating the generated avatar in a digital twin environment;

[1419] A means for automatically generating urban plans based on the simulation results,

[1420] A means for generating avatars that mimic the behavioral patterns and emotional states of workers and for optimizing work efficiency and evaluating work satisfaction in logistics facilities;

[1421] A means for analyzing the avatar's reactions and behavioral patterns and generating proposals to support efficiency improvements in logistics facilities;

[1422] A means for making suggestions for improving the work environment based on the results of the avatar simulation;

[1423] A system including:

[1424] (Claim 2)

[1425] A means of verifying consent from residents to provide data;

[1426] A means of providing local currency as an incentive to residents who agree,

[1427] The system of claim 1 further comprising:

[1428] (Claim 3)

[1429] a means for statistically analyzing the simulation results;

[1430] A means of summarizing residents' needs based on the analysis results, and

[1431] The system of claim 1 further comprising: [Explanation of symbols]

[1432] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting survey data from residents; a means of collecting behavioral data from residents; A means for training and operating a generative AI that generates avatars that mimic the thoughts of residents based on the collected survey data and behavioral data; and A means for simulating the generated avatar in a digital twin environment; A means for automatically generating urban plans based on the simulation results, A system including:

2. A means of verifying consent from residents to provide data; A means of providing local currency as an incentive to residents who agree, The system of claim 1 further comprising:

3. a means for statistically analyzing the simulation results; A means of summarizing residents' needs based on the analysis results, and The system of claim 1 further comprising:

Images