system

Abstract

Provide a system. [Solution] a means of collecting data on residents; a means of pre-processing the collected resident data; A means for extracting features from the preprocessed data and training a learning model; A means of predicting future needs of residents using trained models; and A means for generating optimization proposals for shared facilities and community activities based on the needs forecast results; a means of gathering resident feedback on the proposals; a means for improving the model using the collected feedback; and A system including:

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] In today's large-scale condominiums, residents' needs change over time, but the facilities and services provided remain static, making it difficult to maintain long-term resident satisfaction. Furthermore, there is a lack of mechanisms for restructuring facilities and proposing community activities that adapt to changes in residents' age groups, family structures, and social trends. As a result, the value of the condominiums and the quality of life of residents may decline. [Means for solving the problem]

[0005] The present invention provides a system that collects and analyzes resident data and predicts future needs. Specifically, the system includes a means for collecting information such as residents' age groups, family structures, and facility usage histories; a means for preprocessing the data; a means for extracting features from the preprocessed data and training a machine learning model; and a means for predicting future needs using the trained model. The system also includes a means for generating proposals for restructuring shared facilities and new community activities based on the needs prediction results, a means for collecting resident feedback on the proposals, and a means for improving the model using the collected feedback. This allows the system to flexibly respond to changing resident needs and maintain long-term satisfaction.

[0006] "Resident data" refers to information about residents, such as personal information, age group, family composition, facility usage history, and survey results.

[0007] "External data" refers to data obtained from sources other than the condominium management system, such as government statistical data or reports on social trends.

[0008] "Preprocessing" refers to methods of removing or correcting noise, blank values, and inappropriate values ​​from collected data, and standardizing and anonymizing the data format.

[0009] "Features" refer to variables or indicators that extract important information in analysis and are used as inputs for machine learning models.

[0010] A "learning model" refers to an algorithm or statistical model that learns patterns from collected data and is used to make future predictions or classifications.

[0011] "Needs forecasting" refers to using learning models to predict future wants and needs of residents.

[0012] "Optimization proposals" refer to providing proposals for restructuring shared facilities and new community activities based on the results of needs predictions.

[0013] "Feedback" refers to the opinions and reactions that residents provide to proposals. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention relates to a system that predicts the future needs of residents of large-scale apartment buildings, optimizes shared facilities, and proposes community activities. The system is composed of a server, terminals, and users.

[0036] server

[0037] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices. Specifically, it collects information on residents' ages, family composition, past facility usage history, and survey results, and stores this information in a database. It also periodically obtains external data, such as government statistical data and information on social trends, and integrates these data.

[0038] The server then cleanses the collected data, removing blank and irrelevant values, standardizing the format, and anonymizing the data to protect residents' privacy.

[0039] Once preprocessing is complete, the server extracts features. Important variables are selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests or neural networks are used to create a model for predicting future needs.

[0040] Using the trained model, the server predicts the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, if the prediction results indicate an aging population, it will propose the establishment of fitness facilities and medical consultation rooms for the elderly.

[0041] The server then notifies the apartment management company of the generated proposal and generates a proposal document, which is then uploaded to the resident app and web portal.

[0042] Terminal

[0043] The terminals provide an interface for residents to review the proposals and provide feedback. For example, a survey about new proposals can be sent to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[0044] User

[0045] Users, or residents, can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, and specific requests. This allows the entire system to be optimized to meet the actual needs of residents.

[0046] Specific examples

[0047] For example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[0048] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0049] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0050] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0051] Residents can review these suggestions and provide feedback, which is then fed back into the server and used to refine the predictive model. In this way, the system can always respond to residents' needs and provide the optimal environment.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The server collects resident data from the apartment management system and smart devices, including the resident's age, family composition, past facility usage history, and survey results, and stores this information in a database.

[0055] Step 2:

[0056] The server periodically retrieves external data (government statistics and information on social trends) and integrates it with resident data.

[0057] Step 3:

[0058] The server preprocesses the collected data, specifically removing blank and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[0059] Step 4:

[0060] The server extracts features from the preprocessed data, selecting important variables from residents' age groups, family composition, facility usage history, and external data, and uses them as input for the machine learning model.

[0061] Step 5:

[0062] The server uses the extracted features to train machine learning models, specifically algorithms such as random forests and neural networks, to create models that predict future needs.

[0063] Step 6:

[0064] The server uses the trained model to predict the needs of residents 20-30 years into the future, determining, for example, the need for senior living facilities or family play areas.

[0065] Step 7:

[0066] Based on the prediction results, the server generates suggestions for restructuring shared facilities and new community activities, such as converting a fitness center into a senior rehabilitation center or expanding a community center.

[0067] Step 8:

[0068] The server then notifies the apartment management company of the generated proposal, which then creates a proposal document, which is then uploaded to the resident app or web portal.

[0069] Step 9:

[0070] The terminals distribute a questionnaire about the new proposal to residents, who then provide their opinions about the proposal via the terminals.

[0071] Step 10:

[0072] Users (residents) use terminals to answer questionnaires and provide feedback on their opinions and requests.

[0073] Step 11:

[0074] The server collects feedback from residents and stores it in a database for analysis, improving the accuracy of the predictive model and incorporating it into future proposals.

[0075] This series of processes enables the system to flexibly respond to the changing needs of residents and provide optimal shared facilities and community activities.

[0076] Example 1

[0077] 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."

[0078] In today's large-scale apartment complexes, accurately predicting residents' future needs and optimizing shared facilities and community activities accordingly is a difficult task. In particular, there is a need to propose facilities that respond to changes in residents' living environments and age structures, and to build a feedback system that reflects residents' opinions. However, current systems have difficulty meeting these requirements and are unable to respond to residents' actual needs.

[0079] 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.

[0080] In this invention, the server includes a means for collecting resident data, a means for preprocessing the collected resident data, and a means for extracting features from the preprocessed data and training a machine learning model, thereby enabling accurate prediction of future needs of residents and optimization of shared facilities and community activities based on the prediction.

[0081] "Resident data" refers to information about individual residents living in large apartment complexes, including, for example, age, family composition, past facility usage history, and survey results.

[0082] "Means of data preprocessing" refers to technical methods for processing collected data, such as removing blank or inappropriate values, standardizing formats, and anonymizing data.

[0083] "Features" are particularly important variables or parameters in the data used to train a learning model, including, for example, the age group and family composition of residents, facility usage history, etc.

[0084] A "machine learning model" is a mathematical framework for analyzing large amounts of data and making patterns and predictions based on specific algorithms. Typical examples include random forests and neural networks.

[0085] "Means to predict future needs" refers to technology that uses trained machine learning models to predict residents' future demands and requirements and present specific suggestions and countermeasures.

[0086] "Shared facilities" refer to facilities and areas set up for joint use by residents within a large apartment complex, including fitness facilities, rehabilitation facilities, and community centers.

[0087] "Feedback collection means" refers to the methods and tools used to collect opinions and evaluations of the proposals from residents, and can be done, for example, through a questionnaire form or a web portal.

[0088] "Means to improve the model" refers to techniques that analyze collected feedback and use it to adjust the parameters and algorithms of machine learning models to improve the model's accuracy and predictive capabilities.

[0089] "External data" refers to external information, such as government statistical data and information on social trends, separate from data on the apartment building management system and residents.

[0090] This invention relates to a system that predicts the future needs of residents in large-scale apartment buildings, optimizes shared facilities, and proposes community activities. The system consists of three elements: a server, terminals, and users.

[0091] System Overview

[0092] 1. Server

[0093] The server plays a central role in collecting, preprocessing, analyzing, and predicting the main data. Specifically, it performs the following tasks:

[0094] Data collection: The server collects resident data from the apartment management system and smart devices via APIs. For example, information such as resident age, family composition, past facility usage history, and survey results is collected and stored in a database. It also uses scraping and APIs from external services to collect government statistical data and information on social trends.

[0095] Data preprocessing: Collected data is processed to detect and complete blank and inappropriate values, standardize formats, and anonymize data, thereby improving data quality and protecting privacy.

[0096] Feature extraction and model training: Important features such as residents' age groups, family composition, and facility usage history are extracted from the preprocessed data. Then, machine learning algorithms such as random forests and neural networks are used to train models to predict future needs.

[0097] Generation of prediction results and recommendations: The trained model is used to predict the needs of residents 20-30 years into the future, and based on the results, it generates recommendations for optimizing shared facilities and community activities, such as establishing rehabilitation facilities for the elderly or event spaces for families with children.

[0098] Proposal notification and feedback collection: The generated proposals are notified to the apartment management company, and a proposal document is generated. The proposal document is also uploaded to the resident app and web portal.

[0099] 2. Terminal

[0100] The terminal will serve as an interface for residents to review the proposals and provide feedback. Specifically, it has the following functions:

[0101] Proposal notification: Notify residents of new proposals through their device (app or web portal), for example by sending a push notification to residents through a smartphone app.

[0102] Providing feedback: Provide a function that allows residents to input their opinions, specific requests, and other feedback regarding the proposals via their devices. For example, provide a questionnaire form to collect residents' opinions.

[0103] 3. Users

[0104] The user, i.e., the resident, is responsible for checking the proposals via a terminal and providing feedback. Specifically, he or she performs the following actions:

[0105] Review proposals: Residents review the proposals provided in the app or web portal and understand their contents.

[0106] Providing feedback: Residents can provide feedback on proposals, including pros and cons, opinions, and specific requests, so the entire system can be optimized based on residents' actual needs.

[0107] Specific examples

[0108] For example, the following predictions and proposals may be made for a large apartment complex:

[0109] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0110] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0111] Proposal: Renovate the fitness facility into a rehabilitation center for seniors, and expand the community center to include an event space for parents.

[0112] Residents can review these suggestions and provide feedback, which is then analyzed by the server and used to improve the accuracy of the predictive model. In this way, the system can always respond to residents' latest needs and provide the optimal environment.

[0113] Prompt Sentence Examples

[0114] "Based on the following input data, predict the needs of residents of a large apartment complex 20 years from now and propose optimization plans for shared facilities: The average age of residents is increasing year by year. The number of residents with families is increasing. Use of the fitness facility is decreasing, while use of the community center is increasing."

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1: Data collection

[0117] The server collects information about residents from the apartment management system and smart devices. Specifically, it obtains residents' ages, family composition, past facility usage history, and survey results through APIs. It also uses APIs from external services to collect government statistical data and data on social trends. The input is raw data from the apartment management system and external data APIs, and the output is structured data stored in a database.

[0118] Step 2: Data Preprocessing

[0119] The server preprocesses the collected data. Specific operations include removing empty and inappropriate values, standardizing formats, and anonymizing data. For example, standardizing date formats and hashing identifying information. The input is raw data, and the output is preprocessed, clean data.

[0120] Step 3: Feature extraction

[0121] The server extracts features from the preprocessed data. Specific operations include selecting important variables and parameters from the data. For example, the age group, family structure, and facility usage history of residents are extracted as features. The input is the preprocessed data, and the output is feature data used to train the machine learning model.

[0122] Step 4: Model training

[0123] The server uses the extracted features to train a machine learning model, specifically using algorithms such as random forests and neural networks. The input is the feature data, and the output is the trained machine learning model.

[0124] Step 5: Anticipate future needs

[0125] The server uses the trained model to predict future needs of residents, such as the need for rehabilitation facilities for the elderly or event spaces for families with children. The input is new data, and the output is information about predicted needs.

[0126] Step 6: Generate proposals

[0127] The server generates optimization proposals for shared facilities and community activities based on the prediction results. Specific actions include proposing to convert a fitness center into a rehabilitation facility for the elderly or to expand a community center to include an event space for the parenting generation. The input is the prediction data, and the output is the specific proposals.

[0128] Step 7: Proposal Notification

[0129] The server notifies the condominium management company of the generated proposal and also uploads it to the resident app and web portal. The device then sends push notifications and emails to notify the residents of the proposal. The input is the proposal content, and the output is the notified proposal.

[0130] Step 8: Gather feedback

[0131] The terminal collects feedback from residents. Specifically, it provides a questionnaire form in which residents can enter their opinions, whether they agree or disagree with the proposal, and their specific requests. Users enter their own opinions through this form. The input is the residents' opinions and feedback, and the output is the collected feedback data.

[0132] Step 9: Integrate feedback and retrain the model

[0133] The server analyzes the collected feedback and uses it to improve the machine learning model. Specific operations include text analysis of the feedback data and tuning the model parameters. The input is the feedback data, and the output is an improved machine learning model.

[0134] (Application example 1)

[0135] 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."

[0136] Existing large-scale condominium management systems have difficulty accurately predicting residents' future needs and optimizing facilities and proposing community activities based on those needs. Furthermore, autonomous vehicles lacked mechanisms for providing optimal routes and services tailored to passenger needs. This resulted in the inability to provide the services desired by residents and passengers in a timely manner, leading to lower satisfaction and a deterioration in efficiency.

[0137] 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.

[0138] In this invention, the server includes means for collecting resident data, means for preprocessing the collected data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activity proposals based on the needs prediction results, means for collecting resident feedback on the proposals, means for collecting vehicle usage history and passenger data and generating optimal routes based on the predicted needs, means for providing the optimal routes using an on-board computer, and means for improving the model using the collected feedback. This makes it possible to accurately predict the needs of residents and passengers and provide optimal services and proposals at the appropriate time.

[0139] "Resident data" refers to information such as the age, family composition, past facility usage history, and survey results of individuals living in the apartment complex.

[0140] "Preprocessing" refers to the process of cleansing collected data, removing blank and inappropriate values, and standardizing the format.

[0141] "Features" refer to important variables and patterns extracted from data to optimize the performance of machine learning models.

[0142] A "learning model" refers to an algorithm or model that learns from collected data and makes predictions or classifications based on that data.

[0143] "Trained Model" refers to a predictive model that has been tuned by a machine learning algorithm using collected data.

[0144] "Future needs" refers to the facility usage and service requirements that residents and passengers are expected to require in the future.

[0145] "Shared facilities" refers to facilities and spaces within an apartment building that are shared and used by residents, such as a fitness gym or community center.

[0146] "Optimal route" refers to the optimal route selected for an autonomous vehicle to transport passengers to their destination efficiently and safely.

[0147] "On-board computer" refers to a computer device installed inside a vehicle for data processing and control.

[0148] "Feedback" refers to opinions and evaluations of suggestions and services collected from residents and passengers.

[0149] "Model improvement" refers to the process of using collected feedback to improve the accuracy and performance of existing machine learning models.

[0150] MODE FOR CARRYING OUT THE INVENTION

[0151] server

[0152] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects "resident data" from the apartment management system and smart devices. Specifically, this information includes age, family composition, past facility usage history, and survey results. It also collects usage history and passenger data from autonomous vehicles. Furthermore, it regularly obtains external data, such as government statistical data and information on social trends, and integrates this data into the database.

[0153] The server then "pre-processes" the collected data: it cleanses it, removes blank or irrelevant values, standardizes the format, and anonymizes it to protect residents' privacy.

[0154] Once preprocessing is complete, the server extracts "features," which are key variables selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests and neural networks are used to create a model for predicting future needs.

[0155] Using the trained model, the server predicts the needs of residents and passengers 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. It also generates "optimal routes" for autonomous vehicles based on the predicted needs. The on-board computer provides optimal routes, increasing passenger satisfaction.

[0156] The server then notifies the apartment management company or vehicle operation manager of the generated proposal, and generates a proposal document, which is then uploaded to an app or web portal for residents and passengers.

[0157] Terminal

[0158] The terminals provide an interface for residents and passengers to review the proposals and provide feedback. For example, a survey about new proposals could be distributed through an app or web portal. Residents and passengers can directly provide feedback on the proposals. This allows the entire system to be optimized to better meet actual needs.

[0159] User

[0160] Users, i.e., residents and passengers, can review the proposals and provide feedback via their devices, such as whether they agree or disagree with the new facility proposal, their opinions, or specific requests, so that the entire system can respond to the actual needs of residents and passengers.

[0161] Specific examples

[0162] As a concrete example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[0163] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0164] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0165] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0166] Also, in autonomous vehicles, optimal routes are generated based on passenger data. For example, the following prompts can be used to gather feedback:

[0167] Collect feedback from passengers after they arrive at their destination. Enter the following information:

[0168] Arrival time to destination

[0169] Services used (e.g. route flexibility, ride comfort, etc.)

[0170] comment

[0171] This allows us to collect feedback from residents and passengers and improve the accuracy of the model, so the system can always respond to their needs and provide the best possible environment.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] Data collection

[0175] The server collects "resident data" from the apartment management system and smart devices. This data includes age, family composition, past facility usage history, and survey results. It also collects usage history and passenger data from autonomous vehicles. Furthermore, external data such as government statistical data and social trend information is periodically acquired and integrated into the database.

[0176] Input: Data from management systems and smart devices

[0177] Output: Integrated database

[0178] Step 2:

[0179] Data Preprocessing

[0180] The server preprocesses the collected data: it cleanses it, removes blank and irrelevant values, standardizes the format, and anonymizes it to protect the privacy of residents.

[0181] Input: Integrated Database

[0182] Output: Preprocessed dataset

[0183] Step 3:

[0184] Feature extraction

[0185] The server extracts "features" from the preprocessed data by selecting important variables based on residents' age groups, family structure, facility usage history, and external data.

[0186] Input: Preprocessed dataset

[0187] Output: A dataset with extracted features

[0188] Step 4:

[0189] Training a machine learning model

[0190] The server uses the extracted features to train machine learning models, using algorithms such as random forests and neural networks to create models to predict future needs.

[0191] Input: Feature-extracted dataset

[0192] Output: A trained machine learning model

[0193] Step 5:

[0194] Anticipating future needs

[0195] Using the trained model, the server predicts the needs of residents and passengers 20-30 years into the future.

[0196] Input: A trained machine learning model

[0197] Output: Predicted future needs

[0198] Step 6:

[0199] Proposal generation

[0200] Based on the prediction results, the server generates plans for restructuring shared facilities, suggestions for new community activities, and optimal routes for self-driving vehicles.

[0201] Input: Projected future needs

[0202] Output: Generated proposals and optimal routes

[0203] Step 7:

[0204] proposal notification

[0205] The server then notifies the apartment management company or vehicle operation manager of the generated proposal, which then generates a proposal document, which is then uploaded to an app or web portal for residents and passengers.

[0206] Input: Generated proposals and optimal routes

[0207] Output: Proposal and uploaded content

[0208] Step 8:

[0209] Feedback collection

[0210] The terminals will then distribute surveys about the new proposals via an app or web portal, allowing residents and passengers to provide direct feedback on their opinions of the proposals.

[0211] Input: Uploaded proposal and feedback survey

[0212] Output: Collected feedback

[0213] Step 9:

[0214] Model Improvement

[0215] The server uses the collected feedback to retrain the model to improve its accuracy.

[0216] Input: Collected feedback

[0217] Output: An improved machine learning model

[0218] 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.

[0219] This invention relates to a system that predicts the future needs of residents of large-scale apartment buildings, optimizes shared facilities, and proposes community activities. This system is composed of a server, terminals, and users, and is also combined with an emotion engine that recognizes user emotions.

[0220] server

[0221] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices. Specifically, it acquires information on residents' ages, family composition, past facility usage history, and survey results, and stores this information in a database. It also periodically acquires external data, such as government statistical data and information on social trends, and integrates these data.

[0222] The server then preprocesses the collected data, specifically removing empty and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[0223] Once preprocessing is complete, the server extracts features. Important variables are selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests or neural networks are used to create a model for predicting future needs.

[0224] Using the trained model, the server predicts the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, if the prediction results indicate an aging population, it will propose the establishment of fitness facilities and medical consultation rooms for the elderly.

[0225] The server then notifies the apartment management company of the generated proposal and generates a proposal document, which is then uploaded to the resident app and web portal.

[0226] Terminal

[0227] The terminals provide an interface for residents to review the proposals and provide feedback. For example, a survey about new proposals can be sent to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[0228] User

[0229] Users, or residents, can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, and specific requests. This allows the entire system to be optimized to meet the actual needs of residents.

[0230] Emotion Engine

[0231] The emotion engine analyzes user feedback to identify its emotional tone. For example, it analyzes text and voice data entered by residents as feedback and extracts emotions such as dissatisfaction, satisfaction, and suggestions. The server uses the results of this emotion analysis to understand the nuances of the feedback and conduct more accurate needs assessments.

[0232] Specific examples

[0233] For example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[0234] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0235] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0236] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0237] Residents review these suggestions and provide feedback, which is analyzed through an emotion engine to detect the emotional tone of complaints or requests. For example, if many residents express dissatisfaction with a particular suggestion, the server will perform a new analysis to reassess the suggestion.

[0238] The feedback is then fed back into the server and used to refine the predictive model, ensuring the system is always responsive to residents' needs and providing optimal shared facilities and community activities.

[0239] The system will be able to adapt flexibly to changing needs of residents, maintaining long-term satisfaction, and use an emotion engine to gather more accurate feedback and provide specific, actionable recommendations.

[0240] The processing flow will be explained below.

[0241] Step 1:

[0242] The server collects resident data from the apartment management system and smart devices. Specifically, it obtains information such as the resident's age, family composition, past facility usage history, and survey results, and stores this information in a database. In addition, the server periodically obtains external data such as government statistical data and information on social trends, and integrates this data into the database.

[0243] Step 2:

[0244] The server preprocesses the collected data, specifically removing blank and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[0245] Step 3:

[0246] The server extracts features from the preprocessed data, selecting important variables from resident age groups, family composition, facility usage history, external data, etc., and uses these as input for the machine learning model.

[0247] Step 4:

[0248] The server uses the extracted features to train a machine learning model, such as a random forest or neural network algorithm, to create a model that predicts future needs.

[0249] Step 5:

[0250] The server uses the trained model to predict the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, it predicts the progression of aging and suggests the establishment of fitness facilities and medical consultation rooms for the elderly.

[0251] Step 6:

[0252] The server then notifies the apartment management company of the generated proposal, which then creates a proposal document, which is then uploaded to the resident app or web portal.

[0253] Step 7:

[0254] The terminals will send a questionnaire about the new proposal to residents, who will then answer the questionnaire and provide feedback on their opinions and requests regarding the proposal.

[0255] Step 8:

[0256] Users (residents) can review the proposals via their devices and input their own opinions and requests. For example, they can provide specific feedback such as "I support the proposal for a facility for the elderly" or "I hope the community center will be expanded."

[0257] Step 9:

[0258] The emotion engine analyzes collected feedback and identifies the user's emotional tone, for example, extracting emotions such as dissatisfaction, satisfaction, and suggestions from text and voice data, and generates emotion analysis results.

[0259] Step 10:

[0260] The server uses the feedback analyzed by the emotion engine to understand the nuances of the feedback and conduct more accurate needs assessments, for example, reconsidering and improving proposals that receive a lot of dissatisfaction feedback.

[0261] Step 11:

[0262] The server retrains the model based on the feedback to improve the accuracy of future suggestions, thereby continually adapting to the changing needs of residents.

[0263] As a concrete example, the following process takes place in a large apartment complex:

[0264] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0265] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0266] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0267] In this way, the system can adapt flexibly to changing needs of residents and maintain long-term satisfaction. The introduction of an emotion engine enables deeper feedback analysis, leading to specific and actionable recommendations.

[0268] Example 2

[0269] 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."

[0270] In today's large-scale apartment complexes, the lifestyle needs of residents continue to change over time. It is extremely important for apartment complex managers and residents to accurately predict future needs and plan and implement appropriate facilities and community activities. However, traditional methods rely primarily on short-term surveys and feedback, making it difficult to predict and propose long-term outcomes. Furthermore, the collected feedback often fails to accurately capture the emotional nuances of residents, which can lead to unnecessary issues and dissatisfaction. Another major challenge is conducting accurate data analysis while ensuring residents' privacy.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0272] In this invention, the server includes means for collecting resident data, means for preprocessing the collected resident data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activity proposals based on the needs prediction results, means for notifying residents of the generated proposals, means for collecting resident feedback on the proposals, means for analyzing the collected feedback to identify emotional tones, and means for improving the model using the collected feedback. This makes it possible to accurately predict long-term resident needs and make proposals that take emotional nuances into consideration, thereby increasing resident satisfaction and protecting resident privacy.

[0273] "Resident data" refers to information related to the residents of the apartment building, including, specifically, age, family composition, past facility usage history, survey results, etc.

[0274] "Preprocessing" refers to processing performed on collected data, including removing null and inappropriate values, standardizing data formats, and anonymizing personal information.

[0275] "Features" are important variables extracted from data and are used to train machine learning models.

[0276] A "learning model" is a mathematical model that uses machine learning algorithms to learn patterns from data and make future predictions or classifications.

[0277] "Needs forecasting" is the use of trained learning models to estimate the future wants and needs of residents.

[0278] "Optimization proposals" refer to the generation of improvement proposals for shared facilities and services based on the results of needs predictions.

[0279] "Community activity proposals" involve proposing new community events and activities based on the needs of residents.

[0280] "Feedback" refers to the opinions and thoughts that residents give about the proposals, and includes questionnaires and free comments.

[0281] "Emotional tone" refers to the emotional tendency extracted from the content of feedback, and includes classifications such as positive, negative, and neutral.

[0282] "Analysis" refers to the process of analyzing data to extract meaningful information, specifically identifying the emotional tone of feedback using the emotion engine.

[0283] "Refinement" refers to retraining a learning model based on collected feedback to improve its accuracy and performance.

[0284] This invention relates to a system that predicts the future needs of residents of a large-scale apartment complex, optimizes shared facilities, and proposes community activities.The system for implementing this invention is composed of a server, terminals, and users, and is further combined with an emotion engine that recognizes the user's emotions.

[0285] server

[0286] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices and stores it in a database. Specifically, it obtains information such as resident age, family composition, past facility usage history, and survey results. It also periodically obtains external data such as government statistical data and information on social trends, and integrates these data.

[0287] The server preprocesses the collected data. Specifically, it removes blank and inappropriate values ​​and standardizes the data format. It also anonymizes personal information to protect privacy. Python libraries such as pandas and NumPy can be used.

[0288] Once preprocessing is complete, the server extracts features, selects important variables based on residents' age groups, family composition, facility usage history, and external data, and trains a machine learning model. The trained model is created using tools such as Scikit-learn's RandomForestClassifier and TENSORFLOW®'s Keras.

[0289] Using the trained model, the server predicts residents' needs 20-30 years into the future. For example, if an aging population is predicted, the server generates proposals for establishing fitness facilities and medical consultation rooms for the elderly. The generated proposals are notified to the apartment management company and are also uploaded to the resident app and web portal.

[0290] Terminal

[0291] The terminals provide an interface for residents to review the proposals and provide feedback. Specifically, a survey about the new proposals is distributed to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[0292] User

[0293] Users (residents) can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, or specific requests. This feedback is used to optimize the entire system to better meet the actual needs of residents.

[0294] Emotion Engine

[0295] The emotion engine analyzes user feedback to identify its emotional tone. For example, it analyzes the text entered by the user as feedback and extracts emotions such as dissatisfaction, satisfaction, suggestion, etc. The server uses the emotion analysis results to understand the nuances of the feedback and perform more accurate needs assessment.

[0296] Specific examples

[0297] For example, in a large apartment complex, the following predictions and suggestions are made based on the collected data:

[0298] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0299] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0300] Proposal: Renovate the fitness center into a senior rehabilitation center, and expand the community center to include an event space for parents.

[0301] Residents review these suggestions and provide feedback, which is analyzed through an emotion engine to detect the emotional tone of complaints or requests. For example, if many residents express dissatisfaction with a particular suggestion, the server will perform a new analysis to reassess the suggestion.

[0302] Prompt Sentence Examples

[0303] Here are some example prompts to input to a generative AI model:

[0304] Predict the needs of the residents of an apartment complex 20 years from now and propose a plan to restructure the shared facilities based on that. Use the following data for your analysis: residents' age, family composition, past facility usage history, survey results, government statistics, and social trends. If the population is aging, include suggestions for adding facilities for the elderly and medical consultation rooms.

[0305] In this way, the system can flexibly respond to the changing needs of residents and always provide the best possible shared facilities and community activities. The emotion engine also allows for more accurate feedback and makes specific, actionable recommendations.

[0306] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0307] Step 1:

[0308] The server initiates the data collection process.

[0309] Input: Resident age, family composition, past facility usage history, survey results, government statistics, and social trends.

[0310] Specific operation: The server accesses the apartment management system and smart devices, sets them up to periodically collect data, and uses APIs to retrieve data from public databases and integrate it with internal data.

[0311] Output: Raw data is stored in a database.

[0312] Step 2:

[0313] The server pre-processes the collected data.

[0314] Input: Collected data stored in a database.

[0315] Specific actions: Detect and remove or correct empty or inappropriate values. Standardize data formats and anonymize personal information using Python's pandas and NumPy libraries.

[0316] Output: A clean, pre-processed dataset.

[0317] Step 3:

[0318] The server extracts features.

[0319] Input: A clean, pre-processed dataset.

[0320] Specific operation: Using the Scikit-learn library, important features are selected based on residents' age groups, family composition, facility usage history, and external data.

[0321] Output: A dataset containing the features.

[0322] Step 4:

[0323] The server trains the learning model.

[0324] Input: A dataset containing features.

[0325] Specific operation: Train a model using machine learning algorithms such as Scikit-learn's RandomForestClassifier or TensorFlow's Keras.

[0326] Output: A trained predictive model.

[0327] Step 5:

[0328] The server predicts the future needs of residents.

[0329] Input: A trained predictive model.

[0330] What it does: Use the trained model to predict the needs of residents 20-30 years into the future, for example by simulating scenarios where the population is aging.

[0331] Output: Projected future needs.

[0332] Step 6:

[0333] The server generates optimization suggestions based on the prediction results.

[0334] Input: Projected future needs.

[0335] Specific actions: Generate specific proposals such as rehabilitation facilities for the elderly and event spaces for the parenting generation.

[0336] Output: Proposal.

[0337] Step 7:

[0338] The server notifies the generated proposal and sends it to the terminal.

[0339] Input: Proposal.

[0340] Specific actions: The proposal is notified to the apartment management company and also uploaded to the resident app and web portal.

[0341] Output: Notification of proposal.

[0342] Step 8:

[0343] The device displays the proposals to residents and collects their feedback.

[0344] Input: Proposal.

[0345] What it does: Collect feedback through a citizen interface in the form of surveys and free text.

[0346] Output: Collected feedback.

[0347] Step 9:

[0348] An emotion engine analyzes feedback to identify emotional tone.

[0349] Input: Collected feedback.

[0350] What it does: Uses natural language processing techniques to classify positive, negative, and neutral sentiment.

[0351] Output: Emotional tone analysis results.

[0352] Step 10:

[0353] The server improves the model based on the analysis results.

[0354] Input: Emotional tone analysis results.

[0355] Specific actions: Retrain your learning model to take into account the emotional tone and specific opinions of the feedback.

[0356] Output: An improved predictive model.

[0357] Step 11:

[0358] The server uses the improved model to generate new proposals.

[0359] Input: Improved predictive model.

[0360] Specific Action: Generate an optimized proposal and notify the residents again.

[0361] Output: A new proposal.

[0362] These steps enable the system to constantly adapt to the changing needs of residents and provide optimal shared facilities and community activities.

[0363] (Application example 2)

[0364] 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."

[0365] In today's large-scale condominiums, it is difficult to accurately predict residents' future needs and optimize shared facilities and community activities. Furthermore, because sentiment analysis to effectively utilize resident feedback and gain a deeper understanding has not been implemented, proposals can sometimes deviate from actual needs. Furthermore, because there is no way to use resident data to optimize the operation of physical stores, store services and products do not adequately meet resident demands. These issues need to be resolved.

[0366] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting resident data, means for preprocessing the collected resident data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activities based on the needs prediction results, means for collecting resident feedback on the proposals, means for emotionally analyzing the resident feedback and determining the emotional tone of the feedback, means for improving the model using the collected feedback, and means for generating optimization proposals for brick-and-mortar store operations using resident data. This not only enables accurate prediction of future needs of residents and optimization of shared facilities and community activities, but also makes it possible to reflect detailed feedback through resident emotional analysis and further optimize brick-and-mortar store operations.

[0367] "Resident data" refers to information about individuals and families residing in the apartment complex, including age, family composition, past facility usage history, survey results, etc.

[0368] "Preprocessing" is the process of filling in blanks, removing inappropriate values, standardizing formats, and anonymizing personal information to prepare the collected raw data for analysis.

[0369] "Features" are important variables in the data used to train machine learning models, and include residents' age groups, family composition, facility usage history, external data, etc.

[0370] A "learning model" is an implementation of an algorithm that learns specific patterns and relationships from collected data and makes future predictions.

[0371] Forecasting "needs" means using a trained learning model to estimate the wants and requirements of residents at a specific future point in time.

[0372] The "Optimization Proposal for Shared Facilities" provides specific improvement plans for efficient use of shared spaces and facilities within the condominium based on the predicted needs of residents.

[0373] "Community activity proposals" are proposals for planning events or activities to promote interaction and cooperation among residents.

[0374] "Feedback collection methods" refers to methods and tools used to collect opinions, comments, ratings, and other responses from residents.

[0375] "Sentiment analysis" is a technology that analyzes collected feedback text and audio data to identify the emotional tone contained therein.

[0376] The "Optimization proposal for physical store operations" uses resident data to improve the services and product lineup of specific stores, providing operations that better meet customer needs.

[0377] MODE FOR CARRYING OUT THE INVENTION

[0378] This invention relates to a system that utilizes resident data of large-scale apartment buildings to predict future needs and optimize the operation of shared facilities and brick-and-mortar stores. Below, we will explain in detail how to specifically implement this invention.

[0379] server

[0380] The server is the main device responsible for data collection, preprocessing, analysis, and prediction. The server in this system collects resident data from the apartment management system and smart devices, and preprocesses that data. Specifically, it stores residents' ages, family composition, past facility usage history, and survey results in a database. It also periodically obtains external data such as government statistical data and information on social trends, and integrates them.

[0381] In the data preprocessing stage, we remove empty and inappropriate values, standardize the data format, and protect privacy by anonymizing personal information.

[0382] Once preprocessing is complete, the server extracts features, selecting important variables based on residents' age groups, family composition, facility usage history, and external data, and then training a machine learning model. For example, algorithms such as random forests and neural networks are used to create a model for predicting future needs.

[0383] Using the trained model, the server predicts residents' future needs and generates optimization proposals for shared facilities and community activities. It also uses resident data to make optimization proposals for brick-and-mortar store operations. Based on the prediction results, it suggests, for example, the establishment of facilities for the elderly or play areas for children.

[0384] Terminal

[0385] The terminals are the interface through which residents can review the proposals and provide feedback. For example, residents can use their smartphones or computers to answer a questionnaire about the new proposals. Their feedback is sent to the server and analyzed through the emotion engine.

[0386] User

[0387] Users (residents) review the proposals via their devices and provide their feedback. The feedback is sent to the server, where the emotional tone is analyzed by the emotion engine. For example, users can enter their approval or disapproval of a new facility proposal, as well as specific requests. The server uses the results of this emotion analysis to understand the nuances of the feedback and improve the accuracy of the prediction model.

[0388] Emotion Engine

[0389] The emotion engine analyzes the text and voice data of user feedback to extract emotions such as dissatisfaction, satisfaction, suggestion, etc. This allows the server to understand the emotional tone of the feedback and perform more accurate needs assessment.

[0390] Specific examples

[0391] For example, in a large apartment complex, the following predictions and suggestions may be made:

[0392] The average age of residents is rising, and the number of families living there is increasing.

[0393] Based on the collected data, a proposal was made to renovate the fitness facility into a rehabilitation facility for the elderly.

[0394] We propose expanding the community center and creating an event space for people raising children.

[0395] Residents can review these suggestions and provide feedback, including specific requests for suggestions. The feedback is analyzed through an emotion engine, and the server uses the results to reassess the suggestions and generate more accurate ones.

[0396] Prompt Sentence Examples

[0397] Create a program that uses the residents' age, family composition, past facility usage history, and survey results to predict their needs 20-30 years from now using a random forest model, and proposes the establishment of rehabilitation facilities for the elderly and event spaces for childcare.

[0398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0399] Step 1:

[0400] The server collects resident data from the apartment management system and smart devices. Specifically, it acquires information such as resident age, family composition, past facility usage history, and survey results, and stores it in a database. Input data comes in a variety of formats, but storing it in a unified database enables efficient management. The output is a unified database.

[0401] Step 2:

[0402] The server preprocesses the collected resident data. Specifically, it removes blank and inappropriate values, standardizes the data format, and anonymizes personal information. The input is the collected raw data in various formats, and the output is consistent, anonymized data with no blank values.

[0403] Step 3:

[0404] The server extracts features from the preprocessed data. During this process, important variables are selected based on the residents' age group, family structure, facility usage history, and external data (social trends, etc.). The input is the preprocessed data, and the output is a set of training features.

[0405] Step 4:

[0406] The server uses the extracted features to train a machine learning model, specifically using algorithms such as random forests or neural networks. The training dataset is fed to the model to improve its predictive capabilities. The input is the extracted feature set, and the output is the trained model.

[0407] Step 5:

[0408] The server uses the trained model to predict future needs of residents. The input is new or updated resident data, and the output is predicted future needs. For example, the prediction may be that demand for elderly care facilities will increase.

[0409] Step 6:

[0410] The server generates optimization proposals for shared facilities and community activities based on the needs prediction results. Specifically, it proposes the relocation or new construction of fitness facilities for the elderly and event spaces for children based on the prediction results. The input is the needs prediction results, and the output is the specific proposals.

[0411] Step 7:

[0412] The terminal distributes proposals to residents and collects feedback. The input is the proposal received from the server, and the output is feedback from residents. Residents fill out questionnaires and enter comments via their smartphones or computers.

[0413] Step 8:

[0414] The server performs sentiment analysis on the residents' feedback to determine its emotional tone. Specifically, it feeds the feedback text and audio data into a sentiment analysis engine, which extracts emotional tones such as satisfaction, dissatisfaction, and suggestions. The input is the feedback data, and the output is the sentiment analysis results.

[0415] Step 9:

[0416] The server uses the collected feedback to refine the model. It incorporates the sentiment analysis results into a learning algorithm to improve the accuracy of the predictive model. The input is the sentiment analysis results, and the output is an improved learning model.

[0417] Step 10:

[0418] The server uses resident data to generate optimization proposals for brick-and-mortar store operations. Based on the needs prediction results, it adjusts the product and service lineup. For example, it proposes increasing rehabilitation products for the elderly or events for families. The input is the needs prediction results, and the output is optimization proposals for the brick-and-mortar store.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] [Second embodiment]

[0423] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] In the smart glasses 214, 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.

[0434] 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."

[0435] This invention relates to a system that predicts the future needs of residents of large-scale apartment buildings, optimizes shared facilities, and proposes community activities. The system is composed of a server, terminals, and users.

[0436] server

[0437] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices. Specifically, it collects information on residents' ages, family composition, past facility usage history, and survey results, and stores this information in a database. It also periodically obtains external data, such as government statistical data and information on social trends, and integrates these data.

[0438] The server then cleanses the collected data, removing blank and irrelevant values, standardizing the format, and anonymizing the data to protect residents' privacy.

[0439] Once preprocessing is complete, the server extracts features. Important variables are selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests or neural networks are used to create a model for predicting future needs.

[0440] Using the trained model, the server predicts the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, if the prediction results indicate an aging population, it will propose the establishment of fitness facilities and medical consultation rooms for the elderly.

[0441] The server then notifies the apartment management company of the generated proposal and generates a proposal document, which is then uploaded to the resident app and web portal.

[0442] Terminal

[0443] The terminals provide an interface for residents to review the proposals and provide feedback. For example, a survey about new proposals can be sent to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[0444] User

[0445] Users, or residents, can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, and specific requests. This allows the entire system to be optimized to meet the actual needs of residents.

[0446] Specific examples

[0447] For example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[0448] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0449] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0450] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0451] Residents can review these suggestions and provide feedback, which is then fed back into the server and used to refine the predictive model. In this way, the system can always respond to residents' needs and provide the optimal environment.

[0452] The processing flow will be explained below.

[0453] Step 1:

[0454] The server collects resident data from the apartment management system and smart devices, including the resident's age, family composition, past facility usage history, and survey results, and stores this information in a database.

[0455] Step 2:

[0456] The server periodically retrieves external data (government statistics and information on social trends) and integrates it with resident data.

[0457] Step 3:

[0458] The server preprocesses the collected data, specifically removing blank and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[0459] Step 4:

[0460] The server extracts features from the preprocessed data, selecting important variables from residents' age groups, family composition, facility usage history, and external data, and uses them as input for the machine learning model.

[0461] Step 5:

[0462] The server uses the extracted features to train machine learning models, specifically algorithms such as random forests and neural networks, to create models that predict future needs.

[0463] Step 6:

[0464] The server uses the trained model to predict the needs of residents 20-30 years into the future, determining, for example, the need for senior living facilities or family play areas.

[0465] Step 7:

[0466] Based on the prediction results, the server generates suggestions for restructuring shared facilities and new community activities, such as converting a fitness center into a senior rehabilitation center or expanding a community center.

[0467] Step 8:

[0468] The server then notifies the apartment management company of the generated proposal, which then creates a proposal document, which is then uploaded to the resident app or web portal.

[0469] Step 9:

[0470] The terminals distribute a questionnaire about the new proposal to residents, who then provide their opinions about the proposal via the terminals.

[0471] Step 10:

[0472] Users (residents) use terminals to answer questionnaires and provide feedback on their opinions and requests.

[0473] Step 11:

[0474] The server collects feedback from residents and stores it in a database for analysis, improving the accuracy of the predictive model and incorporating it into future proposals.

[0475] This series of processes enables the system to flexibly respond to the changing needs of residents and provide optimal shared facilities and community activities.

[0476] Example 1

[0477] 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."

[0478] In today's large-scale apartment complexes, accurately predicting residents' future needs and optimizing shared facilities and community activities accordingly is a difficult task. In particular, there is a need to propose facilities that respond to changes in residents' living environments and age structures, and to build a feedback system that reflects residents' opinions. However, current systems have difficulty meeting these requirements and are unable to respond to residents' actual needs.

[0479] 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.

[0480] In this invention, the server includes a means for collecting resident data, a means for preprocessing the collected resident data, and a means for extracting features from the preprocessed data and training a machine learning model, thereby enabling accurate prediction of future needs of residents and optimization of shared facilities and community activities based on the prediction.

[0481] "Resident data" refers to information about individual residents living in large apartment complexes, including, for example, age, family composition, past facility usage history, and survey results.

[0482] "Means of data preprocessing" refers to technical methods for processing collected data, such as removing blank or inappropriate values, standardizing formats, and anonymizing data.

[0483] "Features" are particularly important variables or parameters in the data used to train a learning model, including, for example, the age group and family composition of residents, facility usage history, etc.

[0484] A "machine learning model" is a mathematical framework for analyzing large amounts of data and making patterns and predictions based on specific algorithms. Typical examples include random forests and neural networks.

[0485] "Means to predict future needs" refers to technology that uses trained machine learning models to predict residents' future demands and requirements and present specific suggestions and countermeasures.

[0486] "Shared facilities" refer to facilities and areas set up for joint use by residents within a large apartment complex, including fitness facilities, rehabilitation facilities, and community centers.

[0487] "Feedback collection means" refers to the methods and tools used to collect opinions and evaluations of the proposals from residents, and can be done, for example, through a questionnaire form or a web portal.

[0488] "Means to improve the model" refers to techniques that analyze collected feedback and use it to adjust the parameters and algorithms of machine learning models to improve the model's accuracy and predictive capabilities.

[0489] "External data" refers to external information, such as government statistical data and information on social trends, separate from data on the apartment building management system and residents.

[0490] This invention relates to a system that predicts the future needs of residents in large-scale apartment buildings, optimizes shared facilities, and proposes community activities. The system consists of three elements: a server, terminals, and users.

[0491] System Overview

[0492] 1. Server

[0493] The server plays a central role in collecting, preprocessing, analyzing, and predicting the main data. Specifically, it performs the following tasks:

[0494] Data collection: The server collects resident data from the apartment management system and smart devices via APIs. For example, information such as resident age, family composition, past facility usage history, and survey results is collected and stored in a database. It also uses scraping and APIs from external services to collect government statistical data and information on social trends.

[0495] Data preprocessing: Collected data is processed to detect and complete blank and inappropriate values, standardize formats, and anonymize data, thereby improving data quality and protecting privacy.

[0496] Feature extraction and model training: Important features such as residents' age groups, family composition, and facility usage history are extracted from the preprocessed data. Then, machine learning algorithms such as random forests and neural networks are used to train models to predict future needs.

[0497] Generation of prediction results and recommendations: The trained model is used to predict the needs of residents 20-30 years into the future, and based on the results, it generates recommendations for optimizing shared facilities and community activities, such as establishing rehabilitation facilities for the elderly or event spaces for families with children.

[0498] Proposal notification and feedback collection: The generated proposals are notified to the apartment management company, and a proposal document is generated. The proposal document is also uploaded to the resident app and web portal.

[0499] 2. Terminal

[0500] The terminal will serve as an interface for residents to review the proposals and provide feedback. Specifically, it has the following functions:

[0501] Proposal notification: Notify residents of new proposals through their device (app or web portal), for example by sending a push notification to residents through a smartphone app.

[0502] Providing feedback: Provide a function that allows residents to input their opinions, specific requests, and other feedback regarding the proposals via their devices. For example, provide a questionnaire form to collect residents' opinions.

[0503] 3. Users

[0504] The user, i.e., the resident, is responsible for checking the proposals via a terminal and providing feedback. Specifically, he or she performs the following actions:

[0505] Review proposals: Residents review the proposals provided in the app or web portal and understand their contents.

[0506] Providing feedback: Residents can provide feedback on proposals, including pros and cons, opinions, and specific requests, so the entire system can be optimized based on residents' actual needs.

[0507] Specific examples

[0508] For example, the following predictions and proposals may be made for a large apartment complex:

[0509] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0510] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0511] Proposal: Renovate the fitness facility into a rehabilitation center for seniors, and expand the community center to include an event space for parents.

[0512] Residents can review these suggestions and provide feedback, which is then analyzed by the server and used to improve the accuracy of the predictive model. In this way, the system can always respond to residents' latest needs and provide the optimal environment.

[0513] Prompt Sentence Examples

[0514] "Based on the following input data, predict the needs of residents of a large apartment complex 20 years from now and propose optimization plans for shared facilities: The average age of residents is increasing year by year. The number of residents with families is increasing. Use of the fitness facility is decreasing, while use of the community center is increasing."

[0515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0516] Step 1: Data collection

[0517] The server collects information about residents from the apartment management system and smart devices. Specifically, it obtains residents' ages, family composition, past facility usage history, and survey results through APIs. It also uses APIs from external services to collect government statistical data and data on social trends. The input is raw data from the apartment management system and external data APIs, and the output is structured data stored in a database.

[0518] Step 2: Data Preprocessing

[0519] The server preprocesses the collected data. Specific operations include removing empty and inappropriate values, standardizing formats, and anonymizing data. For example, standardizing date formats and hashing identifying information. The input is raw data, and the output is preprocessed, clean data.

[0520] Step 3: Feature extraction

[0521] The server extracts features from the preprocessed data. Specific operations include selecting important variables and parameters from the data. For example, the age group, family structure, and facility usage history of residents are extracted as features. The input is the preprocessed data, and the output is feature data used to train the machine learning model.

[0522] Step 4: Model training

[0523] The server uses the extracted features to train a machine learning model, specifically using algorithms such as random forests and neural networks. The input is the feature data, and the output is the trained machine learning model.

[0524] Step 5: Anticipate future needs

[0525] The server uses the trained model to predict future needs of residents, such as the need for rehabilitation facilities for the elderly or event spaces for families with children. The input is new data, and the output is information about predicted needs.

[0526] Step 6: Generate proposals

[0527] The server generates optimization proposals for shared facilities and community activities based on the prediction results. Specific actions include proposing to convert a fitness center into a rehabilitation facility for the elderly or to expand a community center to include an event space for the parenting generation. The input is the prediction data, and the output is the specific proposals.

[0528] Step 7: Proposal Notification

[0529] The server notifies the condominium management company of the generated proposal and also uploads it to the resident app and web portal. The device then sends push notifications and emails to notify the residents of the proposal. The input is the proposal content, and the output is the notified proposal.

[0530] Step 8: Gather feedback

[0531] The terminal collects feedback from residents. Specifically, it provides a questionnaire form in which residents can enter their opinions, whether they agree or disagree with the proposal, and their specific requests. Users enter their own opinions through this form. The input is the residents' opinions and feedback, and the output is the collected feedback data.

[0532] Step 9: Integrate feedback and retrain the model

[0533] The server analyzes the collected feedback and uses it to improve the machine learning model. Specific operations include text analysis of the feedback data and tuning the model parameters. The input is the feedback data, and the output is an improved machine learning model.

[0534] (Application example 1)

[0535] 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."

[0536] Existing large-scale condominium management systems have difficulty accurately predicting residents' future needs and optimizing facilities and proposing community activities based on those needs. Furthermore, autonomous vehicles lacked mechanisms for providing optimal routes and services tailored to passenger needs. This resulted in the inability to provide the services desired by residents and passengers in a timely manner, leading to lower satisfaction and a deterioration in efficiency.

[0537] 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.

[0538] In this invention, the server includes means for collecting resident data, means for preprocessing the collected data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activity proposals based on the needs prediction results, means for collecting resident feedback on the proposals, means for collecting vehicle usage history and passenger data and generating optimal routes based on the predicted needs, means for providing the optimal routes using an on-board computer, and means for improving the model using the collected feedback. This makes it possible to accurately predict the needs of residents and passengers and provide optimal services and proposals at the appropriate time.

[0539] "Resident data" refers to information such as the age, family composition, past facility usage history, and survey results of individuals living in the apartment complex.

[0540] "Preprocessing" refers to the process of cleansing collected data, removing blank and inappropriate values, and standardizing the format.

[0541] "Features" refer to important variables and patterns extracted from data to optimize the performance of machine learning models.

[0542] A "learning model" refers to an algorithm or model that learns from collected data and makes predictions or classifications based on that data.

[0543] "Trained Model" refers to a predictive model that has been tuned by a machine learning algorithm using collected data.

[0544] "Future needs" refers to the facility usage and service requirements that residents and passengers are expected to require in the future.

[0545] "Shared facilities" refers to facilities and spaces within an apartment building that are shared and used by residents, such as a fitness gym or community center.

[0546] "Optimal route" refers to the optimal route selected for an autonomous vehicle to transport passengers to their destination efficiently and safely.

[0547] "On-board computer" refers to a computer device installed inside a vehicle for data processing and control.

[0548] "Feedback" refers to opinions and evaluations of suggestions and services collected from residents and passengers.

[0549] "Model improvement" refers to the process of using collected feedback to improve the accuracy and performance of existing machine learning models.

[0550] MODE FOR CARRYING OUT THE INVENTION

[0551] server

[0552] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects "resident data" from the apartment management system and smart devices. Specifically, this information includes age, family composition, past facility usage history, and survey results. It also collects usage history and passenger data from autonomous vehicles. Furthermore, it regularly obtains external data, such as government statistical data and information on social trends, and integrates this data into the database.

[0553] The server then "pre-processes" the collected data: it cleanses it, removes blank or irrelevant values, standardizes the format, and anonymizes it to protect residents' privacy.

[0554] Once preprocessing is complete, the server extracts "features," which are key variables selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests and neural networks are used to create a model for predicting future needs.

[0555] Using the trained model, the server predicts the needs of residents and passengers 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. It also generates "optimal routes" for autonomous vehicles based on the predicted needs. The on-board computer provides optimal routes, increasing passenger satisfaction.

[0556] The server then notifies the apartment management company or vehicle operation manager of the generated proposal, and generates a proposal document, which is then uploaded to an app or web portal for residents and passengers.

[0557] Terminal

[0558] The terminals provide an interface for residents and passengers to review the proposals and provide feedback. For example, a survey about new proposals could be distributed through an app or web portal. Residents and passengers can directly provide feedback on the proposals. This allows the entire system to be optimized to better meet actual needs.

[0559] User

[0560] Users, i.e., residents and passengers, can review the proposals and provide feedback via their devices, such as whether they agree or disagree with the new facility proposal, their opinions, or specific requests, so that the entire system can respond to the actual needs of residents and passengers.

[0561] Specific examples

[0562] As a concrete example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[0563] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0564] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0565] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0566] Also, in autonomous vehicles, optimal routes are generated based on passenger data. For example, the following prompts can be used to gather feedback:

[0567] Collect feedback from passengers after they arrive at their destination. Enter the following information:

[0568] Arrival time to destination

[0569] Services used (e.g. route flexibility, ride comfort, etc.)

[0570] comment

[0571] This allows us to collect feedback from residents and passengers and improve the accuracy of the model, so the system can always respond to their needs and provide the best possible environment.

[0572] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0573] Step 1:

[0574] Data collection

[0575] The server collects "resident data" from the apartment management system and smart devices. This data includes age, family composition, past facility usage history, and survey results. It also collects usage history and passenger data from autonomous vehicles. Furthermore, external data such as government statistical data and social trend information is periodically acquired and integrated into the database.

[0576] Input: Data from management systems and smart devices

[0577] Output: Integrated database

[0578] Step 2:

[0579] Data Preprocessing

[0580] The server preprocesses the collected data: it cleanses it, removes blank and irrelevant values, standardizes the format, and anonymizes it to protect the privacy of residents.

[0581] Input: Integrated Database

[0582] Output: Preprocessed dataset

[0583] Step 3:

[0584] Feature extraction

[0585] The server extracts "features" from the preprocessed data by selecting important variables based on residents' age groups, family structure, facility usage history, and external data.

[0586] Input: Preprocessed dataset

[0587] Output: A dataset with extracted features

[0588] Step 4:

[0589] Training a machine learning model

[0590] The server uses the extracted features to train machine learning models, using algorithms such as random forests and neural networks to create models to predict future needs.

[0591] Input: Feature-extracted dataset

[0592] Output: A trained machine learning model

[0593] Step 5:

[0594] Anticipating future needs

[0595] Using the trained model, the server predicts the needs of residents and passengers 20-30 years into the future.

[0596] Input: A trained machine learning model

[0597] Output: Predicted future needs

[0598] Step 6:

[0599] Proposal generation

[0600] Based on the prediction results, the server generates plans for restructuring shared facilities, suggestions for new community activities, and optimal routes for self-driving vehicles.

[0601] Input: Projected future needs

[0602] Output: Generated proposals and optimal routes

[0603] Step 7:

[0604] proposal notification

[0605] The server then notifies the apartment management company or vehicle operation manager of the generated proposal, which then generates a proposal document, which is then uploaded to an app or web portal for residents and passengers.

[0606] Input: Generated proposals and optimal routes

[0607] Output: Proposal and uploaded content

[0608] Step 8:

[0609] Feedback collection

[0610] The terminals will then distribute surveys about the new proposals via an app or web portal, allowing residents and passengers to provide direct feedback on their opinions of the proposals.

[0611] Input: Uploaded proposal and feedback survey

[0612] Output: Collected feedback

[0613] Step 9:

[0614] Model Improvement

[0615] The server uses the collected feedback to retrain the model to improve its accuracy.

[0616] Input: Collected feedback

[0617] Output: An improved machine learning model

[0618] 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.

[0619] This invention relates to a system that predicts the future needs of residents of large-scale apartment buildings, optimizes shared facilities, and proposes community activities. This system is composed of a server, terminals, and users, and is also combined with an emotion engine that recognizes user emotions.

[0620] server

[0621] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices. Specifically, it acquires information on residents' ages, family composition, past facility usage history, and survey results, and stores this information in a database. It also periodically acquires external data, such as government statistical data and information on social trends, and integrates these data.

[0622] The server then preprocesses the collected data, specifically removing empty and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[0623] Once preprocessing is complete, the server extracts features. Important variables are selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests or neural networks are used to create a model for predicting future needs.

[0624] Using the trained model, the server predicts the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, if the prediction results indicate an aging population, it will propose the establishment of fitness facilities and medical consultation rooms for the elderly.

[0625] The server then notifies the apartment management company of the generated proposal and generates a proposal document, which is then uploaded to the resident app and web portal.

[0626] Terminal

[0627] The terminals provide an interface for residents to review the proposals and provide feedback. For example, a survey about new proposals can be sent to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[0628] User

[0629] Users, or residents, can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, and specific requests. This allows the entire system to be optimized to meet the actual needs of residents.

[0630] Emotion Engine

[0631] The emotion engine analyzes user feedback to identify its emotional tone. For example, it analyzes text and voice data entered by residents as feedback and extracts emotions such as dissatisfaction, satisfaction, and suggestions. The server uses the results of this emotion analysis to understand the nuances of the feedback and conduct more accurate needs assessments.

[0632] Specific examples

[0633] For example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[0634] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0635] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0636] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0637] Residents review these suggestions and provide feedback, which is analyzed through an emotion engine to detect the emotional tone of complaints or requests. For example, if many residents express dissatisfaction with a particular suggestion, the server will perform a new analysis to reassess the suggestion.

[0638] The feedback is then fed back into the server and used to refine the predictive model, ensuring the system is always responsive to residents' needs and providing optimal shared facilities and community activities.

[0639] The system will be able to adapt flexibly to changing needs of residents, maintaining long-term satisfaction, and use an emotion engine to gather more accurate feedback and provide specific, actionable recommendations.

[0640] The processing flow will be explained below.

[0641] Step 1:

[0642] The server collects resident data from the apartment management system and smart devices. Specifically, it obtains information such as the resident's age, family composition, past facility usage history, and survey results, and stores this information in a database. In addition, the server periodically obtains external data such as government statistical data and information on social trends, and integrates this data into the database.

[0643] Step 2:

[0644] The server preprocesses the collected data, specifically removing blank and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[0645] Step 3:

[0646] The server extracts features from the preprocessed data, selecting important variables from resident age groups, family composition, facility usage history, external data, etc., and uses these as input for the machine learning model.

[0647] Step 4:

[0648] The server uses the extracted features to train a machine learning model, such as a random forest or neural network algorithm, to create a model that predicts future needs.

[0649] Step 5:

[0650] The server uses the trained model to predict the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, it predicts the progression of aging and suggests the establishment of fitness facilities and medical consultation rooms for the elderly.

[0651] Step 6:

[0652] The server then notifies the apartment management company of the generated proposal, which then creates a proposal document, which is then uploaded to the resident app or web portal.

[0653] Step 7:

[0654] The terminals will send a questionnaire about the new proposal to residents, who will then answer the questionnaire and provide feedback on their opinions and requests regarding the proposal.

[0655] Step 8:

[0656] Users (residents) can review the proposals via their devices and input their own opinions and requests. For example, they can provide specific feedback such as "I support the proposal for a facility for the elderly" or "I hope the community center will be expanded."

[0657] Step 9:

[0658] The emotion engine analyzes collected feedback and identifies the user's emotional tone, for example, extracting emotions such as dissatisfaction, satisfaction, and suggestions from text and voice data, and generates emotion analysis results.

[0659] Step 10:

[0660] The server uses the feedback analyzed by the emotion engine to understand the nuances of the feedback and conduct more accurate needs assessments, for example, reconsidering and improving proposals that receive a lot of dissatisfaction feedback.

[0661] Step 11:

[0662] The server retrains the model based on the feedback to improve the accuracy of future suggestions, thereby continually adapting to the changing needs of residents.

[0663] As a concrete example, the following process takes place in a large apartment complex:

[0664] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0665] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0666] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0667] In this way, the system can adapt flexibly to changing needs of residents and maintain long-term satisfaction. The introduction of an emotion engine enables deeper feedback analysis, leading to specific and actionable recommendations.

[0668] Example 2

[0669] 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."

[0670] In today's large-scale apartment complexes, the lifestyle needs of residents continue to change over time. It is extremely important for apartment complex managers and residents to accurately predict future needs and plan and implement appropriate facilities and community activities. However, traditional methods rely primarily on short-term surveys and feedback, making it difficult to predict and propose long-term outcomes. Furthermore, the collected feedback often fails to accurately capture the emotional nuances of residents, which can lead to unnecessary issues and dissatisfaction. Another major challenge is conducting accurate data analysis while ensuring residents' privacy.

[0671] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0672] In this invention, the server includes means for collecting resident data, means for preprocessing the collected resident data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activity proposals based on the needs prediction results, means for notifying residents of the generated proposals, means for collecting resident feedback on the proposals, means for analyzing the collected feedback to identify emotional tones, and means for improving the model using the collected feedback. This makes it possible to accurately predict long-term resident needs and make proposals that take emotional nuances into consideration, thereby increasing resident satisfaction and protecting resident privacy.

[0673] "Resident data" refers to information related to the residents of the apartment building, including, specifically, age, family composition, past facility usage history, survey results, etc.

[0674] "Preprocessing" refers to processing performed on collected data, including removing null and inappropriate values, standardizing data formats, and anonymizing personal information.

[0675] "Features" are important variables extracted from data and are used to train machine learning models.

[0676] A "learning model" is a mathematical model that uses machine learning algorithms to learn patterns from data and make future predictions or classifications.

[0677] "Needs forecasting" is the use of trained learning models to estimate the future wants and needs of residents.

[0678] "Optimization proposals" refer to the generation of improvement proposals for shared facilities and services based on the results of needs predictions.

[0679] "Community activity proposals" involve proposing new community events and activities based on the needs of residents.

[0680] "Feedback" refers to the opinions and thoughts that residents give about the proposals, and includes questionnaires and free comments.

[0681] "Emotional tone" refers to the emotional tendency extracted from the content of feedback, and includes classifications such as positive, negative, and neutral.

[0682] "Analysis" refers to the process of analyzing data to extract meaningful information, specifically identifying the emotional tone of feedback using the emotion engine.

[0683] "Refinement" refers to retraining a learning model based on collected feedback to improve its accuracy and performance.

[0684] This invention relates to a system that predicts the future needs of residents of a large-scale apartment complex, optimizes shared facilities, and proposes community activities.The system for implementing this invention is composed of a server, terminals, and users, and is further combined with an emotion engine that recognizes the user's emotions.

[0685] server

[0686] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices and stores it in a database. Specifically, it obtains information such as resident age, family composition, past facility usage history, and survey results. It also periodically obtains external data such as government statistical data and information on social trends, and integrates these data.

[0687] The server preprocesses the collected data. Specifically, it removes blank and inappropriate values ​​and standardizes the data format. It also anonymizes personal information to protect privacy. Python libraries such as pandas and NumPy can be used.

[0688] Once preprocessing is complete, the server extracts features, selects important variables based on residents' age groups, family composition, facility usage history, and external data, and trains a machine learning model. The trained model is created using tools such as Scikit-learn's RandomForestClassifier and TensorFlow's Keras.

[0689] Using the trained model, the server predicts residents' needs 20-30 years into the future. For example, if an aging population is predicted, the server generates proposals for establishing fitness facilities and medical consultation rooms for the elderly. The generated proposals are notified to the apartment management company and are also uploaded to the resident app and web portal.

[0690] Terminal

[0691] The terminals provide an interface for residents to review the proposals and provide feedback. Specifically, a survey about the new proposals is distributed to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[0692] User

[0693] Users (residents) can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, or specific requests. This feedback is used to optimize the entire system to better meet the actual needs of residents.

[0694] Emotion Engine

[0695] The emotion engine analyzes user feedback to identify its emotional tone. For example, it analyzes the text entered by the user as feedback and extracts emotions such as dissatisfaction, satisfaction, suggestion, etc. The server uses the emotion analysis results to understand the nuances of the feedback and perform more accurate needs assessment.

[0696] Specific examples

[0697] For example, in a large apartment complex, the following predictions and suggestions are made based on the collected data:

[0698] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0699] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0700] Proposal: Renovate the fitness center into a senior rehabilitation center, and expand the community center to include an event space for parents.

[0701] Residents review these suggestions and provide feedback, which is analyzed through an emotion engine to detect the emotional tone of complaints or requests. For example, if many residents express dissatisfaction with a particular suggestion, the server will perform a new analysis to reassess the suggestion.

[0702] Prompt Sentence Examples

[0703] Here are some example prompts to input to a generative AI model:

[0704] Predict the needs of the residents of an apartment complex 20 years from now and propose a plan to restructure the shared facilities based on that. Use the following data for your analysis: residents' age, family composition, past facility usage history, survey results, government statistics, and social trends. If the population is aging, include suggestions for adding facilities for the elderly and medical consultation rooms.

[0705] In this way, the system can flexibly respond to the changing needs of residents and always provide the best possible shared facilities and community activities. The emotion engine also allows for more accurate feedback and makes specific, actionable recommendations.

[0706] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0707] Step 1:

[0708] The server initiates the data collection process.

[0709] Input: Resident age, family composition, past facility usage history, survey results, government statistics, and social trends.

[0710] Specific operation: The server accesses the apartment management system and smart devices, sets them up to periodically collect data, and uses APIs to retrieve data from public databases and integrate it with internal data.

[0711] Output: Raw data is stored in a database.

[0712] Step 2:

[0713] The server pre-processes the collected data.

[0714] Input: Collected data stored in a database.

[0715] Specific actions: Detect and remove or correct empty or inappropriate values. Standardize data formats and anonymize personal information using Python's pandas and NumPy libraries.

[0716] Output: A clean, pre-processed dataset.

[0717] Step 3:

[0718] The server extracts features.

[0719] Input: A clean, pre-processed dataset.

[0720] Specific operation: Using the Scikit-learn library, important features are selected based on residents' age groups, family composition, facility usage history, and external data.

[0721] Output: A dataset containing the features.

[0722] Step 4:

[0723] The server trains the learning model.

[0724] Input: A dataset containing features.

[0725] Specific operation: Train a model using machine learning algorithms such as Scikit-learn's RandomForestClassifier or TensorFlow's Keras.

[0726] Output: A trained predictive model.

[0727] Step 5:

[0728] The server predicts the future needs of residents.

[0729] Input: A trained predictive model.

[0730] What it does: Use the trained model to predict the needs of residents 20-30 years into the future, for example by simulating scenarios where the population is aging.

[0731] Output: Projected future needs.

[0732] Step 6:

[0733] The server generates optimization suggestions based on the prediction results.

[0734] Input: Projected future needs.

[0735] Specific actions: Generate specific proposals such as rehabilitation facilities for the elderly and event spaces for the parenting generation.

[0736] Output: Proposal.

[0737] Step 7:

[0738] The server notifies the generated proposal and sends it to the terminal.

[0739] Input: Proposal.

[0740] Specific actions: The proposal is notified to the apartment management company and also uploaded to the resident app and web portal.

[0741] Output: Notification of proposal.

[0742] Step 8:

[0743] The device displays the proposals to residents and collects their feedback.

[0744] Input: Proposal.

[0745] What it does: Collect feedback through a citizen interface in the form of surveys and free text.

[0746] Output: Collected feedback.

[0747] Step 9:

[0748] An emotion engine analyzes feedback to identify emotional tone.

[0749] Input: Collected feedback.

[0750] What it does: Uses natural language processing techniques to classify positive, negative, and neutral sentiment.

[0751] Output: Emotional tone analysis results.

[0752] Step 10:

[0753] The server improves the model based on the analysis results.

[0754] Input: Emotional tone analysis results.

[0755] Specific actions: Retrain your learning model to take into account the emotional tone and specific opinions of the feedback.

[0756] Output: An improved predictive model.

[0757] Step 11:

[0758] The server uses the improved model to generate new proposals.

[0759] Input: Improved predictive model.

[0760] Specific Action: Generate an optimized proposal and notify the residents again.

[0761] Output: A new proposal.

[0762] These steps enable the system to constantly adapt to the changing needs of residents and provide optimal shared facilities and community activities.

[0763] (Application example 2)

[0764] 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."

[0765] In today's large-scale condominiums, it is difficult to accurately predict residents' future needs and optimize shared facilities and community activities. Furthermore, because sentiment analysis to effectively utilize resident feedback and gain a deeper understanding has not been implemented, proposals can sometimes deviate from actual needs. Furthermore, because there is no way to use resident data to optimize the operation of physical stores, store services and products do not adequately meet resident demands. These issues need to be resolved.

[0766] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting resident data, means for preprocessing the collected resident data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activities based on the needs prediction results, means for collecting resident feedback on the proposals, means for emotionally analyzing the resident feedback and determining the emotional tone of the feedback, means for improving the model using the collected feedback, and means for generating optimization proposals for brick-and-mortar store operations using resident data. This not only enables accurate prediction of future needs of residents and optimization of shared facilities and community activities, but also makes it possible to reflect detailed feedback through resident emotional analysis and further optimize brick-and-mortar store operations.

[0767] "Resident data" refers to information about individuals and families residing in the apartment complex, including age, family composition, past facility usage history, survey results, etc.

[0768] "Preprocessing" is the process of filling in blanks, removing inappropriate values, standardizing formats, and anonymizing personal information to prepare the collected raw data for analysis.

[0769] "Features" are important variables in the data used to train machine learning models, and include residents' age groups, family composition, facility usage history, external data, etc.

[0770] A "learning model" is an implementation of an algorithm that learns specific patterns and relationships from collected data and makes future predictions.

[0771] Forecasting "needs" means using a trained learning model to estimate the wants and requirements of residents at a specific future point in time.

[0772] The "Optimization Proposal for Shared Facilities" provides specific improvement plans for efficient use of shared spaces and facilities within the condominium based on the predicted needs of residents.

[0773] "Community activity proposals" are proposals for planning events or activities to promote interaction and cooperation among residents.

[0774] "Feedback collection methods" refers to methods and tools used to collect opinions, comments, ratings, and other responses from residents.

[0775] "Sentiment analysis" is a technology that analyzes collected feedback text and audio data to identify the emotional tone contained therein.

[0776] The "Optimization proposal for physical store operations" uses resident data to improve the services and product lineup of specific stores, providing operations that better meet customer needs.

[0777] MODE FOR CARRYING OUT THE INVENTION

[0778] This invention relates to a system that utilizes resident data of large-scale apartment buildings to predict future needs and optimize the operation of shared facilities and brick-and-mortar stores. Below, we will explain in detail how to specifically implement this invention.

[0779] server

[0780] The server is the main device responsible for data collection, preprocessing, analysis, and prediction. The server in this system collects resident data from the apartment management system and smart devices, and preprocesses that data. Specifically, it stores residents' ages, family composition, past facility usage history, and survey results in a database. It also periodically obtains external data such as government statistical data and information on social trends, and integrates them.

[0781] In the data preprocessing stage, we remove empty and inappropriate values, standardize the data format, and protect privacy by anonymizing personal information.

[0782] Once preprocessing is complete, the server extracts features, selecting important variables based on residents' age groups, family composition, facility usage history, and external data, and then training a machine learning model. For example, algorithms such as random forests and neural networks are used to create a model for predicting future needs.

[0783] Using the trained model, the server predicts residents' future needs and generates optimization proposals for shared facilities and community activities. It also uses resident data to make optimization proposals for brick-and-mortar store operations. Based on the prediction results, it suggests, for example, the establishment of facilities for the elderly or play areas for children.

[0784] Terminal

[0785] The terminals are the interface through which residents can review the proposals and provide feedback. For example, residents can use their smartphones or computers to answer a questionnaire about the new proposals. Their feedback is sent to the server and analyzed through the emotion engine.

[0786] User

[0787] Users (residents) review the proposals via their devices and provide their feedback. The feedback is sent to the server, where the emotional tone is analyzed by the emotion engine. For example, users can enter their approval or disapproval of a new facility proposal, as well as specific requests. The server uses the results of this emotion analysis to understand the nuances of the feedback and improve the accuracy of the prediction model.

[0788] Emotion Engine

[0789] The emotion engine analyzes the text and voice data of user feedback to extract emotions such as dissatisfaction, satisfaction, suggestion, etc. This allows the server to understand the emotional tone of the feedback and perform more accurate needs assessment.

[0790] Specific examples

[0791] For example, in a large apartment complex, the following predictions and suggestions may be made:

[0792] The average age of residents is rising, and the number of families living there is increasing.

[0793] Based on the collected data, a proposal was made to renovate the fitness facility into a rehabilitation facility for the elderly.

[0794] We propose expanding the community center and creating an event space for people raising children.

[0795] Residents can review these suggestions and provide feedback, including specific requests for suggestions. The feedback is analyzed through an emotion engine, and the server uses the results to reassess the suggestions and generate more accurate ones.

[0796] Prompt Sentence Examples

[0797] Create a program that uses the residents' age, family composition, past facility usage history, and survey results to predict their needs 20-30 years from now using a random forest model, and proposes the establishment of rehabilitation facilities for the elderly and event spaces for childcare.

[0798] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0799] Step 1:

[0800] The server collects resident data from the apartment management system and smart devices. Specifically, it acquires information such as resident age, family composition, past facility usage history, and survey results, and stores it in a database. Input data comes in a variety of formats, but storing it in a unified database enables efficient management. The output is a unified database.

[0801] Step 2:

[0802] The server preprocesses the collected resident data. Specifically, it removes blank and inappropriate values, standardizes the data format, and anonymizes personal information. The input is the collected raw data in various formats, and the output is consistent, anonymized data with no blank values.

[0803] Step 3:

[0804] The server extracts features from the preprocessed data. During this process, important variables are selected based on the residents' age group, family structure, facility usage history, and external data (social trends, etc.). The input is the preprocessed data, and the output is a set of training features.

[0805] Step 4:

[0806] The server uses the extracted features to train a machine learning model, specifically using algorithms such as random forests or neural networks. The training dataset is fed to the model to improve its predictive capabilities. The input is the extracted feature set, and the output is the trained model.

[0807] Step 5:

[0808] The server uses the trained model to predict future needs of residents. The input is new or updated resident data, and the output is predicted future needs. For example, the prediction may be that demand for elderly care facilities will increase.

[0809] Step 6:

[0810] The server generates optimization proposals for shared facilities and community activities based on the needs prediction results. Specifically, it proposes the relocation or new construction of fitness facilities for the elderly and event spaces for children based on the prediction results. The input is the needs prediction results, and the output is the specific proposals.

[0811] Step 7:

[0812] The terminal distributes proposals to residents and collects feedback. The input is the proposal received from the server, and the output is feedback from residents. Residents fill out questionnaires and enter comments via their smartphones or computers.

[0813] Step 8:

[0814] The server performs sentiment analysis on the residents' feedback to determine its emotional tone. Specifically, it feeds the feedback text and audio data into a sentiment analysis engine, which extracts emotional tones such as satisfaction, dissatisfaction, and suggestions. The input is the feedback data, and the output is the sentiment analysis results.

[0815] Step 9:

[0816] The server uses the collected feedback to refine the model. It incorporates the sentiment analysis results into a learning algorithm to improve the accuracy of the predictive model. The input is the sentiment analysis results, and the output is an improved learning model.

[0817] Step 10:

[0818] The server uses resident data to generate optimization proposals for brick-and-mortar store operations. Based on the needs prediction results, it adjusts the product and service lineup. For example, it proposes increasing rehabilitation products for the elderly or events for families. The input is the needs prediction results, and the output is optimization proposals for the brick-and-mortar store.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] [Third embodiment]

[0823] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0824] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0825] 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).

[0826] 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.

[0827] 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.

[0828] 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).

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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."

[0835] This invention relates to a system that predicts the future needs of residents of large-scale apartment buildings, optimizes shared facilities, and proposes community activities. The system is composed of a server, terminals, and users.

[0836] server

[0837] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices. Specifically, it collects information on residents' ages, family composition, past facility usage history, and survey results, and stores this information in a database. It also periodically obtains external data, such as government statistical data and information on social trends, and integrates these data.

[0838] The server then cleanses the collected data, removing blank and irrelevant values, standardizing the format, and anonymizing the data to protect residents' privacy.

[0839] Once preprocessing is complete, the server extracts features. Important variables are selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests or neural networks are used to create a model for predicting future needs.

[0840] Using the trained model, the server predicts the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, if the prediction results indicate an aging population, it will propose the establishment of fitness facilities and medical consultation rooms for the elderly.

[0841] The server then notifies the apartment management company of the generated proposal and generates a proposal document, which is then uploaded to the resident app and web portal.

[0842] Terminal

[0843] The terminals provide an interface for residents to review the proposals and provide feedback. For example, a survey about new proposals can be sent to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[0844] User

[0845] Users, or residents, can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, and specific requests. This allows the entire system to be optimized to meet the actual needs of residents.

[0846] Specific examples

[0847] For example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[0848] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0849] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0850] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0851] Residents can review these suggestions and provide feedback, which is then fed back into the server and used to refine the predictive model. In this way, the system can always respond to residents' needs and provide the optimal environment.

[0852] The processing flow will be explained below.

[0853] Step 1:

[0854] The server collects resident data from the apartment management system and smart devices, including the resident's age, family composition, past facility usage history, and survey results, and stores this information in a database.

[0855] Step 2:

[0856] The server periodically retrieves external data (government statistics and information on social trends) and integrates it with resident data.

[0857] Step 3:

[0858] The server preprocesses the collected data, specifically removing blank and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[0859] Step 4:

[0860] The server extracts features from the preprocessed data, selecting important variables from residents' age groups, family composition, facility usage history, and external data, and uses them as input for the machine learning model.

[0861] Step 5:

[0862] The server uses the extracted features to train machine learning models, specifically algorithms such as random forests and neural networks, to create models that predict future needs.

[0863] Step 6:

[0864] The server uses the trained model to predict the needs of residents 20-30 years into the future, determining, for example, the need for senior living facilities or family play areas.

[0865] Step 7:

[0866] Based on the prediction results, the server generates suggestions for restructuring shared facilities and new community activities, such as converting a fitness center into a senior rehabilitation center or expanding a community center.

[0867] Step 8:

[0868] The server then notifies the apartment management company of the generated proposal, which then creates a proposal document, which is then uploaded to the resident app or web portal.

[0869] Step 9:

[0870] The terminals distribute a questionnaire about the new proposal to residents, who then provide their opinions about the proposal via the terminals.

[0871] Step 10:

[0872] Users (residents) use terminals to answer questionnaires and provide feedback on their opinions and requests.

[0873] Step 11:

[0874] The server collects feedback from residents and stores it in a database for analysis, improving the accuracy of the predictive model and incorporating it into future proposals.

[0875] This series of processes enables the system to flexibly respond to the changing needs of residents and provide optimal shared facilities and community activities.

[0876] Example 1

[0877] 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."

[0878] In today's large-scale apartment complexes, accurately predicting residents' future needs and optimizing shared facilities and community activities accordingly is a difficult task. In particular, there is a need to propose facilities that respond to changes in residents' living environments and age structures, and to build a feedback system that reflects residents' opinions. However, current systems have difficulty meeting these requirements and are unable to respond to residents' actual needs.

[0879] 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.

[0880] In this invention, the server includes a means for collecting resident data, a means for preprocessing the collected resident data, and a means for extracting features from the preprocessed data and training a machine learning model, thereby enabling accurate prediction of future needs of residents and optimization of shared facilities and community activities based on the prediction.

[0881] "Resident data" refers to information about individual residents living in large apartment complexes, including, for example, age, family composition, past facility usage history, and survey results.

[0882] "Means of data preprocessing" refers to technical methods for processing collected data, such as removing blank or inappropriate values, standardizing formats, and anonymizing data.

[0883] "Features" are particularly important variables or parameters in the data used to train a learning model, including, for example, the age group and family composition of residents, facility usage history, etc.

[0884] A "machine learning model" is a mathematical framework for analyzing large amounts of data and making patterns and predictions based on specific algorithms. Typical examples include random forests and neural networks.

[0885] "Means to predict future needs" refers to technology that uses trained machine learning models to predict residents' future demands and requirements and present specific suggestions and countermeasures.

[0886] "Shared facilities" refer to facilities and areas set up for joint use by residents within a large apartment complex, including fitness facilities, rehabilitation facilities, and community centers.

[0887] "Feedback collection means" refers to the methods and tools used to collect opinions and evaluations of the proposals from residents, and can be done, for example, through a questionnaire form or a web portal.

[0888] "Means to improve the model" refers to techniques that analyze collected feedback and use it to adjust the parameters and algorithms of machine learning models to improve the model's accuracy and predictive capabilities.

[0889] "External data" refers to external information, such as government statistical data and information on social trends, separate from data on the apartment building management system and residents.

[0890] This invention relates to a system that predicts the future needs of residents in large-scale apartment buildings, optimizes shared facilities, and proposes community activities. The system consists of three elements: a server, terminals, and users.

[0891] System Overview

[0892] 1. Server

[0893] The server plays a central role in collecting, preprocessing, analyzing, and predicting the main data. Specifically, it performs the following tasks:

[0894] Data collection: The server collects resident data from the apartment management system and smart devices via APIs. For example, information such as resident age, family composition, past facility usage history, and survey results is collected and stored in a database. It also uses scraping and APIs from external services to collect government statistical data and information on social trends.

[0895] Data preprocessing: Collected data is processed to detect and complete blank and inappropriate values, standardize formats, and anonymize data, thereby improving data quality and protecting privacy.

[0896] Feature extraction and model training: Important features such as residents' age groups, family composition, and facility usage history are extracted from the preprocessed data. Then, machine learning algorithms such as random forests and neural networks are used to train models to predict future needs.

[0897] Generation of prediction results and recommendations: The trained model is used to predict the needs of residents 20-30 years into the future, and based on the results, it generates recommendations for optimizing shared facilities and community activities, such as establishing rehabilitation facilities for the elderly or event spaces for families with children.

[0898] Proposal notification and feedback collection: The generated proposals are notified to the apartment management company, and a proposal document is generated. The proposal document is also uploaded to the resident app and web portal.

[0899] 2. Terminal

[0900] The terminal will serve as an interface for residents to review the proposals and provide feedback. Specifically, it has the following functions:

[0901] Proposal notification: Notify residents of new proposals through their device (app or web portal), for example by sending a push notification to residents through a smartphone app.

[0902] Providing feedback: Provide a function that allows residents to input their opinions, specific requests, and other feedback regarding the proposals via their devices. For example, provide a questionnaire form to collect residents' opinions.

[0903] 3. Users

[0904] The user, i.e., the resident, is responsible for checking the proposals via a terminal and providing feedback. Specifically, he or she performs the following actions:

[0905] Review proposals: Residents review the proposals provided in the app or web portal and understand their contents.

[0906] Providing feedback: Residents can provide feedback on proposals, including pros and cons, opinions, and specific requests, so the entire system can be optimized based on residents' actual needs.

[0907] Specific examples

[0908] For example, the following predictions and proposals may be made for a large apartment complex:

[0909] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0910] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0911] Proposal: Renovate the fitness facility into a rehabilitation center for seniors, and expand the community center to include an event space for parents.

[0912] Residents can review these suggestions and provide feedback, which is then analyzed by the server and used to improve the accuracy of the predictive model. In this way, the system can always respond to residents' latest needs and provide the optimal environment.

[0913] Prompt Sentence Examples

[0914] "Based on the following input data, predict the needs of residents of a large apartment complex 20 years from now and propose optimization plans for shared facilities: The average age of residents is increasing year by year. The number of residents with families is increasing. Use of the fitness facility is decreasing, while use of the community center is increasing."

[0915] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0916] Step 1: Data collection

[0917] The server collects information about residents from the apartment management system and smart devices. Specifically, it obtains residents' ages, family composition, past facility usage history, and survey results through APIs. It also uses APIs from external services to collect government statistical data and data on social trends. The input is raw data from the apartment management system and external data APIs, and the output is structured data stored in a database.

[0918] Step 2: Data Preprocessing

[0919] The server preprocesses the collected data. Specific operations include removing empty and inappropriate values, standardizing formats, and anonymizing data. For example, standardizing date formats and hashing identifying information. The input is raw data, and the output is preprocessed, clean data.

[0920] Step 3: Feature extraction

[0921] The server extracts features from the preprocessed data. Specific operations include selecting important variables and parameters from the data. For example, the age group, family structure, and facility usage history of residents are extracted as features. The input is the preprocessed data, and the output is feature data used to train the machine learning model.

[0922] Step 4: Model training

[0923] The server uses the extracted features to train a machine learning model, specifically using algorithms such as random forests and neural networks. The input is the feature data, and the output is the trained machine learning model.

[0924] Step 5: Anticipate future needs

[0925] The server uses the trained model to predict future needs of residents, such as the need for rehabilitation facilities for the elderly or event spaces for families with children. The input is new data, and the output is information about predicted needs.

[0926] Step 6: Generate proposals

[0927] The server generates optimization proposals for shared facilities and community activities based on the prediction results. Specific actions include proposing to convert a fitness center into a rehabilitation facility for the elderly or to expand a community center to include an event space for the parenting generation. The input is the prediction data, and the output is the specific proposals.

[0928] Step 7: Proposal Notification

[0929] The server notifies the condominium management company of the generated proposal and also uploads it to the resident app and web portal. The device then sends push notifications and emails to notify the residents of the proposal. The input is the proposal content, and the output is the notified proposal.

[0930] Step 8: Gather feedback

[0931] The terminal collects feedback from residents. Specifically, it provides a questionnaire form in which residents can enter their opinions, whether they agree or disagree with the proposal, and their specific requests. Users enter their own opinions through this form. The input is the residents' opinions and feedback, and the output is the collected feedback data.

[0932] Step 9: Integrate feedback and retrain the model

[0933] The server analyzes the collected feedback and uses it to improve the machine learning model. Specific operations include text analysis of the feedback data and tuning the model parameters. The input is the feedback data, and the output is an improved machine learning model.

[0934] (Application example 1)

[0935] 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."

[0936] Existing large-scale condominium management systems have difficulty accurately predicting residents' future needs and optimizing facilities and proposing community activities based on those needs. Furthermore, autonomous vehicles lacked mechanisms for providing optimal routes and services tailored to passenger needs. This resulted in the inability to provide the services desired by residents and passengers in a timely manner, leading to lower satisfaction and a deterioration in efficiency.

[0937] 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.

[0938] In this invention, the server includes means for collecting resident data, means for preprocessing the collected data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activity proposals based on the needs prediction results, means for collecting resident feedback on the proposals, means for collecting vehicle usage history and passenger data and generating optimal routes based on the predicted needs, means for providing the optimal routes using an on-board computer, and means for improving the model using the collected feedback. This makes it possible to accurately predict the needs of residents and passengers and provide optimal services and proposals at the appropriate time.

[0939] "Resident data" refers to information such as the age, family composition, past facility usage history, and survey results of individuals living in the apartment complex.

[0940] "Preprocessing" refers to the process of cleansing collected data, removing blank and inappropriate values, and standardizing the format.

[0941] "Features" refer to important variables and patterns extracted from data to optimize the performance of machine learning models.

[0942] A "learning model" refers to an algorithm or model that learns from collected data and makes predictions or classifications based on that data.

[0943] "Trained Model" refers to a predictive model that has been tuned by a machine learning algorithm using collected data.

[0944] "Future needs" refers to the facility usage and service requirements that residents and passengers are expected to require in the future.

[0945] "Shared facilities" refers to facilities and spaces within an apartment building that are shared and used by residents, such as a fitness gym or community center.

[0946] "Optimal route" refers to the optimal route selected for an autonomous vehicle to transport passengers to their destination efficiently and safely.

[0947] "On-board computer" refers to a computer device installed inside a vehicle for data processing and control.

[0948] "Feedback" refers to opinions and evaluations of suggestions and services collected from residents and passengers.

[0949] "Model improvement" refers to the process of using collected feedback to improve the accuracy and performance of existing machine learning models.

[0950] MODE FOR CARRYING OUT THE INVENTION

[0951] server

[0952] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects "resident data" from the apartment management system and smart devices. Specifically, this information includes age, family composition, past facility usage history, and survey results. It also collects usage history and passenger data from autonomous vehicles. Furthermore, it regularly obtains external data, such as government statistical data and information on social trends, and integrates this data into the database.

[0953] The server then "pre-processes" the collected data: it cleanses it, removes blank or irrelevant values, standardizes the format, and anonymizes it to protect residents' privacy.

[0954] Once preprocessing is complete, the server extracts "features," which are key variables selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests and neural networks are used to create a model for predicting future needs.

[0955] Using the trained model, the server predicts the needs of residents and passengers 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. It also generates "optimal routes" for autonomous vehicles based on the predicted needs. The on-board computer provides optimal routes, increasing passenger satisfaction.

[0956] The server then notifies the apartment management company or vehicle operation manager of the generated proposal, and generates a proposal document, which is then uploaded to an app or web portal for residents and passengers.

[0957] Terminal

[0958] The terminals provide an interface for residents and passengers to review the proposals and provide feedback. For example, a survey about new proposals could be distributed through an app or web portal. Residents and passengers can directly provide feedback on the proposals. This allows the entire system to be optimized to better meet actual needs.

[0959] User

[0960] Users, i.e., residents and passengers, can review the proposals and provide feedback via their devices, such as whether they agree or disagree with the new facility proposal, their opinions, or specific requests, so that the entire system can respond to the actual needs of residents and passengers.

[0961] Specific examples

[0962] As a concrete example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[0963] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[0964] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[0965] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[0966] Also, in autonomous vehicles, optimal routes are generated based on passenger data. For example, the following prompts can be used to gather feedback:

[0967] Collect feedback from passengers after they arrive at their destination. Enter the following information:

[0968] Arrival time to destination

[0969] Services used (e.g. route flexibility, ride comfort, etc.)

[0970] comment

[0971] This allows us to collect feedback from residents and passengers and improve the accuracy of the model, so the system can always respond to their needs and provide the best possible environment.

[0972] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0973] Step 1:

[0974] Data collection

[0975] The server collects "resident data" from the apartment management system and smart devices. This data includes age, family composition, past facility usage history, and survey results. It also collects usage history and passenger data from autonomous vehicles. Furthermore, external data such as government statistical data and social trend information is periodically acquired and integrated into the database.

[0976] Input: Data from management systems and smart devices

[0977] Output: Integrated database

[0978] Step 2:

[0979] Data Preprocessing

[0980] The server preprocesses the collected data: it cleanses it, removes blank and irrelevant values, standardizes the format, and anonymizes it to protect the privacy of residents.

[0981] Input: Integrated Database

[0982] Output: Preprocessed dataset

[0983] Step 3:

[0984] Feature extraction

[0985] The server extracts "features" from the preprocessed data by selecting important variables based on residents' age groups, family structure, facility usage history, and external data.

[0986] Input: Preprocessed dataset

[0987] Output: A dataset with extracted features

[0988] Step 4:

[0989] Training a machine learning model

[0990] The server uses the extracted features to train machine learning models, using algorithms such as random forests and neural networks to create models to predict future needs.

[0991] Input: Feature-extracted dataset

[0992] Output: A trained machine learning model

[0993] Step 5:

[0994] Anticipating future needs

[0995] Using the trained model, the server predicts the needs of residents and passengers 20-30 years into the future.

[0996] Input: A trained machine learning model

[0997] Output: Predicted future needs

[0998] Step 6:

[0999] Proposal generation

[1000] Based on the prediction results, the server generates plans for restructuring shared facilities, suggestions for new community activities, and optimal routes for self-driving vehicles.

[1001] Input: Projected future needs

[1002] Output: Generated proposals and optimal routes

[1003] Step 7:

[1004] proposal notification

[1005] The server then notifies the apartment management company or vehicle operation manager of the generated proposal, which then generates a proposal document, which is then uploaded to an app or web portal for residents and passengers.

[1006] Input: Generated proposals and optimal routes

[1007] Output: Proposal and uploaded content

[1008] Step 8:

[1009] Feedback collection

[1010] The terminals will then distribute surveys about the new proposals via an app or web portal, allowing residents and passengers to provide direct feedback on their opinions of the proposals.

[1011] Input: Uploaded proposal and feedback survey

[1012] Output: Collected feedback

[1013] Step 9:

[1014] Model Improvement

[1015] The server uses the collected feedback to retrain the model to improve its accuracy.

[1016] Input: Collected feedback

[1017] Output: An improved machine learning model

[1018] 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.

[1019] This invention relates to a system that predicts the future needs of residents of large-scale apartment buildings, optimizes shared facilities, and proposes community activities. This system is composed of a server, terminals, and users, and is also combined with an emotion engine that recognizes user emotions.

[1020] server

[1021] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices. Specifically, it acquires information on residents' ages, family composition, past facility usage history, and survey results, and stores this information in a database. It also periodically acquires external data, such as government statistical data and information on social trends, and integrates these data.

[1022] The server then preprocesses the collected data, specifically removing empty and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[1023] Once preprocessing is complete, the server extracts features. Important variables are selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests or neural networks are used to create a model for predicting future needs.

[1024] Using the trained model, the server predicts the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, if the prediction results indicate an aging population, it will propose the establishment of fitness facilities and medical consultation rooms for the elderly.

[1025] The server then notifies the apartment management company of the generated proposal and generates a proposal document, which is then uploaded to the resident app and web portal.

[1026] Terminal

[1027] The terminals provide an interface for residents to review the proposals and provide feedback. For example, a survey about new proposals can be sent to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[1028] User

[1029] Users, or residents, can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, and specific requests. This allows the entire system to be optimized to meet the actual needs of residents.

[1030] Emotion Engine

[1031] The emotion engine analyzes user feedback to identify its emotional tone. For example, it analyzes text and voice data entered by residents as feedback and extracts emotions such as dissatisfaction, satisfaction, and suggestions. The server uses the results of this emotion analysis to understand the nuances of the feedback and conduct more accurate needs assessments.

[1032] Specific examples

[1033] For example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[1034] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1035] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1036] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[1037] Residents review these suggestions and provide feedback, which is analyzed through an emotion engine to detect the emotional tone of complaints or requests. For example, if many residents express dissatisfaction with a particular suggestion, the server will perform a new analysis to reassess the suggestion.

[1038] The feedback is then fed back into the server and used to refine the predictive model, ensuring the system is always responsive to residents' needs and providing optimal shared facilities and community activities.

[1039] The system will be able to adapt flexibly to changing needs of residents, maintaining long-term satisfaction, and use an emotion engine to gather more accurate feedback and provide specific, actionable recommendations.

[1040] The processing flow will be explained below.

[1041] Step 1:

[1042] The server collects resident data from the apartment management system and smart devices. Specifically, it obtains information such as the resident's age, family composition, past facility usage history, and survey results, and stores this information in a database. In addition, the server periodically obtains external data such as government statistical data and information on social trends, and integrates this data into the database.

[1043] Step 2:

[1044] The server preprocesses the collected data, specifically removing blank and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[1045] Step 3:

[1046] The server extracts features from the preprocessed data, selecting important variables from resident age groups, family composition, facility usage history, external data, etc., and uses these as input for the machine learning model.

[1047] Step 4:

[1048] The server uses the extracted features to train a machine learning model, such as a random forest or neural network algorithm, to create a model that predicts future needs.

[1049] Step 5:

[1050] The server uses the trained model to predict the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, it predicts the progression of aging and suggests the establishment of fitness facilities and medical consultation rooms for the elderly.

[1051] Step 6:

[1052] The server then notifies the apartment management company of the generated proposal, which then creates a proposal document, which is then uploaded to the resident app or web portal.

[1053] Step 7:

[1054] The terminals will send a questionnaire about the new proposal to residents, who will then answer the questionnaire and provide feedback on their opinions and requests regarding the proposal.

[1055] Step 8:

[1056] Users (residents) can review the proposals via their devices and input their own opinions and requests. For example, they can provide specific feedback such as "I support the proposal for a facility for the elderly" or "I hope the community center will be expanded."

[1057] Step 9:

[1058] The emotion engine analyzes collected feedback and identifies the user's emotional tone, for example, extracting emotions such as dissatisfaction, satisfaction, and suggestions from text and voice data, and generates emotion analysis results.

[1059] Step 10:

[1060] The server uses the feedback analyzed by the emotion engine to understand the nuances of the feedback and conduct more accurate needs assessments, for example, reconsidering and improving proposals that receive a lot of dissatisfaction feedback.

[1061] Step 11:

[1062] The server retrains the model based on the feedback to improve the accuracy of future suggestions, thereby continually adapting to the changing needs of residents.

[1063] As a concrete example, the following process takes place in a large apartment complex:

[1064] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1065] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1066] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[1067] In this way, the system can adapt flexibly to changing needs of residents and maintain long-term satisfaction. The introduction of an emotion engine enables deeper feedback analysis, leading to specific and actionable recommendations.

[1068] Example 2

[1069] 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."

[1070] In today's large-scale apartment complexes, the lifestyle needs of residents continue to change over time. It is extremely important for apartment complex managers and residents to accurately predict future needs and plan and implement appropriate facilities and community activities. However, traditional methods rely primarily on short-term surveys and feedback, making it difficult to predict and propose long-term outcomes. Furthermore, the collected feedback often fails to accurately capture the emotional nuances of residents, which can lead to unnecessary issues and dissatisfaction. Another major challenge is conducting accurate data analysis while ensuring residents' privacy.

[1071] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1072] In this invention, the server includes means for collecting resident data, means for preprocessing the collected resident data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activity proposals based on the needs prediction results, means for notifying residents of the generated proposals, means for collecting resident feedback on the proposals, means for analyzing the collected feedback to identify emotional tones, and means for improving the model using the collected feedback. This makes it possible to accurately predict long-term resident needs and make proposals that take emotional nuances into consideration, thereby increasing resident satisfaction and protecting resident privacy.

[1073] "Resident data" refers to information related to the residents of the apartment building, including, specifically, age, family composition, past facility usage history, survey results, etc.

[1074] "Preprocessing" refers to processing performed on collected data, including removing null and inappropriate values, standardizing data formats, and anonymizing personal information.

[1075] "Features" are important variables extracted from data and are used to train machine learning models.

[1076] A "learning model" is a mathematical model that uses machine learning algorithms to learn patterns from data and make future predictions or classifications.

[1077] "Needs forecasting" is the use of trained learning models to estimate the future wants and needs of residents.

[1078] "Optimization proposals" refer to the generation of improvement proposals for shared facilities and services based on the results of needs predictions.

[1079] "Community activity proposals" involve proposing new community events and activities based on the needs of residents.

[1080] "Feedback" refers to the opinions and thoughts that residents give about the proposals, and includes questionnaires and free comments.

[1081] "Emotional tone" refers to the emotional tendency extracted from the content of feedback, and includes classifications such as positive, negative, and neutral.

[1082] "Analysis" refers to the process of analyzing data to extract meaningful information, specifically identifying the emotional tone of feedback using the emotion engine.

[1083] "Refinement" refers to retraining a learning model based on collected feedback to improve its accuracy and performance.

[1084] This invention relates to a system that predicts the future needs of residents of a large-scale apartment complex, optimizes shared facilities, and proposes community activities.The system for implementing this invention is composed of a server, terminals, and users, and is further combined with an emotion engine that recognizes the user's emotions.

[1085] server

[1086] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices and stores it in a database. Specifically, it obtains information such as resident age, family composition, past facility usage history, and survey results. It also periodically obtains external data such as government statistical data and information on social trends, and integrates these data.

[1087] The server preprocesses the collected data. Specifically, it removes blank and inappropriate values ​​and standardizes the data format. It also anonymizes personal information to protect privacy. Python libraries such as pandas and NumPy can be used.

[1088] Once preprocessing is complete, the server extracts features, selects important variables based on residents' age groups, family composition, facility usage history, and external data, and trains a machine learning model. The trained model is created using tools such as Scikit-learn's RandomForestClassifier and TensorFlow's Keras.

[1089] Using the trained model, the server predicts residents' needs 20-30 years into the future. For example, if an aging population is predicted, the server generates proposals for establishing fitness facilities and medical consultation rooms for the elderly. The generated proposals are notified to the apartment management company and are also uploaded to the resident app and web portal.

[1090] Terminal

[1091] The terminals provide an interface for residents to review the proposals and provide feedback. Specifically, a survey about the new proposals is distributed to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[1092] User

[1093] Users (residents) can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, or specific requests. This feedback is used to optimize the entire system to better meet the actual needs of residents.

[1094] Emotion Engine

[1095] The emotion engine analyzes user feedback to identify its emotional tone. For example, it analyzes the text entered by the user as feedback and extracts emotions such as dissatisfaction, satisfaction, suggestion, etc. The server uses the emotion analysis results to understand the nuances of the feedback and perform more accurate needs assessment.

[1096] Specific examples

[1097] For example, in a large apartment complex, the following predictions and suggestions are made based on the collected data:

[1098] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1099] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1100] Proposal: Renovate the fitness center into a senior rehabilitation center, and expand the community center to include an event space for parents.

[1101] Residents review these suggestions and provide feedback, which is analyzed through an emotion engine to detect the emotional tone of complaints or requests. For example, if many residents express dissatisfaction with a particular suggestion, the server will perform a new analysis to reassess the suggestion.

[1102] Prompt Sentence Examples

[1103] Here are some example prompts to input to a generative AI model:

[1104] Predict the needs of the residents of an apartment complex 20 years from now and propose a plan to restructure the shared facilities based on that. Use the following data for your analysis: residents' age, family composition, past facility usage history, survey results, government statistics, and social trends. If the population is aging, include suggestions for adding facilities for the elderly and medical consultation rooms.

[1105] In this way, the system can flexibly respond to the changing needs of residents and always provide the best possible shared facilities and community activities. The emotion engine also allows for more accurate feedback and makes specific, actionable recommendations.

[1106] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1107] Step 1:

[1108] The server initiates the data collection process.

[1109] Input: Resident age, family composition, past facility usage history, survey results, government statistics, and social trends.

[1110] Specific operation: The server accesses the apartment management system and smart devices, sets them up to periodically collect data, and uses APIs to retrieve data from public databases and integrate it with internal data.

[1111] Output: Raw data is stored in a database.

[1112] Step 2:

[1113] The server pre-processes the collected data.

[1114] Input: Collected data stored in a database.

[1115] Specific actions: Detect and remove or correct empty or inappropriate values. Standardize data formats and anonymize personal information using Python's pandas and NumPy libraries.

[1116] Output: A clean, pre-processed dataset.

[1117] Step 3:

[1118] The server extracts features.

[1119] Input: A clean, pre-processed dataset.

[1120] Specific operation: Using the Scikit-learn library, important features are selected based on residents' age groups, family composition, facility usage history, and external data.

[1121] Output: A dataset containing the features.

[1122] Step 4:

[1123] The server trains the learning model.

[1124] Input: A dataset containing features.

[1125] Specific operation: Train a model using machine learning algorithms such as Scikit-learn's RandomForestClassifier or TensorFlow's Keras.

[1126] Output: A trained predictive model.

[1127] Step 5:

[1128] The server predicts the future needs of residents.

[1129] Input: A trained predictive model.

[1130] What it does: Use the trained model to predict the needs of residents 20-30 years into the future, for example by simulating scenarios where the population is aging.

[1131] Output: Projected future needs.

[1132] Step 6:

[1133] The server generates optimization suggestions based on the prediction results.

[1134] Input: Projected future needs.

[1135] Specific actions: Generate specific proposals such as rehabilitation facilities for the elderly and event spaces for the parenting generation.

[1136] Output: Proposal.

[1137] Step 7:

[1138] The server notifies the generated proposal and sends it to the terminal.

[1139] Input: Proposal.

[1140] Specific actions: The proposal is notified to the apartment management company and also uploaded to the resident app and web portal.

[1141] Output: Notification of proposal.

[1142] Step 8:

[1143] The device displays the proposals to residents and collects their feedback.

[1144] Input: Proposal.

[1145] What it does: Collect feedback through a citizen interface in the form of surveys and free text.

[1146] Output: Collected feedback.

[1147] Step 9:

[1148] An emotion engine analyzes feedback to identify emotional tone.

[1149] Input: Collected feedback.

[1150] What it does: Uses natural language processing techniques to classify positive, negative, and neutral sentiment.

[1151] Output: Emotional tone analysis results.

[1152] Step 10:

[1153] The server improves the model based on the analysis results.

[1154] Input: Emotional tone analysis results.

[1155] Specific actions: Retrain your learning model to take into account the emotional tone and specific opinions of the feedback.

[1156] Output: An improved predictive model.

[1157] Step 11:

[1158] The server uses the improved model to generate new proposals.

[1159] Input: Improved predictive model.

[1160] Specific Action: Generate an optimized proposal and notify the residents again.

[1161] Output: A new proposal.

[1162] These steps enable the system to constantly adapt to the changing needs of residents and provide optimal shared facilities and community activities.

[1163] (Application example 2)

[1164] 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."

[1165] In today's large-scale condominiums, it is difficult to accurately predict residents' future needs and optimize shared facilities and community activities. Furthermore, because sentiment analysis to effectively utilize resident feedback and gain a deeper understanding has not been implemented, proposals can sometimes deviate from actual needs. Furthermore, because there is no way to use resident data to optimize the operation of physical stores, store services and products do not adequately meet resident demands. These issues need to be resolved.

[1166] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting resident data, means for preprocessing the collected resident data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activities based on the needs prediction results, means for collecting resident feedback on the proposals, means for emotionally analyzing the resident feedback and determining the emotional tone of the feedback, means for improving the model using the collected feedback, and means for generating optimization proposals for brick-and-mortar store operations using resident data. This not only enables accurate prediction of future needs of residents and optimization of shared facilities and community activities, but also makes it possible to reflect detailed feedback through resident emotional analysis and further optimize brick-and-mortar store operations.

[1167] "Resident data" refers to information about individuals and families residing in the apartment complex, including age, family composition, past facility usage history, survey results, etc.

[1168] "Preprocessing" is the process of filling in blanks, removing inappropriate values, standardizing formats, and anonymizing personal information to prepare the collected raw data for analysis.

[1169] "Features" are important variables in the data used to train machine learning models, and include residents' age groups, family composition, facility usage history, external data, etc.

[1170] A "learning model" is an implementation of an algorithm that learns specific patterns and relationships from collected data and makes future predictions.

[1171] Forecasting "needs" means using a trained learning model to estimate the wants and requirements of residents at a specific future point in time.

[1172] The "Optimization Proposal for Shared Facilities" provides specific improvement plans for efficient use of shared spaces and facilities within the condominium based on the predicted needs of residents.

[1173] "Community activity proposals" are proposals for planning events or activities to promote interaction and cooperation among residents.

[1174] "Feedback collection methods" refers to methods and tools used to collect opinions, comments, ratings, and other responses from residents.

[1175] "Sentiment analysis" is a technology that analyzes collected feedback text and audio data to identify the emotional tone contained therein.

[1176] The "Optimization proposal for physical store operations" uses resident data to improve the services and product lineup of specific stores, providing operations that better meet customer needs.

[1177] MODE FOR CARRYING OUT THE INVENTION

[1178] This invention relates to a system that utilizes resident data of large-scale apartment buildings to predict future needs and optimize the operation of shared facilities and brick-and-mortar stores. Below, we will explain in detail how to specifically implement this invention.

[1179] server

[1180] The server is the main device responsible for data collection, preprocessing, analysis, and prediction. The server in this system collects resident data from the apartment management system and smart devices, and preprocesses that data. Specifically, it stores residents' ages, family composition, past facility usage history, and survey results in a database. It also periodically obtains external data such as government statistical data and information on social trends, and integrates them.

[1181] In the data preprocessing stage, we remove empty and inappropriate values, standardize the data format, and protect privacy by anonymizing personal information.

[1182] Once preprocessing is complete, the server extracts features, selecting important variables based on residents' age groups, family composition, facility usage history, and external data, and then training a machine learning model. For example, algorithms such as random forests and neural networks are used to create a model for predicting future needs.

[1183] Using the trained model, the server predicts residents' future needs and generates optimization proposals for shared facilities and community activities. It also uses resident data to make optimization proposals for brick-and-mortar store operations. Based on the prediction results, it suggests, for example, the establishment of facilities for the elderly or play areas for children.

[1184] Terminal

[1185] The terminals are the interface through which residents can review the proposals and provide feedback. For example, residents can use their smartphones or computers to answer a questionnaire about the new proposals. Their feedback is sent to the server and analyzed through the emotion engine.

[1186] User

[1187] Users (residents) review the proposals via their devices and provide their feedback. The feedback is sent to the server, where the emotional tone is analyzed by the emotion engine. For example, users can enter their approval or disapproval of a new facility proposal, as well as specific requests. The server uses the results of this emotion analysis to understand the nuances of the feedback and improve the accuracy of the prediction model.

[1188] Emotion Engine

[1189] The emotion engine analyzes the text and voice data of user feedback to extract emotions such as dissatisfaction, satisfaction, suggestion, etc. This allows the server to understand the emotional tone of the feedback and perform more accurate needs assessment.

[1190] Specific examples

[1191] For example, in a large apartment complex, the following predictions and suggestions may be made:

[1192] The average age of residents is rising, and the number of families living there is increasing.

[1193] Based on the collected data, a proposal was made to renovate the fitness facility into a rehabilitation facility for the elderly.

[1194] We propose expanding the community center and creating an event space for people raising children.

[1195] Residents can review these suggestions and provide feedback, including specific requests for suggestions. The feedback is analyzed through an emotion engine, and the server uses the results to reassess the suggestions and generate more accurate ones.

[1196] Prompt Sentence Examples

[1197] Create a program that uses the residents' age, family composition, past facility usage history, and survey results to predict their needs 20-30 years from now using a random forest model, and proposes the establishment of rehabilitation facilities for the elderly and event spaces for childcare.

[1198] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1199] Step 1:

[1200] The server collects resident data from the apartment management system and smart devices. Specifically, it acquires information such as resident age, family composition, past facility usage history, and survey results, and stores it in a database. Input data comes in a variety of formats, but storing it in a unified database enables efficient management. The output is a unified database.

[1201] Step 2:

[1202] The server preprocesses the collected resident data. Specifically, it removes blank and inappropriate values, standardizes the data format, and anonymizes personal information. The input is the collected raw data in various formats, and the output is consistent, anonymized data with no blank values.

[1203] Step 3:

[1204] The server extracts features from the preprocessed data. During this process, important variables are selected based on the residents' age group, family structure, facility usage history, and external data (social trends, etc.). The input is the preprocessed data, and the output is a set of training features.

[1205] Step 4:

[1206] The server uses the extracted features to train a machine learning model, specifically using algorithms such as random forests or neural networks. The training dataset is fed to the model to improve its predictive capabilities. The input is the extracted feature set, and the output is the trained model.

[1207] Step 5:

[1208] The server uses the trained model to predict future needs of residents. The input is new or updated resident data, and the output is predicted future needs. For example, the prediction may be that demand for elderly care facilities will increase.

[1209] Step 6:

[1210] The server generates optimization proposals for shared facilities and community activities based on the needs prediction results. Specifically, it proposes the relocation or new construction of fitness facilities for the elderly and event spaces for children based on the prediction results. The input is the needs prediction results, and the output is the specific proposals.

[1211] Step 7:

[1212] The terminal distributes proposals to residents and collects feedback. The input is the proposal received from the server, and the output is feedback from residents. Residents fill out questionnaires and enter comments via their smartphones or computers.

[1213] Step 8:

[1214] The server performs sentiment analysis on the residents' feedback to determine its emotional tone. Specifically, it feeds the feedback text and audio data into a sentiment analysis engine, which extracts emotional tones such as satisfaction, dissatisfaction, and suggestions. The input is the feedback data, and the output is the sentiment analysis results.

[1215] Step 9:

[1216] The server uses the collected feedback to refine the model. It incorporates the sentiment analysis results into a learning algorithm to improve the accuracy of the predictive model. The input is the sentiment analysis results, and the output is an improved learning model.

[1217] Step 10:

[1218] The server uses resident data to generate optimization proposals for brick-and-mortar store operations. Based on the needs prediction results, it adjusts the product and service lineup. For example, it proposes increasing rehabilitation products for the elderly or events for families. The input is the needs prediction results, and the output is optimization proposals for the brick-and-mortar store.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] [Fourth embodiment]

[1223] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1224] 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.

[1225] 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).

[1226] 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.

[1227] 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.

[1228] 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).

[1229] 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.

[1230] 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.

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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."

[1236] This invention relates to a system that predicts the future needs of residents of large-scale apartment buildings, optimizes shared facilities, and proposes community activities. The system is composed of a server, terminals, and users.

[1237] server

[1238] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices. Specifically, it collects information on residents' ages, family composition, past facility usage history, and survey results, and stores this information in a database. It also periodically obtains external data, such as government statistical data and information on social trends, and integrates these data.

[1239] The server then cleanses the collected data, removing blank and irrelevant values, standardizing the format, and anonymizing the data to protect residents' privacy.

[1240] Once preprocessing is complete, the server extracts features. Important variables are selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests or neural networks are used to create a model for predicting future needs.

[1241] Using the trained model, the server predicts the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, if the prediction results indicate an aging population, it will propose the establishment of fitness facilities and medical consultation rooms for the elderly.

[1242] The server then notifies the apartment management company of the generated proposal and generates a proposal document, which is then uploaded to the resident app and web portal.

[1243] Terminal

[1244] The terminals provide an interface for residents to review the proposals and provide feedback. For example, a survey about new proposals can be sent to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[1245] User

[1246] Users, or residents, can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, and specific requests. This allows the entire system to be optimized to meet the actual needs of residents.

[1247] Specific examples

[1248] For example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[1249] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1250] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1251] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[1252] Residents can review these suggestions and provide feedback, which is then fed back into the server and used to refine the predictive model. In this way, the system can always respond to residents' needs and provide the optimal environment.

[1253] The processing flow will be explained below.

[1254] Step 1:

[1255] The server collects resident data from the apartment management system and smart devices, including the resident's age, family composition, past facility usage history, and survey results, and stores this information in a database.

[1256] Step 2:

[1257] The server periodically retrieves external data (government statistics and information on social trends) and integrates it with resident data.

[1258] Step 3:

[1259] The server preprocesses the collected data, specifically removing blank and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[1260] Step 4:

[1261] The server extracts features from the preprocessed data, selecting important variables from residents' age groups, family composition, facility usage history, and external data, and uses them as input for the machine learning model.

[1262] Step 5:

[1263] The server uses the extracted features to train machine learning models, specifically algorithms such as random forests and neural networks, to create models that predict future needs.

[1264] Step 6:

[1265] The server uses the trained model to predict the needs of residents 20-30 years into the future, determining, for example, the need for senior living facilities or family play areas.

[1266] Step 7:

[1267] Based on the prediction results, the server generates suggestions for restructuring shared facilities and new community activities, such as converting a fitness center into a senior rehabilitation center or expanding a community center.

[1268] Step 8:

[1269] The server then notifies the apartment management company of the generated proposal, which then creates a proposal document, which is then uploaded to the resident app or web portal.

[1270] Step 9:

[1271] The terminals distribute a questionnaire about the new proposal to residents, who then provide their opinions about the proposal via the terminals.

[1272] Step 10:

[1273] Users (residents) use terminals to answer questionnaires and provide feedback on their opinions and requests.

[1274] Step 11:

[1275] The server collects feedback from residents and stores it in a database for analysis, improving the accuracy of the predictive model and incorporating it into future proposals.

[1276] This series of processes enables the system to flexibly respond to the changing needs of residents and provide optimal shared facilities and community activities.

[1277] Example 1

[1278] 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."

[1279] In today's large-scale apartment complexes, accurately predicting residents' future needs and optimizing shared facilities and community activities accordingly is a difficult task. In particular, there is a need to propose facilities that respond to changes in residents' living environments and age structures, and to build a feedback system that reflects residents' opinions. However, current systems have difficulty meeting these requirements and are unable to respond to residents' actual needs.

[1280] 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.

[1281] In this invention, the server includes a means for collecting resident data, a means for preprocessing the collected resident data, and a means for extracting features from the preprocessed data and training a machine learning model, thereby enabling accurate prediction of future needs of residents and optimization of shared facilities and community activities based on the prediction.

[1282] "Resident data" refers to information about individual residents living in large apartment complexes, including, for example, age, family composition, past facility usage history, and survey results.

[1283] "Means of data preprocessing" refers to technical methods for processing collected data, such as removing blank or inappropriate values, standardizing formats, and anonymizing data.

[1284] "Features" are particularly important variables or parameters in the data used to train a learning model, including, for example, the age group and family composition of residents, facility usage history, etc.

[1285] A "machine learning model" is a mathematical framework for analyzing large amounts of data and making patterns and predictions based on specific algorithms. Typical examples include random forests and neural networks.

[1286] "Means to predict future needs" refers to technology that uses trained machine learning models to predict residents' future demands and requirements and present specific suggestions and countermeasures.

[1287] "Shared facilities" refer to facilities and areas set up for joint use by residents within a large apartment complex, including fitness facilities, rehabilitation facilities, and community centers.

[1288] "Feedback collection means" refers to the methods and tools used to collect opinions and evaluations of the proposals from residents, and can be done, for example, through a questionnaire form or a web portal.

[1289] "Means to improve the model" refers to techniques that analyze collected feedback and use it to adjust the parameters and algorithms of machine learning models to improve the model's accuracy and predictive capabilities.

[1290] "External data" refers to external information, such as government statistical data and information on social trends, separate from data on the apartment building management system and residents.

[1291] This invention relates to a system that predicts the future needs of residents in large-scale apartment buildings, optimizes shared facilities, and proposes community activities. The system consists of three elements: a server, terminals, and users.

[1292] System Overview

[1293] 1. Server

[1294] The server plays a central role in collecting, preprocessing, analyzing, and predicting the main data. Specifically, it performs the following tasks:

[1295] Data collection: The server collects resident data from the apartment management system and smart devices via APIs. For example, information such as resident age, family composition, past facility usage history, and survey results is collected and stored in a database. It also uses scraping and APIs from external services to collect government statistical data and information on social trends.

[1296] Data preprocessing: Collected data is processed to detect and complete blank and inappropriate values, standardize formats, and anonymize data, thereby improving data quality and protecting privacy.

[1297] Feature extraction and model training: Important features such as residents' age groups, family composition, and facility usage history are extracted from the preprocessed data. Then, machine learning algorithms such as random forests and neural networks are used to train models to predict future needs.

[1298] Generation of prediction results and recommendations: The trained model is used to predict the needs of residents 20-30 years into the future, and based on the results, it generates recommendations for optimizing shared facilities and community activities, such as establishing rehabilitation facilities for the elderly or event spaces for families with children.

[1299] Proposal notification and feedback collection: The generated proposals are notified to the apartment management company, and a proposal document is generated. The proposal document is also uploaded to the resident app and web portal.

[1300] 2. Terminal

[1301] The terminal will serve as an interface for residents to review the proposals and provide feedback. Specifically, it has the following functions:

[1302] Proposal notification: Notify residents of new proposals through their device (app or web portal), for example by sending a push notification to residents through a smartphone app.

[1303] Providing feedback: Provide a function that allows residents to input their opinions, specific requests, and other feedback regarding the proposals via their devices. For example, provide a questionnaire form to collect residents' opinions.

[1304] 3. Users

[1305] The user, i.e., the resident, is responsible for checking the proposals via a terminal and providing feedback. Specifically, he or she performs the following actions:

[1306] Review proposals: Residents review the proposals provided in the app or web portal and understand their contents.

[1307] Providing feedback: Residents can provide feedback on proposals, including pros and cons, opinions, and specific requests, so the entire system can be optimized based on residents' actual needs.

[1308] Specific examples

[1309] For example, the following predictions and proposals may be made for a large apartment complex:

[1310] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1311] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1312] Proposal: Renovate the fitness facility into a rehabilitation center for seniors, and expand the community center to include an event space for parents.

[1313] Residents can review these suggestions and provide feedback, which is then analyzed by the server and used to improve the accuracy of the predictive model. In this way, the system can always respond to residents' latest needs and provide the optimal environment.

[1314] Prompt Sentence Examples

[1315] "Based on the following input data, predict the needs of residents of a large apartment complex 20 years from now and propose optimization plans for shared facilities: The average age of residents is increasing year by year. The number of residents with families is increasing. Use of the fitness facility is decreasing, while use of the community center is increasing."

[1316] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1317] Step 1: Data collection

[1318] The server collects information about residents from the apartment management system and smart devices. Specifically, it obtains residents' ages, family composition, past facility usage history, and survey results through APIs. It also uses APIs from external services to collect government statistical data and data on social trends. The input is raw data from the apartment management system and external data APIs, and the output is structured data stored in a database.

[1319] Step 2: Data Preprocessing

[1320] The server preprocesses the collected data. Specific operations include removing empty and inappropriate values, standardizing formats, and anonymizing data. For example, standardizing date formats and hashing identifying information. The input is raw data, and the output is preprocessed, clean data.

[1321] Step 3: Feature extraction

[1322] The server extracts features from the preprocessed data. Specific operations include selecting important variables and parameters from the data. For example, the age group, family structure, and facility usage history of residents are extracted as features. The input is the preprocessed data, and the output is feature data used to train the machine learning model.

[1323] Step 4: Model training

[1324] The server uses the extracted features to train a machine learning model, specifically using algorithms such as random forests and neural networks. The input is the feature data, and the output is the trained machine learning model.

[1325] Step 5: Anticipate future needs

[1326] The server uses the trained model to predict future needs of residents, such as the need for rehabilitation facilities for the elderly or event spaces for families with children. The input is new data, and the output is information about predicted needs.

[1327] Step 6: Generate proposals

[1328] The server generates optimization proposals for shared facilities and community activities based on the prediction results. Specific actions include proposing to convert a fitness center into a rehabilitation facility for the elderly or to expand a community center to include an event space for the parenting generation. The input is the prediction data, and the output is the specific proposals.

[1329] Step 7: Proposal Notification

[1330] The server notifies the condominium management company of the generated proposal and also uploads it to the resident app and web portal. The device then sends push notifications and emails to notify the residents of the proposal. The input is the proposal content, and the output is the notified proposal.

[1331] Step 8: Gather feedback

[1332] The terminal collects feedback from residents. Specifically, it provides a questionnaire form in which residents can enter their opinions, whether they agree or disagree with the proposal, and their specific requests. Users enter their own opinions through this form. The input is the residents' opinions and feedback, and the output is the collected feedback data.

[1333] Step 9: Integrate feedback and retrain the model

[1334] The server analyzes the collected feedback and uses it to improve the machine learning model. Specific operations include text analysis of the feedback data and tuning the model parameters. The input is the feedback data, and the output is an improved machine learning model.

[1335] (Application example 1)

[1336] 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."

[1337] Existing large-scale condominium management systems have difficulty accurately predicting residents' future needs and optimizing facilities and proposing community activities based on those needs. Furthermore, autonomous vehicles lacked mechanisms for providing optimal routes and services tailored to passenger needs. This resulted in the inability to provide the services desired by residents and passengers in a timely manner, leading to lower satisfaction and a deterioration in efficiency.

[1338] 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.

[1339] In this invention, the server includes means for collecting resident data, means for preprocessing the collected data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activity proposals based on the needs prediction results, means for collecting resident feedback on the proposals, means for collecting vehicle usage history and passenger data and generating optimal routes based on the predicted needs, means for providing the optimal routes using an on-board computer, and means for improving the model using the collected feedback. This makes it possible to accurately predict the needs of residents and passengers and provide optimal services and proposals at the appropriate time.

[1340] "Resident data" refers to information such as the age, family composition, past facility usage history, and survey results of individuals living in the apartment complex.

[1341] "Preprocessing" refers to the process of cleansing collected data, removing blank and inappropriate values, and standardizing the format.

[1342] "Features" refer to important variables and patterns extracted from data to optimize the performance of machine learning models.

[1343] A "learning model" refers to an algorithm or model that learns from collected data and makes predictions or classifications based on that data.

[1344] "Trained Model" refers to a predictive model that has been tuned by a machine learning algorithm using collected data.

[1345] "Future needs" refers to the facility usage and service requirements that residents and passengers are expected to require in the future.

[1346] "Shared facilities" refers to facilities and spaces within an apartment building that are shared and used by residents, such as a fitness gym or community center.

[1347] "Optimal route" refers to the optimal route selected for an autonomous vehicle to transport passengers to their destination efficiently and safely.

[1348] "On-board computer" refers to a computer device installed inside a vehicle for data processing and control.

[1349] "Feedback" refers to opinions and evaluations of suggestions and services collected from residents and passengers.

[1350] "Model improvement" refers to the process of using collected feedback to improve the accuracy and performance of existing machine learning models.

[1351] MODE FOR CARRYING OUT THE INVENTION

[1352] server

[1353] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects "resident data" from the apartment management system and smart devices. Specifically, this information includes age, family composition, past facility usage history, and survey results. It also collects usage history and passenger data from autonomous vehicles. Furthermore, it regularly obtains external data, such as government statistical data and information on social trends, and integrates this data into the database.

[1354] The server then "pre-processes" the collected data: it cleanses it, removes blank or irrelevant values, standardizes the format, and anonymizes it to protect residents' privacy.

[1355] Once preprocessing is complete, the server extracts "features," which are key variables selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests and neural networks are used to create a model for predicting future needs.

[1356] Using the trained model, the server predicts the needs of residents and passengers 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. It also generates "optimal routes" for autonomous vehicles based on the predicted needs. The on-board computer provides optimal routes, increasing passenger satisfaction.

[1357] The server then notifies the apartment management company or vehicle operation manager of the generated proposal, and generates a proposal document, which is then uploaded to an app or web portal for residents and passengers.

[1358] Terminal

[1359] The terminals provide an interface for residents and passengers to review the proposals and provide feedback. For example, a survey about new proposals could be distributed through an app or web portal. Residents and passengers can directly provide feedback on the proposals. This allows the entire system to be optimized to better meet actual needs.

[1360] User

[1361] Users, i.e., residents and passengers, can review the proposals and provide feedback via their devices, such as whether they agree or disagree with the new facility proposal, their opinions, or specific requests, so that the entire system can respond to the actual needs of residents and passengers.

[1362] Specific examples

[1363] As a concrete example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[1364] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1365] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1366] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for parents.

[1367] Also, in autonomous vehicles, optimal routes are generated based on passenger data. For example, the following prompts can be used to gather feedback:

[1368] Collect feedback from passengers after they arrive at their destination. Enter the following information:

[1369] Arrival time to destination

[1370] Services used (e.g. route flexibility, ride comfort, etc.)

[1371] comment

[1372] This allows us to collect feedback from residents and passengers and improve the accuracy of the model, so that the system is always responsive to their needs and provides the best possible environment.

[1373] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1374] Step 1:

[1375] Data collection

[1376] The server collects "resident data" from the apartment management system and smart devices. This data includes age, family composition, past facility usage history, and survey results. It also collects usage history and passenger data from autonomous vehicles. Furthermore, external data such as government statistical data and social trend information is periodically acquired and integrated into the database.

[1377] Input: Data from management systems and smart devices

[1378] Output: Integrated database

[1379] Step 2:

[1380] Data Preprocessing

[1381] The server preprocesses the collected data: it cleanses it, removes blank and irrelevant values, standardizes the format, and anonymizes it to protect the privacy of residents.

[1382] Input: Integrated Database

[1383] Output: Preprocessed dataset

[1384] Step 3:

[1385] Feature extraction

[1386] The server extracts "features" from the preprocessed data by selecting important variables based on residents' age groups, family structure, facility usage history, and external data.

[1387] Input: Preprocessed dataset

[1388] Output: A dataset with extracted features

[1389] Step 4:

[1390] Training a machine learning model

[1391] The server uses the extracted features to train machine learning models, using algorithms such as random forests and neural networks to create models to predict future needs.

[1392] Input: Feature-extracted dataset

[1393] Output: A trained machine learning model

[1394] Step 5:

[1395] Anticipating future needs

[1396] Using the trained model, the server predicts the needs of residents and passengers 20-30 years into the future.

[1397] Input: A trained machine learning model

[1398] Output: Predicted future needs

[1399] Step 6:

[1400] Proposal generation

[1401] Based on the prediction results, the server generates plans for restructuring shared facilities, suggestions for new community activities, and optimal routes for self-driving vehicles.

[1402] Input: Projected future needs

[1403] Output: Generated proposals and optimal routes

[1404] Step 7:

[1405] proposal notification

[1406] The server then notifies the apartment management company or vehicle operation manager of the generated proposal, which then generates a proposal document, which is then uploaded to an app or web portal for residents and passengers.

[1407] Input: Generated proposals and optimal routes

[1408] Output: Proposal and uploaded content

[1409] Step 8:

[1410] Feedback collection

[1411] The terminals will then distribute surveys about the new proposals via an app or web portal, allowing residents and passengers to provide direct feedback on their opinions of the proposals.

[1412] Input: Uploaded proposal and feedback survey

[1413] Output: Collected feedback

[1414] Step 9:

[1415] Model Improvement

[1416] The server uses the collected feedback to retrain the model to improve its accuracy.

[1417] Input: Collected feedback

[1418] Output: An improved machine learning model

[1419] 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.

[1420] This invention relates to a system that predicts the future needs of residents of large-scale apartment buildings, optimizes shared facilities, and proposes community activities. This system is composed of a server, terminals, and users, and is also combined with an emotion engine that recognizes user emotions.

[1421] server

[1422] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices. Specifically, it acquires information on residents' ages, family composition, past facility usage history, and survey results, and stores this information in a database. It also periodically acquires external data, such as government statistical data and information on social trends, and integrates these data.

[1423] The server then preprocesses the collected data, specifically removing empty and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[1424] Once preprocessing is complete, the server extracts features. Important variables are selected based on residents' age groups, family composition, facility usage history, and external data. These features are then used to train a machine learning model. For example, algorithms such as random forests or neural networks are used to create a model for predicting future needs.

[1425] Using the trained model, the server predicts the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, if the prediction results indicate an aging population, it will propose the establishment of fitness facilities and medical consultation rooms for the elderly.

[1426] The server then notifies the apartment management company of the generated proposal and generates a proposal document, which is then uploaded to the resident app and web portal.

[1427] Terminal

[1428] The terminals provide an interface for residents to review the proposals and provide feedback. For example, a survey about new proposals can be sent to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[1429] User

[1430] Users, or residents, can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, and specific requests. This allows the entire system to be optimized to meet the actual needs of residents.

[1431] Emotion Engine

[1432] The emotion engine analyzes user feedback to identify its emotional tone. For example, it analyzes text and voice data entered by residents as feedback and extracts emotions such as dissatisfaction, satisfaction, and suggestions. The server uses the results of this emotion analysis to understand the nuances of the feedback and conduct more accurate needs assessments.

[1433] Specific examples

[1434] For example, in a large apartment complex, the following predictions and suggestions may be made based on the collected data:

[1435] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1436] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1437] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[1438] Residents review these suggestions and provide feedback, which is analyzed through an emotion engine to detect the emotional tone of complaints or requests. For example, if many residents express dissatisfaction with a particular suggestion, the server will perform a new analysis to reassess the suggestion.

[1439] The feedback is then fed back into the server and used to refine the predictive model, ensuring the system is always responsive to residents' needs and providing optimal shared facilities and community activities.

[1440] The system will be able to adapt flexibly to changing needs of residents, maintaining long-term satisfaction, and use an emotion engine to gather more accurate feedback and provide specific, actionable recommendations.

[1441] The processing flow will be explained below.

[1442] Step 1:

[1443] The server collects resident data from the apartment management system and smart devices. Specifically, it obtains information such as the resident's age, family composition, past facility usage history, and survey results, and stores this information in a database. In addition, the server periodically obtains external data such as government statistical data and information on social trends, and integrates this data into the database.

[1444] Step 2:

[1445] The server preprocesses the collected data, specifically removing blank and inappropriate values, standardizing the data format, and anonymizing personal information to protect privacy.

[1446] Step 3:

[1447] The server extracts features from the preprocessed data, selecting important variables from resident age groups, family composition, facility usage history, external data, etc., and uses these as input for the machine learning model.

[1448] Step 4:

[1449] The server uses the extracted features to train a machine learning model, such as a random forest or neural network algorithm, to create a model that predicts future needs.

[1450] Step 5:

[1451] The server uses the trained model to predict the needs of residents 20-30 years into the future. Based on the prediction results, it generates proposals for restructuring shared facilities and new community activities. For example, it predicts the progression of aging and suggests the establishment of fitness facilities and medical consultation rooms for the elderly.

[1452] Step 6:

[1453] The server then notifies the apartment management company of the generated proposal, which then creates a proposal document, which is then uploaded to the resident app or web portal.

[1454] Step 7:

[1455] The terminals will send a questionnaire about the new proposal to residents, who will then answer the questionnaire and provide feedback on their opinions and requests regarding the proposal.

[1456] Step 8:

[1457] Users (residents) can review the proposals via their devices and input their own opinions and requests. For example, they can provide specific feedback such as "I support the proposal for a facility for the elderly" or "I hope the community center will be expanded."

[1458] Step 9:

[1459] The emotion engine analyzes collected feedback and identifies the user's emotional tone, for example, extracting emotions such as dissatisfaction, satisfaction, and suggestions from text and voice data, and generates emotion analysis results.

[1460] Step 10:

[1461] The server uses the feedback analyzed by the emotion engine to understand the nuances of the feedback and conduct more accurate needs assessments, for example, reconsidering and improving proposals that receive a lot of dissatisfaction feedback.

[1462] Step 11:

[1463] The server retrains the model based on the feedback to improve the accuracy of future suggestions, thereby continually adapting to the changing needs of residents.

[1464] As a concrete example, the following process takes place in a large apartment complex:

[1465] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1466] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1467] Proposal: Renovate the fitness center into a rehabilitation center for seniors, and expand the community center to include an event space for families with children.

[1468] In this way, the system can adapt flexibly to changing needs of residents and maintain long-term satisfaction. The introduction of an emotion engine enables deeper feedback analysis, leading to specific and actionable recommendations.

[1469] Example 2

[1470] 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."

[1471] In today's large-scale apartment complexes, the lifestyle needs of residents continue to change over time. It is extremely important for apartment complex managers and residents to accurately predict future needs and plan and implement appropriate facilities and community activities. However, traditional methods rely primarily on short-term surveys and feedback, making it difficult to predict and propose long-term outcomes. Furthermore, the collected feedback often fails to accurately capture the emotional nuances of residents, which can lead to unnecessary issues and dissatisfaction. Another major challenge is conducting accurate data analysis while ensuring residents' privacy.

[1472] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1473] In this invention, the server includes means for collecting resident data, means for preprocessing the collected resident data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activity proposals based on the needs prediction results, means for notifying residents of the generated proposals, means for collecting resident feedback on the proposals, means for analyzing the collected feedback to identify emotional tones, and means for improving the model using the collected feedback. This makes it possible to accurately predict long-term resident needs and make proposals that take emotional nuances into consideration, thereby increasing resident satisfaction and protecting resident privacy.

[1474] "Resident data" refers to information related to the residents of the apartment building, including, specifically, age, family composition, past facility usage history, survey results, etc.

[1475] "Preprocessing" refers to processing performed on collected data, including removing null and inappropriate values, standardizing data formats, and anonymizing personal information.

[1476] "Features" are important variables extracted from data and are used to train machine learning models.

[1477] A "learning model" is a mathematical model that uses machine learning algorithms to learn patterns from data and make future predictions or classifications.

[1478] "Needs forecasting" is the use of trained learning models to estimate the future wants and needs of residents.

[1479] "Optimization proposals" refer to the generation of improvement proposals for shared facilities and services based on the results of needs predictions.

[1480] "Community activity proposals" involve proposing new community events and activities based on the needs of residents.

[1481] "Feedback" refers to the opinions and thoughts that residents give about the proposals, and includes questionnaires and free comments.

[1482] "Emotional tone" refers to the emotional tendency extracted from the content of feedback, and includes classifications such as positive, negative, and neutral.

[1483] "Analysis" refers to the process of analyzing data to extract meaningful information, specifically identifying the emotional tone of feedback using the emotion engine.

[1484] "Refinement" refers to retraining a learning model based on collected feedback to improve its accuracy and performance.

[1485] This invention relates to a system that predicts the future needs of residents of a large-scale apartment complex, optimizes shared facilities, and proposes community activities.The system for implementing this invention is composed of a server, terminals, and users, and is further combined with an emotion engine that recognizes the user's emotions.

[1486] server

[1487] The server is responsible for primary data collection, preprocessing, analysis, and prediction. First, it collects resident data from the apartment management system and smart devices and stores it in a database. Specifically, it obtains information such as resident age, family composition, past facility usage history, and survey results. It also periodically obtains external data such as government statistical data and information on social trends, and integrates these data.

[1488] The server preprocesses the collected data. Specifically, it removes blank and inappropriate values ​​and standardizes the data format. It also anonymizes personal information to protect privacy. Python libraries such as pandas and NumPy can be used.

[1489] Once preprocessing is complete, the server extracts features, selects important variables based on residents' age groups, family composition, facility usage history, and external data, and trains a machine learning model. The trained model is created using tools such as Scikit-learn's RandomForestClassifier and TensorFlow's Keras.

[1490] Using the trained model, the server predicts residents' needs 20-30 years into the future. For example, if an aging population is predicted, the server generates proposals for establishing fitness facilities and medical consultation rooms for the elderly. The generated proposals are notified to the apartment management company and are also uploaded to the resident app and web portal.

[1491] Terminal

[1492] The terminals provide an interface for residents to review the proposals and provide feedback. Specifically, a survey about the new proposals is distributed to residents via an app or web portal. Residents can then directly provide feedback on the proposals.

[1493] User

[1494] Users (residents) can review the proposals via their devices and provide feedback, such as whether they agree or disagree with the new facility proposal, their opinions, or specific requests. This feedback is used to optimize the entire system to better meet the actual needs of residents.

[1495] Emotion Engine

[1496] The emotion engine analyzes user feedback to identify its emotional tone. For example, it analyzes the text entered by the user as feedback and extracts emotions such as dissatisfaction, satisfaction, suggestion, etc. The server uses the emotion analysis results to understand the nuances of the feedback and perform more accurate needs assessment.

[1497] Specific examples

[1498] For example, in a large apartment complex, the following predictions and suggestions are made based on the collected data:

[1499] Data collected: The average age of residents is increasing year by year. The number of families living in the area is increasing. Use of fitness facilities is decreasing, while use of community centers is increasing.

[1500] Result: In 20 years, the average age of residents will continue to rise, increasing the demand for facilities for the elderly. At the same time, the need for family play areas and event spaces will also increase.

[1501] Proposal: Renovate the fitness center into a senior rehabilitation center, and expand the community center to include an event space for parents.

[1502] Residents review these suggestions and provide feedback, which is analyzed through an emotion engine to detect the emotional tone of complaints or requests. For example, if many residents express dissatisfaction with a particular suggestion, the server will perform a new analysis to reassess the suggestion.

[1503] Prompt Sentence Examples

[1504] Here are some example prompts to input to a generative AI model:

[1505] Predict the needs of the residents of an apartment complex 20 years from now and propose a plan to restructure the shared facilities based on that. Use the following data for your analysis: residents' age, family composition, past facility usage history, survey results, government statistics, and social trends. If the population is aging, include suggestions for adding facilities for the elderly and medical consultation rooms.

[1506] In this way, the system can flexibly respond to the changing needs of residents and always provide the best possible shared facilities and community activities. The emotion engine also allows for more accurate feedback and makes specific, actionable recommendations.

[1507] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1508] Step 1:

[1509] The server initiates the data collection process.

[1510] Input: Resident age, family composition, past facility usage history, survey results, government statistics, and social trends.

[1511] Specific operation: The server accesses the apartment management system and smart devices, sets them up to periodically collect data, and uses APIs to retrieve data from public databases and integrate it with internal data.

[1512] Output: Raw data is stored in a database.

[1513] Step 2:

[1514] The server pre-processes the collected data.

[1515] Input: Collected data stored in a database.

[1516] Specific actions: Detect and remove or correct empty or inappropriate values. Standardize data formats and anonymize personal information using Python's pandas and NumPy libraries.

[1517] Output: A clean, pre-processed dataset.

[1518] Step 3:

[1519] The server extracts features.

[1520] Input: A clean, pre-processed dataset.

[1521] Specific operation: Using the Scikit-learn library, important features are selected based on residents' age groups, family composition, facility usage history, and external data.

[1522] Output: A dataset containing the features.

[1523] Step 4:

[1524] The server trains the learning model.

[1525] Input: A dataset containing features.

[1526] Specific operation: Train a model using machine learning algorithms such as Scikit-learn's RandomForestClassifier or TensorFlow's Keras.

[1527] Output: A trained predictive model.

[1528] Step 5:

[1529] The server predicts the future needs of residents.

[1530] Input: A trained predictive model.

[1531] What it does: Use the trained model to predict the needs of residents 20-30 years into the future, for example by simulating scenarios where the population is aging.

[1532] Output: Projected future needs.

[1533] Step 6:

[1534] The server generates optimization suggestions based on the prediction results.

[1535] Input: Projected future needs.

[1536] Specific actions: Generate specific proposals such as rehabilitation facilities for the elderly and event spaces for the parenting generation.

[1537] Output: Proposal.

[1538] Step 7:

[1539] The server notifies the generated proposal and sends it to the terminal.

[1540] Input: Proposal.

[1541] Specific actions: The proposal is notified to the apartment management company and also uploaded to the resident app and web portal.

[1542] Output: Notification of proposal.

[1543] Step 8:

[1544] The device displays the proposals to residents and collects their feedback.

[1545] Input: Proposal.

[1546] What it does: Collect feedback through a citizen interface in the form of surveys and free text.

[1547] Output: Collected feedback.

[1548] Step 9:

[1549] An emotion engine analyzes feedback to identify emotional tone.

[1550] Input: Collected feedback.

[1551] What it does: Uses natural language processing techniques to classify positive, negative, and neutral sentiment.

[1552] Output: Emotional tone analysis results.

[1553] Step 10:

[1554] The server improves the model based on the analysis results.

[1555] Input: Emotional tone analysis results.

[1556] Specific actions: Retrain your learning model to take into account the emotional tone and specific opinions of the feedback.

[1557] Output: An improved predictive model.

[1558] Step 11:

[1559] The server uses the improved model to generate new proposals.

[1560] Input: Improved predictive model.

[1561] Specific Action: Generate an optimized proposal and notify the residents again.

[1562] Output: A new proposal.

[1563] These steps enable the system to constantly adapt to the changing needs of residents and provide optimal shared facilities and community activities.

[1564] (Application example 2)

[1565] 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."

[1566] In today's large-scale condominiums, it is difficult to accurately predict residents' future needs and optimize shared facilities and community activities. Furthermore, because sentiment analysis to effectively utilize resident feedback and gain a deeper understanding has not been implemented, proposals can sometimes deviate from actual needs. Furthermore, because there is no way to use resident data to optimize the operation of physical stores, store services and products do not adequately meet resident demands. These issues need to be resolved.

[1567] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting resident data, means for preprocessing the collected resident data, means for extracting features from the preprocessed data and training a learning model, means for predicting future needs of residents using the trained model, means for generating optimization proposals for shared facilities and community activities based on the needs prediction results, means for collecting resident feedback on the proposals, means for emotionally analyzing the resident feedback and determining the emotional tone of the feedback, means for improving the model using the collected feedback, and means for generating optimization proposals for brick-and-mortar store operations using resident data. This not only enables accurate prediction of future needs of residents and optimization of shared facilities and community activities, but also makes it possible to reflect detailed feedback through resident emotional analysis and further optimize brick-and-mortar store operations.

[1568] "Resident data" refers to information about individuals and families residing in the apartment complex, including age, family composition, past facility usage history, survey results, etc.

[1569] "Preprocessing" is the process of filling in blanks, removing inappropriate values, standardizing formats, and anonymizing personal information to prepare the collected raw data for analysis.

[1570] "Features" are important variables in the data used to train machine learning models, and include residents' age groups, family composition, facility usage history, external data, etc.

[1571] A "learning model" is an implementation of an algorithm that learns specific patterns and relationships from collected data and makes future predictions.

[1572] Forecasting "needs" means using a trained learning model to estimate the wants and requirements of residents at a specific future point in time.

[1573] The "Optimization Proposal for Shared Facilities" provides specific improvement plans for efficient use of shared spaces and facilities within the condominium based on the predicted needs of residents.

[1574] "Community activity proposals" are proposals for planning events or activities to promote interaction and cooperation among residents.

[1575] "Feedback collection methods" refers to methods and tools used to collect opinions, comments, ratings, and other responses from residents.

[1576] "Sentiment analysis" is a technology that analyzes collected feedback text and audio data to identify the emotional tone contained therein.

[1577] The "Optimization proposal for physical store operations" uses resident data to improve the services and product lineup of specific stores, providing operations that better meet customer needs.

[1578] MODE FOR CARRYING OUT THE INVENTION

[1579] This invention relates to a system that utilizes resident data of large-scale apartment buildings to predict future needs and optimize the operation of shared facilities and brick-and-mortar stores. Below, we will explain in detail how to specifically implement this invention.

[1580] server

[1581] The server is the main device responsible for data collection, preprocessing, analysis, and prediction. The server in this system collects resident data from the apartment management system and smart devices, and preprocesses that data. Specifically, it stores residents' ages, family composition, past facility usage history, and survey results in a database. It also periodically obtains external data such as government statistical data and information on social trends, and integrates them.

[1582] In the data preprocessing stage, we remove empty and inappropriate values, standardize the data format, and protect privacy by anonymizing personal information.

[1583] Once preprocessing is complete, the server extracts features, selecting important variables based on residents' age groups, family composition, facility usage history, and external data, and then training a machine learning model. For example, algorithms such as random forests and neural networks are used to create a model for predicting future needs.

[1584] Using the trained model, the server predicts residents' future needs and generates optimization proposals for shared facilities and community activities. It also uses resident data to make optimization proposals for brick-and-mortar store operations. Based on the prediction results, it suggests, for example, the establishment of facilities for the elderly or play areas for children.

[1585] Terminal

[1586] The terminals are the interface through which residents can review the proposals and provide feedback. For example, residents can use their smartphones or computers to answer a questionnaire about the new proposals. Their feedback is sent to the server and analyzed through the emotion engine.

[1587] User

[1588] Users (residents) review the proposals via their devices and provide their feedback. The feedback is sent to the server, where the emotional tone is analyzed by the emotion engine. For example, users can enter their approval or disapproval of a new facility proposal, as well as specific requests. The server uses the results of this emotion analysis to understand the nuances of the feedback and improve the accuracy of the prediction model.

[1589] Emotion Engine

[1590] The emotion engine analyzes the text and voice data of user feedback to extract emotions such as dissatisfaction, satisfaction, suggestion, etc. This allows the server to understand the emotional tone of the feedback and perform more accurate needs assessment.

[1591] Specific examples

[1592] For example, in a large apartment complex, the following predictions and suggestions may be made:

[1593] The average age of residents is rising, and the number of families living there is increasing.

[1594] Based on the collected data, a proposal was made to renovate the fitness facility into a rehabilitation facility for the elderly.

[1595] We propose expanding the community center and creating an event space for people raising children.

[1596] Residents can review these suggestions and provide feedback, including specific requests for suggestions. The feedback is analyzed through an emotion engine, and the server uses the results to reassess the suggestions and generate more accurate ones.

[1597] Prompt Sentence Examples

[1598] Create a program that uses the residents' age, family composition, past facility usage history, and survey results to predict their needs 20-30 years from now using a random forest model, and proposes the establishment of rehabilitation facilities for the elderly and event spaces for childcare.

[1599] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1600] Step 1:

[1601] The server collects resident data from the apartment management system and smart devices. Specifically, it acquires information such as resident age, family composition, past facility usage history, and survey results, and stores it in a database. Input data comes in a variety of formats, but storing it in a unified database enables efficient management. The output is a unified database.

[1602] Step 2:

[1603] The server preprocesses the collected resident data. Specifically, it removes blank and inappropriate values, standardizes the data format, and anonymizes personal information. The input is the collected raw data in various formats, and the output is consistent, anonymized data with no blank values.

[1604] Step 3:

[1605] The server extracts features from the preprocessed data. During this process, important variables are selected based on the residents' age group, family structure, facility usage history, and external data (social trends, etc.). The input is the preprocessed data, and the output is a set of training features.

[1606] Step 4:

[1607] The server uses the extracted features to train a machine learning model, specifically using algorithms such as random forests or neural networks. The training dataset is fed to the model to improve its predictive capabilities. The input is the extracted feature set, and the output is the trained model.

[1608] Step 5:

[1609] The server uses the trained model to predict future needs of residents. The input is new or updated resident data, and the output is predicted future needs. For example, the prediction may be that demand for elderly care facilities will increase.

[1610] Step 6:

[1611] The server generates optimization proposals for shared facilities and community activities based on the needs prediction results. Specifically, it proposes the relocation or new construction of fitness facilities for the elderly and event spaces for children based on the prediction results. The input is the needs prediction results, and the output is the specific proposals.

[1612] Step 7:

[1613] The terminal distributes proposals to residents and collects feedback. The input is the proposal received from the server, and the output is feedback from residents. Residents fill out questionnaires and enter comments via their smartphones or computers.

[1614] Step 8:

[1615] The server performs sentiment analysis on the residents' feedback to determine its emotional tone. Specifically, it feeds the feedback text and audio data into a sentiment analysis engine, which extracts emotional tones such as satisfaction, dissatisfaction, and suggestions. The input is the feedback data, and the output is the sentiment analysis results.

[1616] Step 9:

[1617] The server uses the collected feedback to refine the model. It incorporates the sentiment analysis results into a learning algorithm to improve the accuracy of the predictive model. The input is the sentiment analysis results, and the output is an improved learning model.

[1618] Step 10:

[1619] The server uses resident data to generate optimization proposals for brick-and-mortar store operations. Based on the needs prediction results, it adjusts the product and service lineup. For example, it proposes increasing rehabilitation products for the elderly or events for families. The input is the needs prediction results, and the output is optimization proposals for the brick-and-mortar store.

[1620] 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.

[1621] 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.

[1622] 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 robot 414.

[1623] 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.

[1624] FIG. 9 illustrates 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 behaviors 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.

[1625] 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.

[1626] 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).

[1627] 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.

[1628] 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."

[1629] 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.

[1630] 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).

[1631] 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.

[1632] 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.

[1633] 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.

[1634] 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.

[1635] 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.

[1636] 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.

[1637] 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.

[1638] 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.

[1639] 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.

[1640] 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.

[1641] The following is further disclosed regarding the above embodiment.

[1642] (Claim 1)

[1643] a means of collecting data on residents;

[1644] a means of pre-processing the collected resident data;

[1645] A means for extracting features from the preprocessed data and training a learning model;

[1646] A means of predicting future needs of residents using trained models; and

[1647] A means for generating optimization proposals for shared facilities and community activities based on the needs forecast results;

[1648] a means of gathering resident feedback on the proposals;

[1649] a means for improving the model using the collected feedback; and

[1650] A system including:

[1651] (Claim 2)

[1652] 10. The system of claim 1, further comprising means for acquiring external data, integrating the data with the resident data, and storing the data in the database.

[1653] (Claim 3)

[1654] 10. The system of claim 1, further comprising means for anonymizing and protecting the privacy of resident feedback.

[1655] "Example 1"

[1656] (Claim 1)

[1657] a means of collecting data on residents;

[1658] a means of pre-processing the collected resident data;

[1659] A means of extracting features from the preprocessed data and training a machine learning model;

[1660] A means of predicting future needs of residents using trained models; and

[1661] A means for generating optimization proposals for shared facilities and community activities based on the needs forecast results;

[1662] a means of gathering resident feedback on the proposals;

[1663] a means for improving the model using the collected feedback; and

[1664] A system including:

[1665] (Claim 2)

[1666] 10. The system of claim 1, further comprising means for acquiring external data, integrating the data with the resident data, and storing the data in the database.

[1667] (Claim 3)

[1668] 10. The system of claim 1, further comprising means for anonymizing and protecting the privacy of resident feedback.

[1669] "Application Example 1"

[1670] (Claim 1)

[1671] a means of collecting data on residents;

[1672] a means of pre-processing the collected resident data;

[1673] A means for extracting features from the preprocessed data and training a learning model;

[1674] A means of predicting future needs of residents using trained models; and

[1675] A means for generating optimization proposals for shared facilities and community activities based on the needs forecast results;

[1676] a means of gathering resident feedback on the proposals;

[1677] a means for collecting vehicle usage history and passenger data and generating optimal routes based on predicted needs;

[1678] A means for providing an optimal route using an on-board computer;

[1679] a means for improving the model using the collected feedback; and

[1680] A system including:

[1681] (Claim 2)

[1682] 10. The system of claim 1, further comprising means for acquiring external data, integrating the data with the resident data, and storing the data in the database.

[1683] (Claim 3)

[1684] 10. The system of claim 1, further comprising means for anonymizing and protecting the privacy of resident feedback.

[1685] "Example 2: Combining Emotion Engines"

[1686] (Claim 1)

[1687] a means of collecting data on residents;

[1688] a means of pre-processing the collected resident data;

[1689] A means for extracting features from the preprocessed data and training a learning model;

[1690] A means of predicting future needs of residents using trained models; and

[1691] A means for generating optimization proposals for shared facilities and community activities based on the needs forecast results;

[1692] a means for notifying residents of the generated proposals;

[1693] a means of gathering resident feedback on the proposals;

[1694] a means of analyzing the collected feedback to identify emotional tone;

[1695] a means for improving the model using the collected feedback; and

[1696] A system including:

[1697] (Claim 2)

[1698] 10. The system of claim 1, further comprising means for acquiring external data, integrating the data with the resident data, and storing the data in the database.

[1699] (Claim 3)

[1700] 10. The system of claim 1, further comprising means for anonymizing and protecting the privacy of resident feedback.

[1701] "Application example 2 when combining emotion engines"

[1702] (Claim 1)

[1703] a means of collecting data on residents;

[1704] a means of pre-processing the collected resident data;

[1705] A means for extracting features from the preprocessed data and training a learning model;

[1706] A means of predicting future needs of residents using trained models; and

[1707] A means for generating optimization proposals for shared facilities and community activities based on the needs forecast results;

[1708] a means of gathering resident feedback on the proposals;

[1709] a means for sentiment analysis of the resident feedback to determine the emotional tone of the feedback;

[1710] a means for improving the model using the collected feedback; and

[1711] a means for generating optimization proposals for brick-and-mortar store operations using resident data;

[1712] A system including:

[1713] (Claim 2)

[1714] 10. The system of claim 1, further comprising means for acquiring external data, integrating the data with the resident data, and storing the data in the database.

[1715] (Claim 3)

[1716] 10. The system of claim 1, further comprising means for anonymizing and protecting the privacy of resident feedback. [Explanation of symbols]

[1717] 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 data on residents; a means of pre-processing the collected resident data; A means for extracting features from the preprocessed data and training a learning model; A means of predicting future needs of residents using trained models; and A means for generating optimization proposals for shared facilities and community activities based on the needs forecast results; a means of gathering resident feedback on the proposals; a means for improving the model using the collected feedback; and A system including:

2. The system of claim 1 further comprising means for acquiring external data, integrating the data with the resident data, and storing the data in the database.

3. The system of claim 1 , further comprising means for anonymizing resident feedback to protect privacy.

Images