system

Abstract

We provide the system. [Solution] A means of aggregating city-related data obtained from different sources, A means for converting collected information into a standard format and performing noise reduction and outlier correction to improve data quality, A means for performing pattern analysis and prediction using machine learning algorithms with preprocessed data, A means of formulating the results into text using natural language construction and providing them as a report document, A method for collecting user feedback on the report content and updating the machine learning model, A means of providing an information technology infrastructure for displaying analysis results to users in real time, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern cities, there are a multitude of complex problems such as traffic congestion, increased energy consumption, and environmental issues, which require prompt and effective countermeasures. However, with conventional methods, there are limitations in the dispersion of data and the efficiency of analysis for these problems, making it difficult to provide appropriate solutions. Also, there is a demand for a system that can aggregate information obtained from various data sources and evaluate and improve the situation in real time.

Means for Solving the Problems

[0005] This invention provides means for collecting traffic, energy, environmental, and demographic information from different data sources, converting the collected data into a unified format, and performing noise reduction and outlier processing. Furthermore, it provides means for performing pattern analysis and prediction using a machine learning model based on the pre-processed data. The analyzed results are formalized using natural language generation technology and output as a report. This enables efficient information provision, and the accuracy of future analyses can be improved by retraining the machine learning model based on user feedback. Through these means, the invention provides sustainable and effective solutions to the complex challenges faced by cities.

[0006] "Data sources" refer to sensors and databases that provide diverse information, such as traffic, energy, environmental, and population data.

[0007] "Noise reduction" refers to the process of removing inaccurate data or unnecessary information during data processing.

[0008] An "outlier" refers to an abnormal value in a dataset that deviates significantly from the other data points.

[0009] A "machine learning model" refers to an automated algorithm that performs pattern recognition and prediction based on collected data.

[0010] "Pattern analysis" refers to analytical methods used to detect regularities and trends present within data.

[0011] "Natural language generation technology" refers to the technology that converts visual or machine-readable data into a text format that humans can understand.

[0012] "Retraining" refers to the process of updating an existing machine learning model based on feedback to improve the accuracy and adaptability of the analysis. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention aims to integrate and analyze diverse data in urban areas, such as traffic, energy, environmental, and population information, and to optimize administrative services and improve citizens' lives based on the results. This system has an architecture that primarily processes data centered on a server, and its embodiments are described below.

[0035] The server first collects data in real time from traffic sensors, energy meters, environmental monitoring devices, and other sources. Since this data is transmitted in various formats, the server converts it into a unified format and integrates it into an analyzable format. For example, the server converts traffic data in CSV format and environmental data in JSON format into a common data model.

[0036] Next, the server performs noise reduction and outlier filtering on the collected data to improve its quality. This ensures the accuracy of the data.

[0037] In the analysis step, the server uses pre-trained machine learning models to perform pattern analysis and future predictions. For example, the server analyzes traffic flow data to predict congestion patterns for specific days of the week and weather conditions. Similarly, with regard to energy data, it analyzes changes in consumption patterns and proposes an optimal energy consumption profile.

[0038] The analysis results are transcribed into text using natural language generation technology and provided to government officials and citizens. The server sends the generated reports via email or uploads them to an online portal accessible to users. This process ensures that complex data analysis results are presented in an easily understandable format.

[0039] Furthermore, the server collects user feedback and continuously updates the machine learning model to improve the accuracy and adaptability of the analysis. Specifically, the server aggregates user feedback information and incorporates it into the model's training data, thereby improving the accuracy of future predictions.

[0040] In this way, the present invention can provide effective and sustainable solutions to complex urban challenges through a data-driven approach.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects data in real time from sources such as traffic sensors and energy meters. This involves sending API requests to retrieve information from sensors via data streams and storing the data on the server.

[0044] Step 2:

[0045] The server converts the collected data into a unified format. By integrating data with different formats and structures into a common data model, it prepares the data for analysis. Specifically, it processes CSV files and JSON data and integrates them into a database.

[0046] Step 3:

[0047] The server performs data cleansing, noise reduction, and outlier detection. This eliminates inaccurate data that could affect the analysis and improves data quality. Statistical methods are used to detect outliers.

[0048] Step 4:

[0049] The server applies machine learning models to perform data analysis and prediction. For example, it analyzes traffic flow and energy consumption patterns to detect trends and anomalies. The models applied are executed based on pre-selected algorithms.

[0050] Step 5:

[0051] The server generates reports based on analysis results using natural language generation technology. Based on the insights gained, it creates easy-to-understand text and charts for government officials and citizens. This generated content is then formatted for clarity.

[0052] Step 6:

[0053] The server distributes the generated reports to terminals, making them accessible to users. Information is provided to users through email notifications and report uploads to online portals. This facilitates the sharing of relevant information.

[0054] Step 7:

[0055] Users provide feedback based on information delivered by the server. They submit opinions on the system's ease of use and the appropriateness of the analysis results through online forms or other means.

[0056] Step 8:

[0057] The server updates and retrains the machine learning model based on user feedback. The feedback information is incorporated into the training dataset to improve the model's accuracy and adaptability. This process aims to enhance the model's performance.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] It is difficult to effectively combine multiple statistical data obtained from unintegrated sources, analyze them in real time, and improve the accuracy of decision-making and future predictions. Furthermore, providing analysis results in an intuitively understandable format and quickly utilizing user feedback are also challenges.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for collecting statistical information from different sources, means for converting the collected statistical information into a unified format, and means for asynchronous information removal and processing of exceptional values, and means for performing rule analysis and prediction using an artificial intelligence model. This enables highly integrated data analysis and flexible information provision.

[0063] "Different sources of information" refers to multiple independent data generation platforms, such as transportation, energy, environment, and population data.

[0064] "Statistical information" refers to numerical data that serves as the basis for analyzing various types of data related to a city and extracting meaningful information.

[0065] A "unified format" refers to a standardized data structure used to ensure consistency within a system when data is recorded in different formats.

[0066] "Asynchronous desynchronization" refers to the process of removing inconsistent data and noise that occur during the data collection process, thereby improving data reliability.

[0067] "Exceptional values" refer to data points in statistical information that deviate significantly from normal values, and properly handling these contributes to improving the accuracy of data analysis.

[0068] An "artificial intelligence model" refers to a computational model built on machine learning algorithms that uses data to perform rule analysis and future predictions with high accuracy.

[0069] "String generation technology" refers to the technique of converting the results of data analysis into text in natural language, and is used to make the results easier to understand.

[0070] A "report" refers to a document or digital document containing information that summarizes the results obtained from an analysis.

[0071] "Users" refers to citizens and government officials who use this system to review analysis results and make decisions or provide feedback.

[0072] "Evaluation" refers to information that reflects users' opinions and intentions regarding analysis results and system operation, and is used to improve the system.

[0073] The system of this invention has a data processing architecture primarily based on a server. The server collects and integrates diverse data such as traffic, energy, environmental, and population information. Specifically, the server uses hardware that acquires data in real time from traffic sensors, energy meters, environmental monitoring devices, etc.

[0074] The server uses data format conversion software to convert the received data into a unified format. This conversion process prepares data in CSV or JSON format into a common data model suitable for analysis. The converted data is then processed by a data cleansing algorithm through asynchronous information removal and exception handling to improve data accuracy.

[0075] Next, the server performs analysis using an artificial intelligence model. The trained machine learning model enables pattern analysis and future predictions based on the collected statistical information. The server converts the analysis results into natural language using string generation technology and generates a report. This report is provided to users and government officials via email or a web portal.

[0076] For example, a city's traffic management department could use this system to predict congestion at a specific intersection on Monday mornings and provide citizens with countermeasures. The energy sector could also use it to plan for minimizing peak power consumption.

[0077] For example, by inputting instructions such as, "Predict the traffic congestion pattern in urban area A for the next week based on current statistical information, and list the possible problems that may occur," into the generating AI model, it is possible to obtain more specific analysis results.

[0078] The entire system leverages integrated data from servers to support decision-making in an efficient and sustainable way to solve urban challenges.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server collects data from traffic sensors, energy meters, and environmental monitoring devices. Its inputs include data in various formats obtained in real time. This data is periodically retrieved via standard network protocols. The output is a collection of the collected raw data.

[0082] Step 2:

[0083] The server converts the collected raw data into a unified format. Inputs include data with different structures, such as CSV and JSON. The server performs data format conversion processing, integrating all data into a common data model. The output is a unified dataset prepared in a parseable format.

[0084] Step 3:

[0085] The server cleanses the unified dataset. The processed unified data is used as input. The server performs denoising algorithms and exception filtering to improve data quality. The output is a clean dataset with guaranteed accuracy.

[0086] Step 4:

[0087] The server performs data analysis using an artificial intelligence model with a clean dataset. The input is high-quality data that has been preprocessed. The server performs pattern analysis and future predictions and obtains the results. The output is the analyzed results, including predicted data and the discovery of specific patterns.

[0088] Step 5:

[0089] The server converts the analysis results into text using string generation technology. The input is the raw data obtained as the output of the analysis. This is converted into natural language and formatted into a report. The output is an easily understandable document that can be presented to the user.

[0090] Step 6:

[0091] The server provides the generated report to the user. The input is the generated, written report. The server sends this via email or uploads it to an online portal. The output is the report delivered in a format that can be viewed by the user.

[0092] Step 7:

[0093] Users provide feedback on the content of the provided report. The input consists of the user's opinions and evaluations based on the analysis results. The user's evaluation information is sent to the server and used in the next step. The output is the evaluation data as feedback.

[0094] Step 8:

[0095] The server analyzes user feedback and updates its artificial intelligence model. The input is the feedback data provided by the user. The server uses this data to retrain the model and improve its analysis accuracy. The output is the improved artificial intelligence model.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] Effectively managing diverse information related to urban transportation, energy, and the environment, and using this information to make rapid and accurate predictions and decisions, is a crucial challenge in improving urban life. However, because this information is diverse and in different formats, it is difficult to analyze it uniformly and in real time. Furthermore, there is a lack of means to communicate the analysis results to users in an easily understandable way, which hinders the full utilization of the results in decision-making.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes means for aggregating city-related data acquired from different sources; means for converting the collected information into a standard format and performing noise reduction and anomaly correction to improve data quality; means for performing pattern analysis and prediction using machine learning algorithms with the preprocessed data; means for texting the results using natural language construction and providing them as a report document; means for collecting user feedback on the report content and updating the machine learning model; and means for providing an information technology infrastructure for displaying the analysis results to users in real time. This makes it possible to comprehensively manage diverse information in a city and support prediction and decision-making.

[0101] "Information sources" refer to sources that supply diverse data about a city, including devices such as traffic sensors, energy meters, and environmental monitoring equipment.

[0102] A "standard format" is a consistent data format used to unify and analyze data from different formats.

[0103] "Noise reduction" is the process of removing unnecessary elements and errors from data in order to obtain accurate results during data analysis.

[0104] "Outlier correction" is a process that improves data quality by detecting outliers in the data and replacing them with appropriate values.

[0105] A "machine learning algorithm" is a computational method used to identify patterns and make predictions using large amounts of data. It is widely used as part of artificial intelligence.

[0106] "Pattern analysis" is a procedure that identifies regularities and trends within data and uses them to make various predictions.

[0107] "Natural language construction" is a technology that generates the results of analyzed data into natural language text that is easy for humans to understand.

[0108] An "information technology infrastructure" is a collection of computer systems, networks, and software used for processing, managing, and transmitting information.

[0109] This invention aims to provide an integrated system that streamlines the management of diverse data in cities and supports prediction and decision-making based on that data. The embodiments thereof will be described in detail below.

[0110] First, the server collects data in real time from various sources within the city. For example, it utilizes data obtained from traffic sensors, energy meters, and environmental monitoring equipment. Since this data exists in various formats, the server converts it to a standard format. This process uses data processing scripts built with the Python language and the pandas library. Furthermore, data denoising and outlier correction are performed to improve data quality.

[0111] Next, the server performs pattern analysis and prediction using a model that implements machine learning algorithms. This analysis utilizes machine learning libraries such as TENSORFLOW® and scikit-learn. Once the prediction is complete, the results are converted into text using natural language constructor technology and provided in a format that is easy for users to understand. A GPT-based generative AI model is used for natural language generation.

[0112] The analyzed information is then displayed in real time on the user's smartphone or tablet device via an information technology infrastructure. The front-end is developed using React Native, allowing end users to view real-time data about the city through the application.

[0113] A concrete example is when a user opens the app on a weekend afternoon to check the day's urban traffic conditions and energy consumption forecast. Based on this information, the user can optimize their spending habits and travel plans.

[0114] As an example of a prompt, you can send a request to the AI ​​to "analyze the traffic situation in Tokyo at 8:00 AM on October 15th and the forecast for the next three hours, and create a report in natural language." This prompt will then be used as an instruction to the system.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server collects urban-related data in real time from traffic sensors, energy meters, environmental monitoring equipment, and other sources. Inputs are raw data transmitted from these devices, including various formats. Outputs are unprocessed data sent directly to the server. In this step, an API for data collection operates, periodically querying and retrieving data.

[0118] Step 2:

[0119] The server converts the collected data into a standard format. Here, the pandas library is used to organize CSV and JSON data into a unified format. The input is the data in different formats collected in step 1, and the output is a DataFrame in a unified format. In this step, a format conversion script is generated and performs the mapping process to unify the data.

[0120] Step 3:

[0121] The server performs data noise reduction and outlier correction. It detects outliers and corrects them using the mean and median. The input is a transformed DataFrame, and the output is a clean dataset with improved quality. This operation involves calculations to remove outliers and noise using statistical analysis techniques.

[0122] Step 4:

[0123] The server performs pattern analysis and prediction using a machine learning model based on clean data. It uses TensorFlow, etc., to generate specific patterns and future predictions. The input is the data prepared in step 3, and the output is a dataset of prediction results. The machine learning algorithm operates here, and data predictions are made based on the model.

[0124] Step 5:

[0125] The server converts the analysis results into text using natural language generation technology. A generative AI model is used to transform the prediction results into easily understandable text. The input is the prediction data obtained in step 4, and the output is a report written in natural language. The natural language processing module is responsible for text generation here.

[0126] Step 6:

[0127] The server provides the generated reports to users via an online portal or email. The terminal receives notifications from the server and displays the analysis results to the user. Input is a written report, and output is a report provided to the user as information. The results are displayed on the user interface, allowing for visual confirmation of the information.

[0128] Step 7:

[0129] The user provides feedback on the analysis results, and the server uses this feedback to retrain the machine learning model. The input is the user's feedback, and the output is data for improving the model. In this step, the feedback information is added to the dataset, and the model is retrained to improve its accuracy.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention is a system that comprehensively aggregates and analyzes various data in urban areas and uses the results to optimize the lives of citizens. This system consists of a server-centered data processing and user interface configuration, and its form is described in detail below.

[0132] The server collects data such as traffic, energy, environment, and population information in real time via sensors and external databases. Because this data often exists in diverse formats, the server converts it into a unified, analyzable format. It then performs noise reduction and outlier processing to generate an accurate dataset.

[0133] After data preprocessing is complete, the server uses machine learning algorithms to extract meaningful patterns from the data and predict future situations. At this stage, the prediction results are translated into text using natural language generation technology, generating an easy-to-understand report.

[0134] A distinctive feature of this invention is the integration of an emotion engine. The server collects feedback data from users and analyzes the emotional information contained in the feedback through the emotion engine. For example, it can understand user satisfaction and dissatisfaction from opinions and impressions submitted through the user interface on the terminal.

[0135] Using this sentiment analysis information, the server provides users with further personalized analysis results and suggestions. For example, if the sentiment engine indicates that the user is dissatisfied, the server may add more detailed explanations and alternatives to the report. The sentiment data thus collected is used as feedback when the server retrains its machine learning models, improving the overall adaptability and accuracy of the system.

[0136] In this way, the present invention, by combining a data-driven approach with emotion recognition technology, can provide more precise and efficient solutions to urban challenges and meet the needs of citizens.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server connects to data sources such as traffic sensors, energy meters, and environmental sensors via APIs and begins collecting data in real time. This includes opening data streams, receiving new data, and saving it to a database.

[0140] Step 2:

[0141] The server receives the collected data and converts each data format into a unified, parseable format. It integrates JSON and XML data into a common data model and performs data mapping to ensure consistency.

[0142] Step 3:

[0143] The server denoises the integrated data and filters outliers. This process uses statistical methods to detect and remove data points that deviate significantly from the standard.

[0144] Step 4:

[0145] The server inputs clean data into a machine learning model to perform pattern analysis and predict future situations. Here, past trends are learned, and the predictive algorithm determines the next steps.

[0146] Step 5:

[0147] The server uses natural language generation technology to translate the analysis results into text and format them as a report. Specifically, it creates a text report using concise and clear language, and adds charts and graphs where graphical visual elements are needed.

[0148] Step 6:

[0149] The server delivers the generated report to the terminal and provides the user with access rights. The report is delivered so that users can view it via email, a dashboard, or a mobile app.

[0150] Step 7:

[0151] Users review reports and provide feedback through their devices. This feedback is submitted via online forms or direct messages and includes comments on the user experience and specific suggestions.

[0152] Step 8:

[0153] The server collects user feedback and analyzes the emotional data using an emotion engine. For example, it uses text analysis techniques to extract user emotions and tendencies from the linguistic features contained in the feedback.

[0154] Step 9:

[0155] Based on the analysis results from the emotion engine, the server adjusts the presentation method of the analysis results and the content of the next suggestions as needed. Furthermore, the feedback data is used to improve and retrain the machine learning model, enhancing the overall accuracy and responsiveness of the system.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] In urban environments, there is a need for effective collection and analysis of data related to transportation, energy, environment, and population. However, because information from different data sources is in diverse formats, it is difficult to integrate, process, and quickly analyze it to aid in decision-making. Furthermore, there is a need to effectively utilize user feedback and address individual needs.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes means for collecting traffic, energy, environmental, and resident information from different sources; means for converting the collected information into a unified format, removing noise, and processing exceptional values; and means for performing feature analysis and prediction using machine learning algorithms. This enables rapid analysis of integrated data and the provision of personalized information to users.

[0161] A "source of information" is the starting point or source from which data is collected.

[0162] "Transportation" refers to information related to means of travel and the flow of such travel.

[0163] "Energy" refers to information regarding the consumption and supply of electricity, gas, and other forms of energy.

[0164] "Environment" refers to information related to the natural and artificial environment, such as temperature, precipitation, and the concentration of pollutants.

[0165] "Resident information" refers to information related to demographic trends, lifestyles, and socioeconomic conditions.

[0166] "Data format" refers to the structure and representation method of the collected data.

[0167] "Noise reduction" is a process that removes unnecessary information and errors from data, thereby extracting accurate information.

[0168] An "exceptional value" refers to an unusual value in a data set that deviates from the general pattern.

[0169] A "machine learning algorithm" is a technology that provides a mechanism for computers to learn on their own for data analysis.

[0170] "Feature analysis" refers to the process of finding meaningful patterns and relationships within data.

[0171] "Prediction" is the process of inferring future states or events based on past data.

[0172] "Natural language generation technology" is a technology that allows computers to generate text in a format that humans can understand.

[0173] A "document" refers to a document that contains information in text format.

[0174] "Emotional information" refers to data that reflects users' subjective satisfaction or dissatisfaction.

[0175] "Personalization" refers to providing information and services that meet the individual needs of each user.

[0176] "Users" refers to individuals, companies, or organizations that use the system.

[0177] This invention is a system that efficiently collects and processes diverse data in urban environments and optimizes citizens' lives based on the results. The system is mainly composed of a server and includes the following detailed embodiments.

[0178] The server collects traffic, energy, environmental, and resident information from multiple sources. This collection utilizes communication technologies to connect with various sensors and external databases. For example, traffic sensor data is sent to the server via an API.

[0179] The server converts the collected information into a standardized format. This is done using common data format integration software. For example, information obtained in JSON format is converted to CSV format to facilitate analysis.

[0180] The server performs noise reduction and outlier processing to ensure data quality. At this stage, Python data processing libraries are used to improve the reliability of the dataset.

[0181] The server performs feature analysis and prediction using machine learning algorithms. Here, we utilize open-source machine learning frameworks to build models that predict future situations. For example, one scenario is to predict the occurrence of traffic congestion at a specific location the following day based on traffic data.

[0182] Furthermore, the server uses natural language generation technology to formalize the analysis results and output them as documents. To do this, it utilizes generative AI models to create reports that are easy for humans to understand. For example, it might output traffic congestion predictions in the form of, "Traffic is expected to increase in the city center between 8:00 AM and 10:00 AM tomorrow."

[0183] The terminal collects opinions and feedback from users and transmits them to the server. Users provide feedback through the application, contributing to service improvement. At this stage, users can input their thoughts about the system in the form of, "Reducing the on-time of streetlights at night was good for the environment."

[0184] The server uses natural language processing techniques to analyze emotional information from the collected feedback. This information is then used by an emotion recognition engine to determine the user's satisfaction or dissatisfaction level.

[0185] Based on emotional information, the server provides personalized suggestions to the user. This presents information and alternatives tailored to the user's needs, and may generate more detailed documentation.

[0186] An example of a prompt for the generating AI model would be to input the text, "Based on real-time urban traffic data, predict traffic congestion for the following day and create a user-friendly report."

[0187] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0188] Step 1:

[0189] The server collects traffic, energy, environmental, and resident information in real time from sensors and external databases. The input is provided in various data formats. The server uses a data format integration tool to convert the collected data into a unified format, generating a unified dataset as output. Specifically, it converts JSON data obtained via APIs into CSV format.

[0190] Step 2:

[0191] The server performs noise reduction and processing of outliers on data in a unified format. The input is the dataset generated in step 1. Missing data is interpolated and outliers are filtered using Python data processing libraries. The output is a clean dataset with increased reliability. Specifically, the Pandas library is used to detect and remove anomalous traffic data.

[0192] Step 3:

[0193] The server uses machine learning algorithms to perform feature analysis and prediction based on preprocessed data. The input is a clean dataset. It utilizes open-source machine learning frameworks to predict future conditions and patterns. For example, it trains a model to predict peak traffic volume for the following day based on historical traffic data. The output is the predicted future patterns and events.

[0194] Step 4:

[0195] The server formats the prediction results into a report using natural language generation technology. The input is the prediction result from step 3. The generation AI model is given a prompt and automatically generates human-readable text. The output is an easy-to-understand report provided to the user. Specifically, it might generate a sentence like, "Traffic is expected to increase in the city center between 8:00 AM and 10:00 AM tomorrow."

[0196] Step 5:

[0197] The terminal collects opinions and feedback from users. The input is the feedback provided by the user. Information regarding user satisfaction and dissatisfaction is collected through the application. The output is a set of feedback data that the server uses for analysis. As a concrete example, the user inputs feedback into the terminal such as, "Reducing the on-time of streetlights at night was helpful."

[0198] Step 6:

[0199] The server analyzes the collected feedback using an emotion recognition engine and extracts emotional information. The input is the feedback data from step 5. Natural language processing technology is used to evaluate the user's emotional response. The output is emotional information such as positive or negative. Specifically, Google Cloud's Natural Language API is used to infer user satisfaction from the feedback.

[0200] Step 7:

[0201] The server provides personalized information and suggestions to the user based on emotional information. The input is the emotional analysis results obtained in step 6. Additional information and alternatives are prepared according to the user's emotions and provided as a report. The output is a detailed suggestion or report to the user. Specifically, if negative feedback is received, a more detailed explanation and alternatives are described in the report.

[0202] (Application Example 2)

[0203] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0204] In modern urban life, residents face a variety of challenges in their daily lives, including transportation, energy, and the environment. To solve these problems, it is necessary to efficiently analyze vast amounts of data collected in real time and provide appropriate information tailored to residents' needs. Furthermore, accurately understanding residents' emotions is essential for providing more personalized services. However, conventional technologies have not been able to adequately address these challenges.

[0205] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0206] In this invention, the server includes means for collecting information on means of transportation, power, environment, and population from different information sources; means for converting the collected information into a unified format and processing noise reduction and deviation values; and means for extracting emotional information from users' opinions using emotion analysis means and providing personalized analysis results based on that information. This enables efficient analysis of various challenges in urban life and the provision of services that take into account the emotions of residents.

[0207] "Different sources of information" refers to data sources that provide various types of information, including urban transportation, energy consumption, environmental measurement equipment, and demographic databases.

[0208] "Means of transportation" refers to methods or systems for moving individuals or goods from one point to another, and includes public transportation such as automobiles, buses, and trains.

[0209] "Power" refers to the form or method of providing energy, and includes energy sources such as electricity, gas, and kerosene.

[0210] "Environment" refers to the natural environment and all artificially constructed physical environments, including atmospheric conditions, water quality, and land use.

[0211] "Population information" refers to statistical data about people who live in or visit a specific area, and includes age, gender, occupation, and migration patterns.

[0212] "Means of collection" refers to the methods and devices used to obtain the necessary information, and includes sensors, data collection devices, and database query techniques.

[0213] "Converting to a unified format" refers to the process of standardizing data from different formats and preparing it in a form that can be analyzed.

[0214] "Denoising and handling of deviations" refers to the process of removing or correcting unnecessary or inaccurate data in order to improve the accuracy of the data.

[0215] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and knowledge from data and uses that knowledge to make predictions and classifications.

[0216] "Pattern analysis" refers to the process of finding regularities and trends within a dataset, and using the analysis results to predict future events and actions.

[0217] "Natural language generation technology" refers to technology that uses machines to generate human language and represent data in text format.

[0218] "Opinions" refer to the thoughts and feelings that users have about a system or service.

[0219] "Retraining" refers to the process by which a machine learning model learns again using new data, and is done to improve the model's accuracy and adaptability.

[0220] "Emotional analysis methods" refer to technologies and methods for analyzing emotions and sentiments from collected text data, etc.

[0221] This invention is a system that collects and analyzes diverse information in urban areas in real time to optimize the lives of residents. The following describes an embodiment of the system.

[0222] The server collects information on traffic, energy, environment, and population from diverse sources via sensors and databases. After collection, this information is converted to a unified format, and unnecessary noise is removed and outliers are processed. This creates an accurate dataset suitable for analysis.

[0223] The server performs pattern analysis and prediction using machine learning models based on pre-processed data. Machine learning frameworks such as TensorFlow are used for this analysis. The analysis results are formatted as a text report using natural language generation technology, making it easy for users to understand the results.

[0224] The device is equipped with a user interface that accepts user feedback. This feedback is sent to a server to extract the user's emotional information via an emotion analysis system and to provide more personalized services based on the emotion analysis results.

[0225] For example, if sentiment analysis detects numerous complaints about public transportation services in a particular area, the server reports this information to the city administrator and proposes immediate countermeasures. In this process, a generative AI model is used to optimize natural language generation technology, generating prompt messages that are based on residents' requests.

[0226] An example of a prompt message would be, "Enter text data regarding residents' complaints and output the sentiment score."

[0227] The above system makes it possible to respond quickly to various urban challenges and improve the lives of residents.

[0228] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0229] Step 1:

[0230] The server collects information on transportation, energy, environment, and population from diverse sources. It uses sensors and database APIs to retrieve data in real time. At this point, the input is raw data, and the output is data before conversion to a unified format.

[0231] Step 2:

[0232] The server converts the collected raw data into a unified format. This processing uses a data formatting standardization library to remove noise and handle outliers. This transformation generates an analyzable dataset. The input is raw data in various formats, and the output is formatted data in a unified format.

[0233] Step 3:

[0234] The server runs a machine learning model using preprocessed data. It analyzes patterns using TensorFlow and predicts future situations. This process involves calculations based on a large amount of data. The input is preprocessed data, and the output is predicted data as a result of the analysis.

[0235] Step 4:

[0236] The server utilizes a generative AI model to format predicted data as natural language. Using natural language generation technology, it creates a text-based report. This report is organized in a way that is easily understandable to the user. The input is the predicted data, and the output is the generated report.

[0237] Step 5:

[0238] The terminal collects feedback from residents through its user interface. Users input their opinions on daily public services, which are then sent to the server by the terminal. The input is the user's feedback, and the output is the transfer of that feedback to the server.

[0239] Step 6:

[0240] The server processes the collected feedback using sentiment analysis tools. It extracts sentiment information using natural language processing libraries such as NLTK and analyzes user satisfaction and dissatisfaction. This process yields a sentiment score. The input is user feedback, and the output is sentiment information.

[0241] Step 7:

[0242] The server uses the sentiment analysis results to retrain the machine learning model. New data is added to the training dataset to improve the model's adaptability. This retraining improves the system's accuracy. The input is the sentiment analysis results, and the output is the updated machine learning model.

[0243] Step 8:

[0244] The server generates personalized service recommendations based on the generated report and sentiment analysis results. The generated AI model is displayed in user-friendly natural language as prompts. Users receive specific improvement suggestions. The input is the updated model and sentiment analysis results, and the output is personalized service recommendations.

[0245] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0246] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0247] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0248] [Second Embodiment]

[0249] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0250] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0251] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0252] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0253] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0254] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0255] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0256] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0257] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0258] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0259] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0260] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0261] This invention aims to integrate and analyze diverse data in urban areas, such as traffic, energy, environmental, and population information, and to optimize administrative services and improve citizens' lives based on the results. This system has an architecture that primarily processes data centered on a server, and its embodiments are described below.

[0262] The server first collects data in real time from traffic sensors, energy meters, environmental monitoring devices, and other sources. Since this data is transmitted in various formats, the server converts it into a unified format and integrates it into an analyzable format. For example, the server converts traffic data in CSV format and environmental data in JSON format into a common data model.

[0263] Next, the server performs noise reduction and outlier filtering on the collected data to improve its quality. This ensures the accuracy of the data.

[0264] In the analysis step, the server uses pre-trained machine learning models to perform pattern analysis and future predictions. For example, the server analyzes traffic flow data to predict congestion patterns for specific days of the week and weather conditions. Similarly, with regard to energy data, it analyzes changes in consumption patterns and proposes an optimal energy consumption profile.

[0265] The analysis results are transcribed into text using natural language generation technology and provided to government officials and citizens. The server sends the generated reports via email or uploads them to an online portal accessible to users. This process ensures that complex data analysis results are presented in an easily understandable format.

[0266] Furthermore, the server collects user feedback and continuously updates the machine learning model to improve the accuracy and adaptability of the analysis. Specifically, the server aggregates user feedback information and incorporates it into the model's training data, thereby improving the accuracy of future predictions.

[0267] In this way, the present invention can provide effective and sustainable solutions to complex urban challenges through a data-driven approach.

[0268] The following describes the processing flow.

[0269] Step 1:

[0270] The server collects data in real time from sources such as traffic sensors and energy meters. This involves sending API requests to retrieve information from sensors via data streams and storing the data on the server.

[0271] Step 2:

[0272] The server converts the collected data into a unified format. By integrating data with different formats and structures into a common data model, it prepares the data for analysis. Specifically, it processes CSV files and JSON data and integrates them into a database.

[0273] Step 3:

[0274] The server performs data cleansing, noise reduction, and outlier detection. This eliminates inaccurate data that could affect the analysis and improves data quality. Statistical methods are used to detect outliers.

[0275] Step 4:

[0276] The server applies machine learning models to perform data analysis and prediction. For example, it analyzes traffic flow and energy consumption patterns to detect trends and anomalies. The models applied are executed based on pre-selected algorithms.

[0277] Step 5:

[0278] The server generates reports based on analysis results using natural language generation technology. Based on the insights gained, it creates easy-to-understand text and charts for government officials and citizens. This generated content is then formatted for clarity.

[0279] Step 6:

[0280] The server distributes the generated report to the terminal so that users can access it. Information is provided to users through email sending or report uploading to an online portal. This enables the sharing of relevant information.

[0281] Step 7:

[0282] Users provide feedback based on the information distributed by the server. Opinions on the usability of the system and the appropriateness of the analysis results are sent through an online form or the like.

[0283] Step 8:

[0284] The server updates the machine learning model based on the feedback from users and performs re-learning. To improve the accuracy and adaptability of the model, the feedback information is incorporated into the learning dataset. Through this process, the performance of the model is improved.

[0285] (Example 1)

[0286] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0287] Effectively combining a plurality of statistical information obtained from unintegrated information sources, analyzing it in real time, and improving the accuracy of decision-making and future prediction is difficult. Also, it is an issue to provide the analysis results in a form that is intuitively easy to understand and quickly utilize the feedback from users.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following respective means.

[0289] In this invention, the server includes means for collecting statistical information from different sources, means for converting the collected statistical information into a unified format, and means for asynchronous information removal and processing of exceptional values, and means for performing rule analysis and prediction using an artificial intelligence model. This enables highly integrated data analysis and flexible information provision.

[0290] "Different sources of information" refers to multiple independent data generation platforms, such as transportation, energy, environment, and population data.

[0291] "Statistical information" refers to numerical data that serves as the basis for analyzing various types of data related to a city and extracting meaningful information.

[0292] A "unified format" refers to a standardized data structure used to ensure consistency within a system when data is recorded in different formats.

[0293] "Asynchronous desynchronization" refers to the process of removing inconsistent data and noise that occur during the data collection process, thereby improving the reliability of the data.

[0294] "Exceptional values" refer to data points in statistical information that deviate significantly from normal values, and properly handling these contributes to improving the accuracy of data analysis.

[0295] An "artificial intelligence model" refers to a computational model built on machine learning algorithms that uses data to perform rule analysis and future predictions with high accuracy.

[0296] "String generation technology" refers to the technique of converting data analysis results into text in natural language, and is used to make the results easier to understand.

[0297] A "report" refers to a document or digital document containing information that summarizes the results obtained from an analysis.

[0298] "Users" refers to citizens and government officials who use this system to review analysis results and make decisions or provide feedback.

[0299] "Evaluation" refers to information that reflects users' opinions and intentions regarding analysis results and system operation, and is used to improve the system.

[0300] The system of this invention has a data processing architecture primarily based on a server. The server collects and integrates diverse data such as traffic, energy, environmental, and population information. Specifically, the server uses hardware that acquires data in real time from traffic sensors, energy meters, environmental monitoring devices, etc.

[0301] The server uses data format conversion software to convert the received data into a unified format. This conversion process prepares data in CSV or JSON format into a common data model suitable for analysis. The converted data is then processed by a data cleansing algorithm through asynchronous information removal and exception handling to improve data accuracy.

[0302] Next, the server performs analysis using an artificial intelligence model. The trained machine learning model enables pattern analysis and future predictions based on the collected statistical information. The server converts the analysis results into natural language using string generation technology and generates a report. This report is provided to users and government officials via email or a web portal.

[0303] For example, a city's traffic management department could use this system to predict congestion at a specific intersection on Monday mornings and provide citizens with countermeasures. The energy sector could also use it to plan for minimizing peak power consumption.

[0304] As an example of a prompt sentence, by inputting an instruction such as "Predict the traffic congestion pattern in the urban area A next week from the current statistical information and list up possible problems" into the generative AI model, it is possible to obtain more specific analysis results.

[0305] The entire system supports decision-making to solve urban problems in an efficient and sustainable way by leveraging data integrated by the server.

[0306] The flow of the specific process in Example 1 will be described using FIG. 11.

[0307] Step 1:

[0308] The server collects data from traffic sensors, energy meters, and environmental monitoring devices. The input includes data in various formats obtained in real time. These data are regularly acquired through normal network protocols. The output is a set of raw data collected.

[0309] Step 2:

[0310] The server converts the collected raw data into a unified format. The input includes data with different structures such as CSV format and JSON format. The server performs data format conversion processing and integrates all data into a common data model. The output is a unified dataset arranged in an analyzable format.

[0311] Step 3:

[0312] The server performs cleansing processing on the unified dataset. Processed unified data is used as the input. The server executes a noise removal algorithm and outlier filtering to improve the quality of the data. The output is a clean dataset with guaranteed accuracy.

[0313] Step 4:

[0314] The server performs data analysis using an artificial intelligence model with a clean dataset. The input is high-quality data that has been preprocessed. The server performs pattern analysis and future predictions and obtains the results. The output is the analyzed results, including predicted data and the discovery of specific patterns.

[0315] Step 5:

[0316] The server converts the analysis results into text using string generation technology. The input is the raw data obtained as the output of the analysis. This is converted into natural language and formatted into a report. The output is an easily understandable document that can be presented to the user.

[0317] Step 6:

[0318] The server provides the generated report to the user. The input is the generated, written report. The server sends this via email or uploads it to an online portal. The output is the report delivered in a format that can be viewed by the user.

[0319] Step 7:

[0320] Users provide feedback on the content of the provided report. The input consists of the user's opinions and evaluations based on the analysis results. The user's evaluation information is sent to the server and used in the next step. The output is the evaluation data as feedback.

[0321] Step 8:

[0322] The server analyzes user feedback and updates its artificial intelligence model. The input is the feedback data provided by the user. The server uses this data to retrain the model and improve its analysis accuracy. The output is the improved artificial intelligence model.

[0323] (Application Example 1)

[0324] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0325] Effectively managing diverse information related to urban transportation, energy, and the environment, and using this information to make rapid and accurate predictions and decisions, is a crucial challenge in improving urban life. However, because this information is diverse and in different formats, it is difficult to analyze it uniformly and in real time. Furthermore, there is a lack of means to communicate the analysis results to users in an easily understandable way, which hinders the full utilization of the results in decision-making.

[0326] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0327] In this invention, the server includes means for aggregating city-related data acquired from different sources; means for converting the collected information into a standard format and performing noise reduction and anomaly correction to improve data quality; means for performing pattern analysis and prediction using machine learning algorithms with the preprocessed data; means for texting the results using natural language construction and providing them as a report document; means for collecting user feedback on the report content and updating the machine learning model; and means for providing an information technology infrastructure for displaying the analysis results to users in real time. This makes it possible to comprehensively manage diverse information in a city and support prediction and decision-making.

[0328] "Information sources" refer to sources that supply diverse data about a city, including devices such as traffic sensors, energy meters, and environmental monitoring equipment.

[0329] A "standard format" is a consistent data format used to unify and analyze data from different formats.

[0330] "Noise reduction" is the process of removing unnecessary elements and errors from data in order to obtain accurate results during data analysis.

[0331] "Outlier correction" is a process that improves data quality by detecting outliers in the data and replacing them with appropriate values.

[0332] A "machine learning algorithm" is a computational method used to identify patterns and make predictions using large amounts of data. It is widely used as part of artificial intelligence.

[0333] "Pattern analysis" is a procedure that identifies regularities and trends within data and uses them to make various predictions.

[0334] "Natural language construction" is a technology that generates the results of analyzed data into natural language text that is easy for humans to understand.

[0335] An "information technology infrastructure" is a collection of computer systems, networks, and software used for processing, managing, and transmitting information.

[0336] This invention aims to provide an integrated system that streamlines the management of diverse data in cities and supports prediction and decision-making based on that data. The embodiments thereof will be described in detail below.

[0337] First, the server collects data in real time from various sources within the city. For example, it utilizes data obtained from traffic sensors, energy meters, and environmental monitoring equipment. Since this data exists in various formats, the server converts it to a standard format. This process uses data processing scripts built with the Python language and the pandas library. Furthermore, data denoising and outlier correction are performed to improve data quality.

[0338] Next, the server performs pattern analysis and prediction using a model that implements machine learning algorithms. This analysis utilizes machine learning libraries such as TensorFlow and scikit-learn. Once the prediction is complete, the results are converted into text using natural language constructor technology and provided in a format that is easy for users to understand. A GPT-based generative AI model is used for natural language generation.

[0339] The analyzed information is then displayed in real time on the user's smartphone or tablet device via an information technology infrastructure. The front-end is developed using React Native, allowing end users to view real-time data about the city through the application.

[0340] A concrete example is when a user opens the app on a weekend afternoon to check the day's urban traffic conditions and energy consumption forecast. Based on this information, the user can optimize their spending habits and travel plans.

[0341] As an example of a prompt, you can send a request to the AI ​​to "analyze the traffic situation in Tokyo at 8:00 AM on October 15th and the forecast for the next three hours, and create a report in natural language." This prompt will then be used as an instruction to the system.

[0342] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0343] Step 1:

[0344] The server collects urban-related data in real time from traffic sensors, energy meters, environmental monitoring equipment, and other sources. Inputs are raw data transmitted from these devices, including various formats. Outputs are unprocessed data sent directly to the server. In this step, an API for data collection operates, periodically querying and retrieving data.

[0345] Step 2:

[0346] The server converts the collected data into a standard format. Here, the pandas library is used to organize CSV and JSON data into a unified format. The input is the data in different formats collected in step 1, and the output is a DataFrame in a unified format. In this step, a format conversion script is generated and performs the mapping process to unify the data.

[0347] Step 3:

[0348] The server performs data noise reduction and outlier correction. It detects outliers and corrects them using the mean and median. The input is a transformed DataFrame, and the output is a clean dataset with improved quality. This operation involves calculations to remove outliers and noise using statistical analysis techniques.

[0349] Step 4:

[0350] The server performs pattern analysis and prediction using a machine learning model based on clean data. It uses TensorFlow, etc., to generate specific patterns and future predictions. The input is the data prepared in step 3, and the output is a dataset of prediction results. The machine learning algorithm operates here, and data predictions are made based on the model.

[0351] Step 5:

[0352] The server converts the analysis results into text using natural language generation technology. A generative AI model is used to transform the prediction results into easily understandable text. The input is the prediction data obtained in step 4, and the output is a report written in natural language. The natural language processing module is responsible for text generation here.

[0353] Step 6:

[0354] The server provides the generated reports to users via an online portal or email. The terminal receives notifications from the server and displays the analysis results to the user. Input is a written report, and output is a report provided to the user as information. The results are displayed on the user interface, allowing for visual confirmation of the information.

[0355] Step 7:

[0356] The user provides feedback on the analysis results, and the server uses this feedback to retrain the machine learning model. The input is the user's feedback, and the output is data for improving the model. In this step, the feedback information is added to the dataset, and the model is retrained to improve its accuracy.

[0357] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0358] This invention is a system that comprehensively aggregates and analyzes various data in urban areas and uses the results to optimize the lives of citizens. This system consists of a server-centered data processing and user interface configuration, and its form is described in detail below.

[0359] The server collects data such as traffic, energy, environment, and population information in real time via sensors and external databases. Because this data often exists in diverse formats, the server converts it into a unified, analyzable format. It then performs noise reduction and outlier processing to generate an accurate dataset.

[0360] After data preprocessing is complete, the server uses machine learning algorithms to extract meaningful patterns from the data and predict future situations. At this stage, the prediction results are translated into text using natural language generation technology, generating an easy-to-understand report.

[0361] A distinctive feature of this invention is the integration of an emotion engine. The server collects feedback data from users and analyzes the emotional information contained in the feedback through the emotion engine. For example, it can understand user satisfaction and dissatisfaction from opinions and impressions submitted through the user interface on the terminal.

[0362] Using this sentiment analysis information, the server provides users with further personalized analysis results and suggestions. For example, if the sentiment engine indicates that the user is dissatisfied, the server may add more detailed explanations and alternatives to the report. The sentiment data thus collected is used as feedback when the server retrains its machine learning models, improving the overall adaptability and accuracy of the system.

[0363] In this way, the present invention, by combining a data-driven approach with emotion recognition technology, can provide more precise and efficient solutions to urban challenges and meet the needs of citizens.

[0364] The following describes the processing flow.

[0365] Step 1:

[0366] The server connects to data sources such as traffic sensors, energy meters, and environmental sensors via APIs and begins real-time data collection. This includes opening data streams, receiving new data, and saving it to the database.

[0367] Step 2:

[0368] The server receives the collected data and converts each data format into a unified, parseable format. It integrates JSON and XML data into a common data model and performs data mapping to ensure consistency.

[0369] Step 3:

[0370] The server denoises the integrated data and filters outliers. This process uses statistical methods to detect and remove data points that deviate significantly from the standard.

[0371] Step 4:

[0372] The server inputs clean data into a machine learning model to perform pattern analysis and predict future situations. Here, past trends are learned, and the predictive algorithm determines the next steps.

[0373] Step 5:

[0374] The server uses natural language generation technology to translate the analysis results into text and format them as a report. Specifically, it creates a text report using concise and clear language, and adds charts and graphs where graphical visual elements are needed.

[0375] Step 6:

[0376] The server delivers the generated report to the terminal and provides the user with access rights. The report is delivered via email, a dashboard, or a mobile app, allowing users to view it.

[0377] Step 7:

[0378] Users review reports and provide feedback through their devices. This feedback is submitted via online forms or direct messages and includes comments on the user experience and specific suggestions.

[0379] Step 8:

[0380] The server collects user feedback and analyzes the emotional data using an emotion engine. For example, it uses text analysis techniques to extract user emotions and tendencies from the linguistic features contained in the feedback.

[0381] Step 9:

[0382] Based on the analysis results from the emotion engine, the server adjusts the presentation method of the analysis results and the content of the next suggestions as needed. Furthermore, the feedback data is used to improve and retrain the machine learning model, enhancing the overall accuracy and responsiveness of the system.

[0383] (Example 2)

[0384] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0385] In urban environments, there is a need for effective collection and analysis of data related to transportation, energy, environment, and population. However, because information from different data sources is in diverse formats, it is difficult to integrate, process, and quickly analyze it to aid in decision-making. Furthermore, there is a need to effectively utilize user feedback and address individual needs.

[0386] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0387] In this invention, the server includes means for collecting traffic, energy, environmental, and resident information from different sources; means for converting the collected information into a unified format, removing noise, and processing exceptional values; and means for performing feature analysis and prediction using machine learning algorithms. This enables rapid analysis of integrated data and the provision of personalized information to users.

[0388] A "source of information" is the starting point or source from which data is collected.

[0389] "Transportation" refers to information related to means of travel and the flow of such travel.

[0390] "Energy" refers to information regarding the consumption and supply of electricity, gas, and other forms of energy.

[0391] "Environment" refers to information related to the natural and artificial environment, such as temperature, precipitation, and the concentration of pollutants.

[0392] "Resident information" refers to information related to demographic trends, lifestyles, and socioeconomic conditions.

[0393] "Data format" refers to the structure and representation method of the collected data.

[0394] "Noise reduction" is a process that removes unnecessary information and errors from data, thereby extracting accurate information.

[0395] An "exceptional value" refers to an unusual value in a data set that deviates from the general pattern.

[0396] A "machine learning algorithm" is a technology that provides a mechanism for computers to learn on their own for data analysis.

[0397] "Feature analysis" refers to the process of finding meaningful patterns and relationships within data.

[0398] "Prediction" is the process of inferring future states or events based on past data.

[0399] "Natural language generation technology" is a technology that allows computers to generate text in a format that humans can understand.

[0400] A "document" refers to a document that contains information in text format.

[0401] "Emotional information" refers to data that reflects users' subjective satisfaction or dissatisfaction.

[0402] "Personalization" refers to providing information and services that meet the individual needs of each user.

[0403] "Users" refers to individuals, companies, or organizations that use the system.

[0404] This invention is a system that efficiently collects and processes diverse data in urban environments and optimizes citizens' lives based on the results. The system is mainly composed of a server and includes the following detailed embodiments.

[0405] The server collects traffic, energy, environmental, and resident information from multiple sources. This collection utilizes communication technologies to connect with various sensors and external databases. For example, traffic sensor data is sent to the server via an API.

[0406] The server converts the collected information into a standardized format. This is done using common data format integration software. For example, information obtained in JSON format is converted to CSV format to facilitate analysis.

[0407] The server performs noise reduction and outlier processing to ensure data quality. At this stage, Python data processing libraries are used to improve the reliability of the dataset.

[0408] The server performs feature analysis and prediction using machine learning algorithms. Here, we utilize open-source machine learning frameworks to build models that predict future situations. For example, one scenario is to predict the occurrence of traffic congestion at a specific location the following day based on traffic data.

[0409] Furthermore, the server uses natural language generation technology to formalize the analysis results and output them as documents. To do this, it utilizes generative AI models to create reports that are easy for humans to understand. For example, it might output traffic congestion predictions in the form of, "Traffic is expected to increase in the city center between 8:00 AM and 10:00 AM tomorrow."

[0410] The terminal collects opinions and feedback from users and transmits them to the server. Users provide feedback through the application, contributing to service improvement. At this stage, users can input their thoughts about the system in the form of, "Reducing the on-time of streetlights at night was good for the environment."

[0411] The server uses natural language processing techniques to analyze emotional information from the collected feedback. This information is then used by an emotion recognition engine to determine the user's satisfaction or dissatisfaction level.

[0412] Based on emotional information, the server provides personalized suggestions to the user. This presents information and alternatives tailored to the user's needs, and may generate more detailed documentation.

[0413] An example of a prompt for the generating AI model would be to input the text, "Based on real-time urban traffic data, predict traffic congestion for the following day and create a user-friendly report."

[0414] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0415] Step 1:

[0416] The server collects traffic, energy, environmental, and resident information in real time from sensors and external databases. The input is provided in various data formats. The server uses a data format integration tool to convert the collected data into a unified format, generating a unified dataset as output. Specifically, it converts JSON data obtained via APIs into CSV format.

[0417] Step 2:

[0418] The server performs noise reduction and processing of outliers on data in a unified format. The input is the dataset generated in step 1. Missing data is interpolated and outliers are filtered using Python data processing libraries. The output is a clean dataset with increased reliability. Specifically, the Pandas library is used to detect and remove anomalous traffic data.

[0419] Step 3:

[0420] The server uses machine learning algorithms to perform feature analysis and prediction based on preprocessed data. The input is a clean dataset. It utilizes open-source machine learning frameworks to predict future conditions and patterns. For example, it trains a model to predict peak traffic volume for the following day based on historical traffic data. The output is the predicted future patterns and events.

[0421] Step 4:

[0422] The server formats the prediction results into a report using natural language generation technology. The input is the prediction result from step 3. The generation AI model is given a prompt and automatically generates human-readable text. The output is an easy-to-understand report provided to the user. Specifically, it might generate a sentence like, "Traffic is expected to increase in the city center between 8:00 AM and 10:00 AM tomorrow."

[0423] Step 5:

[0424] The terminal collects opinions and feedback from users. The input is the feedback provided by the user. Information regarding user satisfaction and dissatisfaction is collected through the application. The output is a set of feedback data that the server uses for analysis. As a concrete example, the user inputs feedback into the terminal, such as "Reducing the on-time of streetlights at night was helpful."

[0425] Step 6:

[0426] The server analyzes the collected feedback using an emotion recognition engine and extracts emotional information. The input is the feedback data from step 5. Natural language processing techniques are used to evaluate the user's emotional response. The output is emotional information such as positive or negative. Specifically, Google Cloud's Natural Language API is used to infer user satisfaction from the feedback.

[0427] Step 7:

[0428] The server provides personalized information and suggestions to the user based on emotional information. The input is the emotional analysis results obtained in step 6. Additional information and alternatives are prepared according to the user's emotions and provided as a report. The output is a detailed suggestion or report to the user. Specifically, if negative feedback is received, a more detailed explanation and alternatives are described in the report.

[0429] (Application Example 2)

[0430] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0431] In modern urban life, residents face a variety of challenges in their daily lives, including transportation, energy, and the environment. To solve these problems, it is necessary to efficiently analyze vast amounts of data collected in real time and provide appropriate information tailored to residents' needs. Furthermore, accurately understanding residents' emotions is essential for providing more personalized services. However, conventional technologies have not been able to adequately address these challenges.

[0432] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0433] In this invention, the server includes means for collecting information on means of transportation, power, environment, and population from different information sources; means for converting the collected information into a unified format and processing noise reduction and deviation values; and means for extracting emotional information from users' opinions using emotion analysis means and providing personalized analysis results based on that information. This enables efficient analysis of various challenges in urban life and the provision of services that take into account the emotions of residents.

[0434] "Different sources of information" refers to data sources that provide various types of information, including urban transportation, energy consumption, environmental measurement equipment, and demographic databases.

[0435] "Means of transportation" refers to methods or systems for moving individuals or goods from one point to another, and includes public transportation such as automobiles, buses, and trains.

[0436] "Power" refers to the form or method of providing energy, and includes energy sources such as electricity, gas, and kerosene.

[0437] "Environment" refers to the natural environment and all artificially constructed physical environments, including atmospheric conditions, water quality, and land use.

[0438] "Population information" refers to statistical data about people who live in or visit a specific area, and includes age, gender, occupation, and migration patterns.

[0439] "Means of collection" refers to the methods and devices used to obtain the necessary information, and includes sensors, data collection devices, and database query techniques.

[0440] "Converting to a unified format" refers to the process of standardizing data from different formats and preparing it in a form that can be analyzed.

[0441] "Denoising and handling of deviations" refers to the process of removing or correcting unnecessary or inaccurate data in order to improve the accuracy of the data.

[0442] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and knowledge from data and uses that knowledge to make predictions and classifications.

[0443] "Pattern analysis" refers to the process of finding regularities and trends within a dataset, and using the analysis results to predict future events and actions.

[0444] "Natural language generation technology" refers to technology that uses machines to generate human language and represent data in text format.

[0445] "Opinions" refer to the thoughts and feelings that users have about a system or service.

[0446] "Retraining" refers to the process by which a machine learning model learns again using new data, and is done to improve the model's accuracy and adaptability.

[0447] "Emotional analysis methods" refer to technologies and methods for analyzing emotions and sentiments from collected text data, etc.

[0448] This invention is a system that collects and analyzes diverse information in urban areas in real time to optimize the lives of residents. The following describes an embodiment of the system.

[0449] The server collects information on traffic, energy, environment, and population from diverse sources via sensors and databases. After collection, this information is converted to a unified format, and unnecessary noise is removed and outliers are processed. This creates an accurate dataset suitable for analysis.

[0450] The server performs pattern analysis and prediction using machine learning models based on pre-processed data. Machine learning frameworks such as TensorFlow are used for this analysis. The analysis results are formatted as a text report using natural language generation technology, making it easy for users to understand the results.

[0451] The device is equipped with a user interface that accepts user feedback. This feedback is sent to a server to extract the user's emotional information via an emotion analysis system and to provide more personalized services based on the emotion analysis results.

[0452] For example, if sentiment analysis detects numerous complaints about public transportation services in a particular area, the server reports this information to the city administrator and proposes immediate countermeasures. In this process, a generative AI model is used to optimize natural language generation technology, generating prompt messages that are based on residents' requests.

[0453] An example of a prompt message would be, "Enter text data regarding residents' complaints and output the sentiment score."

[0454] The above system makes it possible to respond quickly to various urban challenges and improve the lives of residents.

[0455] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0456] Step 1:

[0457] The server collects information on transportation, energy, environment, and population from diverse sources. It uses sensors and database APIs to retrieve data in real time. At this point, the input is raw data, and the output is data before conversion to a unified format.

[0458] Step 2:

[0459] The server converts the collected raw data into a unified format. This processing uses a data formatting standardization library to remove noise and handle outliers. This transformation generates an analyzable dataset. The input is raw data in various formats, and the output is formatted data in a unified format.

[0460] Step 3:

[0461] The server runs a machine learning model using preprocessed data. It analyzes patterns using TensorFlow and predicts future situations. This process involves calculations based on a large amount of data. The input is preprocessed data, and the output is predicted data as a result of the analysis.

[0462] Step 4:

[0463] The server utilizes a generative AI model to format predicted data as natural language. Using natural language generation technology, it creates a text-based report. This report is organized in a way that is easily understandable to the user. The input is the predicted data, and the output is the generated report.

[0464] Step 5:

[0465] The terminal collects feedback from residents through its user interface. Users input their opinions on daily public services, which are then sent to the server by the terminal. The input is the user's feedback, and the output is the transfer of that feedback to the server.

[0466] Step 6:

[0467] The server processes the collected feedback using sentiment analysis tools. It extracts sentiment information using natural language processing libraries such as NLTK and analyzes user satisfaction and dissatisfaction. This process yields a sentiment score. The input is user feedback, and the output is sentiment information.

[0468] Step 7:

[0469] The server uses the sentiment analysis results to retrain the machine learning model. New data is added to the training dataset to improve the model's adaptability. This retraining improves the system's accuracy. The input is the sentiment analysis results, and the output is the updated machine learning model.

[0470] Step 8:

[0471] The server generates personalized service recommendations based on the generated report and sentiment analysis results. The generated AI model is displayed in user-friendly natural language as prompts. Users receive specific improvement suggestions. The input is the updated model and sentiment analysis results, and the output is personalized service recommendations.

[0472] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0473] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0474] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0475] [Third Embodiment]

[0476] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0477] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0478] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0479] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0480] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0481] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0482] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0483] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0484] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0485] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0486] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0487] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0488] This invention aims to integrate and analyze diverse data in urban areas, such as traffic, energy, environmental, and population information, and to optimize administrative services and improve citizens' lives based on the results. This system has an architecture that primarily processes data centered on a server, and its embodiments are described below.

[0489] The server first collects data in real time from traffic sensors, energy meters, environmental monitoring devices, and other sources. Since this data is transmitted in various formats, the server converts it into a unified format and integrates it into an analyzable format. For example, the server converts traffic data in CSV format and environmental data in JSON format into a common data model.

[0490] Next, the server performs noise reduction and outlier filtering on the collected data to improve its quality. This ensures the accuracy of the data.

[0491] In the analysis step, the server uses pre-trained machine learning models to perform pattern analysis and future predictions. For example, the server analyzes traffic flow data to predict congestion patterns for specific days of the week and weather conditions. Similarly, with regard to energy data, it analyzes changes in consumption patterns and proposes an optimal energy consumption profile.

[0492] The analysis results are transcribed into text using natural language generation technology and provided to government officials and citizens. The server sends the generated reports via email or uploads them to an online portal accessible to users. This process ensures that complex data analysis results are presented in an easily understandable format.

[0493] Furthermore, the server collects user feedback and continuously updates the machine learning model to improve the accuracy and adaptability of the analysis. Specifically, the server aggregates user feedback information and incorporates it into the model's training data, thereby improving the accuracy of future predictions.

[0494] In this way, the present invention can provide effective and sustainable solutions to complex urban challenges through a data-driven approach.

[0495] The following describes the processing flow.

[0496] Step 1:

[0497] The server collects data in real time from sources such as traffic sensors and energy meters. This involves sending API requests to retrieve information from sensors via data streams and storing the data on the server.

[0498] Step 2:

[0499] The server converts the collected data into a unified format. By integrating data with different formats and structures into a common data model, it prepares the data for analysis. Specifically, it processes CSV files and JSON data and integrates them into a database.

[0500] Step 3:

[0501] The server performs data cleansing, noise reduction, and outlier detection. This eliminates inaccurate data that could affect the analysis and improves data quality. Statistical methods are used to detect outliers.

[0502] Step 4:

[0503] The server applies machine learning models to perform data analysis and prediction. For example, it analyzes traffic flow and energy consumption patterns to detect trends and anomalies. The models applied are executed based on pre-selected algorithms.

[0504] Step 5:

[0505] The server generates reports based on analysis results using natural language generation technology. Based on the insights gained, it creates easy-to-understand text and charts for government officials and citizens. This generated content is then formatted for clarity.

[0506] Step 6:

[0507] The server distributes the generated reports to terminals, making them accessible to users. Information is provided to users through email notifications and report uploads to online portals. This facilitates the sharing of relevant information.

[0508] Step 7:

[0509] Users provide feedback based on information delivered by the server. They submit opinions on the system's ease of use and the appropriateness of the analysis results through online forms or other means.

[0510] Step 8:

[0511] The server updates and retrains the machine learning model based on user feedback. The feedback information is incorporated into the training dataset to improve the model's accuracy and adaptability. This process aims to enhance the model's performance.

[0512] (Example 1)

[0513] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0514] It is difficult to effectively combine multiple statistical data obtained from unintegrated sources, analyze them in real time, and improve the accuracy of decision-making and future predictions. Furthermore, providing analysis results in an intuitively understandable format and quickly utilizing user feedback are also challenges.

[0515] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0516] In this invention, the server includes means for collecting statistical information from different sources, means for converting the collected statistical information into a unified format, and means for asynchronous information removal and processing of exceptional values, and means for performing rule analysis and prediction using an artificial intelligence model. This enables highly integrated data analysis and flexible information provision.

[0517] "Different sources of information" refers to multiple independent data generation platforms, such as transportation, energy, environment, and population data.

[0518] "Statistical information" refers to numerical data that serves as the basis for analyzing various types of data related to a city and extracting meaningful information.

[0519] A "unified format" refers to a standardized data structure used to ensure consistency within a system when data is recorded in different formats.

[0520] "Asynchronous desynchronization" refers to the process of removing inconsistent data and noise that occur during the data collection process, thereby improving the reliability of the data.

[0521] "Exceptional values" refer to data points in statistical information that deviate significantly from normal values, and properly handling these contributes to improving the accuracy of data analysis.

[0522] An "artificial intelligence model" refers to a computational model built on machine learning algorithms that uses data to perform rule analysis and future predictions with high accuracy.

[0523] "String generation technology" refers to the technique of converting data analysis results into text in natural language, and is used to make the results easier to understand.

[0524] A "report" refers to a document or digital document containing information that summarizes the results obtained from an analysis.

[0525] "Users" refers to citizens and government officials who use this system to review analysis results and make decisions or provide feedback.

[0526] "Evaluation" refers to information that reflects users' opinions and intentions regarding analysis results and system operation, and is used to improve the system.

[0527] The system of this invention has a data processing architecture primarily based on a server. The server collects and integrates diverse data such as traffic, energy, environmental, and population information. Specifically, the server uses hardware that acquires data in real time from traffic sensors, energy meters, environmental monitoring devices, etc.

[0528] The server uses data format conversion software to convert the received data into a unified format. This conversion process prepares data in CSV or JSON format into a common data model suitable for analysis. The converted data is then processed by a data cleansing algorithm through asynchronous information removal and exception handling to improve data accuracy.

[0529] Next, the server performs analysis using an artificial intelligence model. The trained machine learning model enables pattern analysis and future predictions based on the collected statistical information. The server converts the analysis results into natural language using string generation technology and generates a report. This report is provided to users and government officials via email or a web portal.

[0530] For example, a city's traffic management department could use this system to predict congestion at a specific intersection on Monday mornings and provide citizens with countermeasures. The energy sector could also use it to plan for minimizing peak power consumption.

[0531] For example, by inputting instructions such as, "Predict the traffic congestion pattern in urban area A for the next week based on current statistical information, and list the possible problems that may occur," into the generating AI model, it is possible to obtain more specific analysis results.

[0532] The entire system leverages integrated data from servers to support decision-making in an efficient and sustainable way to solve urban challenges.

[0533] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0534] Step 1:

[0535] The server collects data from traffic sensors, energy meters, and environmental monitoring devices. Its inputs include data in various formats obtained in real time. This data is periodically retrieved via standard network protocols. The output is a collection of the collected raw data.

[0536] Step 2:

[0537] The server converts the collected raw data into a unified format. Inputs include data with different structures, such as CSV and JSON. The server performs data format conversion processing, integrating all data into a common data model. The output is a unified dataset prepared in a parseable format.

[0538] Step 3:

[0539] The server cleanses the unified dataset. The processed unified data is used as input. The server performs denoising algorithms and exception filtering to improve data quality. The output is a clean dataset with guaranteed accuracy.

[0540] Step 4:

[0541] The server performs data analysis using an artificial intelligence model with a clean dataset. The input is high-quality data that has been preprocessed. The server performs pattern analysis and future predictions and obtains the results. The output is the analyzed results, including predicted data and the discovery of specific patterns.

[0542] Step 5:

[0543] The server converts the analysis results into text using string generation technology. The input is the raw data obtained as the output of the analysis. This is converted into natural language and formatted into a report. The output is an easily understandable document that can be presented to the user.

[0544] Step 6:

[0545] The server provides the generated report to the user. The input is the generated, written report. The server sends this via email or uploads it to an online portal. The output is the report delivered in a format that can be viewed by the user.

[0546] Step 7:

[0547] Users provide feedback on the content of the provided report. The input includes the user's opinions and evaluations based on the analysis results. The user's evaluation information is sent to the server and used in the next step. The output is the evaluation data as feedback.

[0548] Step 8:

[0549] The server analyzes user feedback and updates its artificial intelligence model. The input is the feedback data provided by the user. The server uses this data to retrain the model and improve its analysis accuracy. The output is the improved artificial intelligence model.

[0550] (Application Example 1)

[0551] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0552] Effectively managing diverse information related to urban transportation, energy, and the environment, and using this information to make rapid and accurate predictions and decisions, is a crucial challenge in improving urban life. However, because this information is diverse and in different formats, it is difficult to analyze it uniformly and in real time. Furthermore, there is a lack of means to communicate the analysis results to users in an easily understandable way, which hinders the full utilization of the results in decision-making.

[0553] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0554] In this invention, the server includes means for aggregating city-related data acquired from different sources; means for converting the collected information into a standard format and performing noise reduction and anomaly correction to improve data quality; means for performing pattern analysis and prediction using machine learning algorithms with the preprocessed data; means for texting the results using natural language construction and providing them as a report document; means for collecting user feedback on the report content and updating the machine learning model; and means for providing an information technology infrastructure for displaying the analysis results to users in real time. This makes it possible to comprehensively manage diverse information in a city and support prediction and decision-making.

[0555] "Information sources" refer to sources that supply diverse data about a city, including devices such as traffic sensors, energy meters, and environmental monitoring equipment.

[0556] A "standard format" is a consistent data format used to unify and analyze data from different formats.

[0557] "Noise reduction" is the process of removing unnecessary elements and errors from data in order to obtain accurate results during data analysis.

[0558] "Outlier correction" is a process that improves data quality by detecting outliers in the data and replacing them with appropriate values.

[0559] A "machine learning algorithm" is a computational method used to identify patterns and make predictions using large amounts of data. It is widely used as part of artificial intelligence.

[0560] "Pattern analysis" is a procedure that identifies regularities and trends within data and uses them to make various predictions.

[0561] "Natural language construction" is a technology that generates the results of analyzed data into natural language text that is easy for humans to understand.

[0562] "Information technology infrastructure" refers to a collection of computer systems, networks, and software used for processing, managing, and transmitting information.

[0563] This invention aims to provide an integrated system that streamlines the management of diverse data in cities and supports prediction and decision-making based on that data. The embodiments thereof will be described in detail below.

[0564] First, the server collects data in real time from various sources within the city. For example, it utilizes data obtained from traffic sensors, energy meters, and environmental monitoring equipment. Since this data exists in various formats, the server converts it to a standard format. This process uses data processing scripts built with the Python language and the pandas library. Furthermore, data denoising and outlier correction are performed to improve data quality.

[0565] Next, the server performs pattern analysis and prediction using a model that implements machine learning algorithms. This analysis utilizes machine learning libraries such as TensorFlow and scikit-learn. Once the prediction is complete, the results are converted into text using natural language constructor technology and provided in a format that is easy for users to understand. A GPT-based generative AI model is used for natural language generation.

[0566] The analyzed information is then displayed in real time on the user's smartphone or tablet device via an information technology infrastructure. The front-end is developed using React Native, allowing end users to view real-time data about the city through the application.

[0567] A concrete example is when a user opens the app on a weekend afternoon to check the day's urban traffic conditions and energy consumption forecast. Based on this information, the user can optimize their spending habits and travel plans.

[0568] As an example of a prompt, you can send a request to the AI ​​to "analyze the traffic situation in Tokyo at 8:00 AM on October 15th and the forecast for the next three hours, and create a report in natural language." This prompt will then be used as an instruction to the system.

[0569] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0570] Step 1:

[0571] The server collects urban-related data in real time from traffic sensors, energy meters, environmental monitoring equipment, and other sources. Inputs are raw data transmitted from these devices, including various formats. Outputs are unprocessed data sent directly to the server. In this step, an API for data collection operates, periodically querying and retrieving data.

[0572] Step 2:

[0573] The server converts the collected data into a standard format. Here, the pandas library is used to organize CSV and JSON data into a unified format. The input is the data in different formats collected in step 1, and the output is a DataFrame in a unified format. In this step, a format conversion script is generated and performs the mapping process to unify the data.

[0574] Step 3:

[0575] The server performs data noise reduction and outlier correction. It detects outliers and corrects them using the mean and median. The input is a transformed DataFrame, and the output is a clean dataset with improved quality. This operation involves calculations to remove outliers and noise using statistical analysis techniques.

[0576] Step 4:

[0577] The server performs pattern analysis and prediction using a machine learning model based on clean data. It uses TensorFlow, etc., to generate specific patterns and future predictions. The input is the data prepared in step 3, and the output is a dataset of prediction results. The machine learning algorithm operates here, and data predictions are made based on the model.

[0578] Step 5:

[0579] The server converts the analysis results into text using natural language generation technology. A generative AI model is used to transform the prediction results into easily understandable text. The input is the prediction data obtained in step 4, and the output is a report written in natural language. The natural language processing module is responsible for text generation here.

[0580] Step 6:

[0581] The server provides the generated reports to users via an online portal or email. The terminal receives notifications from the server and displays the analysis results to the user. Input is a written report, and output is a report provided to the user as information. The results are displayed on the user interface, allowing for visual confirmation of the information.

[0582] Step 7:

[0583] The user provides feedback on the analysis results, and the server uses this feedback to retrain the machine learning model. The input is the user's feedback, and the output is data for improving the model. In this step, the feedback information is added to the dataset, and the model is retrained to improve its accuracy.

[0584] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0585] This invention is a system that comprehensively aggregates and analyzes various data in urban areas and uses the results to optimize the lives of citizens. This system consists of a server-centered data processing and user interface configuration, and its form is described in detail below.

[0586] The server collects data such as traffic, energy, environment, and population information in real time via sensors and external databases. Because this data often exists in diverse formats, the server converts it into a unified, analyzable format. It then performs noise reduction and outlier processing to generate an accurate dataset.

[0587] After data preprocessing is complete, the server uses machine learning algorithms to extract meaningful patterns from the data and predict future situations. At this stage, the prediction results are translated into text using natural language generation technology, generating an easy-to-understand report.

[0588] A distinctive feature of this invention is the integration of an emotion engine. The server collects feedback data from users and analyzes the emotional information contained in the feedback through the emotion engine. For example, it can understand user satisfaction and dissatisfaction from opinions and impressions submitted through the user interface on the terminal.

[0589] Using this sentiment analysis information, the server provides users with further personalized analysis results and suggestions. For example, if the sentiment engine indicates that the user is dissatisfied, the server may add more detailed explanations and alternatives to the report. The sentiment data thus collected is used as feedback when the server retrains its machine learning models, improving the overall adaptability and accuracy of the system.

[0590] In this way, the present invention, by combining a data-driven approach with emotion recognition technology, can provide more precise and efficient solutions to urban challenges and meet the needs of citizens.

[0591] The following describes the processing flow.

[0592] Step 1:

[0593] The server connects to data sources such as traffic sensors, energy meters, and environmental sensors via APIs and begins real-time data collection. This includes opening data streams, receiving new data, and saving it to the database.

[0594] Step 2:

[0595] The server receives the collected data and converts each data format into a unified, parseable format. It integrates JSON and XML data into a common data model and performs data mapping to ensure consistency.

[0596] Step 3:

[0597] The server denoises the integrated data and filters outliers. This process uses statistical methods to detect and remove data points that deviate significantly from the standard.

[0598] Step 4:

[0599] The server inputs clean data into a machine learning model to perform pattern analysis and predict future situations. Here, past trends are learned, and the predictive algorithm determines the next steps.

[0600] Step 5:

[0601] The server uses natural language generation technology to translate the analysis results into text and format them as a report. Specifically, it creates a text report using concise and clear language, and adds charts and graphs where graphical visual elements are needed.

[0602] Step 6:

[0603] The server delivers the generated report to the terminal and provides the user with access rights. The report is delivered so that users can view it via email, a dashboard, or a mobile app.

[0604] Step 7:

[0605] Users review reports and provide feedback through their devices. This feedback is submitted via online forms or direct messages and includes comments on the user experience and specific suggestions.

[0606] Step 8:

[0607] The server collects user feedback and analyzes the emotional data using an emotion engine. For example, it uses text analysis techniques to extract user emotions and tendencies from the linguistic features contained in the feedback.

[0608] Step 9:

[0609] Based on the analysis results from the emotion engine, the server adjusts the presentation method of the analysis results and the content of the next suggestions as needed. Furthermore, the feedback data is used to improve and retrain the machine learning model, enhancing the overall accuracy and responsiveness of the system.

[0610] (Example 2)

[0611] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0612] In urban environments, there is a need for effective collection and analysis of data related to transportation, energy, environment, and population. However, because information from different data sources is in diverse formats, it is difficult to integrate, process, and quickly analyze it to aid in decision-making. Furthermore, there is a need to effectively utilize user feedback and address individual needs.

[0613] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0614] In this invention, the server includes means for collecting traffic, energy, environmental, and resident information from different sources; means for converting the collected information into a unified format, removing noise, and processing exceptional values; and means for performing feature analysis and prediction using machine learning algorithms. This enables rapid analysis of integrated data and the provision of personalized information to users.

[0615] A "source of information" is the starting point or source from which data is collected.

[0616] "Transportation" refers to information related to means of travel and the flow of such travel.

[0617] "Energy" refers to information regarding the consumption and supply of electricity, gas, and other forms of energy.

[0618] "Environment" refers to information related to the natural and artificial environment, such as temperature, precipitation, and the concentration of pollutants.

[0619] "Resident information" refers to information related to demographic trends, lifestyles, and socioeconomic conditions.

[0620] "Data format" refers to the structure and representation method of the collected data.

[0621] "Noise reduction" is a process that removes unnecessary information and errors from data, thereby extracting accurate information.

[0622] An "exceptional value" refers to an unusual value in a data set that deviates from the general pattern.

[0623] A "machine learning algorithm" is a technology that provides a mechanism for computers to learn on their own for data analysis.

[0624] "Feature analysis" refers to the process of finding meaningful patterns and relationships within data.

[0625] "Prediction" is the process of inferring future states or events based on past data.

[0626] "Natural language generation technology" is a technology that allows computers to generate text in a format that humans can understand.

[0627] A "document" refers to a document that contains information in text format.

[0628] "Emotional information" refers to data that reflects users' subjective satisfaction or dissatisfaction.

[0629] "Personalization" refers to providing information and services that meet the individual needs of each user.

[0630] "Users" refers to individuals, companies, or organizations that use the system.

[0631] This invention is a system that efficiently collects and processes diverse data in urban environments and optimizes citizens' lives based on the results. The system is mainly composed of a server and includes the following detailed embodiments.

[0632] The server collects traffic, energy, environmental, and resident information from multiple sources. This collection utilizes communication technologies to connect with various sensors and external databases. For example, traffic sensor data is sent to the server via an API.

[0633] The server converts the collected information into a standardized format. This is done using common data format integration software. For example, information obtained in JSON format is converted to CSV format to facilitate analysis.

[0634] The server performs noise reduction and outlier processing to ensure data quality. At this stage, Python data processing libraries are used to improve the reliability of the dataset.

[0635] The server performs feature analysis and prediction using machine learning algorithms. Here, we utilize open-source machine learning frameworks to build models that predict future situations. For example, one scenario is to predict the occurrence of traffic congestion at a specific location the following day based on traffic data.

[0636] Furthermore, the server uses natural language generation technology to formalize the analysis results and output them as documents. To do this, it utilizes generative AI models to create reports that are easy for humans to understand. For example, it might output traffic congestion predictions in the form of, "Traffic is expected to increase in the city center between 8:00 AM and 10:00 AM tomorrow."

[0637] The terminal collects opinions and feedback from users and transmits them to the server. Users provide feedback through the application, contributing to service improvement. At this stage, users can input their thoughts about the system in the form of, "Reducing the on-time of streetlights at night was good for the environment."

[0638] The server uses natural language processing techniques to analyze emotional information from the collected feedback. This information is then used by an emotion recognition engine to determine the user's satisfaction or dissatisfaction level.

[0639] Based on emotional information, the server provides personalized suggestions to the user. This presents information and alternatives tailored to the user's needs, and may generate more detailed documentation.

[0640] An example of a prompt for the generating AI model would be to input the text, "Based on real-time urban traffic data, predict traffic congestion for the following day and create a user-friendly report."

[0641] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0642] Step 1:

[0643] The server collects traffic, energy, environmental, and resident information in real time from sensors and external databases. The input is provided in various data formats. The server uses a data format integration tool to convert the collected data into a unified format, generating a unified dataset as output. Specifically, it converts JSON data obtained via APIs into CSV format.

[0644] Step 2:

[0645] The server performs noise reduction and processing of outliers on data in a unified format. The input is the dataset generated in step 1. Missing data is interpolated and outliers are filtered using Python data processing libraries. The output is a clean dataset with increased reliability. Specifically, the Pandas library is used to detect and remove anomalous traffic data.

[0646] Step 3:

[0647] The server uses machine learning algorithms to perform feature analysis and prediction based on preprocessed data. The input is a clean dataset. It utilizes open-source machine learning frameworks to predict future conditions and patterns. For example, it trains a model to predict peak traffic volume for the following day based on historical traffic data. The output is the predicted future patterns and events.

[0648] Step 4:

[0649] The server formats the prediction results into a report using natural language generation technology. The input is the prediction result from step 3. The generation AI model is given a prompt and automatically generates human-readable text. The output is an easy-to-understand report provided to the user. Specifically, it might generate a sentence like, "Traffic is expected to increase in the city center between 8:00 AM and 10:00 AM tomorrow."

[0650] Step 5:

[0651] The terminal collects opinions and feedback from users. The input is the feedback provided by the user. Information regarding user satisfaction and dissatisfaction is collected through the application. The output is a set of feedback data that the server uses for analysis. As a concrete example, the user inputs feedback into the terminal such as, "Reducing the on-time of streetlights at night was helpful."

[0652] Step 6:

[0653] The server analyzes the collected feedback using an emotion recognition engine and extracts emotional information. The input is the feedback data from step 5. Natural language processing techniques are used to evaluate the user's emotional response. The output is emotional information such as positive or negative. Specifically, Google Cloud's Natural Language API is used to infer user satisfaction from the feedback.

[0654] Step 7:

[0655] The server provides personalized information and suggestions to the user based on emotional information. The input is the emotional analysis results obtained in step 6. Additional information and alternatives are prepared according to the user's emotions and provided as a report. The output is a detailed suggestion or report to the user. Specifically, if negative feedback is received, a more detailed explanation and alternatives are described in the report.

[0656] (Application Example 2)

[0657] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0658] In modern urban life, residents face a variety of challenges in their daily lives, including transportation, energy, and the environment. To solve these problems, it is necessary to efficiently analyze vast amounts of data collected in real time and provide appropriate information tailored to residents' needs. Furthermore, accurately understanding residents' emotions is essential for providing more personalized services. However, conventional technologies have not been able to adequately address these challenges.

[0659] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0660] In this invention, the server includes means for collecting information on means of transportation, power, environment, and population from different information sources; means for converting the collected information into a unified format and processing noise reduction and deviation values; and means for extracting emotional information from users' opinions using emotion analysis means and providing personalized analysis results based on that information. This enables efficient analysis of various challenges in urban life and the provision of services that take into account the emotions of residents.

[0661] "Different sources of information" refers to data sources that provide various types of information, including urban transportation, energy consumption, environmental measurement equipment, and demographic databases.

[0662] "Means of transportation" refers to methods or systems for moving individuals or goods from one point to another, and includes public transportation such as automobiles, buses, and trains.

[0663] "Power" refers to the form or method of providing energy, and includes energy sources such as electricity, gas, and kerosene.

[0664] "Environment" refers to the natural environment and all artificially constructed physical environments, including atmospheric conditions, water quality, and land use.

[0665] "Population information" refers to statistical data about people who live in or visit a specific area, and includes age, gender, occupation, and migration patterns.

[0666] "Means of collection" refers to the methods and devices used to obtain the necessary information, and includes sensors, data collection devices, and database query techniques.

[0667] "Converting to a unified format" refers to the process of standardizing data from different formats and preparing it in a form that can be analyzed.

[0668] "Denoising and handling of deviations" refers to the process of removing or correcting unnecessary or inaccurate data in order to improve the accuracy of the data.

[0669] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and knowledge from data and uses that knowledge to make predictions and classifications.

[0670] "Pattern analysis" refers to the process of finding regularities and trends within a dataset, and using the analysis results to predict future events and actions.

[0671] "Natural language generation technology" refers to technology that uses machines to generate human language and represent data in text format.

[0672] "Opinions" refer to the thoughts and feelings that users have about a system or service.

[0673] "Retraining" refers to the process by which a machine learning model learns again using new data, and is done to improve the model's accuracy and adaptability.

[0674] "Emotional analysis methods" refer to technologies and methods for analyzing emotions and sentiments from collected text data, etc.

[0675] This invention is a system that collects and analyzes diverse information in urban areas in real time to optimize the lives of residents. The following describes an embodiment of the system.

[0676] The server collects information on traffic, energy, environment, and population from diverse sources via sensors and databases. After collection, this information is converted to a unified format, and unnecessary noise is removed and outliers are processed. This creates an accurate dataset suitable for analysis.

[0677] The server performs pattern analysis and prediction using machine learning models based on pre-processed data. Machine learning frameworks such as TensorFlow are used for this analysis. The analysis results are formatted as a text report using natural language generation technology, making it easy for users to understand the results.

[0678] The device is equipped with a user interface that accepts user feedback. This feedback is sent to a server to extract the user's emotional information via an emotion analysis system and to provide more personalized services based on the emotion analysis results.

[0679] For example, if sentiment analysis detects numerous complaints about public transportation services in a particular area, the server reports this information to the city administrator and proposes immediate countermeasures. In this process, a generative AI model is used to optimize natural language generation technology, generating prompt messages that are based on residents' requests.

[0680] An example of a prompt message would be, "Enter text data regarding residents' complaints and output the sentiment score."

[0681] The above system makes it possible to respond quickly to various urban challenges and improve the lives of residents.

[0682] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0683] Step 1:

[0684] The server collects information on transportation, energy, environment, and population from diverse sources. It uses sensors and database APIs to retrieve data in real time. At this point, the input is raw data, and the output is data before conversion to a unified format.

[0685] Step 2:

[0686] The server converts the collected raw data into a unified format. This processing uses a data formatting standardization library to remove noise and handle outliers. This transformation generates an analyzable dataset. The input is raw data in various formats, and the output is formatted data in a unified format.

[0687] Step 3:

[0688] The server runs a machine learning model using preprocessed data. It analyzes patterns using TensorFlow and predicts future situations. This process involves calculations based on a large amount of data. The input is preprocessed data, and the output is predicted data as a result of the analysis.

[0689] Step 4:

[0690] The server utilizes a generative AI model to format predicted data as natural language. Using natural language generation technology, it creates a text-based report. This report is organized in a way that is easily understandable to the user. The input is the predicted data, and the output is the generated report.

[0691] Step 5:

[0692] The terminal collects feedback from residents through its user interface. Users input their opinions on daily public services, which are then sent to the server by the terminal. The input is the user's feedback, and the output is the transfer of that feedback to the server.

[0693] Step 6:

[0694] The server processes the collected feedback using sentiment analysis tools. It extracts sentiment information using natural language processing libraries such as NLTK and analyzes user satisfaction and dissatisfaction. This process yields a sentiment score. The input is user feedback, and the output is sentiment information.

[0695] Step 7:

[0696] The server uses the sentiment analysis results to retrain the machine learning model. New data is added to the training dataset to improve the model's adaptability. This retraining improves the system's accuracy. The input is the sentiment analysis results, and the output is the updated machine learning model.

[0697] Step 8:

[0698] The server generates personalized service recommendations based on the generated report and sentiment analysis results. The generated AI model is displayed in user-friendly natural language as prompts. Users receive specific improvement suggestions. The input is the updated model and sentiment analysis results, and the output is personalized service recommendations.

[0699] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0700] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0701] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0702] [Fourth Embodiment]

[0703] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0704] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0705] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0706] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0707] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0708] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0709] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0710] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0711] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0712] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0713] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0714] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0715] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0716] This invention aims to integrate and analyze diverse data in urban areas, such as traffic, energy, environmental, and population information, and to optimize administrative services and improve citizens' lives based on the results. This system has an architecture that primarily processes data centered on a server, and its embodiments are described below.

[0717] The server first collects data in real time from traffic sensors, energy meters, environmental monitoring devices, and other sources. Since this data is transmitted in various formats, the server converts it into a unified format and integrates it into an analyzable format. For example, the server converts traffic data in CSV format and environmental data in JSON format into a common data model.

[0718] Next, the server performs noise reduction and outlier filtering on the collected data to improve its quality. This ensures the accuracy of the data.

[0719] In the analysis step, the server uses pre-trained machine learning models to perform pattern analysis and future predictions. For example, the server analyzes traffic flow data to predict congestion patterns for specific days of the week and weather conditions. Similarly, with regard to energy data, it analyzes changes in consumption patterns and proposes an optimal energy consumption profile.

[0720] The analysis results are transcribed into text using natural language generation technology and provided to government officials and citizens. The server sends the generated reports via email or uploads them to an online portal accessible to users. This process ensures that complex data analysis results are presented in an easily understandable format.

[0721] Furthermore, the server collects user feedback and continuously updates the machine learning model to improve the accuracy and adaptability of the analysis. Specifically, the server aggregates user feedback information and incorporates it into the model's training data, thereby improving the accuracy of future predictions.

[0722] In this way, the present invention can provide effective and sustainable solutions to complex urban challenges through a data-driven approach.

[0723] The following describes the processing flow.

[0724] Step 1:

[0725] The server collects data in real time from sources such as traffic sensors and energy meters. This involves sending API requests to retrieve information from sensors via data streams and storing the data on the server.

[0726] Step 2:

[0727] The server converts the collected data into a unified format. By integrating data with different formats and structures into a common data model, it prepares the data for analysis. Specifically, it processes CSV files and JSON data and integrates them into a database.

[0728] Step 3:

[0729] The server performs data cleansing, noise reduction, and outlier detection. This eliminates inaccurate data that could affect the analysis and improves data quality. Statistical methods are used to detect outliers.

[0730] Step 4:

[0731] The server applies machine learning models to perform data analysis and prediction. For example, it analyzes traffic flow and energy consumption patterns to detect trends and anomalies. The models applied are executed based on pre-selected algorithms.

[0732] Step 5:

[0733] The server generates reports based on analysis results using natural language generation technology. Based on the insights gained, it creates easy-to-understand text and charts for government officials and citizens. This generated content is then formatted for clarity.

[0734] Step 6:

[0735] The server distributes the generated reports to terminals, making them accessible to users. Information is provided to users through email notifications and report uploads to online portals. This facilitates the sharing of relevant information.

[0736] Step 7:

[0737] Users provide feedback based on information delivered by the server. They submit opinions on the system's ease of use and the appropriateness of the analysis results through online forms or other means.

[0738] Step 8:

[0739] The server updates and retrains the machine learning model based on user feedback. The feedback information is incorporated into the training dataset to improve the model's accuracy and adaptability. This process aims to enhance the model's performance.

[0740] (Example 1)

[0741] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0742] It is difficult to effectively combine multiple statistical data obtained from unintegrated sources, analyze them in real time, and improve the accuracy of decision-making and future predictions. Furthermore, providing analysis results in an intuitively understandable format and quickly utilizing user feedback are also challenges.

[0743] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0744] In this invention, the server includes means for collecting statistical information from different sources, means for converting the collected statistical information into a unified format, and means for asynchronous information removal and processing of exceptional values, and means for performing rule analysis and prediction using an artificial intelligence model. This enables highly integrated data analysis and flexible information provision.

[0745] "Different sources of information" refers to multiple independent data generation platforms, such as transportation, energy, environment, and population data.

[0746] "Statistical information" refers to numerical data that serves as the basis for analyzing various types of data related to a city and extracting meaningful information.

[0747] A "unified format" refers to a standardized data structure used to ensure consistency within a system when data is recorded in different formats.

[0748] "Asynchronous desynchronization" refers to the process of removing inconsistent data and noise that occur during the data collection process, thereby improving the reliability of the data.

[0749] "Exceptional values" refer to data points in statistical information that deviate significantly from normal values, and properly handling these contributes to improving the accuracy of data analysis.

[0750] An "artificial intelligence model" refers to a computational model built on machine learning algorithms that uses data to perform rule analysis and future predictions with high accuracy.

[0751] "String generation technology" refers to the technique of converting data analysis results into text in natural language, and is used to make the results easier to understand.

[0752] A "report" refers to a document or digital document containing information that summarizes the results obtained from an analysis.

[0753] "Users" refers to citizens and government officials who use this system to review analysis results and make decisions or provide feedback.

[0754] "Evaluation" refers to information that reflects users' opinions and intentions regarding analysis results and system operation, and is used to improve the system.

[0755] The system of this invention has a data processing architecture primarily based on a server. The server collects and integrates diverse data such as traffic, energy, environmental, and population information. Specifically, the server uses hardware that acquires data in real time from traffic sensors, energy meters, environmental monitoring devices, etc.

[0756] The server uses data format conversion software to convert the received data into a unified format. This conversion process prepares data in CSV or JSON format into a common data model suitable for analysis. The converted data is then processed by a data cleansing algorithm through asynchronous information removal and exception handling to improve data accuracy.

[0757] Next, the server performs analysis using an artificial intelligence model. The trained machine learning model enables pattern analysis and future predictions based on the collected statistical information. The server converts the analysis results into natural language using string generation technology and generates a report. This report is provided to users and government officials via email or a web portal.

[0758] For example, a city's traffic management department could use this system to predict congestion at a specific intersection on Monday mornings and provide citizens with countermeasures. The energy sector could also use it to plan for minimizing peak power consumption.

[0759] For example, by inputting instructions such as, "Predict the traffic congestion pattern in urban area A for the next week based on current statistical information, and list the possible problems that may occur," into the generating AI model, it is possible to obtain more specific analysis results.

[0760] The entire system leverages integrated data from servers to support decision-making in an efficient and sustainable way to solve urban challenges.

[0761] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0762] Step 1:

[0763] The server collects data from traffic sensors, energy meters, and environmental monitoring devices. Its inputs include data in various formats obtained in real time. This data is periodically retrieved via standard network protocols. The output is a collection of the collected raw data.

[0764] Step 2:

[0765] The server converts the collected raw data into a unified format. Inputs include data with different structures, such as CSV and JSON. The server performs data format conversion processing, integrating all data into a common data model. The output is a unified dataset prepared in a parseable format.

[0766] Step 3:

[0767] The server cleanses the unified dataset. The processed unified data is used as input. The server performs denoising algorithms and exception filtering to improve data quality. The output is a clean dataset with guaranteed accuracy.

[0768] Step 4:

[0769] The server performs data analysis using an artificial intelligence model with a clean dataset. The input is high-quality data that has been preprocessed. The server performs pattern analysis and future predictions and obtains the results. The output is the analyzed results, including predicted data and the discovery of specific patterns.

[0770] Step 5:

[0771] The server converts the analysis results into text using string generation technology. The input is the raw data obtained as the output of the analysis. This is converted into natural language and formatted into a report. The output is an easily understandable document that can be presented to the user.

[0772] Step 6:

[0773] The server provides the generated report to the user. The input is the generated, written report. The server sends this via email or uploads it to an online portal. The output is the report delivered in a format that can be viewed by the user.

[0774] Step 7:

[0775] Users provide feedback on the content of the provided report. The input consists of the user's opinions and evaluations based on the analysis results. The user's evaluation information is sent to the server and used in the next step. The output is the evaluation data as feedback.

[0776] Step 8:

[0777] The server analyzes user feedback and updates its artificial intelligence model. The input is the feedback data provided by the user. The server uses this data to retrain the model and improve its analysis accuracy. The output is the improved artificial intelligence model.

[0778] (Application Example 1)

[0779] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0780] Effectively managing diverse information related to urban transportation, energy, and the environment, and using this information to make rapid and accurate predictions and decisions, is a crucial challenge in improving urban life. However, because this information is diverse and in different formats, it is difficult to analyze it uniformly and in real time. Furthermore, there is a lack of means to communicate the analysis results to users in an easily understandable way, which hinders the full utilization of the results in decision-making.

[0781] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0782] In this invention, the server includes means for aggregating city-related data acquired from different sources; means for converting the collected information into a standard format and performing noise reduction and anomaly correction to improve data quality; means for performing pattern analysis and prediction using machine learning algorithms with the preprocessed data; means for texting the results using natural language construction and providing them as a report document; means for collecting user feedback on the report content and updating the machine learning model; and means for providing an information technology infrastructure for displaying the analysis results to users in real time. This makes it possible to comprehensively manage diverse information in a city and support prediction and decision-making.

[0783] "Information sources" refer to sources that supply diverse data about a city, including devices such as traffic sensors, energy meters, and environmental monitoring equipment.

[0784] A "standard format" is a consistent data format used to unify and analyze data from different formats.

[0785] "Noise reduction" is the process of removing unnecessary elements and errors from data in order to obtain accurate results during data analysis.

[0786] "Outlier correction" is a process that improves data quality by detecting outliers in the data and replacing them with appropriate values.

[0787] A "machine learning algorithm" is a computational method used to identify patterns and make predictions using large amounts of data. It is widely used as part of artificial intelligence.

[0788] "Pattern analysis" is a procedure that identifies regularities and trends within data and uses them to make various predictions.

[0789] "Natural language construction" is a technology that generates the results of analyzed data into natural language text that is easy for humans to understand.

[0790] An "information technology infrastructure" is a collection of computer systems, networks, and software used for processing, managing, and transmitting information.

[0791] This invention aims to provide an integrated system that streamlines the management of diverse data in cities and supports prediction and decision-making based on that data. The embodiments thereof will be described in detail below.

[0792] First, the server collects data in real time from various sources within the city. For example, it utilizes data obtained from traffic sensors, energy meters, and environmental monitoring equipment. Since this data exists in various formats, the server converts it to a standard format. This process uses data processing scripts built with the Python language and the pandas library. Furthermore, data denoising and outlier correction are performed to improve data quality.

[0793] Next, the server performs pattern analysis and prediction using a model that implements machine learning algorithms. This analysis utilizes machine learning libraries such as TensorFlow and scikit-learn. Once the prediction is complete, the results are converted into text using natural language constructor technology and provided in a format that is easy for users to understand. A GPT-based generative AI model is used for natural language generation.

[0794] The analyzed information is then displayed in real time on the user's smartphone or tablet device via an information technology infrastructure. The front-end is developed using React Native, allowing end users to view real-time data about the city through the application.

[0795] A concrete example is when a user opens the app on a weekend afternoon to check the day's urban traffic conditions and energy consumption forecast. Based on this information, the user can optimize their spending habits and travel plans.

[0796] As an example of a prompt, you can send a request to the AI ​​to "analyze the traffic situation in Tokyo at 8:00 AM on October 15th and the forecast for the next three hours, and create a report in natural language." This prompt will then be used as an instruction to the system.

[0797] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0798] Step 1:

[0799] The server collects urban-related data in real time from traffic sensors, energy meters, environmental monitoring equipment, and other sources. Inputs are raw data transmitted from these devices, including various formats. Outputs are unprocessed data sent directly to the server. In this step, an API for data collection operates, periodically querying and retrieving data.

[0800] Step 2:

[0801] The server converts the collected data into a standard format. Here, the pandas library is used to organize CSV and JSON data into a unified format. The input is the data in different formats collected in step 1, and the output is a DataFrame in a unified format. In this step, a format conversion script is generated and performs the mapping process to unify the data.

[0802] Step 3:

[0803] The server performs data noise reduction and outlier correction. It detects outliers and corrects them using the mean and median. The input is a transformed DataFrame, and the output is a clean dataset with improved quality. This operation involves calculations to remove outliers and noise using statistical analysis techniques.

[0804] Step 4:

[0805] The server performs pattern analysis and prediction using a machine learning model based on clean data. It uses TensorFlow, etc., to generate specific patterns and future predictions. The input is the data prepared in step 3, and the output is a dataset of prediction results. The machine learning algorithm operates here, and data predictions are made based on the model.

[0806] Step 5:

[0807] The server converts the analysis results into text using natural language generation technology. A generative AI model is used to transform the prediction results into easily understandable text. The input is the prediction data obtained in step 4, and the output is a report written in natural language. The natural language processing module is responsible for text generation here.

[0808] Step 6:

[0809] The server provides the generated reports to users via an online portal or email. The terminal receives notifications from the server and displays the analysis results to the user. Input is a written report, and output is a report provided to the user as information. The results are displayed on the user interface, allowing for visual confirmation of the information.

[0810] Step 7:

[0811] The user provides feedback on the analysis results, and the server uses this feedback to retrain the machine learning model. The input is the user's feedback, and the output is data for improving the model. In this step, the feedback information is added to the dataset, and the model is retrained to improve its accuracy.

[0812] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0813] This invention is a system that comprehensively aggregates and analyzes various data in urban areas and uses the results to optimize the lives of citizens. This system consists of a server-centered data processing and user interface configuration, and its form is described in detail below.

[0814] The server collects data such as traffic, energy, environment, and population information in real time via sensors and external databases. Because this data often exists in diverse formats, the server converts it into a unified, analyzable format. It then performs noise reduction and outlier processing to generate an accurate dataset.

[0815] After data preprocessing is complete, the server uses machine learning algorithms to extract meaningful patterns from the data and predict future situations. At this stage, the prediction results are translated into text using natural language generation technology, generating an easy-to-understand report.

[0816] A distinctive feature of this invention is the integration of an emotion engine. The server collects feedback data from users and analyzes the emotional information contained in the feedback through the emotion engine. For example, it can understand user satisfaction and dissatisfaction from opinions and impressions submitted through the user interface on the terminal.

[0817] Using this sentiment analysis information, the server provides users with further personalized analysis results and suggestions. For example, if the sentiment engine indicates that the user is dissatisfied, the server may add more detailed explanations and alternatives to the report. The sentiment data thus collected is used as feedback when the server retrains its machine learning models, improving the overall adaptability and accuracy of the system.

[0818] In this way, the present invention, by combining a data-driven approach with emotion recognition technology, can provide more precise and efficient solutions to urban challenges and meet the needs of citizens.

[0819] The following describes the processing flow.

[0820] Step 1:

[0821] The server connects to data sources such as traffic sensors, energy meters, and environmental sensors via APIs and begins real-time data collection. This includes opening data streams, receiving new data, and saving it to the database.

[0822] Step 2:

[0823] The server receives the collected data and converts each data format into a unified, parseable format. It integrates JSON and XML data into a common data model and performs data mapping to ensure consistency.

[0824] Step 3:

[0825] The server denoises the integrated data and filters outliers. This process uses statistical methods to detect and remove data points that deviate significantly from the standard.

[0826] Step 4:

[0827] The server inputs clean data into a machine learning model to perform pattern analysis and predict future situations. Here, past trends are learned, and the predictive algorithm determines the next steps.

[0828] Step 5:

[0829] The server uses natural language generation technology to translate the analysis results into text and format them as a report. Specifically, it creates a text report using concise and clear language, and adds charts and graphs where graphical visual elements are needed.

[0830] Step 6:

[0831] The server delivers the generated report to the terminal and provides the user with access rights. The report is delivered via email, a dashboard, or a mobile app, allowing users to view it.

[0832] Step 7:

[0833] Users review reports and provide feedback through their devices. This feedback is submitted via online forms or direct messages and includes comments on the user experience and specific suggestions.

[0834] Step 8:

[0835] The server collects user feedback and analyzes the emotional data using an emotion engine. For example, it uses text analysis techniques to extract user emotions and tendencies from the linguistic features contained in the feedback.

[0836] Step 9:

[0837] Based on the analysis results from the emotion engine, the server adjusts the presentation method of the analysis results and the content of the next suggestions as needed. Furthermore, the feedback data is used to improve and retrain the machine learning model, enhancing the overall accuracy and responsiveness of the system.

[0838] (Example 2)

[0839] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0840] In urban environments, there is a need for effective collection and analysis of data related to transportation, energy, environment, and population. However, because information from different data sources is in diverse formats, it is difficult to integrate, process, and quickly analyze it to aid in decision-making. Furthermore, there is a need to effectively utilize user feedback and address individual needs.

[0841] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0842] In this invention, the server includes means for collecting traffic, energy, environmental, and resident information from different sources; means for converting the collected information into a unified format, removing noise, and processing exceptional values; and means for performing feature analysis and prediction using machine learning algorithms. This enables rapid analysis of integrated data and the provision of personalized information to users.

[0843] A "source of information" is the starting point or source from which data is collected.

[0844] "Transportation" refers to information related to means of travel and the flow of such travel.

[0845] "Energy" refers to information regarding the consumption and supply of electricity, gas, and other forms of energy.

[0846] "Environment" refers to information related to the natural and artificial environment, such as temperature, precipitation, and the concentration of pollutants.

[0847] "Resident information" refers to information related to demographic trends, lifestyles, and socioeconomic conditions.

[0848] "Data format" refers to the structure and representation method of the collected data.

[0849] "Noise reduction" is a process that removes unnecessary information and errors from data, thereby extracting accurate information.

[0850] An "exceptional value" refers to an unusual value in a data set that deviates from the general pattern.

[0851] A "machine learning algorithm" is a technology that provides a mechanism for computers to learn on their own for data analysis.

[0852] "Feature analysis" refers to the process of finding meaningful patterns and relationships within data.

[0853] "Prediction" is the process of inferring future states or events based on past data.

[0854] "Natural language generation technology" is a technology that allows computers to generate text in a format that humans can understand.

[0855] A "document" refers to a document that contains information in text format.

[0856] "Emotional information" refers to data that reflects users' subjective satisfaction or dissatisfaction.

[0857] "Personalization" refers to providing information and services that meet the individual needs of each user.

[0858] "Users" refers to individuals, companies, or organizations that use the system.

[0859] This invention is a system that efficiently collects and processes diverse data in urban environments and optimizes citizens' lives based on the results. The system is mainly composed of a server and includes the following detailed embodiments.

[0860] The server collects traffic, energy, environmental, and resident information from multiple sources. This collection utilizes communication technologies to connect with various sensors and external databases. For example, traffic sensor data is sent to the server via an API.

[0861] The server converts the collected information into a standardized format. This is done using common data format integration software. For example, information obtained in JSON format is converted to CSV format to facilitate analysis.

[0862] The server performs noise reduction and outlier processing to ensure data quality. At this stage, Python data processing libraries are used to improve the reliability of the dataset.

[0863] The server performs feature analysis and prediction using machine learning algorithms. Here, we utilize open-source machine learning frameworks to build models that predict future situations. For example, one scenario is to predict the occurrence of traffic congestion at a specific location the following day based on traffic data.

[0864] Furthermore, the server uses natural language generation technology to formalize the analysis results and output them as documents. To do this, it utilizes generative AI models to create reports that are easy for humans to understand. For example, it might output traffic congestion predictions in the form of, "Traffic is expected to increase in the city center between 8:00 AM and 10:00 AM tomorrow."

[0865] The terminal collects opinions and feedback from users and transmits them to the server. Users provide feedback through the application, contributing to service improvement. At this stage, users can input their thoughts about the system in the form of, "Reducing the on-time of streetlights at night was good for the environment."

[0866] The server uses natural language processing techniques to analyze emotional information from the collected feedback. This information is then used by an emotion recognition engine to determine the user's satisfaction or dissatisfaction level.

[0867] Based on emotional information, the server provides personalized suggestions to the user. This presents information and alternatives tailored to the user's needs, and may generate more detailed documentation.

[0868] An example of a prompt for the generating AI model would be to input the text, "Based on real-time urban traffic data, predict traffic congestion for the following day and create a user-friendly report."

[0869] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0870] Step 1:

[0871] The server collects traffic, energy, environmental, and resident information in real time from sensors and external databases. The input is provided in various data formats. The server uses a data format integration tool to convert the collected data into a unified format, generating a unified dataset as output. Specifically, it converts JSON data obtained via APIs into CSV format.

[0872] Step 2:

[0873] The server performs noise reduction and processing of outliers on data in a unified format. The input is the dataset generated in step 1. Missing data is interpolated and outliers are filtered using Python data processing libraries. The output is a clean dataset with increased reliability. Specifically, the Pandas library is used to detect and remove anomalous traffic data.

[0874] Step 3:

[0875] The server uses machine learning algorithms to perform feature analysis and prediction based on preprocessed data. The input is a clean dataset. It utilizes open-source machine learning frameworks to predict future conditions and patterns. For example, it trains a model to predict peak traffic volume for the following day based on historical traffic data. The output is the predicted future patterns and events.

[0876] Step 4:

[0877] The server formats the prediction results into a report using natural language generation technology. The input is the prediction result from step 3. The generation AI model is given a prompt and automatically generates human-readable text. The output is an easy-to-understand report provided to the user. Specifically, it might generate a sentence like, "Traffic is expected to increase in the city center between 8:00 AM and 10:00 AM tomorrow."

[0878] Step 5:

[0879] The terminal collects opinions and feedback from users. The input is the feedback provided by the user. Information regarding user satisfaction and dissatisfaction is collected through the application. The output is a set of feedback data that the server uses for analysis. As a concrete example, the user inputs feedback into the terminal, such as "Reducing the on-time of streetlights at night was helpful."

[0880] Step 6:

[0881] The server analyzes the collected feedback using an emotion recognition engine and extracts emotional information. The input is the feedback data from step 5. Natural language processing techniques are used to evaluate the user's emotional response. The output is emotional information such as positive or negative. Specifically, Google Cloud's Natural Language API is used to infer user satisfaction from the feedback.

[0882] Step 7:

[0883] The server provides personalized information and suggestions to the user based on emotional information. The input is the emotional analysis results obtained in step 6. Additional information and alternatives are prepared according to the user's emotions and provided as a report. The output is a detailed suggestion or report to the user. Specifically, if negative feedback is received, a more detailed explanation and alternatives are described in the report.

[0884] (Application Example 2)

[0885] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0886] In modern urban life, residents face a variety of challenges in their daily lives, including transportation, energy, and the environment. To solve these problems, it is necessary to efficiently analyze vast amounts of data collected in real time and provide appropriate information tailored to residents' needs. Furthermore, accurately understanding residents' emotions is essential for providing more personalized services. However, conventional technologies have not been able to adequately address these challenges.

[0887] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0888] In this invention, the server includes means for collecting information on means of transportation, power, environment, and population from different information sources; means for converting the collected information into a unified format and processing noise reduction and deviation values; and means for extracting emotional information from users' opinions using emotion analysis means and providing personalized analysis results based on that information. This enables efficient analysis of various challenges in urban life and the provision of services that take into account the emotions of residents.

[0889] "Different sources of information" refers to data sources that provide various types of information, including urban transportation, energy consumption, environmental measurement equipment, and demographic databases.

[0890] "Means of transportation" refers to methods or systems for moving individuals or goods from one point to another, and includes public transportation such as automobiles, buses, and trains.

[0891] "Power" refers to the form or method of providing energy, and includes energy sources such as electricity, gas, and kerosene.

[0892] "Environment" refers to the natural environment and all artificially constructed physical environments, including atmospheric conditions, water quality, and land use.

[0893] "Population information" refers to statistical data about people who live in or visit a specific area, and includes age, gender, occupation, and migration patterns.

[0894] "Means of collection" refers to the methods and devices used to obtain the necessary information, and includes sensors, data collection devices, and database query techniques.

[0895] "Converting to a unified format" refers to the process of standardizing data from different formats and preparing it in a form that can be analyzed.

[0896] "Denoising and handling of deviations" refers to the process of removing or correcting unnecessary or inaccurate data in order to improve the accuracy of the data.

[0897] A "machine learning model" refers to an algorithm or mathematical model that learns patterns and knowledge from data and uses that knowledge to make predictions and classifications.

[0898] "Pattern analysis" refers to the process of finding regularities and trends within a dataset, and using the analysis results to predict future events and actions.

[0899] "Natural language generation technology" refers to technology that uses machines to generate human language and represent data in text format.

[0900] "Opinions" refer to the thoughts and feelings that users have about a system or service.

[0901] "Retraining" refers to the process by which a machine learning model learns again using new data, and is done to improve the model's accuracy and adaptability.

[0902] "Emotional analysis methods" refer to technologies and methods for analyzing emotions and sentiments from collected text data, etc.

[0903] This invention is a system that collects and analyzes diverse information in urban areas in real time to optimize the lives of residents. The following describes an embodiment of the system.

[0904] The server collects information on traffic, energy, environment, and population from diverse sources via sensors and databases. After collection, this information is converted to a unified format, and unnecessary noise is removed and outliers are processed. This creates an accurate dataset suitable for analysis.

[0905] The server performs pattern analysis and prediction using machine learning models based on pre-processed data. Machine learning frameworks such as TensorFlow are used for this analysis. The analysis results are formatted as a text report using natural language generation technology, making it easy for users to understand the results.

[0906] The device is equipped with a user interface that accepts user feedback. This feedback is sent to a server to extract the user's emotional information via an emotion analysis system and to provide more personalized services based on the emotion analysis results.

[0907] For example, if sentiment analysis detects numerous complaints about public transportation services in a particular area, the server reports this information to the city administrator and proposes immediate countermeasures. In this process, a generative AI model is used to optimize natural language generation technology, generating prompt messages that are based on residents' requests.

[0908] An example of a prompt message would be, "Enter text data regarding residents' complaints and output the sentiment score."

[0909] The above system makes it possible to respond quickly to various urban challenges and improve the lives of residents.

[0910] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0911] Step 1:

[0912] The server collects information on transportation, energy, environment, and population from diverse sources. It uses sensors and database APIs to retrieve data in real time. At this point, the input is raw data, and the output is data before conversion to a unified format.

[0913] Step 2:

[0914] The server converts the collected raw data into a unified format. This processing uses a data formatting standardization library to remove noise and handle outliers. This transformation generates an analyzable dataset. The input is raw data in various formats, and the output is formatted data in a unified format.

[0915] Step 3:

[0916] The server runs a machine learning model using preprocessed data. It analyzes patterns using TensorFlow and predicts future situations. This process involves calculations based on a large amount of data. The input is preprocessed data, and the output is predicted data as a result of the analysis.

[0917] Step 4:

[0918] The server utilizes a generative AI model to format predicted data as natural language. Using natural language generation technology, it creates a text-based report. This report is organized in a way that is easily understandable to the user. The input is the predicted data, and the output is the generated report.

[0919] Step 5:

[0920] The terminal collects feedback from residents through its user interface. Users input their opinions on daily public services, which are then sent to the server by the terminal. The input is the user's feedback, and the output is the transfer of that feedback to the server.

[0921] Step 6:

[0922] The server processes the collected feedback using sentiment analysis tools. It extracts sentiment information using natural language processing libraries such as NLTK and analyzes user satisfaction and dissatisfaction. This process yields a sentiment score. The input is user feedback, and the output is sentiment information.

[0923] Step 7:

[0924] The server uses the sentiment analysis results to retrain the machine learning model. New data is added to the training dataset to improve the model's adaptability. This retraining improves the system's accuracy. The input is the sentiment analysis results, and the output is the updated machine learning model.

[0925] Step 8:

[0926] The server generates personalized service recommendations based on the generated report and sentiment analysis results. The generated AI model is displayed in user-friendly natural language as prompts. Users receive specific improvement suggestions. The input is the updated model and sentiment analysis results, and the output is personalized service recommendations.

[0927] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0928] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0929] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0930] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0931] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0932] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0933] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0934] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0935] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0936] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0937] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0938] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0939] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0940] 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.

[0941] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0942] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0943] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0944] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0945] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0946] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0947] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0948] The following is further disclosed regarding the embodiments described above.

[0949] (Claim 1)

[0950] Means of collecting transportation, energy, environmental, and population information from different data sources,

[0951] A means for converting collected data into a unified format and performing noise reduction and outlier processing,

[0952] A means for performing pattern analysis and prediction using a machine learning model based on preprocessed data,

[0953] A means of formalizing the analysis results using natural language generation technology and outputting them as a report,

[0954] A means of collecting user feedback on reported results and retraining the machine learning model,

[0955] A system that includes this.

[0956] (Claim 2)

[0957] The system according to claim 1, which collects data in real time and enables rapid data analysis and decision-making.

[0958] (Claim 3)

[0959] The system according to claim 1, comprising an interface for visually representing and providing analysis results to the user.

[0960] "Example 1"

[0961] (Claim 1)

[0962] Means of collecting statistical information from different sources,

[0963] A means for converting collected statistical information into a unified format, and for asynchronous information removal and processing of exceptional values,

[0964] A means for performing rule analysis and prediction using an artificial intelligence model based on preprocessed statistical information,

[0965] A means of formatting the analysis results using string generation technology and outputting them as a report,

[0966] A means of collecting user feedback on reported results and retraining the artificial intelligence model,

[0967] A system that includes this.

[0968] (Claim 2)

[0969] The system according to claim 1, which collects statistical information in real time and enables rapid statistical information analysis and decision-making.

[0970] (Claim 3)

[0971] The system according to claim 1, comprising an interactive device for visually displaying and providing analysis results to the user.

[0972] "Application Example 1"

[0973] (Claim 1)

[0974] A means of aggregating city-related data obtained from different sources,

[0975] A means for converting collected information into a standard format and performing noise reduction and outlier correction to improve data quality,

[0976] A means for performing pattern analysis and prediction using machine learning algorithms with preprocessed data,

[0977] A means of formulating the results into text using natural language construction and providing them as a report document,

[0978] A method for collecting user feedback on the report content and updating the machine learning model,

[0979] A means of providing an information technology infrastructure for displaying analysis results to users in real time,

[0980] A system that includes this.

[0981] (Claim 2)

[0982] The system according to claim 1, which collects information in real time and enables rapid information processing and decision-making.

[0983] (Claim 3)

[0984] The system according to claim 1, comprising an information technology interface for visually displaying and providing analysis results to a user.

[0985] "Example 2 of combining an emotion engine"

[0986] (Claim 1)

[0987] Means of collecting transportation, energy, environmental, and population information from different sources,

[0988] A means for converting collected information into a unified format, and for processing noise reduction and exception values,

[0989] A means for performing feature analysis and prediction using a machine learning algorithm based on preprocessed information,

[0990] A means of formalizing the analysis results using natural language generation technology and outputting them as a document,

[0991] A means of collecting user feedback on the reported results and analyzing sentiment information,

[0992] A means of providing users with personalized information and suggestions based on sentiment analysis, and a means of retraining machine learning algorithms.

[0993] A system that includes this.

[0994] (Claim 2)

[0995] The system according to claim 1, which collects information in real time and enables rapid information analysis and decision-making.

[0996] (Claim 3)

[0997] The system according to claim 1, comprising an interface for visually representing and providing analysis results to a user.

[0998] "Application example 2 when combining with an emotional engine"

[0999] (Claim 1)

[1000] Means of collecting information on means of transportation, power, environment, and population from different sources,

[1001] A means for converting collected information into a unified format and processing noise reduction and deviation values,

[1002] A means for performing pattern analysis and prediction using a machine learning model based on preprocessed information,

[1003] A means of formalizing the analysis results using natural language generation technology and outputting them as a report,

[1004] A means of collecting user feedback on the reported results and retraining the machine learning model,

[1005] A means for extracting emotional information from user opinions using emotion analysis methods and providing personalized analysis results based on that information,

[1006] A system that includes this.

[1007] (Claim 2)

[1008] The system according to claim 1, which collects information in real time and enables rapid information analysis and decision-making.

[1009] (Claim 3)

[1010] The system according to claim 1, comprising a screen for visually representing and providing analysis results to the user. [Explanation of symbols]

[1011] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of aggregating city-related data obtained from different sources, A means for converting collected information into a standard format and performing noise reduction and outlier correction to improve data quality, A means for performing pattern analysis and prediction using machine learning algorithms with preprocessed data, A means of formulating the results into text using natural language construction and providing them as a report document, A method for collecting user feedback on the report content and updating the machine learning model, A means of providing an information technology infrastructure for displaying analysis results to users in real time, A system that includes this.

2. The system according to claim 1, which collects information in real time and enables rapid information processing and decision-making.

3. The system according to claim 1, comprising an information technology interface for visually displaying and providing analysis results to a user.

Images