System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting infection data; means for calculating an infection risk for each area using the collected infection data; means for recommending an infection prevention action to a user based on the calculated infection risk; means for acquiring position information of the user; and means for evaluating the infection risk at a specific location based on the position information of the user and providing an action recommendation in real time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, the rapid spread of infectious diseases has become a major social and economic problem. Conventional infection prevention measures make it difficult to accurately grasp the infection risk of an entire region, and do not provide users with specific, individual guidelines for action. This makes it difficult to contain the spread of infection, and users live in anxiety. Furthermore, because real-time infection risk assessments and behavioral recommendations are not provided, there is also the problem that infection prevention measures cannot be taken at the appropriate time. The purpose of the present invention is to solve these issues and realize a society where people can live safely by minimizing the risk of infection. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting infection data, a means for calculating the infection risk for each region using the collected infection data, a means for recommending infection prevention actions to users based on the calculated infection risk, a means for acquiring user location information, and a means for evaluating the infection risk at a specific location based on the user location information and providing recommended actions in real time. The system also includes a means for visualizing and displaying the calculated infection risk, and a means for training and applying an AI model to generate an infection risk index. The system also includes a means for collecting user behavioral data and providing it to the system as feedback, and a means for analyzing the feedback data and updating the AI ​​model, thereby achieving highly accurate infection risk assessment and behavioral recommendations. This allows users to recognize the infection risk in their region in real time and take optimal infection prevention measures.

[0006] "Infection data" refers to information necessary to show the spread and impact of infectious diseases, such as the number of infected people, the number of new infections, age groups, severity, and location of the infection.

[0007] "Regional infection risk" refers to the risk of infectious disease spreading in a specific geographical area (such as a city, town, or village, or a specific facility) expressed as a number or index.

[0008] "User" refers to an individual or organization that uses this system to receive infection risk information and behavioral recommendations.

[0009] "Action recommendations" are information that suggests specific actions and measures that users should take to prevent infection.

[0010] "Location information" means data indicating a user's current location obtained using GPS or other technologies.

[0011] An "AI model" is a computational model that uses artificial intelligence technology to calculate infection risk from infection data and generate behavioral recommendations.

[0012] "Feedback data" refers to data returned to the system based on user actions, location information, etc., and is used to optimize AI models.

[0013] "Real-time" refers to the fact that data collection, analysis, and provision of action recommendations are carried out almost simultaneously, meaning that the latest information is reflected without delay. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides action recommendations in real time using AI. The system is configured as follows.

[0036] 1. Data Collection

[0037] The server receives real-time infection data provided by medical institutions, including the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis.

[0038] 2. Data Analysis

[0039] The server uses an AI model to calculate the infection risk for each region based on the collected infection data. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded, visually indicating the level of infection risk.

[0040] 3. Obtaining user location information

[0041] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or other location services, allowing the server to determine the user's current location in real time.

[0042] 4. Risk assessment and action recommendations

[0043] The server obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user, such as advice on avoiding rush hours, refraining from using public transportation, and wearing masks in high-risk areas.

[0044] 5. Notification of recommended actions

[0045] The device notifies the user of the action recommendations received from the server via a pop-up or push notification, and displays additional details as needed.

[0046] 6. User Behavior and Feedback

[0047] Users can take specific actions to prevent infection, such as avoiding crowded times and wearing a mask in designated areas, according to the recommended actions.

[0048] 7. Feedback data collection and analysis

[0049] The device feeds back user behavior data (location information, prevention measures implementation status, etc.) to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data will be used to improve the accuracy of recommendations in the future.

[0050] Specific examples

[0051] Morning commute scenario

[0052] 1. The server receives the latest infection data from each medical institution, analyzes it, and detects high infection risks around specific stations in Tokyo.

[0053] 2. Let's say the user is on their morning commute and heading to Shinjuku Station.

[0054] 3. The device sends the user's current location (around Shinjuku Station) to the server.

[0055] 4. The server detects that the area around Shinjuku Station is a high-risk area and generates specific recommendations for actions, such as "avoiding rush hours," "switching to remote work if possible," and "always wearing a mask at the station and maintaining social distance."

[0056] 5. The device notifies the user of these recommendations and encourages them to act on them.

[0057] 6. Users should follow these guidelines and take measures to prevent infection, such as avoiding travel during designated times and wearing a mask, to reduce the risk of infection.

[0058] The above is an embodiment of the invention. The present invention allows users to receive the latest infection risk information and optimal action guidelines in real time, enabling them to take appropriate infection prevention actions. This allows them to live their daily lives with peace of mind.

[0059] The processing flow will be explained below.

[0060] Step 1: Collect data

[0061] The server periodically retrieves infection data from medical institution databases. The collected data includes information such as the number of infected people, the number of new infections, age, severity, and location of the infection. The retrieved data is stored in the system's database.

[0062] Step 2: Preprocessing the data

[0063] The server performs data cleaning (removal of duplicate data, completion of missing values, etc.) and data standardization (normalization of values, etc.) to make the collected infection data easier to analyze. The preprocessed data is used for infection risk diagnosis.

[0064] Step 3: Infection risk analysis

[0065] The server uses an AI model to calculate the infection risk for each region based on the preprocessed data. The infection risk index is calculated by taking into account the trend in the number of infected people and their geographic distribution, and this quantifies the infection risk for each region.

[0066] Step 4: Obtaining location information

[0067] The user's device (smartphone or tablet) uses location information services to obtain the user's current location. Location information is collected in real time using GPS, Wi-Fi, and Bluetooth and is updated periodically.

[0068] Step 5: Send location information

[0069] The device transmits the acquired user's current location information to the server, allowing the server to grasp the user's real-time location.

[0070] Step 6: Risk assessment

[0071] The server obtains and evaluates the latest infection risk index for the area based on the user's current location, thereby determining the infection risk level of the user's current location in real time.

[0072] Step 7: Generate action recommendations

[0073] The server uses an AI model to generate specific recommendations for users based on the assessed infection risk index, such as "avoid crowds," "wear a mask," and "wash your hands thoroughly" in high-risk areas.

[0074] Step 8: Recommendation Notification

[0075] The server sends the generated behavioral recommendations to the device, and notifications are sent in real time via push notifications, encouraging users to take infection prevention measures.

[0076] Step 9: User behavior feedback

[0077] Users can take specific actions to prevent infection based on the recommendations they receive, such as wearing a mask in high-risk areas and avoiding crowded places at certain times.

[0078] Step 10: Collect feedback data

[0079] The device collects user behavior data (location information, implementation status of preventive measures, etc.) and periodically feeds it back to the server, allowing the system to understand the user's behavioral history.

[0080] Step 11: Analyze feedback data

[0081] The server analyzes the collected feedback data and uses it as training data for the AI ​​model. The analysis results are used to improve the accuracy of future action recommendations.

[0082] Step 12: Update the AI ​​model

[0083] The server uses the feedback data to regularly update and refine the AI ​​model, improving the accuracy of infection risk assessment and behavioral recommendations, and providing users with more reliable information.

[0084] Through these steps, the system provides accurate infection risk information and optimal behavior recommendations in real time, supporting users in taking infection prevention actions.

[0085] Example 1

[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0087] To prevent the spread of infectious diseases, it is important to provide accurate infection risk information and appropriate guidelines in real time. However, current systems suffer from delays in the collection and analysis of infection data, or lack the functionality to provide immediate action recommendations using users' location information. As a result, users are unable to take appropriate infection prevention actions based on the latest risk information, which increases the risk of infection.

[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0089] In this invention, the server includes means for collecting infection data from medical institutions, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring and transmitting user location information, and means for evaluating the infection risk in a specific location based on the user location information and providing recommended actions in real time. This allows the user to always receive appropriate recommended actions in real time based on the latest infection risk information, thereby effectively preventing the spread of infectious diseases.

[0090] "Infection data" refers to a variety of data related to infectious diseases, such as the number of infected people, the number of new infections, age, severity, and location of the outbreak.

[0091] "Infection risk" is an indicator of the possibility of the spread of an infectious disease in a particular area or location. Infection risk is calculated based on collected infection data.

[0092] "Recommendations" refers to guidelines and advice provided to users by the system, including suggestions for infection prevention actions.

[0093] "Location Information" means data about your current location collected using GPS or Wi-Fi location services.

[0094] An "artificial intelligence model" is an analytical model that uses machine learning algorithms. It learns trends in infection data and is used to calculate infection risk indices and generate behavioral recommendations.

[0095] "Real-time" refers to data collection, analysis, and information provision being carried out immediately without delay.

[0096] "Feedback data" refers to data about user behavior (such as location and preventative measures taken) that is sent back to the system, which analyzes it to help improve the model.

[0097] MODE FOR CARRYING OUT THE INVENTION

[0098] This invention is a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides action recommendations in real time using AI. The system is configured as follows.

[0099] Data collection

[0100] The server receives real-time infection data provided by medical institutions. This data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a relational database (e.g., MySQL) and performs preprocessing for analysis. Preprocessing includes missing value imputation and outlier detection and correction.

[0101] Data analysis

[0102] The server uses a trained artificial intelligence model (such as a model using TensorFlow or PyTorch) to calculate the infection risk for each region based on the collected infection data. The risk index is expressed numerically and color-coded, and displayed visually on a map. This allows users to understand the level of infection risk at a glance.

[0103] Obtaining user location information

[0104] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or Wi-Fi location services, allowing the server to grasp the user's current location in real time. The location information is transmitted securely using the HTTPS protocol.

[0105] Providing risk assessment and action recommendations

[0106] The server obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user, such as advice on avoiding rush hours, refraining from using public transportation, and wearing masks in high-risk areas.

[0107] Notification of recommended actions

[0108] The device notifies the user of the action recommendations received from the server via a pop-up or push notification, and displays additional details as needed.

[0109] User Behavior and Feedback

[0110] Users can take specific actions to prevent infection, such as avoiding crowded times and wearing a mask in designated areas, according to the recommended actions.

[0111] Feedback data collection and analysis

[0112] The device feeds back user behavior data (such as location information and the implementation status of preventive measures) to the server. The server analyzes the collected feedback data to evaluate and improve the performance of the AI ​​model. This feedback data is used to improve the accuracy of future behavioral recommendations.

[0113] Specific examples

[0114] Morning commute scenario

[0115] 1. The server receives the latest infection data from each medical institution, analyzes it, and detects high infection risks around specific stations in Tokyo.

[0116] 2. Let's say the user is on their morning commute and heading to Shinjuku Station.

[0117] 3. The device sends the user's current location (around Shinjuku Station) to the server.

[0118] 4. The server detects that the area around Shinjuku Station is a high-risk area and generates specific recommendations for actions, such as "avoiding rush hours," "switching to remote work if possible," and "always wearing a mask at the station and maintaining social distance."

[0119] 5. The device notifies the user of these recommendations and encourages them to act on them.

[0120] 6. Users should follow these guidelines and take measures to prevent infection, such as avoiding travel during designated times and wearing a mask, to reduce the risk of infection.

[0121] Prompt Sentence Examples

[0122] Here is an example of a prompt to input to a generative AI model:

[0123] Design a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides behavioral recommendations in real time. Include a scenario in which the server receives the infection data and notifies the user via their device.

[0124] The present invention allows users to receive the latest infection risk information and optimal action guidelines in real time, enabling them to take appropriate infection prevention actions, thereby allowing them to live their daily lives with peace of mind.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1: Data collection

[0127] The server uses APIs and data transfer protocols to collect real-time infection data from medical institutions. As input, it receives data provided by each medical institution, such as the latest number of infected people, the number of new infected people, age group, severity, and location of the outbreak. The server stores this data in a relational database such as MySQL. As preprocessing, it also performs missing value completion and outlier detection and correction. As output, it obtains data in a format suitable for analysis.

[0128] Step 2: Data analysis

[0129] The server loads the preprocessed data from the database and performs analysis using an AI model. The infection data collected and preprocessed in step 1 is used as input. Machine learning libraries such as TensorFlow and PyTorch are used for the analysis. The AI ​​model has learned the trends in the number of infected people and their geographical distribution, and calculates the infection risk based on this. The output is a numerical infection risk index for each region, which is displayed visually using color coding.

[0130] Step 3: Obtaining user location information

[0131] The device obtains the user's current location and sends it to the server. As input, it periodically obtains the user's location using GPS or Wi-Fi location services. The device securely transmits this location information to the server using the HTTPS protocol. As output, real-time updated user location information is sent to the server.

[0132] Step 4: Risk assessment and action recommendations

[0133] The server obtains the latest infection risk index for the area based on the user's current location and generates specific behavioral recommendations using an AI model. The inputs are the infection risk index obtained in step 2 and the user's location information obtained in step 3. The analysis combines the user's current location and the risk index for the surrounding area to make an evaluation. The output is specific behavioral recommendations such as "avoiding busy times," "avoiding the use of public transportation," and "ensuring the wearing of masks."

[0134] Step 5: Notification of action recommendations

[0135] The device notifies the user of the recommended actions received from the server. As input, the device receives the recommended actions generated in step 4 from the server. The notification is in the form of a pop-up or push notification, and is immediately visible to the user. As output, the recommended actions are displayed in a format that the user can check.

[0136] Step 6: User Action

[0137] The user takes infection prevention actions according to the recommended actions notified from the device. For example, they take actions such as avoiding crowded times or wearing a mask in designated areas. The recommended information notified in step 5 is used as input. By taking the action, the risk of infection is reduced.

[0138] Step 7: Collect and analyze feedback data

[0139] The device collects user behavior data (such as location information and the status of infection prevention measures) and feeds it back to the server. As input, data on the user's behavior is collected and sent to the server using the HTTPS protocol. The server analyzes the feedback data to evaluate and improve the performance of the AI ​​model. As output, the accuracy of behavioral recommendations for future visits is improved.

[0140] (Application example 1)

[0141] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0142] To prevent the spread of infectious diseases, it is important to assess the infection risk in specific areas and locations in real time and recommend appropriate actions to users. However, conventional technologies have not adequately provided specific behavioral recommendations based on real-time data analysis and infection risk. Furthermore, there has been a lack of a means to provide users with route information with low infection risk while in a moving vehicle. As a result, appropriate actions to reduce the risk of infection cannot be taken, posing a risk of infection spreading.

[0143] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0144] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for evaluating the infection risk at a specific location based on the user location information and providing recommended actions in real time, means for calculating a travel route with a low infection risk based on the vehicle's current location and destination and providing passengers with the route and recommended actions via an in-vehicle display or audio notification, and means for detecting approach to a high-risk point on the route and warning the passengers. This makes it possible to recommend actions with a low infection risk to the user in real time and to instruct appropriate infection prevention measures even while traveling to a specific location.

[0145] "Infection data" refers to information provided by medical institutions, such as the number of infected people, the number of new infections, age, severity, and location of the infection.

[0146] "Infection risk" is an indicator of the risk of infection for each region or location, calculated using an AI model based on collected infection data.

[0147] "Action recommendations" are guidelines and advice that suggest specific infection prevention actions to users.

[0148] "Location information" is data about the current location of a user or vehicle obtained using GPS or other location services.

[0149] The "server" is a central control device for collecting infection data, analyzing it, generating recommendations, etc.

[0150] "Data collection means" refers to a system for receiving infection data from medical institutions and storing it in a database.

[0151] The "data analysis means" is an analytical device that uses an AI model to calculate the infection risk for each region based on collected infection data.

[0152] The "user location information acquisition means" is a mechanism for acquiring current location information of a user or vehicle and transmitting it to a server.

[0153] The "route calculation means" is an algorithm that calculates a travel route with a low risk of infection based on the vehicle's current location and destination.

[0154] "Warning means" is a mechanism for detecting the approach of high-risk points on the route and warning passengers.

[0155] A "visualization means" is a device or software for visually displaying the calculated infection risk.

[0156] "Feedback data" refers to evaluation data provided to the system, such as user behavior data, location information, and the implementation status of preventive measures.

[0157] The detailed description of the embodiment of the present invention is divided into three main processes: collecting infection data, analyzing it, and providing behavioral recommendations.

[0158] 1. Data Collection

[0159] The server receives real-time infection data provided by each medical institution, including the number of infected people, the number of new infections, age, severity, location of the infection, etc. The collected data is stored in a database and preprocessed for subsequent analysis.

[0160] 2. Data Analysis

[0161] The server uses an AI model based on the collected infection data to calculate the infection risk for each region. This AI model uses a trained algorithm to analyze past trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded, visually indicating the level of infection risk.

[0162] 3. Obtaining User Location Information and Risk Assessment

[0163] The user's device acquires location information using GPS and other location services and sends it to the server, allowing the server to grasp the user's current location in real time. The server then obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user.

[0164] 4. Example of an automobile

[0165] When this invention is applied to an autonomous vehicle, the following functions are further added.

[0166] Route calculation

[0167] The server calculates a route with a low risk of infection based on the vehicle's current location and destination, taking into account the infection risk index and road congestion. The calculated route information is provided to passengers via an in-car display and voice notification system.

[0168] Warning function

[0169] The server will alert passengers when they are approaching high-risk areas. The alerts will be delivered as audio or visual notifications, prompting passengers to take additional action to prevent infection.

[0170] 5. Visualization and Feedback

[0171] The calculated infection risk is visualized using graphs and color-coded maps. In addition, user behavior data (e.g., selection of avoidance routes, implementation of preventive measures, etc.) is sent to the server as feedback. The feedback data is used to evaluate and improve the performance of the AI ​​model.

[0172] Specific examples

[0173] For example, if a user is currently near Shinjuku Station and planning to travel to Tokyo Station, the system will analyze the latest infection data for the area and suggest routes with a low risk of infection. It will also provide advice on changing departure times to avoid peak times. This information is communicated to passengers via in-car displays and voice notification systems.

[0174] Prompt Sentence Examples

[0175] Below are some example prompts that can be used to prompt an AI model to generate behavioral recommendations based on infection risk.

[0176] Current location: "35.6895, 139.6917" (Shinjuku Station)

[0177] Destination: "35.6812, 139.7649" (Tokyo Station)

[0178] Based on current infection data, suggest routes with low risk of infection.

[0179] Also, suggest the best time to leave to avoid times when the risk of infection is higher.

[0180] This allows users to receive optimal guidelines for action in real time and reduce the risk of infection.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1: Data collection

[0183] The server receives real-time infection data from medical institutions. This infection data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The input is data from medical institutions, and the output is the collected dataset. The server stores this dataset in a database and performs preprocessing for subsequent analysis.

[0184] Step 2: Data analysis

[0185] The server uses the collected infection data and an AI model to calculate the infection risk for each region. The input is the dataset collected in step 1, and the output is an infection risk index for each region. This analysis uses an AI model to generate the infection risk index. Specifically, the server applies the AI ​​model to analyze the increase / decrease trends in the number of infected people and their geographical distribution.

[0186] Step 3: Obtaining user location information

[0187] The device obtains the user's current location using GPS or other location information services and sends that information to the server. The input is the current location information obtained by the device, and the output is the user's location data sent to the server. This allows the server to know the user's current location in real time.

[0188] Step 4: Risk assessment and action recommendation generation

[0189] The server obtains the latest infection risk index for the area based on the user's current location and generates specific behavioral recommendations using an AI model. The input is the infection risk index from step 2 and the location data from step 3, and the output is behavioral recommendations for the user. Specifically, the server performs a risk assessment and generates recommendations such as "avoiding busy times," "switching to remote work," and "ensuring the wearing of masks."

[0190] Step 5: Calculate the travel path

[0191] The server calculates a travel route with a low risk of infection based on the vehicle's current location and destination. The inputs are the vehicle's location data, destination information, and the infection risk index from step 2, and the output is a recommended low-risk travel route. Specifically, the server calculates the optimal route by taking into account road congestion and infection risk.

[0192] Step 6: Real-time notifications and alerts

[0193] The device notifies the user of the recommended actions and route information received from the server. The input is the recommended actions and route information generated by the server, and the output is a notification to the user. Specifically, the device uses pop-ups and audio notifications to warn the user about approaching high-risk locations and provides additional guidelines for action.

[0194] Step 7: Collect and analyze feedback

[0195] The device feeds back user behavior data (location information and implementation status of preventive measures) to the server. The input is the user behavior data, and the output is analyzed feedback information. The server analyzes the feedback data and uses it to improve the performance of the AI ​​model. Specifically, it analyzes the collected data and improves the accuracy of recommendations from the next time onwards.

[0196] The above are the processing steps of the system that realizes this application example.

[0197] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0198] This invention combines a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides real-time AI-based action recommendations with an emotion engine that recognizes the user's emotions. This makes it possible to adjust recommendations for infection prevention actions according to the user's emotional state, providing more effective infection prevention support to users. The system is configured as follows:

[0199] 1. Data Collection

[0200] The server receives real-time infection data provided by medical institutions, including the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis.

[0201] 2. Data Analysis

[0202] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded to visually indicate the level of infection risk.

[0203] 3. Obtaining user location information

[0204] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or other location services, allowing the server to determine the user's current location in real time.

[0205] 4. Emotion recognition

[0206] The device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine uses image and audio analysis techniques to identify the user's current emotional state (e.g., joy, sadness, anxiety, stress, etc.). The recognized emotion data is sent to the server.

[0207] 5. Risk assessment and action recommendations

[0208] The server obtains and evaluates the latest infection risk index for the area based on the user's current location. This evaluation is combined with the user's emotional data obtained from the emotion engine, and specific behavioral recommendations are generated using an AI model. For example, if the user is feeling anxious, advice that takes their emotions into consideration is provided, such as "avoid crowds and rest in a quiet place" and "increase online communication."

[0209] 6. Recommendation Notification

[0210] The server sends the generated action recommendations to the device. Notifications are sent in the form of pop-up or push notifications, and additional details are displayed as needed. In particular, notifications that correspond to the user's emotions may be delivered as text or voice messages.

[0211] 7. User Behavior and Feedback

[0212] Users can take preventative measures to prevent infection by following the recommended actions. For example, they can take specific actions such as wearing a mask in designated areas and avoiding crowded places. In addition, by taking emotionally sensitive actions, it is possible to reduce psychological stress.

[0213] 8. Feedback Data Collection and Analysis

[0214] The device collects user behavioral and emotional data and periodically sends it back to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data is used to improve the accuracy of future recommendations.

[0215] Specific examples

[0216] Internal meeting scenario

[0217] 1. The server receives the latest infection data and detects that a specific commercial area in Tokyo is at high risk of infection.

[0218] 2. Assume the user works in an office within the commercial area.

[0219] 3. The device sends the user's current location (office) to the server.

[0220] 4. The device's emotion engine recognizes when the user is feeling stressed or anxious during the meeting.

[0221] 5. The server assesses the risk of infection around the office and generates recommendations that take into account emotions, such as "taking a break to relax" and "listening to music to relieve stress," in addition to standard infection prevention actions such as "opening windows to ventilate" and "holding meetings while maintaining distance."

[0222] 6. The device notifies the user of these recommendations, for example, by displaying specific advice such as "Take a short break and refresh yourself."

[0223] 7. Users must follow these guidelines to take precautions against infection and take care of their emotions.

[0224] The above is an embodiment of the invention. The present invention enables highly accurate infection risk assessment and behavior recommendations that take into account the user's emotional state, allowing users to live their daily lives with greater peace of mind.

[0225] The processing flow will be explained below.

[0226] Step 1: Collect data

[0227] The server periodically retrieves infection data from medical institution databases. The retrieved data includes information such as the number of infected people, the number of new infections, age, severity, and location of the infection. The retrieved data is then stored in the system's database.

[0228] Step 2: Preprocessing the data

[0229] The server performs data cleaning (removal of duplicate data, completion of missing values, etc.) and data standardization (normalization of values, etc.) to make the collected infection data easier to analyze. The preprocessed data is used for infection risk diagnosis.

[0230] Step 3: Infection risk analysis

[0231] The server uses an AI model to calculate the infection risk for each region based on the preprocessed data. The infection risk index is calculated by taking into account the trend in the number of infected people and their geographic distribution, and this quantifies the infection risk for each region.

[0232] Step 4: Obtaining location information

[0233] The user's device (smartphone or tablet) uses location information services to obtain the user's current location. Location information is collected in real time using GPS, Wi-Fi, and Bluetooth and is updated periodically.

[0234] Step 5: Send location information

[0235] The device transmits the acquired user's current location information to the server, allowing the server to grasp the user's real-time location.

[0236] Step 6: Obtaining emotion data

[0237] The device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine identifies the user's emotional state by analyzing the user's facial expressions using the camera and the tone of voice using the microphone. The recognized emotion data is sent to the server.

[0238] Step 7: Risk Assessment

[0239] The server obtains and evaluates the latest infection risk index for the area based on the user's current location, thereby determining the infection risk level of the user's current location in real time.

[0240] Step 8: Generate action recommendations

[0241] The server uses an AI model to generate specific recommendations based on the infection risk index and the user's emotional data obtained from the emotion engine. For example, if a user is feeling anxious, the server will create advice that takes their emotions into consideration, such as "avoid crowds and rest in a quiet place" or "increase online communication."

[0242] Step 9: Recommendation Notification

[0243] The server sends the generated action recommendations to the device. Notifications are sent in the form of push notifications or pop-ups, and additional details are displayed as needed. Notifications can also be sent in the form of text or voice messages depending on the user's emotions.

[0244] Step 10: Implementing User Actions

[0245] Users can take specific actions to prevent infection according to the recommended actions they receive, such as wearing a mask in designated high-risk areas or resting in a quiet place with a low risk of infection.

[0246] Step 11: Collect feedback data

[0247] The device collects user behavioral data (location information, implementation status of preventive measures, etc.) and emotional data, and periodically feeds this data back to the server, allowing the system to understand the user's behavioral and emotional history.

[0248] Step 12: Analyze the feedback data

[0249] The server analyzes the collected feedback data and uses it as learning data for the AI ​​model. The analysis results are used to improve the accuracy of future action recommendations.

[0250] Step 13: Update the AI ​​model

[0251] The server uses the feedback data to regularly update and refine the AI ​​model, improving the accuracy of infection risk assessment and behavioral recommendations, and providing users with more reliable information.

[0252] Through these steps, this system provides accurate infection risk information in real time and recommends optimal actions based on the user's emotional state, supporting users in taking infection prevention actions.

[0253] Example 2

[0254] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0255] In modern society, technology to quickly predict the spread of infectious diseases and take preventative measures is extremely important. However, current technology has limitations in risk assessment and behavioral recommendations based on infection data, and in particular, it lacks individually optimized advice that takes user emotions into consideration, preventing more effective infection spread prevention. Furthermore, due to insufficient capabilities for collecting, analyzing, and providing feedback on real-time data from diverse data sources, there is a need for accurate and immediate risk assessment and behavioral recommendations.

[0256] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0257] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for recognizing the user's emotions, means for adjusting the recommended actions using the emotion data, and means for evaluating the infection risk in a specific location based on the user's location information and providing the recommended actions in real time. This enables highly accurate infection risk assessment that takes the user's emotional state into account and individually optimized recommendations for infection prevention actions.

[0258] "Infection data" refers to information related to infectious diseases, such as the number of infected people, the number of new infections, age, severity, and location of the outbreak.

[0259] "Infection risk" refers to the numerical or index expression of the possibility of an infectious disease occurring and spreading in a particular area or location.

[0260] "AI model" refers to a mathematical model used to analyze data using machine learning algorithms and predict infection risk.

[0261] "User Location Information" means your geographic location data obtained using GPS or other location services.

[0262] "Emotion engine" refers to a software or hardware system that uses image and audio analysis techniques to recognize a user's emotional state.

[0263] "Behavioral recommendations" refer to suggestions for specific infection prevention actions and psychological care provided based on the infection risk and the user's emotional state.

[0264] "Real-time" refers to data collection, analysis, and delivery of results in near-instantaneous time.

[0265] "Feedback data" refers to data relating to changes in user behavior and emotions that is used to improve and learn from the system.

[0266] An "algorithm" refers to a definite procedure or computational method for solving a particular problem.

[0267] "Visualization" refers to a method of visually displaying data or information to make it easier to understand.

[0268] This invention combines a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides real-time AI-based action recommendations with an emotion engine that recognizes the user's emotions. This makes it possible to adjust recommendations for infection prevention actions according to the user's emotional state, providing more effective infection prevention support to users.

[0269] The server receives real-time infection data provided by medical institutions. This data includes the number of infected people, the number of new infections, age groups, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis. The database management system used is MySQL or similar.

[0270] Next, the server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. This AI model uses machine learning algorithms such as TensorFlow. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution, and expresses a risk index as a number and color-coded value to visually indicate the level of infection risk.

[0271] The device periodically obtains the user's current location using GPS or other location services and sends it to the server, allowing the server to grasp the user's current location in real time.

[0272] Additionally, the device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine uses image and voice analysis technologies to identify the user's current emotional state (e.g., joy, sadness, anxiety, stress, etc.). OpenCV is used for image analysis, and the Google Speech-to-Text API is used for voice analysis. The recognized emotion data is sent to the server.

[0273] The server obtains and evaluates the latest infection risk index for the area based on the user's current location. This evaluation is combined with the user's emotional data obtained from the emotion engine, and specific behavioral recommendations are generated using an AI model. For example, if the user is feeling anxious, advice that takes their emotions into consideration is provided, such as "avoid crowds and rest in a quiet place" and "increase online communication."

[0274] The generated action recommendations are sent from the server to the device. Notifications are sent in the form of pop-up or push notifications, and additional details are displayed as needed. In particular, notifications that correspond to the user's emotions may be delivered as text or voice messages.

[0275] Users can take preventative measures to prevent infection by following the recommended actions. For example, they can take specific actions such as wearing a mask in designated areas and avoiding crowded places. In addition, by taking emotionally sensitive actions, it is possible to reduce psychological stress.

[0276] The device collects user behavioral and emotional data and periodically sends it back to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data is used to improve the accuracy of future recommendations.

[0277] A specific example is a scenario during an internal meeting. The server receives the latest infection data and detects that a particular commercial area has a high risk of infection. Assuming the user works in an office within that commercial area, the device sends the user's current location (office) to the server. The device's emotion engine recognizes the user's emotional state, and the server generates recommended actions based on that data. For example, recommendations such as "open windows for ventilation," "hold the meeting while maintaining distance," and "take a break to relax" are notified to the device.

[0278] Example prompt sentence:

[0279] Imagine a situation where a user working in an office in a commercial area with a high risk of infection feels stressed or anxious during a meeting, and generate appropriate behavioral recommendations for that user. Specifically, include advice such as "open windows to ventilate," "conduct meetings while maintaining social distance," and "take breaks to relax."

[0280] The above is an embodiment of the invention. The present invention makes it possible to realize highly accurate infection risk assessment and behavior recommendations that take into account the emotional state of the user, allowing them to live their daily lives with peace of mind.

[0281] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0282] Step 1:

[0283] The server receives real-time infection data provided by medical institutions.

[0284] Input: Infection data from medical institutions (number of infected people, number of new infected people, age, severity, location of outbreak, etc.)

[0285] Specific operation: The server retrieves data via API using the HTTPS protocol and saves the received data in JSON format.

[0286] The extracted information is parsed according to the format and organized into an appropriate form.

[0287] Output: Infection data stored in a database.

[0288] Step 2:

[0289] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data.

[0290] Input: Preprocessed infection data

[0291] Specific operation: The server uses TensorFlow to apply a trained machine learning model to calculate a risk index for each region. The calculation results are displayed numerically and color-coded.

[0292] Output: Infection risk index (numerical, color-coded)

[0293] Step 3:

[0294] The device periodically obtains the user's current location information using GPS or other location information services and sends it to the server.

[0295] Input: User's current location information obtained from the GPS sensor

[0296] Specific operation: The device periodically uses location information services to obtain the user's current location and sends that data to the server via a POST request.

[0297] Output: Current location information sent to the server

[0298] Step 4:

[0299] The device is equipped with an emotion engine that recognizes the user's emotions and performs image and audio analysis.

[0300] Input: Face and voice data collected from the front camera and microphone

[0301] Specific operation: The device analyzes facial expressions using OpenCV, converts voice data into text using the Google Speech-to-Text API, and recognizes emotions. The recognized emotion data is then sent to the server.

[0302] Output: Emotion data (happiness, sadness, anxiety, stress, etc.)

[0303] Step 5:

[0304] The server generates recommended activities based on the user's current location and the latest infection risk index.

[0305] Input: User's current location, infection risk index, emotional data

[0306] Specific actions: The server takes into account the local infection risk index and the user's emotional state, and generates specific action recommendations using random forests and neural networks.

[0307] Output: Action recommendation (specific action suggestion)

[0308] Step 6:

[0309] The server transmits the generated behavioral recommendations to the terminal and notifies the user.

[0310] Input: Generated action recommendations

[0311] Specific operation: The server sends recommendation information in JSON format to the device, and the device notifies the user in the form of a push notification or a pop-up.

[0312] Output: Action recommendations notified to the user

[0313] Step 7:

[0314] Users then take specific infection prevention actions in accordance with the recommended actions.

[0315] Input: Recommended action notification from device

[0316] Specific actions: The user checks the notification and follows the instructions to take infection prevention measures, such as wearing a mask and avoiding crowded places.

[0317] Output: Practice infection prevention behaviors

[0318] Step 8:

[0319] The terminal collects the user's behavioral data and emotional data and feeds it back to the server.

[0320] Input: User behavior data, emotion data

[0321] Specific operation: The device periodically records changes in the user's behavior and emotions and sends the data to the server.

[0322] Output: Feedback data sent to the server

[0323] Step 9:

[0324] The server analyzes the received feedback data to evaluate and improve the performance of the AI ​​model.

[0325] Input: Feedback data

[0326] Specific operation: The server analyzes the collected feedback data and improves the accuracy of the AI ​​model by retraining it with new data.

[0327] Output: Improved AI model

[0328] (Application example 2)

[0329] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0330] Many conventional infection prevention systems assess infection risk and recommend actions to users, but because these systems do not take into account the user's emotional state, they have the problem of not being able to provide sufficient support to users who are feeling stressed or anxious. Users in areas with a higher risk of infection in particular need mental care, and a system that can address this is needed.

[0331] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0332] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for recognizing the user's emotions, and means for evaluating the infection risk in a specific location based on the user's location information and emotions and providing emotion-conscious behavior recommendations in real time. This makes it possible to provide appropriate infection prevention actions while taking the user's emotional state into consideration.

[0333] "Infection data" refers to information provided by medical institutions, such as the number of infected people, the number of new infections, age, severity, and location of the infection.

[0334] "Regional infection risk" refers to a risk index calculated by analyzing the trend in the number of infected people and their geographical distribution within a specific geographical area.

[0335] "Behavioral recommendations" refers to suggesting specific actions recommended for preventing infection based on the user's emotional state and location information.

[0336] "User Location Information" means information about a user's current location obtained through GPS or other location-based services.

[0337] "Emotion recognition" refers to the use of image and audio analysis techniques to identify a user's current emotional state.

[0338] The "infection risk index" refers to an index that expresses infection risk numerically and in color, calculated using an AI model.

[0339] "AI model" refers to the trained algorithm used to calculate infection risk.

[0340] "Feedback data" refers to data about actions performed by a user and their emotional state at the time.

[0341] A "generative AI model" refers to an AI algorithm that uses a specific prompt sentence as input to generate appropriate behavioral recommendations.

[0342] The system that embodies this invention consists of a server, a terminal, and a user, in order to collect infection data, calculate the infection risk for each region, and recommend infection prevention actions to users. Below, we will explain the specific processing steps of each element and the hardware and software used.

[0343] server

[0344] The server performs the following functions:

[0345] 1. Data Collection:

[0346] The server receives real-time infection data (number of infected people, number of new infections, age group, severity, location of outbreak, etc.) provided by medical institutions and stores it in a database.

[0347] Technologies used: Cloud platforms (e.g., AWS, Google Cloud), databases (e.g., MySQL, PostgreSQL)

[0348] 2. Data Analysis:

[0349] The server uses an AI model (machine learning libraries such as Scikit-learn and TensorFlow) to calculate the infection risk for each region based on the preprocessed infection data. The infection risk index is visualized numerically and color-coded.

[0350] Technologies used: Python, Scikit-learn, TensorFlow

[0351] 3. Action recommendation generation:

[0352] The server integrates the user's location information and emotional data and uses a generative AI model to create behavioral recommendations tailored to the user. For example, if the user feels anxious, the server generates advice such as "take a break in a quiet place."

[0353] Technology used: AI model (generative AI model)

[0354] 4. Recommendation Notification:

[0355] The server notifies the device of the generated action recommendations using a push notification service.

[0356] Technology used: Firebase Cloud Messaging (FCM)

[0357] Terminal

[0358] The device (smartphone) will:

[0359] 1. Obtaining user location information:

[0360] The terminal obtains its current location information using GPS or other location information services and periodically transmits it to the server.

[0361] Technologies used: GPS sensor, location services API

[0362] 2. Emotion recognition:

[0363] The device uses the user's camera and microphone to recognize the user's emotional state using an emotion engine (e.g., OpenCV for facial recognition technology and TensorFlow for voice analysis), and sends the data to the server.

[0364] Technologies used: OpenCV, TensorFlow, device camera, microphone

[0365] 3. Receiving notifications:

[0366] The device receives the action recommendations sent from the server and presents them to the user as a pop-up or push notification.

[0367] Technologies used: Notification API, FCM

[0368] User

[0369] The user plays the following roles:

[0370] 1. Implementing action recommendations:

[0371] Users practice infection prevention behaviors according to behavioral recommendations provided by the device, such as wearing a mask in designated areas.

[0372] 2. Providing Feedback:

[0373] Users can send their actions and results as feedback from their devices to the server, contributing to the improvement of the AI ​​model.

[0374] Specific examples

[0375] Internal meeting scenario

[0376] 1. The server receives the latest infection data and detects that a particular commercial area is at high risk of infection.

[0377] 2. Assume the user works in an office within the commercial area.

[0378] 3. The device sends the user's current location (office) to the server.

[0379] 4. The device's emotion engine recognizes when the user is feeling stressed or anxious during the meeting.

[0380] 5. The server assesses the risk of infection around the office and generates recommendations that take into account emotions, such as "taking a break to relax" and "listening to music to relieve stress," in addition to standard infection prevention actions such as "opening windows to ventilate" and "holding meetings while maintaining distance."

[0381] 6. The device will notify the user of these recommendations, for example, by displaying specific advice such as "Take a short break and refresh yourself."

[0382] 7. Users must follow these guidelines to take precautions against infection and take care of their emotions.

[0383] Example prompts

[0384] Currently, the user is located in Shinjuku Ward, Tokyo, and the number of new infections is increasing. The user's emotional state is anxious and stressed. Please generate behavioral recommendations appropriate for the user.

[0385] Example output:

[0386] Your current location poses a high risk of infection. We recommend the following actions:

[0387] Avoid crowds

[0388] Take a break in a quiet place

[0389] Wear a mask at all times

[0390] Communicate online when necessary

[0391] Exercise moderately to reduce stress

[0392] This example shows how the present invention takes into account a user's emotional state and infection risk to suggest personalized infection prevention actions.

[0393] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0394] Step 1: Data collection

[0395] The server receives real-time infection data provided by medical institutions and stores it in a database. The collected data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The input is the infection data sent from medical institutions, and the output is preprocessed infection data stored in the server's database.

[0396] Step 2: Data analysis

[0397] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. This AI model is trained using machine learning libraries such as Scikit-learn and TensorFlow. The input is infection data stored in the database, and the output is the infection risk index calculated for each region. The risk index is visualized using numbers and color coding and displayed on a dashboard, etc.

[0398] Step 3: Obtaining user location information

[0399] The device acquires the user's current location information using the smartphone's GPS sensor and location information services, and sends it to the server. The input is the GPS data collected by the device, and the output is the user's location information received by the server.

[0400] Step 4: Emotion Recognition

[0401] To recognize the user's emotional state, the device uses a camera and microphone to perform analysis using an emotion engine. Specifically, it uses facial expression analysis using OpenCV and voice analysis using TensorFlow. The input is camera footage and voice data obtained from the user, and the output is recognized emotion data (e.g., joy, sadness, anxiety, stress, etc.). This emotion data is also sent to the server.

[0402] Step 5: Generate action recommendations

[0403] The server integrates the user's location information and emotional data and uses a generative AI model to create behavioral recommendations appropriate for the user. The input is the user's location information, emotional data, and existing infection risk index, and the output is a specific behavioral recommendation. For example, actions such as "avoid crowds" and "take a break in a quiet place" are generated.

[0404] Step 6: Recommendation Notification

[0405] The server sends the generated action recommendations to the device, and the device notifies the user. The notification is sent in the form of a push notification using Firebase Cloud Messaging (FCM). The input is the action recommendations generated by the server, and the output is the notification content displayed on the device.

[0406] Step 7: User feedback

[0407] The user follows the recommended actions to prevent infection and records the results as feedback on the device. The input is the data on the actions taken by the user, and the output is the feedback data recorded by the device.

[0408] Step 8: Collect and analyze feedback data

[0409] The device collects user feedback data and periodically sends it to the server. The server analyzes this data and updates the AI ​​model. The input is the feedback data sent from the device, and the output is the updated AI model. This data is used to improve the accuracy of future action recommendations.

[0410] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0411] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0412] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0413] [Second embodiment]

[0414] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0415] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0416] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0417] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0418] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0419] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0420] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0421] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0422] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0423] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0424] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0425] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0426] This invention is a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides action recommendations in real time using AI. The system is configured as follows.

[0427] 1. Data Collection

[0428] The server receives real-time infection data provided by medical institutions, including the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis.

[0429] 2. Data Analysis

[0430] The server uses an AI model to calculate the infection risk for each region based on the collected infection data. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded, visually indicating the level of infection risk.

[0431] 3. Obtaining user location information

[0432] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or other location services, allowing the server to determine the user's current location in real time.

[0433] 4. Risk assessment and action recommendations

[0434] The server obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user, such as advice on avoiding rush hours, refraining from using public transportation, and wearing masks in high-risk areas.

[0435] 5. Notification of recommended actions

[0436] The device notifies the user of the action recommendations received from the server via a pop-up or push notification, and displays additional details as needed.

[0437] 6. User Behavior and Feedback

[0438] Users can take specific actions to prevent infection, such as avoiding crowded times and wearing a mask in designated areas, according to the recommended actions.

[0439] 7. Feedback data collection and analysis

[0440] The device feeds back user behavior data (location information, prevention measures implementation status, etc.) to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data will be used to improve the accuracy of recommendations in the future.

[0441] Specific examples

[0442] Morning commute scenario

[0443] 1. The server receives the latest infection data from each medical institution, analyzes it, and detects high infection risks around specific stations in Tokyo.

[0444] 2. Let's say the user is on their morning commute and heading to Shinjuku Station.

[0445] 3. The device sends the user's current location (around Shinjuku Station) to the server.

[0446] 4. The server detects that the area around Shinjuku Station is a high-risk area and generates specific recommendations for actions, such as "avoiding rush hours," "switching to remote work if possible," and "always wearing a mask at the station and maintaining social distance."

[0447] 5. The device notifies the user of these recommendations and encourages them to act on them.

[0448] 6. Users should follow these guidelines and take measures to prevent infection, such as avoiding travel during designated times and wearing a mask, to reduce the risk of infection.

[0449] The above is an embodiment of the invention. The present invention allows users to receive the latest infection risk information and optimal action guidelines in real time, enabling them to take appropriate infection prevention actions. This allows them to live their daily lives with peace of mind.

[0450] The processing flow will be explained below.

[0451] Step 1: Collect data

[0452] The server periodically retrieves infection data from medical institution databases. The collected data includes information such as the number of infected people, the number of new infections, age, severity, and location of the infection. The retrieved data is stored in the system's database.

[0453] Step 2: Preprocessing the data

[0454] The server performs data cleaning (removal of duplicate data, completion of missing values, etc.) and data standardization (normalization of values, etc.) to make the collected infection data easier to analyze. The preprocessed data is used for infection risk diagnosis.

[0455] Step 3: Infection risk analysis

[0456] The server uses an AI model to calculate the infection risk for each region based on the preprocessed data. The infection risk index is calculated by taking into account the trend in the number of infected people and their geographic distribution, and this quantifies the infection risk for each region.

[0457] Step 4: Obtaining location information

[0458] The user's device (smartphone or tablet) uses location information services to obtain the user's current location. Location information is collected in real time using GPS, Wi-Fi, and Bluetooth and is updated periodically.

[0459] Step 5: Send location information

[0460] The device transmits the acquired user's current location information to the server, allowing the server to grasp the user's real-time location.

[0461] Step 6: Risk assessment

[0462] The server obtains and evaluates the latest infection risk index for the area based on the user's current location, thereby determining the infection risk level of the user's current location in real time.

[0463] Step 7: Generate action recommendations

[0464] The server uses an AI model to generate specific recommendations for users based on the assessed infection risk index, such as "avoid crowds," "wear a mask," and "wash your hands thoroughly" in high-risk areas.

[0465] Step 8: Recommendation Notification

[0466] The server sends the generated behavioral recommendations to the device, and notifications are sent in real time via push notifications, encouraging users to take infection prevention measures.

[0467] Step 9: User behavior feedback

[0468] Users can take specific actions to prevent infection based on the recommendations they receive, such as wearing a mask in high-risk areas and avoiding crowded places at certain times.

[0469] Step 10: Collect feedback data

[0470] The device collects user behavior data (location information, implementation status of preventive measures, etc.) and periodically feeds it back to the server, allowing the system to understand the user's behavioral history.

[0471] Step 11: Analyze feedback data

[0472] The server analyzes the collected feedback data and uses it as training data for the AI ​​model. The analysis results are used to improve the accuracy of future action recommendations.

[0473] Step 12: Update the AI ​​model

[0474] The server uses the feedback data to regularly update and refine the AI ​​model, improving the accuracy of infection risk assessment and behavioral recommendations, and providing users with more reliable information.

[0475] Through these steps, the system provides accurate infection risk information and optimal behavior recommendations in real time, supporting users in taking infection prevention actions.

[0476] Example 1

[0477] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0478] To prevent the spread of infectious diseases, it is important to provide accurate infection risk information and appropriate guidelines in real time. However, current systems suffer from delays in the collection and analysis of infection data, or lack the functionality to provide immediate action recommendations using users' location information. As a result, users are unable to take appropriate infection prevention actions based on the latest risk information, which increases the risk of infection.

[0479] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0480] In this invention, the server includes means for collecting infection data from medical institutions, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring and transmitting user location information, and means for evaluating the infection risk in a specific location based on the user location information and providing recommended actions in real time. This allows the user to always receive appropriate recommended actions in real time based on the latest infection risk information, thereby effectively preventing the spread of infectious diseases.

[0481] "Infection data" refers to a variety of data related to infectious diseases, such as the number of infected people, the number of new infections, age, severity, and location of the outbreak.

[0482] "Infection risk" is an indicator of the possibility of the spread of an infectious disease in a particular area or location. Infection risk is calculated based on collected infection data.

[0483] "Recommendations" refers to guidelines and advice provided to users by the system, including suggestions for infection prevention actions.

[0484] "Location Information" means data about your current location collected using GPS or Wi-Fi location services.

[0485] An "artificial intelligence model" is an analytical model that uses machine learning algorithms. It learns trends in infection data and is used to calculate infection risk indices and generate behavioral recommendations.

[0486] "Real-time" refers to data collection, analysis, and information provision being carried out immediately without delay.

[0487] "Feedback data" refers to data about user behavior (such as location and preventative measures taken) that is sent back to the system, which analyzes it to help improve the model.

[0488] MODE FOR CARRYING OUT THE INVENTION

[0489] This invention is a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides action recommendations in real time using AI. The system is configured as follows.

[0490] Data collection

[0491] The server receives real-time infection data provided by medical institutions. This data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a relational database (e.g., MySQL) and performs preprocessing for analysis. Preprocessing includes missing value imputation and outlier detection and correction.

[0492] Data analysis

[0493] The server uses a trained artificial intelligence model (such as a model using TensorFlow or PyTorch) to calculate the infection risk for each region based on the collected infection data. The risk index is expressed numerically and color-coded, and displayed visually on a map. This allows users to understand the level of infection risk at a glance.

[0494] Obtaining user location information

[0495] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or Wi-Fi location services, allowing the server to grasp the user's current location in real time. The location information is transmitted securely using the HTTPS protocol.

[0496] Providing risk assessment and action recommendations

[0497] The server obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user, such as advice on avoiding rush hours, refraining from using public transportation, and wearing masks in high-risk areas.

[0498] Notification of recommended actions

[0499] The device notifies the user of the action recommendations received from the server via a pop-up or push notification, and displays additional details as needed.

[0500] User Behavior and Feedback

[0501] Users can take specific actions to prevent infection, such as avoiding crowded times and wearing a mask in designated areas, according to the recommended actions.

[0502] Feedback data collection and analysis

[0503] The device feeds back user behavior data (such as location information and the implementation status of preventive measures) to the server. The server analyzes the collected feedback data to evaluate and improve the performance of the AI ​​model. This feedback data is used to improve the accuracy of future behavioral recommendations.

[0504] Specific examples

[0505] Morning commute scenario

[0506] 1. The server receives the latest infection data from each medical institution, analyzes it, and detects high infection risks around specific stations in Tokyo.

[0507] 2. Let's say the user is on their morning commute and heading to Shinjuku Station.

[0508] 3. The device sends the user's current location (around Shinjuku Station) to the server.

[0509] 4. The server detects that the area around Shinjuku Station is a high-risk area and generates specific recommendations for actions, such as "avoiding rush hours," "switching to remote work if possible," and "always wearing a mask at the station and maintaining social distance."

[0510] 5. The device notifies the user of these recommendations and encourages them to act on them.

[0511] 6. Users should follow these guidelines and take measures to prevent infection, such as avoiding travel during designated times and wearing a mask, to reduce the risk of infection.

[0512] Prompt Sentence Examples

[0513] Here is an example of a prompt to input to a generative AI model:

[0514] Design a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides behavioral recommendations in real time. Include a scenario in which the server receives the infection data and notifies the user via their device.

[0515] The present invention allows users to receive the latest infection risk information and optimal action guidelines in real time, enabling them to take appropriate infection prevention actions, thereby allowing them to live their daily lives with peace of mind.

[0516] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0517] Step 1: Data collection

[0518] The server uses APIs and data transfer protocols to collect real-time infection data from medical institutions. As input, it receives data provided by each medical institution, such as the latest number of infected people, the number of new infected people, age group, severity, and location of the outbreak. The server stores this data in a relational database such as MySQL. As preprocessing, it also performs missing value completion and outlier detection and correction. As output, it obtains data in a format suitable for analysis.

[0519] Step 2: Data analysis

[0520] The server loads the preprocessed data from the database and performs analysis using an AI model. The infection data collected and preprocessed in step 1 is used as input. Machine learning libraries such as TensorFlow and PyTorch are used for the analysis. The AI ​​model has learned the trends in the number of infected people and their geographical distribution, and calculates the infection risk based on this. The output is a numerical infection risk index for each region, which is displayed visually using color coding.

[0521] Step 3: Obtaining user location information

[0522] The device obtains the user's current location and sends it to the server. As input, it periodically obtains the user's location using GPS or Wi-Fi location services. The device securely transmits this location information to the server using the HTTPS protocol. As output, real-time updated user location information is sent to the server.

[0523] Step 4: Risk assessment and action recommendations

[0524] The server obtains the latest infection risk index for the area based on the user's current location and generates specific behavioral recommendations using an AI model. The inputs are the infection risk index obtained in step 2 and the user's location information obtained in step 3. The analysis combines the user's current location and the risk index for the surrounding area to make an evaluation. The output is specific behavioral recommendations such as "avoiding busy times," "avoiding the use of public transportation," and "ensuring the wearing of masks."

[0525] Step 5: Notification of action recommendations

[0526] The device notifies the user of the recommended actions received from the server. As input, the device receives the recommended actions generated in step 4 from the server. The notification is in the form of a pop-up or push notification, and is immediately visible to the user. As output, the recommended actions are displayed in a format that the user can check.

[0527] Step 6: User Action

[0528] The user takes infection prevention actions according to the recommended actions notified from the device. For example, they take actions such as avoiding crowded times or wearing a mask in designated areas. The recommended information notified in step 5 is used as input. By taking the action, the risk of infection is reduced.

[0529] Step 7: Collect and analyze feedback data

[0530] The device collects user behavior data (such as location information and the status of infection prevention measures) and feeds it back to the server. As input, data on the user's behavior is collected and sent to the server using the HTTPS protocol. The server analyzes the feedback data to evaluate and improve the performance of the AI ​​model. As output, the accuracy of behavioral recommendations for future visits is improved.

[0531] (Application example 1)

[0532] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0533] To prevent the spread of infectious diseases, it is important to assess the infection risk in specific areas and locations in real time and recommend appropriate actions to users. However, conventional technologies have not adequately provided specific behavioral recommendations based on real-time data analysis and infection risk. Furthermore, there has been a lack of a means to provide users with route information with low infection risk while in a moving vehicle. As a result, appropriate actions to reduce the risk of infection cannot be taken, posing a risk of infection spreading.

[0534] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0535] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for evaluating the infection risk at a specific location based on the user location information and providing recommended actions in real time, means for calculating a travel route with a low infection risk based on the vehicle's current location and destination and providing passengers with the route and recommended actions via an in-vehicle display or audio notification, and means for detecting approach to a high-risk point on the route and warning the passengers. This makes it possible to recommend actions with a low infection risk to the user in real time and to instruct appropriate infection prevention measures even while traveling to a specific location.

[0536] "Infection data" refers to information provided by medical institutions, such as the number of infected people, the number of new infections, age, severity, and location of the infection.

[0537] "Infection risk" is an indicator of the risk of infection for each region or location, calculated using an AI model based on collected infection data.

[0538] "Action recommendations" are guidelines and advice that suggest specific infection prevention actions to users.

[0539] "Location information" is data about the current location of a user or vehicle obtained using GPS or other location services.

[0540] The "server" is a central control device for collecting infection data, analyzing it, generating recommendations, etc.

[0541] "Data collection means" refers to a system for receiving infection data from medical institutions and storing it in a database.

[0542] The "data analysis means" is an analytical device that uses an AI model to calculate the infection risk for each region based on collected infection data.

[0543] The "user location information acquisition means" is a mechanism for acquiring current location information of a user or vehicle and transmitting it to a server.

[0544] The "route calculation means" is an algorithm that calculates a travel route with a low risk of infection based on the vehicle's current location and destination.

[0545] "Warning means" is a mechanism for detecting the approach of high-risk points on the route and warning passengers.

[0546] A "visualization means" is a device or software for visually displaying the calculated infection risk.

[0547] "Feedback data" refers to evaluation data provided to the system, such as user behavior data, location information, and the implementation status of preventive measures.

[0548] The detailed description of the embodiment of the present invention is divided into three main processes: collecting infection data, analyzing it, and providing behavioral recommendations.

[0549] 1. Data Collection

[0550] The server receives real-time infection data provided by each medical institution, including the number of infected people, the number of new infections, age, severity, location of the infection, etc. The collected data is stored in a database and preprocessed for subsequent analysis.

[0551] 2. Data Analysis

[0552] The server uses an AI model based on the collected infection data to calculate the infection risk for each region. This AI model uses a trained algorithm to analyze past trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded, visually indicating the level of infection risk.

[0553] 3. Obtaining User Location Information and Risk Assessment

[0554] The user's device acquires location information using GPS and other location services and sends it to the server, allowing the server to grasp the user's current location in real time. The server then obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user.

[0555] 4. Example of an automobile

[0556] When this invention is applied to an autonomous vehicle, the following functions are further added.

[0557] Route calculation

[0558] The server calculates a route with a low risk of infection based on the vehicle's current location and destination, taking into account the infection risk index and road congestion. The calculated route information is provided to passengers via an in-car display and voice notification system.

[0559] Warning function

[0560] The server will alert passengers when they are approaching high-risk areas. The alerts will be delivered as audio or visual notifications, prompting passengers to take additional action to prevent infection.

[0561] 5. Visualization and Feedback

[0562] The calculated infection risk is visualized using graphs and color-coded maps. In addition, user behavior data (e.g., selection of avoidance routes, implementation of preventive measures, etc.) is sent to the server as feedback. The feedback data is used to evaluate and improve the performance of the AI ​​model.

[0563] Specific examples

[0564] For example, if a user is currently near Shinjuku Station and planning to travel to Tokyo Station, the system will analyze the latest infection data for the area and suggest routes with a low risk of infection. It will also provide advice on changing departure times to avoid peak times. This information is communicated to passengers via in-car displays and voice notification systems.

[0565] Prompt Sentence Examples

[0566] Below are some example prompts that can be used to prompt an AI model to generate behavioral recommendations based on infection risk.

[0567] Current location: "35.6895, 139.6917" (Shinjuku Station)

[0568] Destination: "35.6812, 139.7649" (Tokyo Station)

[0569] Based on current infection data, suggest routes with low risk of infection.

[0570] Also, suggest the best time to leave to avoid times when the risk of infection is higher.

[0571] This allows users to receive optimal guidelines for action in real time and reduce the risk of infection.

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

[0573] Step 1: Data collection

[0574] The server receives real-time infection data from medical institutions. This infection data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The input is data from medical institutions, and the output is the collected dataset. The server stores this dataset in a database and performs preprocessing for subsequent analysis.

[0575] Step 2: Data analysis

[0576] The server uses the collected infection data and an AI model to calculate the infection risk for each region. The input is the dataset collected in step 1, and the output is an infection risk index for each region. This analysis uses an AI model to generate the infection risk index. Specifically, the server applies the AI ​​model to analyze the increase / decrease trends in the number of infected people and their geographical distribution.

[0577] Step 3: Obtaining user location information

[0578] The device obtains the user's current location using GPS or other location information services and sends that information to the server. The input is the current location information obtained by the device, and the output is the user's location data sent to the server. This allows the server to know the user's current location in real time.

[0579] Step 4: Risk assessment and action recommendation generation

[0580] The server obtains the latest infection risk index for the area based on the user's current location and generates specific behavioral recommendations using an AI model. The input is the infection risk index from step 2 and the location data from step 3, and the output is behavioral recommendations for the user. Specifically, the server performs a risk assessment and generates recommendations such as "avoiding busy times," "switching to remote work," and "ensuring the wearing of masks."

[0581] Step 5: Calculate the travel path

[0582] The server calculates a travel route with a low risk of infection based on the vehicle's current location and destination. The inputs are the vehicle's location data, destination information, and the infection risk index from step 2, and the output is a recommended low-risk travel route. Specifically, the server calculates the optimal route by taking into account road congestion and infection risk.

[0583] Step 6: Real-time notifications and alerts

[0584] The device notifies the user of the recommended actions and route information received from the server. The input is the recommended actions and route information generated by the server, and the output is a notification to the user. Specifically, the device uses pop-ups and audio notifications to warn the user about approaching high-risk locations and provides additional guidelines for action.

[0585] Step 7: Collect and analyze feedback

[0586] The device feeds back user behavior data (location information and implementation status of preventive measures) to the server. The input is the user behavior data, and the output is analyzed feedback information. The server analyzes the feedback data and uses it to improve the performance of the AI ​​model. Specifically, it analyzes the collected data and improves the accuracy of recommendations from the next time onwards.

[0587] The above are the processing steps of the system that realizes this application example.

[0588] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0589] This invention combines a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides real-time AI-based action recommendations with an emotion engine that recognizes the user's emotions. This makes it possible to adjust recommendations for infection prevention actions according to the user's emotional state, providing more effective infection prevention support to users. The system is configured as follows:

[0590] 1. Data Collection

[0591] The server receives real-time infection data provided by medical institutions, including the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis.

[0592] 2. Data Analysis

[0593] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded to visually indicate the level of infection risk.

[0594] 3. Obtaining user location information

[0595] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or other location services, allowing the server to determine the user's current location in real time.

[0596] 4. Emotion recognition

[0597] The device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine uses image and audio analysis techniques to identify the user's current emotional state (e.g., joy, sadness, anxiety, stress, etc.). The recognized emotion data is sent to the server.

[0598] 5. Risk assessment and action recommendations

[0599] The server obtains and evaluates the latest infection risk index for the area based on the user's current location. This evaluation is combined with the user's emotional data obtained from the emotion engine, and specific behavioral recommendations are generated using an AI model. For example, if the user is feeling anxious, advice that takes their emotions into consideration is provided, such as "avoid crowds and rest in a quiet place" and "increase online communication."

[0600] 6. Recommendation Notification

[0601] The server sends the generated action recommendations to the device. Notifications are sent in the form of pop-up or push notifications, and additional details are displayed as needed. In particular, notifications that correspond to the user's emotions may be delivered as text or voice messages.

[0602] 7. User Behavior and Feedback

[0603] Users can take preventative measures to prevent infection by following the recommended actions. For example, they can take specific actions such as wearing a mask in designated areas and avoiding crowded places. In addition, by taking emotionally sensitive actions, it is possible to reduce psychological stress.

[0604] 8. Feedback Data Collection and Analysis

[0605] The device collects user behavioral and emotional data and periodically sends it back to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data is used to improve the accuracy of future recommendations.

[0606] Specific examples

[0607] Internal meeting scenario

[0608] 1. The server receives the latest infection data and detects that a specific commercial area in Tokyo is at high risk of infection.

[0609] 2. Assume the user works in an office within the commercial area.

[0610] 3. The device sends the user's current location (office) to the server.

[0611] 4. The device's emotion engine recognizes when the user is feeling stressed or anxious during the meeting.

[0612] 5. The server assesses the risk of infection around the office and generates recommendations that take into account emotions, such as "taking a break to relax" and "listening to music to relieve stress," in addition to standard infection prevention actions such as "opening windows to ventilate" and "holding meetings while maintaining distance."

[0613] 6. The device notifies the user of these recommendations, for example, by displaying specific advice such as "Take a short break and refresh yourself."

[0614] 7. Users must follow these guidelines to take precautions against infection and take care of their emotions.

[0615] The above is an embodiment of the invention. The present invention enables highly accurate infection risk assessment and behavior recommendations that take into account the user's emotional state, allowing users to live their daily lives with greater peace of mind.

[0616] The processing flow will be explained below.

[0617] Step 1: Collect data

[0618] The server periodically retrieves infection data from medical institution databases. The retrieved data includes information such as the number of infected people, the number of new infections, age, severity, and location of the infection. The retrieved data is then stored in the system's database.

[0619] Step 2: Preprocessing the data

[0620] The server performs data cleaning (removal of duplicate data, completion of missing values, etc.) and data standardization (normalization of values, etc.) to make the collected infection data easier to analyze. The preprocessed data is used for infection risk diagnosis.

[0621] Step 3: Infection risk analysis

[0622] The server uses an AI model to calculate the infection risk for each region based on the preprocessed data. The infection risk index is calculated by taking into account the trend in the number of infected people and their geographic distribution, and this quantifies the infection risk for each region.

[0623] Step 4: Obtaining location information

[0624] The user's device (smartphone or tablet) uses location information services to obtain the user's current location. Location information is collected in real time using GPS, Wi-Fi, and Bluetooth and is updated periodically.

[0625] Step 5: Send location information

[0626] The device transmits the acquired user's current location information to the server, allowing the server to grasp the user's real-time location.

[0627] Step 6: Obtaining emotion data

[0628] The device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine identifies the user's emotional state by analyzing the user's facial expressions using the camera and the tone of voice using the microphone. The recognized emotion data is sent to the server.

[0629] Step 7: Risk Assessment

[0630] The server obtains and evaluates the latest infection risk index for the area based on the user's current location, thereby determining the infection risk level of the user's current location in real time.

[0631] Step 8: Generate action recommendations

[0632] The server uses an AI model to generate specific recommendations based on the infection risk index and the user's emotional data obtained from the emotion engine. For example, if a user is feeling anxious, the server will create advice that takes their emotions into consideration, such as "avoid crowds and rest in a quiet place" or "increase online communication."

[0633] Step 9: Recommendation Notification

[0634] The server sends the generated action recommendations to the device. Notifications are sent in the form of push notifications or pop-ups, and additional details are displayed as needed. Notifications can also be sent in the form of text or voice messages depending on the user's emotions.

[0635] Step 10: Implementing User Actions

[0636] Users can take specific actions to prevent infection according to the recommended actions they receive, such as wearing a mask in designated high-risk areas or resting in a quiet place with a low risk of infection.

[0637] Step 11: Collect feedback data

[0638] The device collects user behavioral data (location information, implementation status of preventive measures, etc.) and emotional data, and periodically feeds this data back to the server, allowing the system to understand the user's behavioral and emotional history.

[0639] Step 12: Analyze the feedback data

[0640] The server analyzes the collected feedback data and uses it as learning data for the AI ​​model. The analysis results are used to improve the accuracy of future action recommendations.

[0641] Step 13: Update the AI ​​model

[0642] The server uses the feedback data to regularly update and refine the AI ​​model, improving the accuracy of infection risk assessment and behavioral recommendations, and providing users with more reliable information.

[0643] Through these steps, this system provides accurate infection risk information in real time and recommends optimal actions based on the user's emotional state, supporting users in taking infection prevention actions.

[0644] Example 2

[0645] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0646] In modern society, technology to quickly predict the spread of infectious diseases and take preventative measures is extremely important. However, current technology has limitations in risk assessment and behavioral recommendations based on infection data, and in particular, it lacks individually optimized advice that takes user emotions into consideration, preventing more effective infection spread prevention. Furthermore, due to insufficient capabilities for collecting, analyzing, and providing feedback on real-time data from diverse data sources, there is a need for accurate and immediate risk assessment and behavioral recommendations.

[0647] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0648] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for recognizing the user's emotions, means for adjusting the recommended actions using the emotion data, and means for evaluating the infection risk in a specific location based on the user's location information and providing the recommended actions in real time. This enables highly accurate infection risk assessment that takes the user's emotional state into account and individually optimized recommendations for infection prevention actions.

[0649] "Infection data" refers to information related to infectious diseases, such as the number of infected people, the number of new infections, age, severity, and location of the outbreak.

[0650] "Infection risk" refers to the numerical or index expression of the possibility of an infectious disease occurring and spreading in a particular area or location.

[0651] "AI model" refers to a mathematical model used to analyze data using machine learning algorithms and predict infection risk.

[0652] "User Location Information" means your geographic location data obtained using GPS or other location services.

[0653] "Emotion engine" refers to a software or hardware system that uses image and audio analysis techniques to recognize a user's emotional state.

[0654] "Behavioral recommendations" refer to suggestions for specific infection prevention actions and psychological care provided based on the infection risk and the user's emotional state.

[0655] "Real-time" refers to data collection, analysis, and delivery of results in near-instantaneous time.

[0656] "Feedback data" refers to data relating to changes in user behavior and emotions that is used to improve and learn from the system.

[0657] An "algorithm" refers to a definite procedure or computational method for solving a particular problem.

[0658] "Visualization" refers to a method of visually displaying data or information to make it easier to understand.

[0659] This invention combines a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides real-time AI-based action recommendations with an emotion engine that recognizes the user's emotions. This makes it possible to adjust recommendations for infection prevention actions according to the user's emotional state, providing more effective infection prevention support to users.

[0660] The server receives real-time infection data provided by medical institutions. This data includes the number of infected people, the number of new infections, age groups, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis. The database management system used is MySQL or similar.

[0661] Next, the server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. This AI model uses machine learning algorithms such as TensorFlow. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution, and expresses a risk index as a number and color-coded value to visually indicate the level of infection risk.

[0662] The device periodically obtains the user's current location using GPS or other location services and sends it to the server, allowing the server to grasp the user's current location in real time.

[0663] Additionally, the device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine uses image and voice analysis technologies to identify the user's current emotional state (e.g., joy, sadness, anxiety, stress, etc.). OpenCV is used for image analysis, and the Google Speech-to-Text API is used for voice analysis. The recognized emotion data is sent to the server.

[0664] The server obtains and evaluates the latest infection risk index for the area based on the user's current location. This evaluation is combined with the user's emotional data obtained from the emotion engine, and specific behavioral recommendations are generated using an AI model. For example, if the user is feeling anxious, advice that takes their emotions into consideration is provided, such as "avoid crowds and rest in a quiet place" and "increase online communication."

[0665] The generated action recommendations are sent from the server to the device. Notifications are sent in the form of pop-up or push notifications, and additional details are displayed as needed. In particular, notifications that correspond to the user's emotions may be delivered as text or voice messages.

[0666] Users can take preventative measures to prevent infection by following the recommended actions. For example, they can take specific actions such as wearing a mask in designated areas and avoiding crowded places. In addition, by taking emotionally sensitive actions, it is possible to reduce psychological stress.

[0667] The device collects user behavioral and emotional data and periodically sends it back to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data is used to improve the accuracy of future recommendations.

[0668] A specific example is a scenario during an internal meeting. The server receives the latest infection data and detects that a particular commercial area has a high risk of infection. Assuming the user works in an office within that commercial area, the device sends the user's current location (office) to the server. The device's emotion engine recognizes the user's emotional state, and the server generates recommended actions based on that data. For example, recommendations such as "open windows for ventilation," "hold the meeting while maintaining distance," and "take a break to relax" are notified to the device.

[0669] Example prompt sentence:

[0670] Imagine a situation where a user working in an office in a commercial area with a high risk of infection feels stressed or anxious during a meeting, and generate appropriate behavioral recommendations for that user. Specifically, include advice such as "open windows to ventilate," "conduct meetings while maintaining social distance," and "take breaks to relax."

[0671] The above is an embodiment of the invention. The present invention makes it possible to realize highly accurate infection risk assessment and behavior recommendations that take into account the emotional state of the user, allowing them to live their daily lives with peace of mind.

[0672] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0673] Step 1:

[0674] The server receives real-time infection data provided by medical institutions.

[0675] Input: Infection data from medical institutions (number of infected people, number of new infected people, age, severity, location of outbreak, etc.)

[0676] Specific operation: The server retrieves data via API using the HTTPS protocol and saves the received data in JSON format.

[0677] The extracted information is parsed according to the format and organized into an appropriate form.

[0678] Output: Infection data stored in a database.

[0679] Step 2:

[0680] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data.

[0681] Input: Preprocessed infection data

[0682] Specific operation: The server uses TensorFlow to apply a trained machine learning model to calculate a risk index for each region. The calculation results are displayed numerically and color-coded.

[0683] Output: Infection risk index (numerical, color-coded)

[0684] Step 3:

[0685] The device periodically obtains the user's current location information using GPS or other location information services and sends it to the server.

[0686] Input: User's current location information obtained from the GPS sensor

[0687] Specific operation: The device periodically uses location information services to obtain the user's current location and sends that data to the server via a POST request.

[0688] Output: Current location information sent to the server

[0689] Step 4:

[0690] The device is equipped with an emotion engine that recognizes the user's emotions and performs image and audio analysis.

[0691] Input: Face and voice data collected from the front camera and microphone

[0692] Specific operation: The device analyzes facial expressions using OpenCV, converts voice data into text using the Google Speech-to-Text API, and recognizes emotions. The recognized emotion data is then sent to the server.

[0693] Output: Emotion data (happiness, sadness, anxiety, stress, etc.)

[0694] Step 5:

[0695] The server generates recommended activities based on the user's current location and the latest infection risk index.

[0696] Input: User's current location, infection risk index, emotional data

[0697] Specific actions: The server takes into account the local infection risk index and the user's emotional state, and generates specific action recommendations using random forests and neural networks.

[0698] Output: Action recommendation (specific action suggestion)

[0699] Step 6:

[0700] The server transmits the generated behavioral recommendations to the terminal and notifies the user.

[0701] Input: Generated action recommendations

[0702] Specific operation: The server sends recommendation information in JSON format to the device, and the device notifies the user in the form of a push notification or a pop-up.

[0703] Output: Action recommendations notified to the user

[0704] Step 7:

[0705] Users then take specific infection prevention actions in accordance with the recommended actions.

[0706] Input: Recommended action notification from device

[0707] Specific actions: The user checks the notification and follows the instructions to take infection prevention measures, such as wearing a mask and avoiding crowded places.

[0708] Output: Practice infection prevention behaviors

[0709] Step 8:

[0710] The terminal collects the user's behavioral data and emotional data and feeds it back to the server.

[0711] Input: User behavior data, emotion data

[0712] Specific operation: The device periodically records changes in the user's behavior and emotions and sends the data to the server.

[0713] Output: Feedback data sent to the server

[0714] Step 9:

[0715] The server analyzes the received feedback data to evaluate and improve the performance of the AI ​​model.

[0716] Input: Feedback data

[0717] Specific operation: The server analyzes the collected feedback data and improves the accuracy of the AI ​​model by retraining it with new data.

[0718] Output: Improved AI model

[0719] (Application example 2)

[0720] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0721] Many conventional infection prevention systems assess infection risk and recommend actions to users, but because these systems do not take into account the user's emotional state, they have the problem of not being able to provide sufficient support to users who are feeling stressed or anxious. Users in areas with a higher risk of infection in particular need mental care, and a system that can address this is needed.

[0722] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0723] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for recognizing the user's emotions, and means for evaluating the infection risk in a specific location based on the user's location information and emotions and providing emotion-conscious behavior recommendations in real time. This makes it possible to provide appropriate infection prevention actions while taking the user's emotional state into consideration.

[0724] "Infection data" refers to information provided by medical institutions, such as the number of infected people, the number of new infections, age, severity, and location of the infection.

[0725] "Regional infection risk" refers to a risk index calculated by analyzing the trend in the number of infected people and their geographical distribution within a specific geographical area.

[0726] "Behavioral recommendations" refers to suggesting specific actions recommended for preventing infection based on the user's emotional state and location information.

[0727] "User Location Information" means information about a user's current location obtained through GPS or other location-based services.

[0728] "Emotion recognition" refers to the use of image and audio analysis techniques to identify a user's current emotional state.

[0729] The "infection risk index" refers to an index that expresses infection risk numerically and in color, calculated using an AI model.

[0730] "AI model" refers to the trained algorithm used to calculate infection risk.

[0731] "Feedback data" refers to data about actions performed by a user and their emotional state at the time.

[0732] A "generative AI model" refers to an AI algorithm that uses a specific prompt sentence as input to generate appropriate behavioral recommendations.

[0733] The system that embodies this invention consists of a server, a terminal, and a user, in order to collect infection data, calculate the infection risk for each region, and recommend infection prevention actions to users. Below, we will explain the specific processing steps of each element and the hardware and software used.

[0734] server

[0735] The server performs the following functions:

[0736] 1. Data Collection:

[0737] The server receives real-time infection data (number of infected people, number of new infections, age group, severity, location of outbreak, etc.) provided by medical institutions and stores it in a database.

[0738] Technologies used: Cloud platforms (e.g., AWS, Google Cloud), databases (e.g., MySQL, PostgreSQL)

[0739] 2. Data Analysis:

[0740] The server uses an AI model (machine learning libraries such as Scikit-learn and TensorFlow) to calculate the infection risk for each region based on the preprocessed infection data. The infection risk index is visualized numerically and color-coded.

[0741] Technologies used: Python, Scikit-learn, TensorFlow

[0742] 3. Action recommendation generation:

[0743] The server integrates the user's location information and emotional data and uses a generative AI model to create behavioral recommendations tailored to the user. For example, if the user feels anxious, the server generates advice such as "take a break in a quiet place."

[0744] Technology used: AI model (generative AI model)

[0745] 4. Recommendation Notification:

[0746] The server notifies the device of the generated action recommendations using a push notification service.

[0747] Technology used: Firebase Cloud Messaging (FCM)

[0748] Terminal

[0749] The device (smartphone) will:

[0750] 1. Obtaining user location information:

[0751] The terminal obtains its current location information using GPS or other location information services and periodically transmits it to the server.

[0752] Technologies used: GPS sensor, location services API

[0753] 2. Emotion recognition:

[0754] The device uses the user's camera and microphone to recognize the user's emotional state using an emotion engine (e.g., OpenCV for facial recognition technology and TensorFlow for voice analysis), and sends the data to the server.

[0755] Technologies used: OpenCV, TensorFlow, device camera, microphone

[0756] 3. Receiving notifications:

[0757] The device receives the action recommendations sent from the server and presents them to the user as a pop-up or push notification.

[0758] Technologies used: Notification API, FCM

[0759] User

[0760] The user plays the following roles:

[0761] 1. Implementing action recommendations:

[0762] Users practice infection prevention behaviors according to behavioral recommendations provided by the device, such as wearing a mask in designated areas.

[0763] 2. Providing Feedback:

[0764] Users can send their actions and results as feedback from their devices to the server, contributing to the improvement of the AI ​​model.

[0765] Specific examples

[0766] Internal meeting scenario

[0767] 1. The server receives the latest infection data and detects that a particular commercial area is at high risk of infection.

[0768] 2. Assume the user works in an office within the commercial area.

[0769] 3. The device sends the user's current location (office) to the server.

[0770] 4. The device's emotion engine recognizes when the user is feeling stressed or anxious during the meeting.

[0771] 5. The server assesses the risk of infection around the office and generates recommendations that take into account emotions, such as "taking a break to relax" and "listening to music to relieve stress," in addition to standard infection prevention actions such as "opening windows to ventilate" and "holding meetings while maintaining distance."

[0772] 6. The device will notify the user of these recommendations, for example, by displaying specific advice such as "Take a short break and refresh yourself."

[0773] 7. Users must follow these guidelines to take precautions against infection and take care of their emotions.

[0774] Example prompts

[0775] Currently, the user is located in Shinjuku Ward, Tokyo, and the number of new infections is increasing. The user's emotional state is anxious and stressed. Please generate behavioral recommendations appropriate for the user.

[0776] Example output:

[0777] Your current location poses a high risk of infection. We recommend the following actions:

[0778] Avoid crowds

[0779] Take a break in a quiet place

[0780] Wear a mask at all times

[0781] Communicate online when necessary

[0782] Exercise moderately to reduce stress

[0783] This example shows how the present invention takes into account a user's emotional state and infection risk to suggest personalized infection prevention actions.

[0784] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0785] Step 1: Data collection

[0786] The server receives real-time infection data provided by medical institutions and stores it in a database. The collected data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The input is the infection data sent from medical institutions, and the output is preprocessed infection data stored in the server's database.

[0787] Step 2: Data analysis

[0788] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. This AI model is trained using machine learning libraries such as Scikit-learn and TensorFlow. The input is infection data stored in the database, and the output is the infection risk index calculated for each region. The risk index is visualized using numbers and color coding and displayed on a dashboard, etc.

[0789] Step 3: Obtaining user location information

[0790] The device acquires the user's current location information using the smartphone's GPS sensor and location information services, and sends it to the server. The input is the GPS data collected by the device, and the output is the user's location information received by the server.

[0791] Step 4: Emotion Recognition

[0792] To recognize the user's emotional state, the device uses a camera and microphone to perform analysis using an emotion engine. Specifically, it uses facial expression analysis using OpenCV and voice analysis using TensorFlow. The input is camera footage and voice data obtained from the user, and the output is recognized emotion data (e.g., joy, sadness, anxiety, stress, etc.). This emotion data is also sent to the server.

[0793] Step 5: Generate action recommendations

[0794] The server integrates the user's location information and emotional data and uses a generative AI model to create behavioral recommendations appropriate for the user. The input is the user's location information, emotional data, and existing infection risk index, and the output is a specific behavioral recommendation. For example, actions such as "avoid crowds" and "take a break in a quiet place" are generated.

[0795] Step 6: Recommendation Notification

[0796] The server sends the generated action recommendations to the device, and the device notifies the user. The notification is sent in the form of a push notification using Firebase Cloud Messaging (FCM). The input is the action recommendations generated by the server, and the output is the notification content displayed on the device.

[0797] Step 7: User feedback

[0798] The user follows the recommended actions to prevent infection and records the results as feedback on the device. The input is the data on the actions taken by the user, and the output is the feedback data recorded by the device.

[0799] Step 8: Collect and analyze feedback data

[0800] The device collects user feedback data and periodically sends it to the server. The server analyzes this data and updates the AI ​​model. The input is the feedback data sent from the device, and the output is the updated AI model. This data is used to improve the accuracy of future action recommendations.

[0801] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0802] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0803] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0804] [Third embodiment]

[0805] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0806] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0807] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0808] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0809] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0810] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0811] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0812] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0813] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0814] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0815] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0816] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0817] This invention is a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides action recommendations in real time using AI. The system is configured as follows.

[0818] 1. Data Collection

[0819] The server receives real-time infection data provided by medical institutions, including the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis.

[0820] 2. Data Analysis

[0821] The server uses an AI model to calculate the infection risk for each region based on the collected infection data. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded, visually indicating the level of infection risk.

[0822] 3. Obtaining user location information

[0823] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or other location services, allowing the server to determine the user's current location in real time.

[0824] 4. Risk assessment and action recommendations

[0825] The server obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user, such as advice on avoiding rush hours, refraining from using public transportation, and wearing masks in high-risk areas.

[0826] 5. Notification of recommended actions

[0827] The device notifies the user of the action recommendations received from the server via a pop-up or push notification, and displays additional details as needed.

[0828] 6. User Behavior and Feedback

[0829] Users can take specific actions to prevent infection, such as avoiding crowded times and wearing a mask in designated areas, according to the recommended actions.

[0830] 7. Feedback data collection and analysis

[0831] The device feeds back user behavior data (location information, prevention measures implementation status, etc.) to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data will be used to improve the accuracy of recommendations in the future.

[0832] Specific examples

[0833] Morning commute scenario

[0834] 1. The server receives the latest infection data from each medical institution, analyzes it, and detects high infection risks around specific stations in Tokyo.

[0835] 2. Let's say the user is on their morning commute and heading to Shinjuku Station.

[0836] 3. The device sends the user's current location (around Shinjuku Station) to the server.

[0837] 4. The server detects that the area around Shinjuku Station is a high-risk area and generates specific recommendations for actions, such as "avoiding rush hours," "switching to remote work if possible," and "always wearing a mask at the station and maintaining social distance."

[0838] 5. The device notifies the user of these recommendations and encourages them to act on them.

[0839] 6. Users should follow these guidelines and take measures to prevent infection, such as avoiding travel during designated times and wearing a mask, to reduce the risk of infection.

[0840] The above is an embodiment of the invention. The present invention allows users to receive the latest infection risk information and optimal action guidelines in real time, enabling them to take appropriate infection prevention actions. This allows them to live their daily lives with peace of mind.

[0841] The processing flow will be explained below.

[0842] Step 1: Collect data

[0843] The server periodically retrieves infection data from medical institution databases. The collected data includes information such as the number of infected people, the number of new infections, age, severity, and location of the infection. The retrieved data is stored in the system's database.

[0844] Step 2: Preprocessing the data

[0845] The server performs data cleaning (removal of duplicate data, completion of missing values, etc.) and data standardization (normalization of values, etc.) to make the collected infection data easier to analyze. The preprocessed data is used for infection risk diagnosis.

[0846] Step 3: Infection risk analysis

[0847] The server uses an AI model to calculate the infection risk for each region based on the preprocessed data. The infection risk index is calculated by taking into account the trend in the number of infected people and their geographic distribution, and this quantifies the infection risk for each region.

[0848] Step 4: Obtaining location information

[0849] The user's device (smartphone or tablet) uses location information services to obtain the user's current location. Location information is collected in real time using GPS, Wi-Fi, and Bluetooth and is updated periodically.

[0850] Step 5: Send location information

[0851] The device transmits the acquired user's current location information to the server, allowing the server to grasp the user's real-time location.

[0852] Step 6: Risk assessment

[0853] The server obtains and evaluates the latest infection risk index for the area based on the user's current location, thereby determining the infection risk level of the user's current location in real time.

[0854] Step 7: Generate action recommendations

[0855] The server uses an AI model to generate specific recommendations for users based on the assessed infection risk index, such as "avoid crowds," "wear a mask," and "wash your hands thoroughly" in high-risk areas.

[0856] Step 8: Recommendation Notification

[0857] The server sends the generated behavioral recommendations to the device, and notifications are sent in real time via push notifications, encouraging users to take infection prevention measures.

[0858] Step 9: User behavior feedback

[0859] Users can take specific actions to prevent infection based on the recommendations they receive, such as wearing a mask in high-risk areas and avoiding crowded places at certain times.

[0860] Step 10: Collect feedback data

[0861] The device collects user behavior data (location information, implementation status of preventive measures, etc.) and periodically feeds it back to the server, allowing the system to understand the user's behavioral history.

[0862] Step 11: Analyze feedback data

[0863] The server analyzes the collected feedback data and uses it as training data for the AI ​​model. The analysis results are used to improve the accuracy of future action recommendations.

[0864] Step 12: Update the AI ​​model

[0865] The server uses the feedback data to regularly update and refine the AI ​​model, improving the accuracy of infection risk assessment and behavioral recommendations, and providing users with more reliable information.

[0866] Through these steps, the system provides accurate infection risk information and optimal behavior recommendations in real time, supporting users in taking infection prevention actions.

[0867] Example 1

[0868] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0869] To prevent the spread of infectious diseases, it is important to provide accurate infection risk information and appropriate guidelines in real time. However, current systems suffer from delays in the collection and analysis of infection data, or lack the functionality to provide immediate action recommendations using users' location information. As a result, users are unable to take appropriate infection prevention actions based on the latest risk information, which increases the risk of infection.

[0870] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0871] In this invention, the server includes means for collecting infection data from medical institutions, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring and transmitting user location information, and means for evaluating the infection risk in a specific location based on the user location information and providing recommended actions in real time. This allows the user to always receive appropriate recommended actions in real time based on the latest infection risk information, thereby effectively preventing the spread of infectious diseases.

[0872] "Infection data" refers to a variety of data related to infectious diseases, such as the number of infected people, the number of new infections, age, severity, and location of the outbreak.

[0873] "Infection risk" is an indicator of the possibility of the spread of an infectious disease in a particular area or location. Infection risk is calculated based on collected infection data.

[0874] "Recommendations" refers to guidelines and advice provided to users by the system, including suggestions for infection prevention actions.

[0875] "Location Information" means data about your current location collected using GPS or Wi-Fi location services.

[0876] An "artificial intelligence model" is an analytical model that uses machine learning algorithms. It learns trends in infection data and is used to calculate infection risk indices and generate behavioral recommendations.

[0877] "Real-time" refers to data collection, analysis, and information provision being carried out immediately without delay.

[0878] "Feedback data" refers to data about user behavior (such as location and preventative measures taken) that is sent back to the system, which analyzes it to help improve the model.

[0879] MODE FOR CARRYING OUT THE INVENTION

[0880] This invention is a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides action recommendations in real time using AI. The system is configured as follows.

[0881] Data collection

[0882] The server receives real-time infection data provided by medical institutions. This data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a relational database (e.g., MySQL) and performs preprocessing for analysis. Preprocessing includes missing value imputation and outlier detection and correction.

[0883] Data analysis

[0884] The server uses a trained artificial intelligence model (such as a model using TensorFlow or PyTorch) to calculate the infection risk for each region based on the collected infection data. The risk index is expressed numerically and color-coded, and displayed visually on a map. This allows users to understand the level of infection risk at a glance.

[0885] Obtaining user location information

[0886] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or Wi-Fi location services, allowing the server to grasp the user's current location in real time. The location information is transmitted securely using the HTTPS protocol.

[0887] Providing risk assessment and action recommendations

[0888] The server obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user, such as advice on avoiding rush hours, refraining from using public transportation, and wearing masks in high-risk areas.

[0889] Notification of recommended actions

[0890] The device notifies the user of the action recommendations received from the server via a pop-up or push notification, and displays additional details as needed.

[0891] User Behavior and Feedback

[0892] Users can take specific actions to prevent infection, such as avoiding crowded times and wearing a mask in designated areas, according to the recommended actions.

[0893] Feedback data collection and analysis

[0894] The device feeds back user behavior data (such as location information and the implementation status of preventive measures) to the server. The server analyzes the collected feedback data to evaluate and improve the performance of the AI ​​model. This feedback data is used to improve the accuracy of future behavioral recommendations.

[0895] Specific examples

[0896] Morning commute scenario

[0897] 1. The server receives the latest infection data from each medical institution, analyzes it, and detects high infection risks around specific stations in Tokyo.

[0898] 2. Let's say the user is on their morning commute and heading to Shinjuku Station.

[0899] 3. The device sends the user's current location (around Shinjuku Station) to the server.

[0900] 4. The server detects that the area around Shinjuku Station is a high-risk area and generates specific recommendations for actions, such as "avoiding rush hours," "switching to remote work if possible," and "always wearing a mask at the station and maintaining social distance."

[0901] 5. The device notifies the user of these recommendations and encourages them to act on them.

[0902] 6. Users should follow these guidelines and take measures to prevent infection, such as avoiding travel during designated times and wearing a mask, to reduce the risk of infection.

[0903] Prompt Sentence Examples

[0904] Here is an example of a prompt to input to a generative AI model:

[0905] Design a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides behavioral recommendations in real time. Include a scenario in which the server receives the infection data and notifies the user via their device.

[0906] The present invention allows users to receive the latest infection risk information and optimal action guidelines in real time, enabling them to take appropriate infection prevention actions, thereby allowing them to live their daily lives with peace of mind.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Step 1: Data collection

[0909] The server uses APIs and data transfer protocols to collect real-time infection data from medical institutions. As input, it receives data provided by each medical institution, such as the latest number of infected people, the number of new infected people, age group, severity, and location of the outbreak. The server stores this data in a relational database such as MySQL. As preprocessing, it also performs missing value completion and outlier detection and correction. As output, it obtains data in a format suitable for analysis.

[0910] Step 2: Data analysis

[0911] The server loads the preprocessed data from the database and performs analysis using an AI model. The infection data collected and preprocessed in step 1 is used as input. Machine learning libraries such as TensorFlow and PyTorch are used for the analysis. The AI ​​model has learned the trends in the number of infected people and their geographical distribution, and calculates the infection risk based on this. The output is a numerical infection risk index for each region, which is displayed visually using color coding.

[0912] Step 3: Obtaining user location information

[0913] The device obtains the user's current location and sends it to the server. As input, it periodically obtains the user's location using GPS or Wi-Fi location services. The device securely transmits this location information to the server using the HTTPS protocol. As output, real-time updated user location information is sent to the server.

[0914] Step 4: Risk assessment and action recommendations

[0915] The server obtains the latest infection risk index for the area based on the user's current location and generates specific behavioral recommendations using an AI model. The inputs are the infection risk index obtained in step 2 and the user's location information obtained in step 3. The analysis combines the user's current location and the risk index for the surrounding area to make an evaluation. The output is specific behavioral recommendations such as "avoiding busy times," "avoiding the use of public transportation," and "ensuring the wearing of masks."

[0916] Step 5: Notification of action recommendations

[0917] The device notifies the user of the recommended actions received from the server. As input, the device receives the recommended actions generated in step 4 from the server. The notification is in the form of a pop-up or push notification, and is immediately visible to the user. As output, the recommended actions are displayed in a format that the user can check.

[0918] Step 6: User Action

[0919] The user takes infection prevention actions according to the recommended actions notified from the device. For example, they take actions such as avoiding crowded times or wearing a mask in designated areas. The recommended information notified in step 5 is used as input. By taking the action, the risk of infection is reduced.

[0920] Step 7: Collect and analyze feedback data

[0921] The device collects user behavior data (such as location information and the status of infection prevention measures) and feeds it back to the server. As input, data on the user's behavior is collected and sent to the server using the HTTPS protocol. The server analyzes the feedback data to evaluate and improve the performance of the AI ​​model. As output, the accuracy of behavioral recommendations for future visits is improved.

[0922] (Application example 1)

[0923] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0924] To prevent the spread of infectious diseases, it is important to assess the infection risk in specific areas and locations in real time and recommend appropriate actions to users. However, conventional technologies have not adequately provided specific behavioral recommendations based on real-time data analysis and infection risk. Furthermore, there has been a lack of a means to provide users with route information with low infection risk while in a moving vehicle. As a result, appropriate actions to reduce the risk of infection cannot be taken, posing a risk of infection spreading.

[0925] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0926] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for evaluating the infection risk at a specific location based on the user location information and providing recommended actions in real time, means for calculating a travel route with a low infection risk based on the vehicle's current location and destination and providing passengers with the route and recommended actions via an in-vehicle display or audio notification, and means for detecting approach to a high-risk point on the route and warning the passengers. This makes it possible to recommend actions with a low infection risk to the user in real time and to instruct appropriate infection prevention measures even while traveling to a specific location.

[0927] "Infection data" refers to information provided by medical institutions, such as the number of infected people, the number of new infections, age, severity, and location of the infection.

[0928] "Infection risk" is an indicator of the risk of infection for each region or location, calculated using an AI model based on collected infection data.

[0929] "Action recommendations" are guidelines and advice that suggest specific infection prevention actions to users.

[0930] "Location information" is data about the current location of a user or vehicle obtained using GPS or other location services.

[0931] The "server" is a central control device for collecting infection data, analyzing it, generating recommendations, etc.

[0932] "Data collection means" refers to a system for receiving infection data from medical institutions and storing it in a database.

[0933] The "data analysis means" is an analytical device that uses an AI model to calculate the infection risk for each region based on collected infection data.

[0934] The "user location information acquisition means" is a mechanism for acquiring current location information of a user or vehicle and transmitting it to a server.

[0935] The "route calculation means" is an algorithm that calculates a travel route with a low risk of infection based on the vehicle's current location and destination.

[0936] "Warning means" is a mechanism for detecting the approach of high-risk points on the route and warning passengers.

[0937] A "visualization means" is a device or software for visually displaying the calculated infection risk.

[0938] "Feedback data" refers to evaluation data provided to the system, such as user behavior data, location information, and the implementation status of preventive measures.

[0939] The detailed description of the embodiment of the present invention is divided into three main processes: collecting infection data, analyzing it, and providing behavioral recommendations.

[0940] 1. Data Collection

[0941] The server receives real-time infection data provided by each medical institution, including the number of infected people, the number of new infections, age, severity, location of the infection, etc. The collected data is stored in a database and preprocessed for subsequent analysis.

[0942] 2. Data Analysis

[0943] The server uses an AI model based on the collected infection data to calculate the infection risk for each region. This AI model uses a trained algorithm to analyze past trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded, visually indicating the level of infection risk.

[0944] 3. Obtaining User Location Information and Risk Assessment

[0945] The user's device acquires location information using GPS and other location services and sends it to the server, allowing the server to grasp the user's current location in real time. The server then obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user.

[0946] 4. Example of an automobile

[0947] When this invention is applied to an autonomous vehicle, the following functions are further added.

[0948] Route calculation

[0949] The server calculates a route with a low risk of infection based on the vehicle's current location and destination, taking into account the infection risk index and road congestion. The calculated route information is provided to passengers via an in-car display and voice notification system.

[0950] Warning function

[0951] The server will alert passengers when they are approaching high-risk areas. The alerts will be delivered as audio or visual notifications, prompting passengers to take additional action to prevent infection.

[0952] 5. Visualization and Feedback

[0953] The calculated infection risk is visualized using graphs and color-coded maps. In addition, user behavior data (e.g., selection of avoidance routes, implementation of preventive measures, etc.) is sent to the server as feedback. The feedback data is used to evaluate and improve the performance of the AI ​​model.

[0954] Specific examples

[0955] For example, if a user is currently near Shinjuku Station and planning to travel to Tokyo Station, the system will analyze the latest infection data for the area and suggest routes with a low risk of infection. It will also provide advice on changing departure times to avoid peak times. This information is communicated to passengers via in-car displays and voice notification systems.

[0956] Prompt Sentence Examples

[0957] Below are some example prompts that can be used to prompt an AI model to generate behavioral recommendations based on infection risk.

[0958] Current location: "35.6895, 139.6917" (Shinjuku Station)

[0959] Destination: "35.6812, 139.7649" (Tokyo Station)

[0960] Based on current infection data, suggest routes with low risk of infection.

[0961] Also, suggest the best time to leave to avoid times when the risk of infection is higher.

[0962] This allows users to receive optimal guidelines for action in real time and reduce the risk of infection.

[0963] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0964] Step 1: Data collection

[0965] The server receives real-time infection data from medical institutions. This infection data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The input is data from medical institutions, and the output is the collected dataset. The server stores this dataset in a database and performs preprocessing for subsequent analysis.

[0966] Step 2: Data analysis

[0967] The server uses the collected infection data and an AI model to calculate the infection risk for each region. The input is the dataset collected in step 1, and the output is an infection risk index for each region. This analysis uses an AI model to generate the infection risk index. Specifically, the server applies the AI ​​model to analyze the increase / decrease trends in the number of infected people and their geographical distribution.

[0968] Step 3: Obtaining user location information

[0969] The device obtains the user's current location using GPS or other location information services and sends that information to the server. The input is the current location information obtained by the device, and the output is the user's location data sent to the server. This allows the server to know the user's current location in real time.

[0970] Step 4: Risk assessment and action recommendation generation

[0971] The server obtains the latest infection risk index for the area based on the user's current location and generates specific behavioral recommendations using an AI model. The input is the infection risk index from step 2 and the location data from step 3, and the output is behavioral recommendations for the user. Specifically, the server performs a risk assessment and generates recommendations such as "avoiding busy times," "switching to remote work," and "ensuring the wearing of masks."

[0972] Step 5: Calculate the travel path

[0973] The server calculates a travel route with a low risk of infection based on the vehicle's current location and destination. The inputs are the vehicle's location data, destination information, and the infection risk index from step 2, and the output is a recommended low-risk travel route. Specifically, the server calculates the optimal route by taking into account road congestion and infection risk.

[0974] Step 6: Real-time notifications and alerts

[0975] The device notifies the user of the recommended actions and route information received from the server. The input is the recommended actions and route information generated by the server, and the output is a notification to the user. Specifically, the device uses pop-ups and audio notifications to warn the user about approaching high-risk locations and provides additional guidelines for action.

[0976] Step 7: Collect and analyze feedback

[0977] The device feeds back user behavior data (location information and implementation status of preventive measures) to the server. The input is the user behavior data, and the output is analyzed feedback information. The server analyzes the feedback data and uses it to improve the performance of the AI ​​model. Specifically, it analyzes the collected data and improves the accuracy of recommendations from the next time onwards.

[0978] The above are the processing steps of the system that realizes this application example.

[0979] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0980] This invention combines a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides real-time AI-based action recommendations with an emotion engine that recognizes the user's emotions. This makes it possible to adjust recommendations for infection prevention actions according to the user's emotional state, providing more effective infection prevention support to users. The system is configured as follows:

[0981] 1. Data Collection

[0982] The server receives real-time infection data provided by medical institutions, including the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis.

[0983] 2. Data Analysis

[0984] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded to visually indicate the level of infection risk.

[0985] 3. Obtaining user location information

[0986] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or other location services, allowing the server to determine the user's current location in real time.

[0987] 4. Emotion recognition

[0988] The device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine uses image and audio analysis techniques to identify the user's current emotional state (e.g., joy, sadness, anxiety, stress, etc.). The recognized emotion data is sent to the server.

[0989] 5. Risk assessment and action recommendations

[0990] The server obtains and evaluates the latest infection risk index for the area based on the user's current location. This evaluation is combined with the user's emotional data obtained from the emotion engine, and specific behavioral recommendations are generated using an AI model. For example, if the user is feeling anxious, advice that takes their emotions into consideration is provided, such as "avoid crowds and rest in a quiet place" and "increase online communication."

[0991] 6. Recommendation Notification

[0992] The server sends the generated action recommendations to the device. Notifications are sent in the form of pop-up or push notifications, and additional details are displayed as needed. In particular, notifications that correspond to the user's emotions may be delivered as text or voice messages.

[0993] 7. User Behavior and Feedback

[0994] Users can take preventative measures to prevent infection by following the recommended actions. For example, they can take specific actions such as wearing a mask in designated areas and avoiding crowded places. In addition, by taking emotionally sensitive actions, it is possible to reduce psychological stress.

[0995] 8. Feedback Data Collection and Analysis

[0996] The device collects user behavioral and emotional data and periodically sends it back to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data is used to improve the accuracy of future recommendations.

[0997] Specific examples

[0998] Internal meeting scenario

[0999] 1. The server receives the latest infection data and detects that a specific commercial area in Tokyo is at high risk of infection.

[1000] 2. Assume the user works in an office within the commercial area.

[1001] 3. The device sends the user's current location (office) to the server.

[1002] 4. The device's emotion engine recognizes when the user is feeling stressed or anxious during the meeting.

[1003] 5. The server assesses the risk of infection around the office and generates recommendations that take into account emotions, such as "taking a break to relax" and "listening to music to relieve stress," in addition to standard infection prevention actions such as "opening windows to ventilate" and "holding meetings while maintaining distance."

[1004] 6. The device notifies the user of these recommendations, for example, by displaying specific advice such as "Take a short break and refresh yourself."

[1005] 7. Users must follow these guidelines to take precautions against infection and take care of their emotions.

[1006] The above is an embodiment of the invention. The present invention enables highly accurate infection risk assessment and behavior recommendations that take into account the user's emotional state, allowing users to live their daily lives with greater peace of mind.

[1007] The processing flow will be explained below.

[1008] Step 1: Collect data

[1009] The server periodically retrieves infection data from medical institution databases. The retrieved data includes information such as the number of infected people, the number of new infections, age, severity, and location of the infection. The retrieved data is then stored in the system's database.

[1010] Step 2: Preprocessing the data

[1011] The server performs data cleaning (removal of duplicate data, completion of missing values, etc.) and data standardization (normalization of values, etc.) to make the collected infection data easier to analyze. The preprocessed data is used for infection risk diagnosis.

[1012] Step 3: Infection risk analysis

[1013] The server uses an AI model to calculate the infection risk for each region based on the preprocessed data. The infection risk index is calculated by taking into account the trend in the number of infected people and their geographic distribution, and this quantifies the infection risk for each region.

[1014] Step 4: Obtaining location information

[1015] The user's device (smartphone or tablet) uses location information services to obtain the user's current location. Location information is collected in real time using GPS, Wi-Fi, and Bluetooth and is updated periodically.

[1016] Step 5: Send location information

[1017] The device transmits the acquired user's current location information to the server, allowing the server to grasp the user's real-time location.

[1018] Step 6: Obtaining emotion data

[1019] The device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine identifies the user's emotional state by analyzing the user's facial expressions using the camera and the tone of voice using the microphone. The recognized emotion data is sent to the server.

[1020] Step 7: Risk Assessment

[1021] The server obtains and evaluates the latest infection risk index for the area based on the user's current location, thereby determining the infection risk level of the user's current location in real time.

[1022] Step 8: Generate action recommendations

[1023] The server uses an AI model to generate specific recommendations based on the infection risk index and the user's emotional data obtained from the emotion engine. For example, if a user is feeling anxious, the server will create advice that takes their emotions into consideration, such as "avoid crowds and rest in a quiet place" or "increase online communication."

[1024] Step 9: Recommendation Notification

[1025] The server sends the generated action recommendations to the device. Notifications are sent in the form of push notifications or pop-ups, and additional details are displayed as needed. Notifications can also be sent in the form of text or voice messages depending on the user's emotions.

[1026] Step 10: Implementing User Actions

[1027] Users can take specific actions to prevent infection according to the recommended actions they receive, such as wearing a mask in designated high-risk areas or resting in a quiet place with a low risk of infection.

[1028] Step 11: Collect feedback data

[1029] The device collects user behavioral data (location information, implementation status of preventive measures, etc.) and emotional data, and periodically feeds this data back to the server, allowing the system to understand the user's behavioral and emotional history.

[1030] Step 12: Analyze the feedback data

[1031] The server analyzes the collected feedback data and uses it as learning data for the AI ​​model. The analysis results are used to improve the accuracy of future action recommendations.

[1032] Step 13: Update the AI ​​model

[1033] The server uses the feedback data to regularly update and refine the AI ​​model, improving the accuracy of infection risk assessment and behavioral recommendations, and providing users with more reliable information.

[1034] Through these steps, this system provides accurate infection risk information in real time and recommends optimal actions based on the user's emotional state, supporting users in taking infection prevention actions.

[1035] Example 2

[1036] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1037] In modern society, technology to quickly predict the spread of infectious diseases and take preventative measures is extremely important. However, current technology has limitations in risk assessment and behavioral recommendations based on infection data, and in particular, it lacks individually optimized advice that takes user emotions into consideration, preventing more effective infection spread prevention. Furthermore, due to insufficient capabilities for collecting, analyzing, and providing feedback on real-time data from diverse data sources, there is a need for accurate and immediate risk assessment and behavioral recommendations.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1039] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for recognizing the user's emotions, means for adjusting the recommended actions using the emotion data, and means for evaluating the infection risk in a specific location based on the user's location information and providing the recommended actions in real time. This enables highly accurate infection risk assessment that takes the user's emotional state into account and individually optimized recommendations for infection prevention actions.

[1040] "Infection data" refers to information related to infectious diseases, such as the number of infected people, the number of new infections, age, severity, and location of the outbreak.

[1041] "Infection risk" refers to the numerical or index expression of the possibility of an infectious disease occurring and spreading in a particular area or location.

[1042] "AI model" refers to a mathematical model used to analyze data using machine learning algorithms and predict infection risk.

[1043] "User Location Information" means your geographic location data obtained using GPS or other location services.

[1044] "Emotion engine" refers to a software or hardware system that uses image and audio analysis techniques to recognize a user's emotional state.

[1045] "Behavioral recommendations" refer to suggestions for specific infection prevention actions and psychological care provided based on the infection risk and the user's emotional state.

[1046] "Real-time" refers to data collection, analysis, and delivery of results in near-instantaneous time.

[1047] "Feedback data" refers to data relating to changes in user behavior and emotions that is used to improve and learn from the system.

[1048] An "algorithm" refers to a definite procedure or computational method for solving a particular problem.

[1049] "Visualization" refers to a method of visually displaying data or information to make it easier to understand.

[1050] This invention combines a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides real-time AI-based action recommendations with an emotion engine that recognizes the user's emotions. This makes it possible to adjust recommendations for infection prevention actions according to the user's emotional state, providing more effective infection prevention support to users.

[1051] The server receives real-time infection data provided by medical institutions. This data includes the number of infected people, the number of new infections, age groups, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis. The database management system used is MySQL or similar.

[1052] Next, the server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. This AI model uses machine learning algorithms such as TensorFlow. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution, and expresses a risk index as a number and color-coded value to visually indicate the level of infection risk.

[1053] The device periodically obtains the user's current location using GPS or other location services and sends it to the server, allowing the server to grasp the user's current location in real time.

[1054] Additionally, the device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine uses image and voice analysis technologies to identify the user's current emotional state (e.g., joy, sadness, anxiety, stress, etc.). OpenCV is used for image analysis, and the Google Speech-to-Text API is used for voice analysis. The recognized emotion data is sent to the server.

[1055] The server obtains and evaluates the latest infection risk index for the area based on the user's current location. This evaluation is combined with the user's emotional data obtained from the emotion engine, and specific behavioral recommendations are generated using an AI model. For example, if the user is feeling anxious, advice that takes their emotions into consideration is provided, such as "avoid crowds and rest in a quiet place" and "increase online communication."

[1056] The generated action recommendations are sent from the server to the device. Notifications are sent in the form of pop-up or push notifications, and additional details are displayed as needed. In particular, notifications that correspond to the user's emotions may be delivered as text or voice messages.

[1057] Users can take preventative measures to prevent infection by following the recommended actions. For example, they can take specific actions such as wearing a mask in designated areas and avoiding crowded places. In addition, by taking emotionally sensitive actions, it is possible to reduce psychological stress.

[1058] The device collects user behavioral and emotional data and periodically sends it back to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data is used to improve the accuracy of future recommendations.

[1059] A specific example is a scenario during an internal meeting. The server receives the latest infection data and detects that a particular commercial area has a high risk of infection. Assuming the user works in an office within that commercial area, the device sends the user's current location (office) to the server. The device's emotion engine recognizes the user's emotional state, and the server generates recommended actions based on that data. For example, recommendations such as "open windows for ventilation," "hold the meeting while maintaining distance," and "take a break to relax" are notified to the device.

[1060] Example prompt sentence:

[1061] Imagine a situation where a user working in an office in a commercial area with a high risk of infection feels stressed or anxious during a meeting, and generate appropriate behavioral recommendations for that user. Specifically, include advice such as "open windows to ventilate," "conduct meetings while maintaining social distance," and "take breaks to relax."

[1062] The above is an embodiment of the invention. The present invention makes it possible to realize highly accurate infection risk assessment and behavior recommendations that take into account the emotional state of the user, allowing them to live their daily lives with peace of mind.

[1063] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1064] Step 1:

[1065] The server receives real-time infection data provided by medical institutions.

[1066] Input: Infection data from medical institutions (number of infected people, number of new infected people, age, severity, location of outbreak, etc.)

[1067] Specific operation: The server retrieves data via API using the HTTPS protocol and saves the received data in JSON format.

[1068] The extracted information is parsed according to the format and organized into an appropriate form.

[1069] Output: Infection data stored in a database.

[1070] Step 2:

[1071] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data.

[1072] Input: Preprocessed infection data

[1073] Specific operation: The server uses TensorFlow to apply a trained machine learning model to calculate a risk index for each region. The calculation results are displayed numerically and color-coded.

[1074] Output: Infection risk index (numerical, color-coded)

[1075] Step 3:

[1076] The device periodically obtains the user's current location information using GPS or other location information services and sends it to the server.

[1077] Input: User's current location information obtained from the GPS sensor

[1078] Specific operation: The device periodically uses location information services to obtain the user's current location and sends that data to the server via a POST request.

[1079] Output: Current location information sent to the server

[1080] Step 4:

[1081] The device is equipped with an emotion engine that recognizes the user's emotions and performs image and audio analysis.

[1082] Input: Face and voice data collected from the front camera and microphone

[1083] Specific operation: The device analyzes facial expressions using OpenCV, converts voice data into text using the Google Speech-to-Text API, and recognizes emotions. The recognized emotion data is then sent to the server.

[1084] Output: Emotion data (happiness, sadness, anxiety, stress, etc.)

[1085] Step 5:

[1086] The server generates recommended activities based on the user's current location and the latest infection risk index.

[1087] Input: User's current location, infection risk index, emotional data

[1088] Specific actions: The server takes into account the local infection risk index and the user's emotional state, and generates specific action recommendations using random forests and neural networks.

[1089] Output: Action recommendation (specific action suggestion)

[1090] Step 6:

[1091] The server transmits the generated behavioral recommendations to the terminal and notifies the user.

[1092] Input: Generated action recommendations

[1093] Specific operation: The server sends recommendation information in JSON format to the device, and the device notifies the user in the form of a push notification or a pop-up.

[1094] Output: Action recommendations notified to the user

[1095] Step 7:

[1096] Users then take specific infection prevention actions in accordance with the recommended actions.

[1097] Input: Recommended action notification from device

[1098] Specific actions: The user checks the notification and follows the instructions to take infection prevention measures, such as wearing a mask and avoiding crowded places.

[1099] Output: Practice infection prevention behaviors

[1100] Step 8:

[1101] The terminal collects the user's behavioral data and emotional data and feeds it back to the server.

[1102] Input: User behavior data, emotion data

[1103] Specific operation: The device periodically records changes in the user's behavior and emotions and sends the data to the server.

[1104] Output: Feedback data sent to the server

[1105] Step 9:

[1106] The server analyzes the received feedback data to evaluate and improve the performance of the AI ​​model.

[1107] Input: Feedback data

[1108] Specific operation: The server analyzes the collected feedback data and improves the accuracy of the AI ​​model by retraining it with new data.

[1109] Output: Improved AI model

[1110] (Application example 2)

[1111] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1112] Many conventional infection prevention systems assess infection risk and recommend actions to users, but because these systems do not take into account the user's emotional state, they have the problem of not being able to provide sufficient support to users who are feeling stressed or anxious. Users in areas with a higher risk of infection in particular need mental care, and a system that can address this is needed.

[1113] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1114] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for recognizing the user's emotions, and means for evaluating the infection risk in a specific location based on the user's location information and emotions and providing emotion-conscious behavior recommendations in real time. This makes it possible to provide appropriate infection prevention actions while taking the user's emotional state into consideration.

[1115] "Infection data" refers to information provided by medical institutions, such as the number of infected people, the number of new infections, age, severity, and location of the infection.

[1116] "Regional infection risk" refers to a risk index calculated by analyzing the trend in the number of infected people and their geographical distribution within a specific geographical area.

[1117] "Behavioral recommendations" refers to suggesting specific actions recommended for preventing infection based on the user's emotional state and location information.

[1118] "User Location Information" means information about a user's current location obtained through GPS or other location-based services.

[1119] "Emotion recognition" refers to the use of image and audio analysis techniques to identify a user's current emotional state.

[1120] The "infection risk index" refers to an index that expresses infection risk numerically and in color, calculated using an AI model.

[1121] "AI model" refers to the trained algorithm used to calculate infection risk.

[1122] "Feedback data" refers to data about actions performed by a user and their emotional state at the time.

[1123] A "generative AI model" refers to an AI algorithm that uses a specific prompt sentence as input to generate appropriate behavioral recommendations.

[1124] The system that embodies this invention consists of a server, a terminal, and a user, in order to collect infection data, calculate the infection risk for each region, and recommend infection prevention actions to users. Below, we will explain the specific processing steps of each element and the hardware and software used.

[1125] server

[1126] The server performs the following functions:

[1127] 1. Data Collection:

[1128] The server receives real-time infection data (number of infected people, number of new infections, age group, severity, location of outbreak, etc.) provided by medical institutions and stores it in a database.

[1129] Technologies used: Cloud platforms (e.g., AWS, Google Cloud), databases (e.g., MySQL, PostgreSQL)

[1130] 2. Data Analysis:

[1131] The server uses an AI model (machine learning libraries such as Scikit-learn and TensorFlow) to calculate the infection risk for each region based on the preprocessed infection data. The infection risk index is visualized numerically and color-coded.

[1132] Technologies used: Python, Scikit-learn, TensorFlow

[1133] 3. Action recommendation generation:

[1134] The server integrates the user's location information and emotional data and uses a generative AI model to create behavioral recommendations tailored to the user. For example, if the user feels anxious, the server generates advice such as "take a break in a quiet place."

[1135] Technology used: AI model (generative AI model)

[1136] 4. Recommendation Notification:

[1137] The server notifies the device of the generated action recommendations using a push notification service.

[1138] Technology used: Firebase Cloud Messaging (FCM)

[1139] Terminal

[1140] The device (smartphone) will:

[1141] 1. Obtaining user location information:

[1142] The terminal obtains its current location information using GPS or other location information services and periodically transmits it to the server.

[1143] Technologies used: GPS sensor, location services API

[1144] 2. Emotion recognition:

[1145] The device uses the user's camera and microphone to recognize the user's emotional state using an emotion engine (e.g., OpenCV for facial recognition technology and TensorFlow for voice analysis), and sends the data to the server.

[1146] Technologies used: OpenCV, TensorFlow, device camera, microphone

[1147] 3. Receiving notifications:

[1148] The device receives the action recommendations sent from the server and presents them to the user as a pop-up or push notification.

[1149] Technologies used: Notification API, FCM

[1150] User

[1151] The user plays the following roles:

[1152] 1. Implementing action recommendations:

[1153] Users practice infection prevention behaviors according to behavioral recommendations provided by the device, such as wearing a mask in designated areas.

[1154] 2. Providing Feedback:

[1155] Users can send their actions and results as feedback from their devices to the server, contributing to the improvement of the AI ​​model.

[1156] Specific examples

[1157] Internal meeting scenario

[1158] 1. The server receives the latest infection data and detects that a particular commercial area is at high risk of infection.

[1159] 2. Assume the user works in an office within the commercial area.

[1160] 3. The device sends the user's current location (office) to the server.

[1161] 4. The device's emotion engine recognizes when the user is feeling stressed or anxious during the meeting.

[1162] 5. The server assesses the risk of infection around the office and generates recommendations that take into account emotions, such as "taking a break to relax" and "listening to music to relieve stress," in addition to standard infection prevention actions such as "opening windows to ventilate" and "holding meetings while maintaining distance."

[1163] 6. The device will notify the user of these recommendations, for example, by displaying specific advice such as "Take a short break and refresh yourself."

[1164] 7. Users must follow these guidelines to take precautions against infection and take care of their emotions.

[1165] Example prompts

[1166] Currently, the user is located in Shinjuku Ward, Tokyo, and the number of new infections is increasing. The user's emotional state is anxious and stressed. Please generate behavioral recommendations appropriate for the user.

[1167] Example output:

[1168] Your current location poses a high risk of infection. We recommend the following actions:

[1169] Avoid crowds

[1170] Take a break in a quiet place

[1171] Wear a mask at all times

[1172] Communicate online when necessary

[1173] Exercise moderately to reduce stress

[1174] This example shows how the present invention takes into account a user's emotional state and infection risk to suggest personalized infection prevention actions.

[1175] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1176] Step 1: Data collection

[1177] The server receives real-time infection data provided by medical institutions and stores it in a database. The collected data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The input is the infection data sent from medical institutions, and the output is preprocessed infection data stored in the server's database.

[1178] Step 2: Data analysis

[1179] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. This AI model is trained using machine learning libraries such as Scikit-learn and TensorFlow. The input is infection data stored in the database, and the output is the infection risk index calculated for each region. The risk index is visualized using numbers and color coding and displayed on a dashboard, etc.

[1180] Step 3: Obtaining user location information

[1181] The device acquires the user's current location information using the smartphone's GPS sensor and location information services, and sends it to the server. The input is the GPS data collected by the device, and the output is the user's location information received by the server.

[1182] Step 4: Emotion Recognition

[1183] To recognize the user's emotional state, the device uses a camera and microphone to perform analysis using an emotion engine. Specifically, it uses facial expression analysis using OpenCV and voice analysis using TensorFlow. The input is camera footage and voice data obtained from the user, and the output is recognized emotion data (e.g., joy, sadness, anxiety, stress, etc.). This emotion data is also sent to the server.

[1184] Step 5: Generate action recommendations

[1185] The server integrates the user's location information and emotional data and uses a generative AI model to create behavioral recommendations appropriate for the user. The input is the user's location information, emotional data, and existing infection risk index, and the output is a specific behavioral recommendation. For example, actions such as "avoid crowds" and "take a break in a quiet place" are generated.

[1186] Step 6: Recommendation Notification

[1187] The server sends the generated action recommendations to the device, and the device notifies the user. The notification is sent in the form of a push notification using Firebase Cloud Messaging (FCM). The input is the action recommendations generated by the server, and the output is the notification content displayed on the device.

[1188] Step 7: User feedback

[1189] The user follows the recommended actions to prevent infection and records the results as feedback on the device. The input is the data on the actions taken by the user, and the output is the feedback data recorded by the device.

[1190] Step 8: Collect and analyze feedback data

[1191] The device collects user feedback data and periodically sends it to the server. The server analyzes this data and updates the AI ​​model. The input is the feedback data sent from the device, and the output is the updated AI model. This data is used to improve the accuracy of future action recommendations.

[1192] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1193] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1194] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1195] [Fourth embodiment]

[1196] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1197] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1198] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1199] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1200] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1201] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1202] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1203] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1204] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1205] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1206] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1207] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1208] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1209] This invention is a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides action recommendations in real time using AI. The system is configured as follows.

[1210] 1. Data Collection

[1211] The server receives real-time infection data provided by medical institutions, including the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis.

[1212] 2. Data Analysis

[1213] The server uses an AI model to calculate the infection risk for each region based on the collected infection data. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded, visually indicating the level of infection risk.

[1214] 3. Obtaining user location information

[1215] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or other location services, allowing the server to determine the user's current location in real time.

[1216] 4. Risk assessment and action recommendations

[1217] The server obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user, such as advice on avoiding rush hours, refraining from using public transportation, and wearing masks in high-risk areas.

[1218] 5. Notification of recommended actions

[1219] The device notifies the user of the action recommendations received from the server via a pop-up or push notification, and displays additional details as needed.

[1220] 6. User Behavior and Feedback

[1221] Users can take specific actions to prevent infection, such as avoiding crowded times and wearing a mask in designated areas, according to the recommended actions.

[1222] 7. Feedback data collection and analysis

[1223] The device feeds back user behavior data (location information, prevention measures implementation status, etc.) to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data will be used to improve the accuracy of recommendations in the future.

[1224] Specific examples

[1225] Morning commute scenario

[1226] 1. The server receives the latest infection data from each medical institution, analyzes it, and detects high infection risks around specific stations in Tokyo.

[1227] 2. Let's say the user is on their morning commute and heading to Shinjuku Station.

[1228] 3. The device sends the user's current location (around Shinjuku Station) to the server.

[1229] 4. The server detects that the area around Shinjuku Station is a high-risk area and generates specific recommendations for actions, such as "avoiding rush hours," "switching to remote work if possible," and "always wearing a mask at the station and maintaining social distance."

[1230] 5. The device notifies the user of these recommendations and encourages them to act on them.

[1231] 6. Users should follow these guidelines and take measures to prevent infection, such as avoiding travel during designated times and wearing a mask, to reduce the risk of infection.

[1232] The above is an embodiment of the invention. The present invention allows users to receive the latest infection risk information and optimal action guidelines in real time, enabling them to take appropriate infection prevention actions. This allows them to live their daily lives with peace of mind.

[1233] The processing flow will be explained below.

[1234] Step 1: Collect data

[1235] The server periodically retrieves infection data from medical institution databases. The collected data includes information such as the number of infected people, the number of new infections, age, severity, and location of the infection. The retrieved data is stored in the system's database.

[1236] Step 2: Preprocessing the data

[1237] The server performs data cleaning (removal of duplicate data, completion of missing values, etc.) and data standardization (normalization of values, etc.) to make the collected infection data easier to analyze. The preprocessed data is used for infection risk diagnosis.

[1238] Step 3: Infection risk analysis

[1239] The server uses an AI model to calculate the infection risk for each region based on the preprocessed data. The infection risk index is calculated by taking into account the trend in the number of infected people and their geographic distribution, and this quantifies the infection risk for each region.

[1240] Step 4: Obtaining location information

[1241] The user's device (smartphone or tablet) uses location information services to obtain the user's current location. Location information is collected in real time using GPS, Wi-Fi, and Bluetooth and is updated periodically.

[1242] Step 5: Send location information

[1243] The device transmits the acquired user's current location information to the server, allowing the server to grasp the user's real-time location.

[1244] Step 6: Risk assessment

[1245] The server obtains and evaluates the latest infection risk index for the area based on the user's current location, thereby determining the infection risk level of the user's current location in real time.

[1246] Step 7: Generate action recommendations

[1247] The server uses an AI model to generate specific recommendations for users based on the assessed infection risk index, such as "avoid crowds," "wear a mask," and "wash your hands thoroughly" in high-risk areas.

[1248] Step 8: Recommendation Notification

[1249] The server sends the generated behavioral recommendations to the device, and notifications are sent in real time via push notifications, encouraging users to take infection prevention measures.

[1250] Step 9: User behavior feedback

[1251] Users can take specific actions to prevent infection based on the recommendations they receive, such as wearing a mask in high-risk areas and avoiding crowded places at certain times.

[1252] Step 10: Collect feedback data

[1253] The device collects user behavior data (location information, implementation status of preventive measures, etc.) and periodically feeds it back to the server, allowing the system to understand the user's behavioral history.

[1254] Step 11: Analyze feedback data

[1255] The server analyzes the collected feedback data and uses it as training data for the AI ​​model. The analysis results are used to improve the accuracy of future action recommendations.

[1256] Step 12: Update the AI ​​model

[1257] The server uses the feedback data to regularly update and refine the AI ​​model, improving the accuracy of infection risk assessment and behavioral recommendations, and providing users with more reliable information.

[1258] Through these steps, the system provides accurate infection risk information and optimal behavior recommendations in real time, supporting users in taking infection prevention actions.

[1259] Example 1

[1260] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1261] To prevent the spread of infectious diseases, it is important to provide accurate infection risk information and appropriate guidelines in real time. However, current systems suffer from delays in the collection and analysis of infection data, or lack the functionality to provide immediate action recommendations using users' location information. As a result, users are unable to take appropriate infection prevention actions based on the latest risk information, which increases the risk of infection.

[1262] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1263] In this invention, the server includes means for collecting infection data from medical institutions, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring and transmitting user location information, and means for evaluating the infection risk in a specific location based on the user location information and providing recommended actions in real time. This allows the user to always receive appropriate recommended actions in real time based on the latest infection risk information, thereby effectively preventing the spread of infectious diseases.

[1264] "Infection data" refers to a variety of data related to infectious diseases, such as the number of infected people, the number of new infections, age, severity, and location of the outbreak.

[1265] "Infection risk" is an indicator of the possibility of the spread of an infectious disease in a particular area or location. Infection risk is calculated based on collected infection data.

[1266] "Recommendations" refers to guidelines and advice provided to users by the system, including suggestions for infection prevention actions.

[1267] "Location Information" means data about your current location collected using GPS or Wi-Fi location services.

[1268] An "artificial intelligence model" is an analytical model that uses machine learning algorithms. It learns trends in infection data and is used to calculate infection risk indices and generate behavioral recommendations.

[1269] "Real-time" refers to data collection, analysis, and information provision being carried out immediately without delay.

[1270] "Feedback data" refers to data about user behavior (such as location and preventative measures taken) that is sent back to the system, which analyzes it to help improve the model.

[1271] MODE FOR CARRYING OUT THE INVENTION

[1272] This invention is a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides action recommendations in real time using AI. The system is configured as follows.

[1273] Data collection

[1274] The server receives real-time infection data provided by medical institutions. This data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a relational database (e.g., MySQL) and performs preprocessing for analysis. Preprocessing includes missing value imputation and outlier detection and correction.

[1275] Data analysis

[1276] The server uses a trained artificial intelligence model (such as a model using TensorFlow or PyTorch) to calculate the infection risk for each region based on the collected infection data. The risk index is expressed numerically and color-coded, and displayed visually on a map. This allows users to understand the level of infection risk at a glance.

[1277] Obtaining user location information

[1278] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or Wi-Fi location services, allowing the server to grasp the user's current location in real time. The location information is transmitted securely using the HTTPS protocol.

[1279] Providing risk assessment and action recommendations

[1280] The server obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user, such as advice on avoiding rush hours, refraining from using public transportation, and wearing masks in high-risk areas.

[1281] Notification of recommended actions

[1282] The device notifies the user of the action recommendations received from the server via a pop-up or push notification, and displays additional details as needed.

[1283] User Behavior and Feedback

[1284] Users can take specific actions to prevent infection, such as avoiding crowded times and wearing a mask in designated areas, according to the recommended actions.

[1285] Feedback data collection and analysis

[1286] The device feeds back user behavior data (such as location information and the implementation status of preventive measures) to the server. The server analyzes the collected feedback data to evaluate and improve the performance of the AI ​​model. This feedback data is used to improve the accuracy of future behavioral recommendations.

[1287] Specific examples

[1288] Morning commute scenario

[1289] 1. The server receives the latest infection data from each medical institution, analyzes it, and detects high infection risks around specific stations in Tokyo.

[1290] 2. Let's say the user is on their morning commute and heading to Shinjuku Station.

[1291] 3. The device sends the user's current location (around Shinjuku Station) to the server.

[1292] 4. The server detects that the area around Shinjuku Station is a high-risk area and generates specific recommendations for actions, such as "avoiding rush hours," "switching to remote work if possible," and "always wearing a mask at the station and maintaining social distance."

[1293] 5. The device notifies the user of these recommendations and encourages them to act on them.

[1294] 6. Users should follow these guidelines and take measures to prevent infection, such as avoiding travel during designated times and wearing a mask, to reduce the risk of infection.

[1295] Prompt Sentence Examples

[1296] Here is an example of a prompt to input to a generative AI model:

[1297] Design a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides behavioral recommendations in real time. Include a scenario in which the server receives the infection data and notifies the user via their device.

[1298] The present invention allows users to receive the latest infection risk information and optimal action guidelines in real time, enabling them to take appropriate infection prevention actions, thereby allowing them to live their daily lives with peace of mind.

[1299] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1300] Step 1: Data collection

[1301] The server uses APIs and data transfer protocols to collect real-time infection data from medical institutions. As input, it receives data provided by each medical institution, such as the latest number of infected people, the number of new infected people, age group, severity, and location of the outbreak. The server stores this data in a relational database such as MySQL. As preprocessing, it also performs missing value completion and outlier detection and correction. As output, it obtains data in a format suitable for analysis.

[1302] Step 2: Data analysis

[1303] The server loads the preprocessed data from the database and performs analysis using an AI model. The infection data collected and preprocessed in step 1 is used as input. Machine learning libraries such as TensorFlow and PyTorch are used for the analysis. The AI ​​model has learned the trends in the number of infected people and their geographical distribution, and calculates the infection risk based on this. The output is a numerical infection risk index for each region, which is displayed visually using color coding.

[1304] Step 3: Obtaining user location information

[1305] The device obtains the user's current location and sends it to the server. As input, it periodically obtains the user's location using GPS or Wi-Fi location services. The device securely transmits this location information to the server using the HTTPS protocol. As output, real-time updated user location information is sent to the server.

[1306] Step 4: Risk assessment and action recommendations

[1307] The server obtains the latest infection risk index for the area based on the user's current location and generates specific behavioral recommendations using an AI model. The inputs are the infection risk index obtained in step 2 and the user's location information obtained in step 3. The analysis combines the user's current location and the risk index for the surrounding area to make an evaluation. The output is specific behavioral recommendations such as "avoiding busy times," "avoiding the use of public transportation," and "ensuring the wearing of masks."

[1308] Step 5: Notification of action recommendations

[1309] The device notifies the user of the recommended actions received from the server. As input, the device receives the recommended actions generated in step 4 from the server. The notification is in the form of a pop-up or push notification, and is immediately visible to the user. As output, the recommended actions are displayed in a format that the user can check.

[1310] Step 6: User Action

[1311] The user takes infection prevention actions according to the recommended actions notified from the device. For example, they take actions such as avoiding crowded times or wearing a mask in designated areas. The recommended information notified in step 5 is used as input. By taking the action, the risk of infection is reduced.

[1312] Step 7: Collect and analyze feedback data

[1313] The device collects user behavior data (such as location information and the status of infection prevention measures) and feeds it back to the server. As input, data on the user's behavior is collected and sent to the server using the HTTPS protocol. The server analyzes the feedback data to evaluate and improve the performance of the AI ​​model. As output, the accuracy of behavioral recommendations for future visits is improved.

[1314] (Application example 1)

[1315] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1316] To prevent the spread of infectious diseases, it is important to assess the infection risk in specific areas and locations in real time and recommend appropriate actions to users. However, conventional technologies have not adequately provided specific behavioral recommendations based on real-time data analysis and infection risk. Furthermore, there has been a lack of a means to provide users with route information with low infection risk while in a moving vehicle. As a result, appropriate actions to reduce the risk of infection cannot be taken, posing a risk of infection spreading.

[1317] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1318] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for evaluating the infection risk at a specific location based on the user location information and providing recommended actions in real time, means for calculating a travel route with a low infection risk based on the vehicle's current location and destination and providing passengers with the route and recommended actions via an in-vehicle display or audio notification, and means for detecting approach to a high-risk point on the route and warning the passengers. This makes it possible to recommend actions with a low infection risk to the user in real time and to instruct appropriate infection prevention measures even while traveling to a specific location.

[1319] "Infection data" refers to information provided by medical institutions, such as the number of infected people, the number of new infections, age, severity, and location of the infection.

[1320] "Infection risk" is an indicator of the risk of infection for each region or location, calculated using an AI model based on collected infection data.

[1321] "Action recommendations" are guidelines and advice that suggest specific infection prevention actions to users.

[1322] "Location information" is data about the current location of a user or vehicle obtained using GPS or other location services.

[1323] The "server" is a central control device for collecting infection data, analyzing it, generating recommendations, etc.

[1324] "Data collection means" refers to a system for receiving infection data from medical institutions and storing it in a database.

[1325] The "data analysis means" is an analytical device that uses an AI model to calculate the infection risk for each region based on collected infection data.

[1326] The "user location information acquisition means" is a mechanism for acquiring current location information of a user or vehicle and transmitting it to a server.

[1327] The "route calculation means" is an algorithm that calculates a travel route with a low risk of infection based on the vehicle's current location and destination.

[1328] "Warning means" is a mechanism for detecting the approach of high-risk points on the route and warning passengers.

[1329] A "visualization means" is a device or software for visually displaying the calculated infection risk.

[1330] "Feedback data" refers to evaluation data provided to the system, such as user behavior data, location information, and the implementation status of preventive measures.

[1331] The detailed description of the embodiment of the present invention is divided into three main processes: collecting infection data, analyzing it, and providing behavioral recommendations.

[1332] 1. Data Collection

[1333] The server receives real-time infection data provided by each medical institution, including the number of infected people, the number of new infections, age, severity, location of the infection, etc. The collected data is stored in a database and preprocessed for subsequent analysis.

[1334] 2. Data Analysis

[1335] The server uses an AI model based on the collected infection data to calculate the infection risk for each region. This AI model uses a trained algorithm to analyze past trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded, visually indicating the level of infection risk.

[1336] 3. Obtaining User Location Information and Risk Assessment

[1337] The user's device acquires location information using GPS and other location services and sends it to the server, allowing the server to grasp the user's current location in real time. The server then obtains the latest infection risk index for the area based on the user's current location and uses an AI model to generate specific behavioral recommendations for the user.

[1338] 4. Example of an automobile

[1339] When this invention is applied to an autonomous vehicle, the following functions are further added.

[1340] Route calculation

[1341] The server calculates a route with a low risk of infection based on the vehicle's current location and destination, taking into account the infection risk index and road congestion. The calculated route information is provided to passengers via an in-car display and voice notification system.

[1342] Warning function

[1343] The server will alert passengers when they are approaching high-risk areas. The alerts will be delivered as audio or visual notifications, prompting passengers to take additional action to prevent infection.

[1344] 5. Visualization and Feedback

[1345] The calculated infection risk is visualized using graphs and color-coded maps. In addition, user behavior data (e.g., selection of avoidance routes, implementation of preventive measures, etc.) is sent to the server as feedback. The feedback data is used to evaluate and improve the performance of the AI ​​model.

[1346] Specific examples

[1347] For example, if a user is currently near Shinjuku Station and planning to travel to Tokyo Station, the system will analyze the latest infection data for the area and suggest routes with a low risk of infection. It will also provide advice on changing departure times to avoid peak times. This information is communicated to passengers via in-car displays and voice notification systems.

[1348] Prompt Sentence Examples

[1349] Below are some example prompts that can be used to prompt an AI model to generate behavioral recommendations based on infection risk.

[1350] Current location: "35.6895, 139.6917" (Shinjuku Station)

[1351] Destination: "35.6812, 139.7649" (Tokyo Station)

[1352] Based on current infection data, suggest routes with low risk of infection.

[1353] Also, suggest the best time to leave to avoid times when the risk of infection is higher.

[1354] This allows users to receive optimal guidelines for action in real time and reduce the risk of infection.

[1355] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1356] Step 1: Data collection

[1357] The server receives real-time infection data from medical institutions. This infection data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The input is data from medical institutions, and the output is the collected dataset. The server stores this dataset in a database and performs preprocessing for subsequent analysis.

[1358] Step 2: Data analysis

[1359] The server uses the collected infection data and an AI model to calculate the infection risk for each region. The input is the dataset collected in step 1, and the output is an infection risk index for each region. This analysis uses an AI model to generate the infection risk index. Specifically, the server applies the AI ​​model to analyze the increase / decrease trends in the number of infected people and their geographical distribution.

[1360] Step 3: Obtaining user location information

[1361] The device obtains the user's current location using GPS or other location information services and sends that information to the server. The input is the current location information obtained by the device, and the output is the user's location data sent to the server. This allows the server to know the user's current location in real time.

[1362] Step 4: Risk assessment and action recommendation generation

[1363] The server obtains the latest infection risk index for the area based on the user's current location and generates specific behavioral recommendations using an AI model. The input is the infection risk index from step 2 and the location data from step 3, and the output is behavioral recommendations for the user. Specifically, the server performs a risk assessment and generates recommendations such as "avoiding busy times," "switching to remote work," and "ensuring the wearing of masks."

[1364] Step 5: Calculate the travel path

[1365] The server calculates a travel route with a low risk of infection based on the vehicle's current location and destination. The inputs are the vehicle's location data, destination information, and the infection risk index from step 2, and the output is a recommended low-risk travel route. Specifically, the server calculates the optimal route by taking into account road congestion and infection risk.

[1366] Step 6: Real-time notifications and alerts

[1367] The device notifies the user of the recommended actions and route information received from the server. The input is the recommended actions and route information generated by the server, and the output is a notification to the user. Specifically, the device uses pop-ups and audio notifications to warn the user about approaching high-risk locations and provides additional guidelines for action.

[1368] Step 7: Collect and analyze feedback

[1369] The device feeds back user behavior data (location information and implementation status of preventive measures) to the server. The input is the user behavior data, and the output is analyzed feedback information. The server analyzes the feedback data and uses it to improve the performance of the AI ​​model. Specifically, it analyzes the collected data and improves the accuracy of recommendations from the next time onwards.

[1370] The above are the processing steps of the system that realizes this application example.

[1371] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1372] This invention combines a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides real-time AI-based action recommendations with an emotion engine that recognizes the user's emotions. This makes it possible to adjust recommendations for infection prevention actions according to the user's emotional state, providing more effective infection prevention support to users. The system is configured as follows:

[1373] 1. Data Collection

[1374] The server receives real-time infection data provided by medical institutions, including the number of infected people, the number of new infections, age, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis.

[1375] 2. Data Analysis

[1376] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution. The risk index is expressed numerically and color-coded to visually indicate the level of infection risk.

[1377] 3. Obtaining user location information

[1378] The device acquires the user's current location information and sends it to the server. The location information is periodically updated using GPS or other location services, allowing the server to determine the user's current location in real time.

[1379] 4. Emotion recognition

[1380] The device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine uses image and audio analysis techniques to identify the user's current emotional state (e.g., joy, sadness, anxiety, stress, etc.). The recognized emotion data is sent to the server.

[1381] 5. Risk assessment and action recommendations

[1382] The server obtains and evaluates the latest infection risk index for the area based on the user's current location. This evaluation is combined with the user's emotional data obtained from the emotion engine, and specific behavioral recommendations are generated using an AI model. For example, if the user is feeling anxious, advice that takes their emotions into consideration is provided, such as "avoid crowds and rest in a quiet place" and "increase online communication."

[1383] 6. Recommendation Notification

[1384] The server sends the generated action recommendations to the device. Notifications are sent in the form of pop-up or push notifications, and additional details are displayed as needed. In particular, notifications that correspond to the user's emotions may be delivered as text or voice messages.

[1385] 7. User Behavior and Feedback

[1386] Users can take preventative measures to prevent infection by following the recommended actions. For example, they can take specific actions such as wearing a mask in designated areas and avoiding crowded places. In addition, by taking emotionally sensitive actions, it is possible to reduce psychological stress.

[1387] 8. Feedback Data Collection and Analysis

[1388] The device collects user behavioral and emotional data and periodically sends it back to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data is used to improve the accuracy of future recommendations.

[1389] Specific examples

[1390] Internal meeting scenario

[1391] 1. The server receives the latest infection data and detects that a specific commercial area in Tokyo is at high risk of infection.

[1392] 2. Assume the user works in an office within the commercial area.

[1393] 3. The device sends the user's current location (office) to the server.

[1394] 4. The device's emotion engine recognizes when the user is feeling stressed or anxious during the meeting.

[1395] 5. The server assesses the risk of infection around the office and generates recommendations that take into account emotions, such as "taking a break to relax" and "listening to music to relieve stress," in addition to standard infection prevention actions such as "opening windows to ventilate" and "holding meetings while maintaining distance."

[1396] 6. The device notifies the user of these recommendations, for example, by displaying specific advice such as "Take a short break and refresh yourself."

[1397] 7. Users must follow these guidelines to take precautions against infection and take care of their emotions.

[1398] The above is an embodiment of the invention. The present invention enables highly accurate infection risk assessment and behavior recommendations that take into account the user's emotional state, allowing users to live their daily lives with greater peace of mind.

[1399] The processing flow will be explained below.

[1400] Step 1: Collect data

[1401] The server periodically retrieves infection data from medical institution databases. The retrieved data includes information such as the number of infected people, the number of new infections, age, severity, and location of the infection. The retrieved data is then stored in the system's database.

[1402] Step 2: Preprocessing the data

[1403] The server performs data cleaning (removal of duplicate data, completion of missing values, etc.) and data standardization (normalization of values, etc.) to make the collected infection data easier to analyze. The preprocessed data is used for infection risk diagnosis.

[1404] Step 3: Infection risk analysis

[1405] The server uses an AI model to calculate the infection risk for each region based on the preprocessed data. The infection risk index is calculated by taking into account the trend in the number of infected people and their geographic distribution, and this quantifies the infection risk for each region.

[1406] Step 4: Obtaining location information

[1407] The user's device (smartphone or tablet) uses location information services to obtain the user's current location. Location information is collected in real time using GPS, Wi-Fi, and Bluetooth and is updated periodically.

[1408] Step 5: Send location information

[1409] The device transmits the acquired user's current location information to the server, allowing the server to grasp the user's real-time location.

[1410] Step 6: Obtaining emotion data

[1411] The device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine identifies the user's emotional state by analyzing the user's facial expressions using the camera and the tone of voice using the microphone. The recognized emotion data is sent to the server.

[1412] Step 7: Risk Assessment

[1413] The server obtains and evaluates the latest infection risk index for the area based on the user's current location, thereby determining the infection risk level of the user's current location in real time.

[1414] Step 8: Generate action recommendations

[1415] The server uses an AI model to generate specific recommendations based on the infection risk index and the user's emotional data obtained from the emotion engine. For example, if a user is feeling anxious, the server will create advice that takes their emotions into consideration, such as "avoid crowds and rest in a quiet place" or "increase online communication."

[1416] Step 9: Recommendation Notification

[1417] The server sends the generated action recommendations to the device. Notifications are sent in the form of push notifications or pop-ups, and additional details are displayed as needed. Notifications can also be sent in the form of text or voice messages depending on the user's emotions.

[1418] Step 10: Implementing User Actions

[1419] Users can take specific actions to prevent infection according to the recommended actions they receive, such as wearing a mask in designated high-risk areas or resting in a quiet place with a low risk of infection.

[1420] Step 11: Collect feedback data

[1421] The device collects user behavioral data (location information, implementation status of preventive measures, etc.) and emotional data, and periodically feeds this data back to the server, allowing the system to understand the user's behavioral and emotional history.

[1422] Step 12: Analyze the feedback data

[1423] The server analyzes the collected feedback data and uses it as learning data for the AI ​​model. The analysis results are used to improve the accuracy of future action recommendations.

[1424] Step 13: Update the AI ​​model

[1425] The server uses the feedback data to regularly update and refine the AI ​​model, improving the accuracy of infection risk assessment and behavioral recommendations, and providing users with more reliable information.

[1426] Through these steps, this system provides accurate infection risk information in real time and recommends optimal actions based on the user's emotional state, supporting users in taking infection prevention actions.

[1427] Example 2

[1428] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1429] In modern society, technology to quickly predict the spread of infectious diseases and take preventative measures is extremely important. However, current technology has limitations in risk assessment and behavioral recommendations based on infection data, and in particular, it lacks individually optimized advice that takes user emotions into consideration, preventing more effective infection spread prevention. Furthermore, due to insufficient capabilities for collecting, analyzing, and providing feedback on real-time data from diverse data sources, there is a need for accurate and immediate risk assessment and behavioral recommendations.

[1430] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1431] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for recognizing the user's emotions, means for adjusting the recommended actions using the emotion data, and means for evaluating the infection risk in a specific location based on the user's location information and providing the recommended actions in real time. This enables highly accurate infection risk assessment that takes the user's emotional state into account and individually optimized recommendations for infection prevention actions.

[1432] "Infection data" refers to information related to infectious diseases, such as the number of infected people, the number of new infections, age, severity, and location of the outbreak.

[1433] "Infection risk" refers to the numerical or index expression of the possibility of an infectious disease occurring and spreading in a particular area or location.

[1434] "AI model" refers to a mathematical model used to analyze data using machine learning algorithms and predict infection risk.

[1435] "User Location Information" means your geographic location data obtained using GPS or other location services.

[1436] "Emotion engine" refers to a software or hardware system that uses image and audio analysis techniques to recognize a user's emotional state.

[1437] "Behavioral recommendations" refer to suggestions for specific infection prevention actions and psychological care provided based on the infection risk and the user's emotional state.

[1438] "Real-time" refers to data collection, analysis, and delivery of results in near-instantaneous time.

[1439] "Feedback data" refers to data relating to changes in user behavior and emotions that is used to improve and learn from the system.

[1440] An "algorithm" refers to a definite procedure or computational method for solving a particular problem.

[1441] "Visualization" refers to a method of visually displaying data or information to make it easier to understand.

[1442] This invention combines a system that calculates the infection risk for each region and spot based on infection data collected from medical institutions and provides real-time AI-based action recommendations with an emotion engine that recognizes the user's emotions. This makes it possible to adjust recommendations for infection prevention actions according to the user's emotional state, providing more effective infection prevention support to users.

[1443] The server receives real-time infection data provided by medical institutions. This data includes the number of infected people, the number of new infections, age groups, severity, and location of the infection. The server stores this data in a database and preprocesses it for analysis. The database management system used is MySQL or similar.

[1444] Next, the server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. This AI model uses machine learning algorithms such as TensorFlow. The AI ​​model uses a trained algorithm to analyze trends in the number of infected people and their geographic distribution, and expresses a risk index as a number and color-coded value to visually indicate the level of infection risk.

[1445] The device periodically obtains the user's current location using GPS or other location services and sends it to the server, allowing the server to grasp the user's current location in real time.

[1446] Additionally, the device is equipped with an emotion engine for recognizing the user's emotions. The emotion engine uses image and voice analysis technologies to identify the user's current emotional state (e.g., joy, sadness, anxiety, stress, etc.). OpenCV is used for image analysis, and the Google Speech-to-Text API is used for voice analysis. The recognized emotion data is sent to the server.

[1447] The server obtains and evaluates the latest infection risk index for the area based on the user's current location. This evaluation is combined with the user's emotional data obtained from the emotion engine, and specific behavioral recommendations are generated using an AI model. For example, if the user is feeling anxious, advice that takes their emotions into consideration is provided, such as "avoid crowds and rest in a quiet place" and "increase online communication."

[1448] The generated action recommendations are sent from the server to the device. Notifications are sent in the form of pop-up or push notifications, and additional details are displayed as needed. In particular, notifications that correspond to the user's emotions may be delivered as text or voice messages.

[1449] Users can take preventative measures to prevent infection by following the recommended actions. For example, they can take specific actions such as wearing a mask in designated areas and avoiding crowded places. In addition, by taking emotionally sensitive actions, it is possible to reduce psychological stress.

[1450] The device collects user behavioral and emotional data and periodically sends it back to the server. The server analyzes this feedback data to evaluate and improve the performance of the AI ​​model. This data is used to improve the accuracy of future recommendations.

[1451] A specific example is a scenario during an internal meeting. The server receives the latest infection data and detects that a particular commercial area has a high risk of infection. Assuming the user works in an office within that commercial area, the device sends the user's current location (office) to the server. The device's emotion engine recognizes the user's emotional state, and the server generates recommended actions based on that data. For example, recommendations such as "open windows for ventilation," "hold the meeting while maintaining distance," and "take a break to relax" are notified to the device.

[1452] Example prompt sentence:

[1453] Imagine a situation where a user working in an office in a commercial area with a high risk of infection feels stressed or anxious during a meeting, and generate appropriate behavioral recommendations for that user. Specifically, include advice such as "open windows to ventilate," "conduct meetings while maintaining social distance," and "take breaks to relax."

[1454] The above is an embodiment of the invention. The present invention makes it possible to realize highly accurate infection risk assessment and behavior recommendations that take into account the emotional state of the user, allowing them to live their daily lives with peace of mind.

[1455] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1456] Step 1:

[1457] The server receives real-time infection data provided by medical institutions.

[1458] Input: Infection data from medical institutions (number of infected people, number of new infected people, age, severity, location of outbreak, etc.)

[1459] Specific operation: The server retrieves data via API using the HTTPS protocol and saves the received data in JSON format.

[1460] The extracted information is parsed according to the format and organized into an appropriate form.

[1461] Output: Infection data stored in a database.

[1462] Step 2:

[1463] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data.

[1464] Input: Preprocessed infection data

[1465] Specific operation: The server uses TensorFlow to apply a trained machine learning model to calculate a risk index for each region. The calculation results are displayed numerically and color-coded.

[1466] Output: Infection risk index (numerical, color-coded)

[1467] Step 3:

[1468] The device periodically obtains the user's current location information using GPS or other location information services and sends it to the server.

[1469] Input: User's current location information obtained from the GPS sensor

[1470] Specific operation: The device periodically uses location information services to obtain the user's current location and sends that data to the server via a POST request.

[1471] Output: Current location information sent to the server

[1472] Step 4:

[1473] The device is equipped with an emotion engine that recognizes the user's emotions and performs image and audio analysis.

[1474] Input: Face and voice data collected from the front camera and microphone

[1475] Specific operation: The device analyzes facial expressions using OpenCV, converts voice data into text using the Google Speech-to-Text API, and recognizes emotions. The recognized emotion data is then sent to the server.

[1476] Output: Emotion data (happiness, sadness, anxiety, stress, etc.)

[1477] Step 5:

[1478] The server generates recommended activities based on the user's current location and the latest infection risk index.

[1479] Input: User's current location, infection risk index, emotional data

[1480] Specific actions: The server takes into account the local infection risk index and the user's emotional state, and generates specific action recommendations using random forests and neural networks.

[1481] Output: Action recommendation (specific action suggestion)

[1482] Step 6:

[1483] The server transmits the generated behavioral recommendations to the terminal and notifies the user.

[1484] Input: Generated action recommendations

[1485] Specific operation: The server sends recommendation information in JSON format to the device, and the device notifies the user in the form of a push notification or a pop-up.

[1486] Output: Action recommendations notified to the user

[1487] Step 7:

[1488] Users then take specific infection prevention actions in accordance with the recommended actions.

[1489] Input: Recommended action notification from device

[1490] Specific actions: The user checks the notification and follows the instructions to take infection prevention measures, such as wearing a mask and avoiding crowded places.

[1491] Output: Practice infection prevention behaviors

[1492] Step 8:

[1493] The terminal collects the user's behavioral data and emotional data and feeds it back to the server.

[1494] Input: User behavior data, emotion data

[1495] Specific operation: The device periodically records changes in the user's behavior and emotions and sends the data to the server.

[1496] Output: Feedback data sent to the server

[1497] Step 9:

[1498] The server analyzes the received feedback data to evaluate and improve the performance of the AI ​​model.

[1499] Input: Feedback data

[1500] Specific operation: The server analyzes the collected feedback data and improves the accuracy of the AI ​​model by retraining it with new data.

[1501] Output: Improved AI model

[1502] (Application example 2)

[1503] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1504] Many conventional infection prevention systems assess infection risk and recommend actions to users, but because these systems do not take into account the user's emotional state, they have the problem of not being able to provide sufficient support to users who are feeling stressed or anxious. Users in areas with a higher risk of infection in particular need mental care, and a system that can address this is needed.

[1505] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1506] In this invention, the server includes means for collecting infection data, means for calculating the infection risk for each region using the collected infection data, means for recommending infection prevention actions to the user based on the calculated infection risk, means for acquiring user location information, means for recognizing the user's emotions, and means for evaluating the infection risk in a specific location based on the user's location information and emotions and providing emotion-conscious behavior recommendations in real time. This makes it possible to provide appropriate infection prevention actions while taking the user's emotional state into consideration.

[1507] "Infection data" refers to information provided by medical institutions, such as the number of infected people, the number of new infections, age, severity, and location of the infection.

[1508] "Regional infection risk" refers to a risk index calculated by analyzing the trend in the number of infected people and their geographical distribution within a specific geographical area.

[1509] "Behavioral recommendations" refers to suggesting specific actions recommended for preventing infection based on the user's emotional state and location information.

[1510] "User Location Information" means information about a user's current location obtained through GPS or other location-based services.

[1511] "Emotion recognition" refers to the use of image and audio analysis techniques to identify a user's current emotional state.

[1512] The "infection risk index" refers to an index that expresses infection risk numerically and in color, calculated using an AI model.

[1513] "AI model" refers to the trained algorithm used to calculate infection risk.

[1514] "Feedback data" refers to data about actions performed by a user and their emotional state at the time.

[1515] A "generative AI model" refers to an AI algorithm that uses a specific prompt sentence as input to generate appropriate behavioral recommendations.

[1516] The system that embodies this invention consists of a server, a terminal, and a user, in order to collect infection data, calculate the infection risk for each region, and recommend infection prevention actions to users. Below, we will explain the specific processing steps of each element and the hardware and software used.

[1517] server

[1518] The server performs the following functions:

[1519] 1. Data Collection:

[1520] The server receives real-time infection data (number of infected people, number of new infections, age group, severity, location of outbreak, etc.) provided by medical institutions and stores it in a database.

[1521] Technologies used: Cloud platforms (e.g., AWS, Google Cloud), databases (e.g., MySQL, PostgreSQL)

[1522] 2. Data Analysis:

[1523] The server uses an AI model (machine learning libraries such as Scikit-learn and TensorFlow) to calculate the infection risk for each region based on the preprocessed infection data. The infection risk index is visualized numerically and color-coded.

[1524] Technologies used: Python, Scikit-learn, TensorFlow

[1525] 3. Action recommendation generation:

[1526] The server integrates the user's location information and emotional data and uses a generative AI model to create behavioral recommendations tailored to the user. For example, if the user feels anxious, the server generates advice such as "take a break in a quiet place."

[1527] Technology used: AI model (generative AI model)

[1528] 4. Recommendation Notification:

[1529] The server notifies the device of the generated action recommendations using a push notification service.

[1530] Technology used: Firebase Cloud Messaging (FCM)

[1531] Terminal

[1532] The device (smartphone) will:

[1533] 1. Obtaining user location information:

[1534] The terminal obtains its current location information using GPS or other location information services and periodically transmits it to the server.

[1535] Technologies used: GPS sensor, location services API

[1536] 2. Emotion recognition:

[1537] The device uses the user's camera and microphone to recognize the user's emotional state using an emotion engine (e.g., OpenCV for facial recognition technology and TensorFlow for voice analysis), and sends the data to the server.

[1538] Technologies used: OpenCV, TensorFlow, device camera, microphone

[1539] 3. Receiving notifications:

[1540] The device receives the action recommendations sent from the server and presents them to the user as a pop-up or push notification.

[1541] Technologies used: Notification API, FCM

[1542] User

[1543] The user plays the following roles:

[1544] 1. Implementing action recommendations:

[1545] Users practice infection prevention behaviors according to behavioral recommendations provided by the device, such as wearing a mask in designated areas.

[1546] 2. Providing Feedback:

[1547] Users can send their actions and results as feedback from their devices to the server, contributing to the improvement of the AI ​​model.

[1548] Specific examples

[1549] Internal meeting scenario

[1550] 1. The server receives the latest infection data and detects that a particular commercial area is at high risk of infection.

[1551] 2. Assume the user works in an office within the commercial area.

[1552] 3. The device sends the user's current location (office) to the server.

[1553] 4. The device's emotion engine recognizes when the user is feeling stressed or anxious during the meeting.

[1554] 5. The server assesses the risk of infection around the office and generates recommendations that take into account emotions, such as "taking a break to relax" and "listening to music to relieve stress," in addition to standard infection prevention actions such as "opening windows to ventilate" and "holding meetings while maintaining distance."

[1555] 6. The device will notify the user of these recommendations, for example, by displaying specific advice such as "Take a short break and refresh yourself."

[1556] 7. Users must follow these guidelines to take precautions against infection and take care of their emotions.

[1557] Example prompts

[1558] Currently, the user is located in Shinjuku Ward, Tokyo, and the number of new infections is increasing. The user's emotional state is anxious and stressed. Please generate behavioral recommendations appropriate for the user.

[1559] Example output:

[1560] Your current location poses a high risk of infection. We recommend the following actions:

[1561] Avoid crowds

[1562] Take a break in a quiet place

[1563] Wear a mask at all times

[1564] Communicate online when necessary

[1565] Exercise moderately to reduce stress

[1566] This example shows how the present invention takes into account a user's emotional state and infection risk to suggest personalized infection prevention actions.

[1567] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1568] Step 1: Data collection

[1569] The server receives real-time infection data provided by medical institutions and stores it in a database. The collected data includes the number of infected people, the number of new infections, age, severity, and location of the infection. The input is the infection data sent from medical institutions, and the output is preprocessed infection data stored in the server's database.

[1570] Step 2: Data analysis

[1571] The server uses an AI model to calculate the infection risk for each region based on the preprocessed infection data. This AI model is trained using machine learning libraries such as Scikit-learn and TensorFlow. The input is infection data stored in the database, and the output is the infection risk index calculated for each region. The risk index is visualized using numbers and color coding and displayed on a dashboard, etc.

[1572] Step 3: Obtaining user location information

[1573] The device acquires the user's current location information using the smartphone's GPS sensor and location information services, and sends it to the server. The input is the GPS data collected by the device, and the output is the user's location information received by the server.

[1574] Step 4: Emotion Recognition

[1575] To recognize the user's emotional state, the device uses a camera and microphone to perform analysis using an emotion engine. Specifically, it uses facial expression analysis using OpenCV and voice analysis using TensorFlow. The input is camera footage and voice data obtained from the user, and the output is recognized emotion data (e.g., joy, sadness, anxiety, stress, etc.). This emotion data is also sent to the server.

[1576] Step 5: Generate action recommendations

[1577] The server integrates the user's location information and emotional data and uses a generative AI model to create behavioral recommendations appropriate for the user. The input is the user's location information, emotional data, and existing infection risk index, and the output is a specific behavioral recommendation. For example, actions such as "avoid crowds" and "take a break in a quiet place" are generated.

[1578] Step 6: Recommendation Notification

[1579] The server sends the generated action recommendations to the device, and the device notifies the user. The notification is sent in the form of a push notification using Firebase Cloud Messaging (FCM). The input is the action recommendations generated by the server, and the output is the notification content displayed on the device.

[1580] Step 7: User feedback

[1581] The user follows the recommended actions to prevent infection and records the results as feedback on the device. The input is the data on the actions taken by the user, and the output is the feedback data recorded by the device.

[1582] Step 8: Collect and analyze feedback data

[1583] The device collects user feedback data and periodically sends it to the server. The server analyzes this data and updates the AI ​​model. The input is the feedback data sent from the device, and the output is the updated AI model. This data is used to improve the accuracy of future action recommendations.

[1584] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1585] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1586] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1587] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1588] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1589] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1590] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1591] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1592] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1593] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1594] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1595] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1596] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1597] 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.

[1598] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1599] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1600] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1601] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1602] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1603] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1604] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1605] The following is further disclosed regarding the above embodiment.

[1606] (Claim 1)

[1607] a means of collecting infection data;

[1608] A means of calculating the infection risk for each region using the collected infection data, and

[1609] A means for recommending infection prevention actions to a user based on the calculated infection risk;

[1610] A means for acquiring user location information;

[1611] A means to evaluate the risk of infection in a specific location based on the user's location information and provide behavioral recommendations in real time;

[1612] A system including:

[1613] (Claim 2)

[1614] A means for visualizing and displaying the calculated infection risk;

[1615] a means for training and applying an AI model to generate an infection risk index;

[1616] 10. The system of claim 1, further comprising:

[1617] (Claim 3)

[1618] A means for collecting user behavior data and providing it as feedback to the system;

[1619] A means of analyzing the feedback data and updating the AI ​​model;

[1620] 10. The system of claim 1, further comprising:

[1621] "Example 1"

[1622] (Claim 1)

[1623] A means of collecting infection data from medical institutions;

[1624] A means of calculating the infection risk for each region using the collected infection data, and

[1625] A means for recommending infection prevention actions to a user based on the calculated infection risk;

[1626] means for acquiring and transmitting user location information;

[1627] A means to evaluate the risk of infection in a specific location based on the user's location information and provide behavioral recommendations in real time;

[1628] A system including:

[1629] (Claim 2)

[1630] A means for visualizing and displaying the calculated infection risk;

[1631] a means for training and applying an artificial intelligence model to generate an infection risk index;

[1632] 10. The system of claim 1, further comprising:

[1633] (Claim 3)

[1634] A means for collecting user behavior data and providing it as feedback to the system;

[1635] a means for analyzing the feedback data to update the artificial intelligence model;

[1636] 10. The system of claim 1, further comprising:

[1637] "Application Example 1"

[1638] (Claim 1)

[1639] a means of collecting infection data;

[1640] A means of calculating the infection risk for each region using the collected infection data, and

[1641] A means for recommending infection prevention actions to a user based on the calculated infection risk;

[1642] A means for acquiring user location information;

[1643] A means to evaluate the risk of infection in a specific location based on the user's location information and provide behavioral recommendations in real time;

[1644] A means for calculating a travel route with a low risk of infection based on the current location and destination of the vehicle...

Claims

1. a means of collecting infection data; A means of calculating the infection risk for each region using the collected infection data, and A means for recommending infection prevention actions to a user based on the calculated infection risk; A means for acquiring user location information; A means to evaluate the risk of infection in a specific location based on the user's location information and provide behavioral recommendations in real time; A system including:

2. A means for visualizing and displaying the calculated infection risk; a means for training and applying an AI model to generate an infection risk index; The system of claim 1 further comprising:

3. A means for collecting user behavior data and providing it as feedback to the system; A means of analyzing the feedback data and updating the AI ​​model; The system of claim 1 further comprising:

Images