system

Abstract

A system is provided.SOLUTION: A system comprising: means for pressing a button when a user feels danger in a city; a GPS module for acquiring position information of the place when the button is pressed; a communication module for transmitting the acquired position information to a server; means for analyzing the position information received by the server and providing information of the place determined to be dangerous to a local government; and means for notifying the user approaching the place determined to be dangerous by the server of a warning by voice.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] It is important to create an environment in which elderly people and other users can move around town safely, but currently there are many potential hazards, such as steep steps and broken tactile paving blocks. These hazards can cause users to fall and get injured. It is also difficult for local governments to quickly identify and repair these hazards. It is also difficult for users to recognize hazards themselves and take precautions in advance. Therefore, in order to create safe cities and promote safe outings for elderly people, a system is needed that can quickly identify and repair hazards and provide appropriate warnings to users. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that includes a button that a user presses when they sense danger in town, a GPS module that acquires location information of the location when the button is pressed, a communication module that transmits the acquired location information to a server, a means for the server to analyze the received location information and provide information on locations determined to be dangerous to the local government, and a means for issuing an audio warning to users who approach a location determined to be dangerous by the server. This system quickly identifies dangerous locations, promoting repairs by the local government and enabling users to recognize dangerous locations in advance and take precautions.

[0006] "Users" refers to the elderly and other pedestrians who actually use the system.

[0007] "Downtown" refers to public places such as urban areas, city streets, and parks.

[0008] A "button" refers to a physical input device that a user can press when they sense danger to notify the system of the danger.

[0009] A "GPS module" refers to an electronic component that receives signals from Earth's artificial satellites and calculates and obtains one's current position.

[0010] The "communication module" refers to a wireless communication device for transmitting acquired data to a server.

[0011] "Server" refers to a computer system that receives, stores, and analyzes data sent from a terminal and provides appropriate information or warnings.

[0012] "Location information" refers to geographical data such as longitude and latitude that is obtained when a user presses a button in a dangerous area.

[0013] "Local government" refers to local public bodies (cities, towns, villages, etc.), and refers to the entities that repair dangerous areas and take measures to ensure safety in the city.

[0014] "Warning" refers to the act of the server providing information to the user by voice or other means to notify them of dangerous areas.

[0015] "Locations determined to be dangerous" refers to locations with longitude and latitude that the server has analyzed multiple data and identified as being actually dangerous to the user. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The system for carrying out this invention is designed to create an environment in which users can move safely around town. The specific configuration of this system and the processing of the program will be described below.

[0038] System configuration

[0039] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0040] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[0041] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[0042] Program processing overview

[0043] Use in the city

[0044] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[0045] Sending and Receiving Data

[0046] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. Encryption technology is generally used to ensure security.

[0047] Analyzing the data

[0048] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if there is a specific pattern.The server then provides information on locations that are deemed dangerous to local governments, facilitating repairs.

[0049] Creating a predictive model

[0050] The server generates a machine learning model based on the collected data to predict future danger zones. This prediction model is updated regularly. When a danger zone is predicted, local governments are notified in advance so that preventive measures can be taken.

[0051] Warning notice

[0052] When the user approaches a known dangerous spot, the device will issue a warning using the built-in speaker. For example, it may announce, "There is a step ahead, so be careful." This function allows the user to recognize danger in advance and move safely.

[0053] Specific examples

[0054] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[0055] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0056] 3. The recorded data is sent to the server via the terminal's communication module.

[0057] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0058] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[0059] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[0060] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps."

[0061] This system will enable users to go out safely and local governments to efficiently manage safety in their cities. This invention will contribute to creating an environment where pedestrians, including the elderly, can go out with peace of mind.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The user launches Silver Guide.

[0065] The device will initialize the GPS module and begin obtaining current location information.

[0066] Step 2:

[0067] As users walk around town, the device periodically updates its GPS data to track their location.

[0068] Step 3:

[0069] When the user reaches a location where he or she feels danger, he or she presses the danger detection button on the terminal.

[0070] Step 4:

[0071] The device records the GPS data and timestamp of the location where the button was pressed. For example, the data is generated in the format location_data = {timestamp: current time, latitude: latitude, longitude: longitude}.

[0072] Step 5:

[0073] The device sends the recorded location information and a timestamp to the server using a POST request via the REST API.

[0074] Step 6:

[0075] The server receives the data sent from the device and stores it in a database, for example using an SQL query such as INSERT INTO danger_points (timestamp, latitude, longitude) VALUES (current time, latitude, longitude).

[0076] Step 7:

[0077] The server periodically retrieves the data on danger points from the database and analyzes it. Specifically, it counts the number of reports at common points using an SQL query. Example: SELECT latitude, longitude, COUNT() FROM danger_points GROUP BY latitude, longitude HAVING COUNT() > n

[0078] Step 8:

[0079] The server identifies locations that have been reported a certain number of times and marks them as dangerous.

[0080] Step 9:

[0081] The server prepares to provide details of locations marked as dangerous to local authorities. It generates a list of danger points and sends it to the municipal system via API or notification system. Example: POST / api / municipalities / danger_points {dangerous_locations: [location1, location2,...]}

[0082] Step 10:

[0083] The server uses the collected data to train a machine learning model to predict future hazards, and this predictive model is updated regularly.

[0084] Step 11:

[0085] When the user approaches a known danger point, the device will use its built-in speaker to issue an audible warning, such as "There is a step ahead, so be careful."

[0086] Example 1

[0087] 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."

[0088] The present invention relates to a system for creating an environment in which elderly people and other pedestrians can move around town safely. Conventional systems have the drawback of being time-consuming to detect and report dangerous areas, making it difficult to take measures before danger actually occurs. Furthermore, information on dangerous areas is not properly managed, which can delay the response of local governments. There is a need to solve these problems by more quickly and accurately predicting dangerous areas, providing warnings to users, and promoting the provision of appropriate information to local governments.

[0089] 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.

[0090] In this invention, the server includes means for analyzing the received location information and providing information on locations determined to be dangerous to local governments, means for predicting future dangerous locations using a machine learning library, and means for periodically analyzing the location information stored in the database using a statistical anomaly detection algorithm.As a result, when a user senses danger in a city, the location information is quickly obtained and sent to a computer system, thereby providing accurate information to local governments, predicting future dangerous locations, and enabling them to take preventative measures.

[0091] "Users" refers to elderly people and pedestrians who use the system to get around town.

[0092] A "button" refers to an input device that a user presses when they sense danger to notify the system of the danger.

[0093] A "Global Positioning System module" refers to a device that measures its location on Earth using satellite signals, commonly known as a GPS module.

[0094] A "communication module" is a communication device for transmitting recorded data to other devices or systems.

[0095] "Computer system" refers to a computing device for receiving, storing, analyzing, and communicating data.

[0096] A "hazardous location" is a location that the system has analyzed multiple data points and deemed dangerous because it exceeded certain criteria.

[0097] "Local government" refers to a regional administrative unit such as a city, town, or village, and is an organization responsible for managing public safety.

[0098] "Audio notification means" refers to a device or technology that generates audio to alert the user to a danger.

[0099] "Encryption" is the process of converting information to protect it from external interference or unauthorized access.

[0100] "Database" refers to a software system for systematically storing and managing collected data.

[0101] A "statistical anomaly detection algorithm" is a mathematical method used to identify patterns and outliers in data.

[0102] "Machine learning library" refers to software tools and libraries used to build and train machine learning models.

[0103] A "machine learning model" is an algorithm that predicts future data and patterns based on past data.

[0104] This invention relates to a system for providing an environment in which elderly people and other pedestrians can move around safely in the city. This system consists of a user, a terminal (Silver Guide), and a server. The specific processing of each component and program is explained below.

[0105] System configuration

[0106] 1. Users: Elderly people and other pedestrians who use the system. Users move around the city with the Silver Guide.

[0107] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[0108] 3. Server: A computer system that receives, stores, and analyzes data sent from terminals and provides appropriate information to local governments and users.

[0109] Program processing overview

[0110] Initial setup and data acquisition

[0111] When a user launches Silver Guide, the device initializes the GPS module and acquires real-time location information. Specifically, the device receives signals from GPS satellites and calculates the current location's longitude and latitude. This process uses the NMEA protocol.

[0112] Recording of dangerous areas

[0113] When a user presses the danger detection button at a location where they sense danger, the device records the location information and timestamp at that moment. For example, if a user discovers a large step on the sidewalk, they press the danger detection button on the spot and the device records the location information.

[0114] Sending and Receiving Data

[0115] The recorded location information and timestamp are sent to the server via the device's communication module (e.g., 4G LTE module). The sent data is AES encrypted to ensure security. The server receives the data, stores it in temporary memory, and then saves it in a database (e.g., MySQL or PostgreSQL).

[0116] Analyzing the data

[0117] The server periodically analyzes the received data, and if multiple users report the same location or if a specific pattern is found, it determines that location as a "danger zone." The data is analyzed using a statistical anomaly detection algorithm using Python and the Pandas library.

[0118] Notification to local governments

[0119] If the server determines that a location is at risk, it will notify the local government using an automated email system (e.g., SendGrid). The email notification will include specific location information (e.g., longitude and latitude), a timestamp, and the number of reports.

[0120] Prediction using machine learning models

[0121] The server uses machine learning libraries (e.g., TensorFlow) to train a predictive model based on the collected data to predict future hazards. The model is periodically updated with new data and notifies local governments in advance.

[0122] User warning notification

[0123] When the user approaches a known dangerous spot, the device will issue a voice warning using the built-in speaker. For example, it will make an announcement such as, "There is a step ahead, so please be careful." This function allows the user to recognize danger in advance and move safely.

[0124] Specific examples

[0125] 1. The user discovers a steep step on a path in a park they usually walk through and presses the danger detection button on the spot.

[0126] 2. The device records its current location (e.g., longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0127] 3. The recorded data is sent to the server via the terminal's communication module.

[0128] 4. The server receives the data and stores it in a database.

[0129] 5. The server analyzes the incident and determines that similar reports have been made multiple times by other users of the same park.

[0130] 6. The server provides this information to local authorities, notifying them that repairs are needed.

[0131] 7. Local governments will use the information provided to promptly begin repair work on the steps.

[0132] 8. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps."

[0133] Examples of prompt statements

[0134] "Record and send the GPS information of your current location"

[0135] "Analyze the patterns in the data that report hot spots at this location."

[0136] "Generate a model that predicts future danger spots based on the collected data."

[0137] "Generate an audio message to warn users when they approach this location"

[0138] In this way, this system provides an environment in which users can move around safely, and enables local governments to efficiently manage the safety of their cities.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] Initial setup and data acquisition

[0142] The user starts Silver Guide. The input is a start command from the user. The device first initializes the GPS module (e.g., u-blox module) and receives signals from GPS satellites to collect current location information. For data calculation, the device analyzes the received data using the NMEA protocol and calculates the current longitude and latitude. The output is the current location information (longitude, latitude).

[0143] Step 2:

[0144] Recording of dangerous areas

[0145] When a user senses danger, they press the danger detection button. The input is the user pressing the button event. The device records the location information and timestamp at that moment. As data processing, the longitude, latitude, and time information of the current location are saved in memory as a single data set. The output is the recorded location data (longitude, latitude, timestamp).

[0146] Step 3:

[0147] Sending data

[0148] The device sends the recorded location information and timestamp to the server via a communication module (e.g., 4G LTE module). The input is the recorded location data. The data operation protects the data using AES encryption and sends it to the server using a transmission protocol (e.g., HTTP or MQTT). The output is the encrypted data transmission result.

[0149] Step 4:

[0150] Receiving and storing data

[0151] The server stores the received data in memory. The input is the encrypted data sent from the device. The data is then processed by decrypting it using AES encryption and checking the integrity of the data. An SQL query is created to store the data in a database (e.g., MySQL, PostgreSQL). The output is the location data stored in the database.

[0152] Step 5:

[0153] Analyzing the data

[0154] The server periodically analyzes the location data in the database. The input is the location data in the database. For data processing, Python and the Pandas library are used to analyze the frequency and consistency of data points based on statistical anomaly detection algorithms. The output is a list of locations that are determined to be dangerous.

[0155] Step 6:

[0156] Notification to local governments

[0157] The server provides information on identified dangerous locations to local governments. The input is the analysis results of the dangerous location data. Data is processed using an automated email system (e.g., SendGrid) to generate a notification email about the dangerous location. The output is a notification email sent to the local government.

[0158] Step 7:

[0159] Prediction using machine learning models

[0160] The server uses a machine learning library (e.g., TensorFlow) to train a model based on the collected data and predict future hazardous locations. The inputs are past location data and hazardous location data. Data calculations include data preprocessing, model training, and evaluation. The output is a prediction model for future hazardous locations and the prediction results.

[0161] Step 8:

[0162] User warning notification

[0163] When the user approaches a known dangerous spot, the device issues a voice warning through its built-in speaker. The inputs are current location information and dangerous spot data. Data calculations compare the current location information with known dangerous spot data and generate a voice message if a warning is necessary. The output is a voice warning such as "There is a step ahead, so be careful."

[0164] (Application example 1)

[0165] 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."

[0166] Modern society demands support systems to help elderly people and those with walking difficulties navigate safely around town. However, current systems are limited in their scope of effectiveness, and lack of coordination with autonomous vehicles in particular makes it difficult to fully ensure pedestrian safety. In addition, the detection and improvement of dangerous areas is often delayed, requiring rapid action by local governments and related organizations.

[0167] 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.

[0168] In this invention, the server includes: a means for a user to press a button when they sense danger in a city; a satellite positioning system that acquires location information of the location when the button is pressed; a communication means for transmitting the acquired location information to the server; a means for the server to analyze the received location information and provide information on locations determined to be dangerous to public institutions; a means for issuing an audio warning to a user approaching a location determined to be dangerous by the server; a means for the autonomous vehicle to adjust or stop its speed when approaching a dangerous location; and a means for the autonomous vehicle to acquire data on dangerous locations from the server. This enables the autonomous vehicle to take appropriate action in real time while ensuring the safety of pedestrians. It also provides information to local governments so that they can quickly improve dangerous locations.

[0169] "Users" refers to elderly people and people who have difficulty walking who use the system to move safely around the city.

[0170] "City" refers to areas where pedestrians frequently come and go, such as urban areas and public places.

[0171] "Means for pressing a button when danger is sensed" refers to an interface that a user can physically press when they sense danger, in order to notify the system of the presence of danger.

[0172] "Satellite Positioning System" means a satellite technology used to precisely determine location on Earth, and typically includes GPS.

[0173] "Communication Method" refers to the process of using the Internet or other network technology to transmit data to a server.

[0174] A "server" is a computer system that receives, stores, and analyzes data and provides appropriate information to users and public institutions.

[0175] "Public agency" refers to a government or administrative organization responsible for managing public safety, such as a local government, police, or fire department.

[0176] An "autonomous vehicle" refers to a vehicle that can drive itself without human intervention.

[0177] "Danger points" refer to specific locations that the server determines pose a high risk to users or autonomous vehicles.

[0178] "Means of issuing audio warnings" refers to a system that uses speakers or voice synthesis technology to issue audio warnings to alert users to danger.

[0179] "Means to adjust speed or stop" refers to a control system that takes appropriate action when an autonomous vehicle approaches a hazard.

[0180] "Means for obtaining data" refers to the communication process by which an autonomous vehicle obtains the necessary data from a server.

[0181] The system for implementing this invention ensures the safety of pedestrians while cooperating with autonomous vehicles to share and utilize safety information in real time. The specific configuration and operation of this system are described below.

[0182] 1. System Configuration

[0183] Users: Elderly people and other pedestrians who use the system. They carry a stick-shaped device (Silver Guide) and move around the city.

[0184] Device (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[0185] Autonomous vehicle: A vehicle that can drive itself without human intervention, equipped with a communication module and control system.

[0186] Server: A computer system that receives, stores, and analyzes data sent from terminals and autonomous vehicles, and provides appropriate information to local governments, users, and autonomous vehicles.

[0187] 2. Program Processing

[0188] Program Overview

[0189] The server receives and analyzes the location information of the device and the autonomous vehicle, identifies and predicts dangerous areas, and provides this information to public institutions, users, and autonomous vehicles in real time.

[0190] User's walking movements

[0191] When a user walks around town with the stick-shaped device, the device acquires GPS data in real time and tracks the user's current location. When the user presses the danger detection button at a point where they sense danger, the location information and timestamp at that time are recorded.

[0192] Sending and Receiving Data

[0193] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database, using encryption technology to ensure security.

[0194] Analyzing data and identifying hot spots

[0195] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is identified. Furthermore, it generates a machine learning model based on the collected data to predict future dangerous locations.

[0196] Collaboration with autonomous vehicles

[0197] The autonomous vehicle periodically retrieves data on dangerous locations from the server and calculates the distance between its current location and the dangerous location in real time. When approaching a dangerous location, the autonomous vehicle will adjust its speed or stop appropriately to ensure the safety of pedestrians.

[0198] Warning notice

[0199] Users approaching known danger points will receive a voice warning using the device's built-in speaker. Similarly, autonomous vehicles will issue warnings to pedestrians when approaching danger points.

[0200] 3. Adding specific examples

[0201] Usage example 1:

[0202] A user discovers a steep step on a path in a park they regularly walk through. They press the danger detection button on the spot. The device records its current location information (e.g., longitude 35.6895, latitude 139.6917) and a timestamp, and sends them to a server. The server then confirms similar reports from other pedestrians and notifies the local government. The local government quickly repairs the step, and when the user returns, a voice message is sent to the user saying, "Please be careful as there is a step ahead."

[0203] Usage example 2:

[0204] A self-driving vehicle approaches while a user is walking in a city. The self-driving vehicle receives the danger point data from the server, detects that the user is approaching a danger point, and adjusts its speed appropriately as it proceeds. This ensures the user's safety.

[0205] Prompt Sentence Examples

[0206] "Please develop a system that allows elderly people to move around safely using a smart cane. The system will acquire GPS data, record dangerous locations, and send them to a server. It will also provide autonomous vehicles with the ability to detect danger in real time based on this data and adjust their speed or stop."

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] The user starts walking around town. The device acquires the user's current location (GPS data) in real time using the built-in satellite positioning system. The input at this point is the user's current longitude and latitude. The device continues to record this GPS data. The output is the user's current location information.

[0210] Step 2:

[0211] When a user senses danger, they press the danger detection button on their device. This causes the device to acquire location information (longitude and latitude) and a timestamp at that time. The inputs are the signal that the button was pressed, current location information, and the current time. The output is the location information and timestamp of the danger area.

[0212] Step 3:

[0213] The terminal transmits the acquired location information and timestamp of the dangerous spot to the server via the communication module. The input is the location information and timestamp of the dangerous spot. The output is the result of data transmission to the server (success or failure).

[0214] Step 4:

[0215] The server stores the data received from the device in a database. This database also includes information on previously reported dangerous locations. The input is the location information and timestamp of the dangerous location sent from the device. The output is the result of storing the data in the database (success or failure).

[0216] Step 5:

[0217] The server periodically analyzes the data stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is present. The input is the past data of dangerous locations in the database. The output is a list of dangerous locations as a result of the analysis.

[0218] Step 6:

[0219] To ensure safety, the server predicts future dangerous locations by incorporating information about dangerous locations into a prediction model. The collected data is processed using a machine learning model to generate prediction results. The input is data on past dangerous locations. The output is a list of predicted dangerous locations.

[0220] Step 7:

[0221] The server provides information on predicted dangerous locations to public institutions and autonomous vehicles. It retrieves data from its own database and sends it to the necessary entities. The input is a list of predicted dangerous locations. The output is the result of sending the data to the public institutions or autonomous vehicles (success or failure).

[0222] Step 8:

[0223] The autonomous vehicle receives the hazard location data sent from the server in real time and calculates the distance between its current location and the hazard location. The input is the autonomous vehicle's current location information and the hazard location data. The output is the distance information to the hazard location.

[0224] Step 9:

[0225] When an autonomous vehicle approaches a dangerous spot, it automatically adjusts its speed or stops. The input is information about the distance to the dangerous spot and the autonomous vehicle's control system. The output is the speed adjustment or stopping action.

[0226] Step 10:

[0227] The server issues an audio warning to users approaching dangerous locations. The server checks the user's current location information and issues a warning based on a list of dangerous locations. The input is the user's current location information and a list of dangerous locations. The output is an audio warning notification.

[0228] 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.

[0229] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion engine that recognizes the user's emotions, a high level of safety and comfort is achieved. The specific configuration of this system and the program processing are described below.

[0230] System configuration

[0231] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0232] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, emotion engine, sensors (voice and facial expressions), and voice notification function.

[0233] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[0234] Program processing overview

[0235] Use in the city

[0236] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[0237] Sending and Receiving Data

[0238] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. Encryption technology is generally used to ensure security.

[0239] Analyzing the data

[0240] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if there is a specific pattern.The server then provides information on locations that are deemed dangerous to local governments, facilitating repairs.

[0241] Emotion Engine Functions

[0242] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. For example, it is equipped with a camera and microphone to detect when the user is feeling anxious or scared. It also adjusts the intensity and content of warnings depending on the user's emotional state.

[0243] Creating a predictive model

[0244] The server generates a machine learning model based on the collected data to predict future danger zones. This prediction model is updated regularly. When a danger zone is predicted, local governments are notified in advance so that preventive measures can be taken.

[0245] Emergency reporting

[0246] The device is equipped with a sensor that detects the user's fall or impact, and if the user falls, it will make an emergency call to the police, fire department, or family members.

[0247] Warning notice

[0248] When the user approaches a known danger point, the device will issue a warning using its built-in speaker, such as "There is a step ahead, please be careful." If the emotion engine detects the user's anxiety or fear, it will increase the intensity of the warning or provide more detailed instructions.

[0249] Specific examples

[0250] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[0251] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0252] 3. The recorded data is sent to the server via the terminal's communication module.

[0253] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0254] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[0255] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[0256] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps." Furthermore, if the emotion engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[0257] This system allows users to go out safely and enables local governments to efficiently manage the safety of their cities. The introduction of an emotion engine enables flexible responses according to the individual conditions of each user, providing an even higher level of safety.

[0258] The processing flow will be explained below.

[0259] Step 1:

[0260] The user launches Silver Guide.

[0261] The device will initialize the GPS module and begin obtaining current location information.

[0262] Step 2:

[0263] As users walk around town, the device periodically updates its GPS data to track their location.

[0264] Step 3:

[0265] The device's emotion engine analyzes the user's voice and facial expressions to assess their emotional state in real time. Specifically, the camera captures facial expression data and the microphone captures voice data.

[0266] Step 4:

[0267] When the user reaches a location where he or she feels danger, he or she presses the danger detection button on the terminal.

[0268] Step 5:

[0269] The device records the GPS data and timestamp of the location where the button was pressed. For example, the data is generated in the format location_data = {timestamp: current time, latitude: latitude, longitude: longitude}.

[0270] Step 6:

[0271] The device sends the recorded location information, timestamp, and emotion data (e.g., anxiety score) generated by the emotion engine to the server using a POST request via the REST API.

[0272] Step 7:

[0273] The server receives the data sent from the device and stores it in a database, for example, using an SQL query such as INSERT INTO danger_points (timestamp, latitude, longitude, emotion_score) VALUES (current time, latitude, longitude, emotion_score).

[0274] Step 8:

[0275] The server periodically retrieves the danger point data from the database and analyzes it. Specifically, it counts the number of reports and emotion scores for common points using an SQL query. Example: SELECT latitude, longitude, COUNT(), AVG(emotion_score) FROM danger_points GROUP BY latitude, longitude HAVING COUNT() > n

[0276] Step 9:

[0277] The server identifies locations that have been reported more than a certain number of times or have a high emotional score and marks them as dangerous locations.

[0278] Step 10:

[0279] The server prepares to provide details of locations marked as dangerous to local authorities. It generates a list of danger points and sends it to the municipal system via API or notification system. Example: POST / api / municipalities / danger_points {dangerous_locations: [location1, location2,...]}

[0280] Step 11:

[0281] The server uses the collected data to train a machine learning model to predict future hazards, and this predictive model is updated regularly.

[0282] Step 12:

[0283] When the user approaches a known danger point, the device will issue a warning using the built-in speaker, such as "Be careful, there is a step ahead." If the emotion engine detects anxiety or fear, the device will issue an additional instruction such as "Walk slowly."

[0284] Step 13:

[0285] When the device's fall and shock sensors detect that the user has fallen, the device automatically makes an emergency call to the police, fire department, or family members. The call includes latitude and longitude information and emotional data.

[0286] In this way, the Silver Guide increases the safety of users and enables local governments to respond quickly. Furthermore, the introduction of an emotion engine allows for flexible responses according to individual conditions, providing an even higher level of safety.

[0287] Example 2

[0288] 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."

[0289] There is a need for effective methods to ensure safe urban mobility for elderly people and pedestrians, and to quickly identify and repair potential hazards. There is also a need for flexible warning functions that respond to the user's emotional state, and for systems that instantly report falls and impacts.

[0290] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing the user's voice and facial expression to detect the user's emotional state, a means for adjusting the strength and content of the warning depending on the user's emotional state, and a means for generating a machine learning model using collected location information data to predict future dangerous locations. This allows users to move safely around town, provides a flexible warning function according to the user's emotional state, and enables potential dangerous locations to be quickly identified and repaired. Furthermore, an emergency reporting function is also provided, further improving user safety.

[0291] "Users" refers to elderly people and other pedestrians who use the system to get around town.

[0292] "Means for pressing a button" refers to a button device that a user can press when they sense danger.

[0293] "Location information acquisition device" refers to a device that acquires location information in real time, such as a GPS module.

[0294] "Communication device" refers to a device that uses wireless communication technology to transmit acquired location information to a server.

[0295] "Server" refers to the computer system that analyzes received location information and stores and processes the data.

[0296] "Municipality" refers to local public bodies such as cities, towns, villages, and wards.

[0297] "Means for notifying the user by voice" refers to a device that uses a built-in speaker to issue a voice warning to the user.

[0298] "Means for detecting emotional state" refers to algorithms or devices that analyze the user's voice and facial expressions to determine their emotions in real time.

[0299] "Means for adjusting the intensity and content of warnings" refers to the ability to dynamically change the content and intensity of warnings based on the user's emotional state.

[0300] "Means for generating a machine learning model" refers to a process of using a machine learning algorithm to predict future hot spots using collected data.

[0301] "Devices that detect falls and impacts" refers to devices that use acceleration sensors, gyroscopes, etc. to detect falls and impacts by users.

[0302] "Means for making emergency calls" refers to a system that automatically notifies the police, fire department, or family members when the user experiences an emergency such as a fall.

[0303] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion engine that recognizes the user's emotions, a high level of safety and comfort is achieved. The specific configuration of this system and the program processing are described below.

[0304] System configuration

[0305] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0306] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, emotion engine, sensors (voice and facial expressions), and voice notification function.

[0307] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[0308] Program processing overview

[0309] Use in the city

[0310] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[0311] Sending and Receiving Data

[0312] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. To ensure security, encryption technology is generally used. Specifically, AES (Advanced Encryption Standard) encryption technology is used.

[0313] Analyzing the data

[0314] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is identified. For example, it runs scripts using Python to cross-tabulate the data and apply anomaly detection algorithms. The server then provides information on dangerous locations to local governments to facilitate repairs.

[0315] Emotion Engine Functions

[0316] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. For example, it uses the Google Cloud Speech-to-Text API to analyze audio recorded by the microphone, and OpenCV and facial recognition APIs to analyze facial images captured by the camera. The emotion engine detects when the user feels anxiety or fear, and adjusts the intensity and content of warnings depending on the user's emotional state.

[0317] Creating a predictive model

[0318] The server generates a machine learning model based on the collected data to predict future dangerous areas. This predictive model is created using machine learning libraries such as TensorFlow and Scikit-learn. New data is periodically imported and the model is updated to maintain the accuracy of the predictions. When dangerous areas are predicted, local governments are notified in advance so that preventive measures can be taken.

[0319] Emergency reporting

[0320] The device is equipped with a sensor that detects falls and impacts. When the user falls, the device will make an emergency call to the police, fire department, or family members that have been registered in advance. This function is implemented, for example, using an acceleration sensor.

[0321] Warning notice

[0322] When the user approaches a known danger point, the device will issue a warning using its built-in speaker, such as "There is a step ahead, please be careful." If the emotion engine detects the user's anxiety or fear, it will increase the intensity of the warning or provide more detailed instructions.

[0323] Specific examples

[0324] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[0325] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0326] 3. The recorded data is sent to the server via the terminal's communication module.

[0327] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0328] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[0329] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[0330] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps." Furthermore, if the emotion engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[0331] As a concrete example, it is possible to simulate the system by inputting the following prompts into the generative AI model:

[0332] Example prompt: "A user discovers a steep step while walking through a park and presses the danger detection button on the Silver Guide. Please explain in detail how this information is sent to the server and how repair work is subsequently carried out."

[0333] This system allows users to go out safely and enables local governments to efficiently manage the safety of their cities. The introduction of an emotion engine enables flexible responses according to the individual conditions of each user, providing an even higher level of safety.

[0334] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0335] Step 1:

[0336] When a user starts walking around town with the Silver Guide, the device uses the GPS module to obtain real-time location information. The GPS module outputs longitude and latitude data as input. The device temporarily stores this location information in its internal memory.

[0337] Specific behavior:

[0338] The device acquires longitude and latitude data every 10 seconds and stores it in memory.

[0339] Step 2:

[0340] When a user presses the danger detection button at a location where they sense danger, the device records the location information and timestamp at that time. The input is the button press signal, longitude, latitude, and timestamp, and the device outputs it.

[0341] Specific behavior:

[0342] When the user presses the button, the device displays the message "Danger button has been pressed" and stores the acquired longitude, latitude and timestamp in memory.

[0343] Step 3:

[0344] The recorded location information and timestamp are sent to the server using the device's communication module. The input is the acquired longitude, latitude, and timestamp, and the output is AES encrypted to ensure data security.

[0345] Specific behavior:

[0346] The device encrypts the data within 5 seconds and sends it to the server.

[0347] Step 4:

[0348] The server receives the data sent from the device and stores it in a database. The input is the encrypted longitude, latitude, and timestamp. The data is decrypted before being stored in the database.

[0349] Specific behavior:

[0350] The server decrypts the received data and adds it to the PostgreSQL database.

[0351] Step 5:

[0352] The server periodically analyzes the data of dangerous locations stored in the database. It takes as input the collected location data and outputs it. It runs a Python script and applies cross-tabulation and anomaly detection algorithms to report information on locations that are deemed dangerous to local authorities.

[0353] Specific behavior:

[0354] The server cross-tabulates data from the past week to identify areas where the same location has been reported multiple times.

[0355] Step 6:

[0356] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. The input is voice data captured by the microphone and camera, and facial image data is output. Data analysis is performed using the Google Cloud Speech-to-Text API and OpenCV. Alerts are adjusted based on the emotional state detected.

[0357] Specific behavior:

[0358] If the device determines that the user is feeling anxious, it will increase the intensity of the warning.

[0359] Step 7:

[0360] The server generates a machine learning model based on the accumulated data and predicts future dangerous areas. The collected location information data is output as input. The machine learning model is trained using TensorFlow and Scikit-learn.

[0361] Specific behavior:

[0362] The server retrains the model every time new data is collected, maintaining prediction accuracy.

[0363] Step 8:

[0364] The device is equipped with sensors to detect falls and impacts, and if the user falls, it will make an emergency call to the police, fire department, or family members. Data from the accelerometer and gyroscope is output as input.

[0365] Specific behavior:

[0366] When the device detects a fall, it will send an SMS or an automated call to a pre-set emergency number.

[0367] Step 9:

[0368] When the user approaches a known danger point, the device will issue an audio warning using the built-in speaker. Location data and emotional state data are output as inputs.

[0369] Specific behavior:

[0370] The device will announce, "Be careful, there is a step ahead," and provide additional instructions if necessary.

[0371] Through the specific processing flow described above, the system supports users in moving safely around the city and enables the rapid identification and repair of dangerous areas.

[0372] (Application example 2)

[0373] 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."

[0374] Ensuring safety when walking around town is an extremely important issue these days. Detecting and responding to potential dangers is especially important for the elderly and physically frail. Users may feel anxious or scared in certain places, and a means to respond quickly to these situations is needed. However, current systems have difficulty detecting these emotions in real time and issuing appropriate warnings immediately. Furthermore, they lack the ability to predict future dangers.

[0375] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing received location information and providing information on places determined to be dangerous to the local government, means for issuing an audio warning to a user who approaches a place determined to be dangerous, and an emotion analysis engine for analyzing the emotional state of the user and adjusting the content of the warning notification if the user feels anxiety or fear. This supports users to move around town more safely and comfortably, and enables the local government to effectively manage dangerous areas and respond quickly.

[0376] A "location measurement module" is a device for acquiring the current location of a user and outputs data including location information.

[0377] The "information transmission module" is a communication device for transmitting the acquired location information to a server, and transmits and receives data.

[0378] An "emotion analysis engine" is software or hardware that analyzes a user's voice, facial expressions, etc. to detect their emotional state, making it possible to grasp the anxiety or fear the user is feeling in real time.

[0379] A "machine learning model" is an algorithm that performs statistical analysis and predictions based on collected data, and is a system that can predict future dangerous areas.

[0380] "Warning notification means" refers to devices or software that issue audio or visual warnings when a user approaches a dangerous area.

[0381] "Users" refers to people who use the system to get around town, especially elderly people and other pedestrians.

[0382] A "server" is a computer system that receives, stores, and analyzes location information and emotional data, thereby providing appropriate information to local governments and users.

[0383] The "danger detection button" is a means that users can press when they sense danger in the city, and this records their current location information.

[0384] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion analysis engine that recognizes the user's emotions, a high level of safety and comfort is achieved.

[0385] System configuration

[0386] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0387] 2. Terminal (Silver Guide): An intelligent accessory equipped with a location measurement module, information transmission module, danger detection button, emotion analysis engine, sensors (voice and facial expressions), and voice notification function.

[0388] 3. Server: A computer system that receives, stores, and analyzes data sent from terminals and provides appropriate information to local governments and users.

[0389] Program processing overview

[0390] 1. User location tracking

[0391] We use your device's built-in location measurement module (e.g., GPS) to track your location in real time, allowing us to accurately track your movements.

[0392] 2. Detecting dangerous areas

[0393] The location information acquired through the device's information transmission module is sent to a server, which then identifies dangerous areas and automatically stores them in a database. Information on dangerous areas reported by store employees and other customers is also incorporated.

[0394] 3. Analysis using a sentiment analysis engine

[0395] The device uses a microphone and camera to analyze the user's voice and facial expressions in real time, and an emotion analysis engine is used to detect their emotional state (anxiety or fear), allowing the device to understand their mental state and provide appropriate warnings and support.

[0396] 4. Warning notice

[0397] When a user approaches a known dangerous spot, the device's voice notification function will issue an audible warning, and if the emotion analysis engine detects anxiety or fear in the user, the strength and content of the warning will be adjusted.

[0398] 5. Data transmission and analysis

[0399] The device encrypts the collected data and sends it to a server, which stores it in a database and periodically analyzes the data to generate a machine learning model for predicting future risk areas.

[0400] Specific examples

[0401] 1. A user discovers a steep step on a path in a park they regularly walk through. They press the danger detection button on the spot. The device records the location information and timestamp at that time and sends them to the server.

[0402] 2. The recorded data is received by a server and stored in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0403] 3. The server uses this information to notify the local government that repairs are necessary, and the local government uses the information provided to promptly begin repair work on the steps.

[0404] 4. When the user returns to the park, the device will issue a voice warning saying, "Be careful, there are steps." If the emotion analysis engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[0405] This system allows users to go out safely and enables local governments to efficiently manage safety in their cities. The introduction of an emotion analysis engine enables flexible responses according to the individual state of each user, providing an even higher level of safety.

[0406] *Example of a prompt to input to the generative AI model:

[0407] Design an AI system that monitors users' facial expressions in real time as they move through a physical store, and issues audio and visual warnings to ensure safety. The system also issues warnings when users approach known hazards or crowded areas. The system manages the user's location and adapts to their emotional state.

[0408] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0409] Step 1:

[0410] The user walks around the city

[0411] Input: User's location, voice, facial expression

[0412] Processing: The device acquires real-time location information using a location measurement module (GPS) and captures voice and facial expressions using a camera and microphone.

[0413] Specific operation: While the user is walking, the device's sensors continuously collect data. The device collects this data in real time and performs initial processing in its internal processor.

[0414] Output: Real-time location information, audio data, facial expression data

[0415] Step 2:

[0416] The danger detection button is pressed

[0417] Input: Button press event, current location, timestamp

[0418] Processing: When the button is pressed, the device records the current location and a timestamp.

[0419] Specific operation: When the user senses danger and presses the button, the device acquires data from the location information measurement module and temporarily stores it in memory along with a timestamp.

[0420] Output: Recorded location information, timestamp

[0421] Step 3:

[0422] Sending data

[0423] Input: Recorded location information, timestamp

[0424] Processing: The device sends the recorded location information and timestamp to the server via the information transmission module. The data is encrypted before transmission.

[0425] Specific operation: Data packets sent from the device are sent to the server using a communication protocol. The data is protected by encryption technology such as SSL / TLS.

[0426] Output: Location information received by the server, timestamp

[0427] Step 4:

[0428] Analyzing incoming data

[0429] Input: Location information stored on the server, timestamp

[0430] Processing: The server analyzes the received data and decides whether to mark a hotspot. If there are multiple reports, they are prioritized according to a specific algorithm.

[0431] Specific operation: The analysis engine on the server retrieves and analyzes the received data from the database. If there are multiple reports, the risk level is evaluated based on frequency and degree of agreement. For example, cluster analysis of data surrounding the reporting location can be performed to ensure that risk areas are identified.

[0432] Output: Location information and details of locations that are deemed dangerous

[0433] Step 5:

[0434] Warning notice

[0435] Input: Server analysis results (location information and details of dangerous areas)

[0436] Processing: The server sends information about the danger zone back to the device, which then issues a voice warning to the user. An emotion analysis engine evaluates the user's real-time emotional state and adjusts the warning accordingly.

[0437] Specific operation: The device that receives the data sent by the server uses its voice notification function to play a message such as "There is a step ahead, please be careful." If the emotion analysis engine detects the user's anxiety, it provides additional instructions such as "Please walk slowly."

[0438] Output: Audio alert, adjust notification content based on emotion

[0439] Through these steps, the system will help users move safely around the city and enable local governments to efficiently manage dangerous areas and respond quickly.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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."

[0456] The system for carrying out this invention is designed to create an environment in which users can move safely around town. The specific configuration of this system and the processing of the program will be described below.

[0457] System configuration

[0458] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0459] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[0460] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[0461] Program processing overview

[0462] Use in the city

[0463] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[0464] Sending and Receiving Data

[0465] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. Encryption technology is generally used to ensure security.

[0466] Analyzing the data

[0467] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if there is a specific pattern.The server then provides information on locations that are deemed dangerous to local governments, facilitating repairs.

[0468] Creating a predictive model

[0469] The server generates a machine learning model based on the collected data to predict future danger zones. This prediction model is updated regularly. When a danger zone is predicted, local governments are notified in advance so that preventive measures can be taken.

[0470] Warning notice

[0471] When the user approaches a known dangerous spot, the device will issue a warning using the built-in speaker. For example, it may announce, "There is a step ahead, so be careful." This function allows the user to recognize danger in advance and move safely.

[0472] Specific examples

[0473] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[0474] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0475] 3. The recorded data is sent to the server via the terminal's communication module.

[0476] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0477] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[0478] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[0479] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps."

[0480] This system will enable users to go out safely and local governments to efficiently manage safety in their cities. This invention will contribute to creating an environment where pedestrians, including the elderly, can go out with peace of mind.

[0481] The processing flow will be explained below.

[0482] Step 1:

[0483] The user launches Silver Guide.

[0484] The device will initialize the GPS module and begin obtaining current location information.

[0485] Step 2:

[0486] As users walk around town, the device periodically updates its GPS data to track their location.

[0487] Step 3:

[0488] When the user reaches a location where he or she feels danger, he or she presses the danger detection button on the terminal.

[0489] Step 4:

[0490] The device records the GPS data and timestamp of the location where the button was pressed. For example, the data is generated in the format location_data = {timestamp: current time, latitude: latitude, longitude: longitude}.

[0491] Step 5:

[0492] The device sends the recorded location information and a timestamp to the server using a POST request via the REST API.

[0493] Step 6:

[0494] The server receives the data sent from the device and stores it in a database, for example using an SQL query such as INSERT INTO danger_points (timestamp, latitude, longitude) VALUES (current time, latitude, longitude).

[0495] Step 7:

[0496] The server periodically retrieves the data on danger points from the database and analyzes it. Specifically, it counts the number of reports at common points using an SQL query. Example: SELECT latitude, longitude, COUNT() FROM danger_points GROUP BY latitude, longitude HAVING COUNT() > n

[0497] Step 8:

[0498] The server identifies locations that have been reported a certain number of times and marks them as dangerous.

[0499] Step 9:

[0500] The server prepares to provide details of locations marked as dangerous to local authorities. It generates a list of danger points and sends it to the municipal system via API or notification system. Example: POST / api / municipalities / danger_points {dangerous_locations: [location1, location2,...]}

[0501] Step 10:

[0502] The server uses the collected data to train a machine learning model to predict future hazards, and this predictive model is updated regularly.

[0503] Step 11:

[0504] When the user approaches a known danger point, the device will use its built-in speaker to issue an audible warning, such as "There is a step ahead, so be careful."

[0505] Example 1

[0506] 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."

[0507] The present invention relates to a system for creating an environment in which elderly people and other pedestrians can move around town safely. Conventional systems have the drawback of being time-consuming to detect and report dangerous areas, making it difficult to take measures before danger actually occurs. Furthermore, information on dangerous areas is not properly managed, which can delay the response of local governments. There is a need to solve these problems by more quickly and accurately predicting dangerous areas, providing warnings to users, and promoting the provision of appropriate information to local governments.

[0508] 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.

[0509] In this invention, the server includes means for analyzing the received location information and providing information on locations determined to be dangerous to local governments, means for predicting future dangerous locations using a machine learning library, and means for periodically analyzing the location information stored in the database using a statistical anomaly detection algorithm.As a result, when a user senses danger in a city, the location information is quickly obtained and sent to a computer system, thereby providing accurate information to local governments, predicting future dangerous locations, and enabling them to take preventative measures.

[0510] "Users" refers to elderly people and pedestrians who use the system to get around town.

[0511] A "button" refers to an input device that a user presses when they sense danger to notify the system of the danger.

[0512] A "Global Positioning System module" refers to a device that measures its location on Earth using satellite signals, commonly known as a GPS module.

[0513] A "communication module" is a communication device for transmitting recorded data to other devices or systems.

[0514] "Computer system" refers to a computing device for receiving, storing, analyzing, and communicating data.

[0515] A "hazardous location" is a location that the system has analyzed multiple data points and deemed dangerous because it exceeded certain criteria.

[0516] "Local government" refers to a regional administrative unit such as a city, town, or village, and is an organization responsible for managing public safety.

[0517] "Audio notification means" refers to a device or technology that generates audio to alert the user to a danger.

[0518] "Encryption" is the process of converting information to protect it from external interference or unauthorized access.

[0519] "Database" refers to a software system for systematically storing and managing collected data.

[0520] A "statistical anomaly detection algorithm" is a mathematical method used to identify patterns and outliers in data.

[0521] "Machine learning library" refers to software tools and libraries used to build and train machine learning models.

[0522] A "machine learning model" is an algorithm that predicts future data and patterns based on past data.

[0523] This invention relates to a system for providing an environment in which elderly people and other pedestrians can move around safely in the city. This system consists of a user, a terminal (Silver Guide), and a server. The specific processing of each component and program is explained below.

[0524] System configuration

[0525] 1. Users: Elderly people and other pedestrians who use the system. Users move around the city with the Silver Guide.

[0526] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[0527] 3. Server: A computer system that receives, stores, and analyzes data sent from terminals and provides appropriate information to local governments and users.

[0528] Program processing overview

[0529] Initial setup and data acquisition

[0530] When a user launches Silver Guide, the device initializes the GPS module and acquires real-time location information. Specifically, the device receives signals from GPS satellites and calculates the current location's longitude and latitude. This process uses the NMEA protocol.

[0531] Recording of dangerous areas

[0532] When a user presses the danger detection button at a location where they sense danger, the device records the location information and timestamp at that moment. For example, if a user discovers a large step on the sidewalk, they press the danger detection button on the spot and the device records the location information.

[0533] Sending and Receiving Data

[0534] The recorded location information and timestamp are sent to the server via the device's communication module (e.g., 4G LTE module). The sent data is AES encrypted to ensure security. The server receives the data, stores it in temporary memory, and then saves it in a database (e.g., MySQL or PostgreSQL).

[0535] Analyzing the data

[0536] The server periodically analyzes the received data, and if multiple users report the same location or if a specific pattern is found, it determines that location as a "danger zone." The data is analyzed using a statistical anomaly detection algorithm using Python and the Pandas library.

[0537] Notification to local governments

[0538] If the server determines that a location is at risk, it will notify the local government using an automated email system (e.g., SendGrid). The email notification will include specific location information (e.g., longitude and latitude), a timestamp, and the number of reports.

[0539] Prediction using machine learning models

[0540] The server uses machine learning libraries (e.g., TensorFlow) to train a predictive model based on the collected data to predict future hazards. The model is periodically updated with new data and notifies local governments in advance.

[0541] User warning notification

[0542] When the user approaches a known dangerous spot, the device will issue a voice warning using the built-in speaker. For example, it will make an announcement such as, "There is a step ahead, so please be careful." This function allows the user to recognize danger in advance and move safely.

[0543] Specific examples

[0544] 1. The user discovers a steep step on a path in a park they usually walk through and presses the danger detection button on the spot.

[0545] 2. The device records its current location (e.g., longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0546] 3. The recorded data is sent to the server via the terminal's communication module.

[0547] 4. The server receives the data and stores it in a database.

[0548] 5. The server analyzes the incident and determines that similar reports have been made multiple times by other users of the same park.

[0549] 6. The server provides this information to local authorities, notifying them that repairs are needed.

[0550] 7. Local governments will use the information provided to promptly begin repair work on the steps.

[0551] 8. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps."

[0552] Examples of prompt statements

[0553] "Record and send the GPS information of your current location"

[0554] "Analyze the patterns in the data that report hot spots at this location."

[0555] "Generate a model that predicts future danger spots based on the collected data."

[0556] "Generate an audio message to warn users when they approach this location"

[0557] In this way, this system provides an environment in which users can move around safely, and enables local governments to efficiently manage the safety of their cities.

[0558] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0559] Step 1:

[0560] Initial setup and data acquisition

[0561] The user starts Silver Guide. The input is a start command from the user. The device first initializes the GPS module (e.g., u-blox module) and receives signals from GPS satellites to collect current location information. For data calculation, the device analyzes the received data using the NMEA protocol and calculates the current longitude and latitude. The output is the current location information (longitude, latitude).

[0562] Step 2:

[0563] Recording of dangerous areas

[0564] When a user senses danger, they press the danger detection button. The input is the user pressing the button event. The device records the location information and timestamp at that moment. As data processing, the longitude, latitude, and time information of the current location are saved in memory as a single data set. The output is the recorded location data (longitude, latitude, timestamp).

[0565] Step 3:

[0566] Sending data

[0567] The device sends the recorded location information and timestamp to the server via a communication module (e.g., 4G LTE module). The input is the recorded location data. The data operation protects the data using AES encryption and sends it to the server using a transmission protocol (e.g., HTTP or MQTT). The output is the encrypted data transmission result.

[0568] Step 4:

[0569] Receiving and storing data

[0570] The server stores the received data in memory. The input is the encrypted data sent from the device. The data is then processed by decrypting it using AES encryption and checking the integrity of the data. An SQL query is created to store the data in a database (e.g., MySQL, PostgreSQL). The output is the location data stored in the database.

[0571] Step 5:

[0572] Analyzing the data

[0573] The server periodically analyzes the location data in the database. The input is the location data in the database. For data processing, Python and the Pandas library are used to analyze the frequency and consistency of data points based on statistical anomaly detection algorithms. The output is a list of locations that are determined to be dangerous.

[0574] Step 6:

[0575] Notification to local governments

[0576] The server provides information on identified dangerous locations to local governments. The input is the analysis results of the dangerous location data. Data is processed using an automated email system (e.g., SendGrid) to generate a notification email about the dangerous location. The output is a notification email sent to the local government.

[0577] Step 7:

[0578] Prediction using machine learning models

[0579] The server uses a machine learning library (e.g., TensorFlow) to train a model based on the collected data and predict future hazardous locations. The inputs are past location data and hazardous location data. Data calculations include data preprocessing, model training, and evaluation. The output is a prediction model for future hazardous locations and the prediction results.

[0580] Step 8:

[0581] User warning notification

[0582] When the user approaches a known dangerous spot, the device issues a voice warning through its built-in speaker. The inputs are current location information and dangerous spot data. Data calculations compare the current location information with known dangerous spot data and generate a voice message if a warning is necessary. The output is a voice warning such as "There is a step ahead, so be careful."

[0583] (Application example 1)

[0584] 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."

[0585] Modern society demands support systems to help elderly people and those with walking difficulties navigate safely around town. However, current systems are limited in their scope of effectiveness, and lack of coordination with autonomous vehicles in particular makes it difficult to fully ensure pedestrian safety. In addition, the detection and improvement of dangerous areas is often delayed, requiring rapid action by local governments and related organizations.

[0586] 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.

[0587] In this invention, the server includes: a means for a user to press a button when they sense danger in a city; a satellite positioning system that acquires location information of the location when the button is pressed; a communication means for transmitting the acquired location information to the server; a means for the server to analyze the received location information and provide information on locations determined to be dangerous to public institutions; a means for issuing an audio warning to a user approaching a location determined to be dangerous by the server; a means for the autonomous vehicle to adjust or stop its speed when approaching a dangerous location; and a means for the autonomous vehicle to acquire data on dangerous locations from the server. This enables the autonomous vehicle to take appropriate action in real time while ensuring the safety of pedestrians. It also provides information to local governments so that they can quickly improve dangerous locations.

[0588] "Users" refers to elderly people and people who have difficulty walking who use the system to move safely around the city.

[0589] "City" refers to areas where pedestrians frequently come and go, such as urban areas and public places.

[0590] "Means for pressing a button when danger is sensed" refers to an interface that a user can physically press when they sense danger, in order to notify the system of the presence of danger.

[0591] "Satellite Positioning System" means a satellite technology used to precisely determine location on Earth, and typically includes GPS.

[0592] "Communication Method" refers to the process of using the Internet or other network technology to transmit data to a server.

[0593] A "server" is a computer system that receives, stores, and analyzes data and provides appropriate information to users and public institutions.

[0594] "Public agency" refers to a government or administrative organization responsible for managing public safety, such as a local government, police, or fire department.

[0595] An "autonomous vehicle" refers to a vehicle that can drive itself without human intervention.

[0596] "Danger points" refer to specific locations that the server determines pose a high risk to users or autonomous vehicles.

[0597] "Means of issuing audio warnings" refers to a system that uses speakers or voice synthesis technology to issue audio warnings to alert users to danger.

[0598] "Means to adjust speed or stop" refers to a control system that takes appropriate action when an autonomous vehicle approaches a hazard.

[0599] "Means for obtaining data" refers to the communication process by which an autonomous vehicle obtains the necessary data from a server.

[0600] The system for implementing this invention ensures the safety of pedestrians while cooperating with autonomous vehicles to share and utilize safety information in real time. The specific configuration and operation of this system are described below.

[0601] 1. System Configuration

[0602] Users: Elderly people and other pedestrians who use the system. They carry a stick-shaped device (Silver Guide) and move around the city.

[0603] Device (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[0604] Autonomous vehicle: A vehicle that can drive itself without human intervention, equipped with a communication module and control system.

[0605] Server: A computer system that receives, stores, and analyzes data sent from terminals and autonomous vehicles, and provides appropriate information to local governments, users, and autonomous vehicles.

[0606] 2. Program Processing

[0607] Program Overview

[0608] The server receives and analyzes the location information of the device and the autonomous vehicle, identifies and predicts dangerous areas, and provides this information to public institutions, users, and autonomous vehicles in real time.

[0609] User's walking movements

[0610] When a user walks around town with the stick-shaped device, the device acquires GPS data in real time and tracks the user's current location. When the user presses the danger detection button at a point where they sense danger, the location information and timestamp at that time are recorded.

[0611] Sending and Receiving Data

[0612] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database, using encryption technology to ensure security.

[0613] Analyzing data and identifying hot spots

[0614] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is identified. Furthermore, it generates a machine learning model based on the collected data to predict future dangerous locations.

[0615] Collaboration with autonomous vehicles

[0616] The autonomous vehicle periodically retrieves data on dangerous locations from the server and calculates the distance between its current location and the dangerous location in real time. When approaching a dangerous location, the autonomous vehicle will adjust its speed or stop appropriately to ensure the safety of pedestrians.

[0617] Warning notice

[0618] Users approaching known danger points will receive a voice warning using the device's built-in speaker. Similarly, autonomous vehicles will issue warnings to pedestrians when approaching danger points.

[0619] 3. Adding specific examples

[0620] Usage example 1:

[0621] A user discovers a steep step on a path in a park they regularly walk through. They press the danger detection button on the spot. The device records its current location information (e.g., longitude 35.6895, latitude 139.6917) and a timestamp, and sends them to a server. The server then confirms similar reports from other pedestrians and notifies the local government. The local government quickly repairs the step, and when the user returns, a voice message is sent to the user saying, "Please be careful as there is a step ahead."

[0622] Usage example 2:

[0623] A self-driving vehicle approaches while a user is walking in a city. The self-driving vehicle receives the danger point data from the server, detects that the user is approaching a danger point, and adjusts its speed appropriately as it proceeds. This ensures the user's safety.

[0624] Prompt Sentence Examples

[0625] "Please develop a system that allows elderly people to move around safely using a smart cane. The system will acquire GPS data, record dangerous locations, and send them to a server. It will also provide autonomous vehicles with the ability to detect danger in real time based on this data and adjust their speed or stop."

[0626] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0627] Step 1:

[0628] The user starts walking around town. The device acquires the user's current location (GPS data) in real time using the built-in satellite positioning system. The input at this point is the user's current longitude and latitude. The device continues to record this GPS data. The output is the user's current location information.

[0629] Step 2:

[0630] When a user senses danger, they press the danger detection button on their device. This causes the device to acquire location information (longitude and latitude) and a timestamp at that time. The inputs are the signal that the button was pressed, current location information, and the current time. The output is the location information and timestamp of the danger area.

[0631] Step 3:

[0632] The terminal transmits the acquired location information and timestamp of the dangerous spot to the server via the communication module. The input is the location information and timestamp of the dangerous spot. The output is the result of data transmission to the server (success or failure).

[0633] Step 4:

[0634] The server stores the data received from the device in a database. This database also includes information on previously reported dangerous locations. The input is the location information and timestamp of the dangerous location sent from the device. The output is the result of storing the data in the database (success or failure).

[0635] Step 5:

[0636] The server periodically analyzes the data stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is present. The input is the past data of dangerous locations in the database. The output is a list of dangerous locations as a result of the analysis.

[0637] Step 6:

[0638] To ensure safety, the server predicts future dangerous locations by incorporating information about dangerous locations into a prediction model. The collected data is processed using a machine learning model to generate prediction results. The input is data on past dangerous locations. The output is a list of predicted dangerous locations.

[0639] Step 7:

[0640] The server provides information on predicted dangerous locations to public institutions and autonomous vehicles. It retrieves data from its own database and sends it to the necessary entities. The input is a list of predicted dangerous locations. The output is the result of sending the data to the public institutions or autonomous vehicles (success or failure).

[0641] Step 8:

[0642] The autonomous vehicle receives the hazard location data sent from the server in real time and calculates the distance between its current location and the hazard location. The input is the autonomous vehicle's current location information and the hazard location data. The output is the distance information to the hazard location.

[0643] Step 9:

[0644] When an autonomous vehicle approaches a dangerous spot, it automatically adjusts its speed or stops. The input is information about the distance to the dangerous spot and the autonomous vehicle's control system. The output is the speed adjustment or stopping action.

[0645] Step 10:

[0646] The server issues an audio warning to users approaching dangerous locations. The server checks the user's current location information and issues a warning based on a list of dangerous locations. The input is the user's current location information and a list of dangerous locations. The output is an audio warning notification.

[0647] 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.

[0648] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion engine that recognizes the user's emotions, a high level of safety and comfort is achieved. The specific configuration of this system and the program processing are described below.

[0649] System configuration

[0650] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0651] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, emotion engine, sensors (voice and facial expressions), and voice notification function.

[0652] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[0653] Program processing overview

[0654] Use in the city

[0655] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[0656] Sending and Receiving Data

[0657] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. Encryption technology is generally used to ensure security.

[0658] Analyzing the data

[0659] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if there is a specific pattern.The server then provides information on locations that are deemed dangerous to local governments, facilitating repairs.

[0660] Emotion Engine Functions

[0661] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. For example, it is equipped with a camera and microphone to detect when the user is feeling anxious or scared. It also adjusts the intensity and content of warnings depending on the user's emotional state.

[0662] Creating a predictive model

[0663] The server generates a machine learning model based on the collected data to predict future danger zones. This prediction model is updated regularly. When a danger zone is predicted, local governments are notified in advance so that preventive measures can be taken.

[0664] Emergency reporting

[0665] The device is equipped with a sensor that detects the user's fall or impact, and if the user falls, it will make an emergency call to the police, fire department, or family members.

[0666] Warning notice

[0667] When the user approaches a known danger point, the device will issue a warning using its built-in speaker, such as "There is a step ahead, please be careful." If the emotion engine detects the user's anxiety or fear, it will increase the intensity of the warning or provide more detailed instructions.

[0668] Specific examples

[0669] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[0670] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0671] 3. The recorded data is sent to the server via the terminal's communication module.

[0672] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0673] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[0674] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[0675] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps." Furthermore, if the emotion engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[0676] This system allows users to go out safely and enables local governments to efficiently manage the safety of their cities. The introduction of an emotion engine enables flexible responses according to the individual conditions of each user, providing an even higher level of safety.

[0677] The processing flow will be explained below.

[0678] Step 1:

[0679] The user launches Silver Guide.

[0680] The device will initialize the GPS module and begin obtaining current location information.

[0681] Step 2:

[0682] As users walk around town, the device periodically updates its GPS data to track their location.

[0683] Step 3:

[0684] The device's emotion engine analyzes the user's voice and facial expressions to assess their emotional state in real time. Specifically, the camera captures facial expression data and the microphone captures voice data.

[0685] Step 4:

[0686] When the user reaches a location where he or she feels danger, he or she presses the danger detection button on the terminal.

[0687] Step 5:

[0688] The device records the GPS data and timestamp of the location where the button was pressed. For example, the data is generated in the format location_data = {timestamp: current time, latitude: latitude, longitude: longitude}.

[0689] Step 6:

[0690] The device sends the recorded location information, timestamp, and emotion data (e.g., anxiety score) generated by the emotion engine to the server using a POST request via the REST API.

[0691] Step 7:

[0692] The server receives the data sent from the device and stores it in a database, for example, using an SQL query such as INSERT INTO danger_points (timestamp, latitude, longitude, emotion_score) VALUES (current time, latitude, longitude, emotion_score).

[0693] Step 8:

[0694] The server periodically retrieves the danger point data from the database and analyzes it. Specifically, it counts the number of reports and emotion scores for common points using an SQL query. Example: SELECT latitude, longitude, COUNT(), AVG(emotion_score) FROM danger_points GROUP BY latitude, longitude HAVING COUNT() > n

[0695] Step 9:

[0696] The server identifies locations that have been reported more than a certain number of times or have a high emotional score and marks them as dangerous locations.

[0697] Step 10:

[0698] The server prepares to provide details of locations marked as dangerous to local authorities. It generates a list of danger points and sends it to the municipal system via API or notification system. Example: POST / api / municipalities / danger_points {dangerous_locations: [location1, location2,...]}

[0699] Step 11:

[0700] The server uses the collected data to train a machine learning model to predict future hazards, and this predictive model is updated regularly.

[0701] Step 12:

[0702] When the user approaches a known danger point, the device will issue a warning using the built-in speaker, such as "Be careful, there is a step ahead." If the emotion engine detects anxiety or fear, the device will issue an additional instruction such as "Walk slowly."

[0703] Step 13:

[0704] When the device's fall and shock sensors detect that the user has fallen, the device automatically makes an emergency call to the police, fire department, or family members. The call includes latitude and longitude information and emotional data.

[0705] In this way, the Silver Guide increases the safety of users and enables local governments to respond quickly. Furthermore, the introduction of an emotion engine allows for flexible responses according to individual conditions, providing an even higher level of safety.

[0706] Example 2

[0707] 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."

[0708] There is a need for effective methods to ensure safe urban mobility for elderly people and pedestrians, and to quickly identify and repair potential hazards. There is also a need for flexible warning functions that respond to the user's emotional state, and for systems that instantly report falls and impacts.

[0709] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing the user's voice and facial expression to detect the user's emotional state, a means for adjusting the strength and content of the warning depending on the user's emotional state, and a means for generating a machine learning model using collected location information data to predict future dangerous locations. This allows users to move safely around town, provides a flexible warning function according to the user's emotional state, and enables potential dangerous locations to be quickly identified and repaired. Furthermore, an emergency reporting function is also provided, further improving user safety.

[0710] "Users" refers to elderly people and other pedestrians who use the system to get around town.

[0711] "Means for pressing a button" refers to a button device that a user can press when they sense danger.

[0712] "Location information acquisition device" refers to a device that acquires location information in real time, such as a GPS module.

[0713] "Communication device" refers to a device that uses wireless communication technology to transmit acquired location information to a server.

[0714] "Server" refers to the computer system that analyzes received location information and stores and processes the data.

[0715] "Municipality" refers to local public bodies such as cities, towns, villages, and wards.

[0716] "Means for notifying the user by voice" refers to a device that uses a built-in speaker to issue a voice warning to the user.

[0717] "Means for detecting emotional state" refers to algorithms or devices that analyze the user's voice and facial expressions to determine their emotions in real time.

[0718] "Means for adjusting the intensity and content of warnings" refers to the ability to dynamically change the content and intensity of warnings based on the user's emotional state.

[0719] "Means for generating a machine learning model" refers to a process of using a machine learning algorithm to predict future hot spots using collected data.

[0720] "Devices that detect falls and impacts" refers to devices that use acceleration sensors, gyroscopes, etc. to detect falls and impacts by users.

[0721] "Means for making emergency calls" refers to a system that automatically notifies the police, fire department, or family members when the user experiences an emergency such as a fall.

[0722] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion engine that recognizes the user's emotions, a high level of safety and comfort is achieved. The specific configuration of this system and the program processing are described below.

[0723] System configuration

[0724] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0725] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, emotion engine, sensors (voice and facial expressions), and voice notification function.

[0726] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[0727] Program processing overview

[0728] Use in the city

[0729] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[0730] Sending and Receiving Data

[0731] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. To ensure security, encryption technology is generally used. Specifically, AES (Advanced Encryption Standard) encryption technology is used.

[0732] Analyzing the data

[0733] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is identified. For example, it runs scripts using Python to cross-tabulate the data and apply anomaly detection algorithms. The server then provides information on dangerous locations to local governments to facilitate repairs.

[0734] Emotion Engine Functions

[0735] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. For example, it uses the Google Cloud Speech-to-Text API to analyze audio recorded by the microphone, and OpenCV and facial recognition APIs to analyze facial images captured by the camera. The emotion engine detects when the user feels anxiety or fear, and adjusts the intensity and content of warnings depending on the user's emotional state.

[0736] Creating a predictive model

[0737] The server generates a machine learning model based on the collected data to predict future dangerous areas. This predictive model is created using machine learning libraries such as TensorFlow and Scikit-learn. New data is periodically imported and the model is updated to maintain the accuracy of the predictions. When dangerous areas are predicted, local governments are notified in advance so that preventive measures can be taken.

[0738] Emergency reporting

[0739] The device is equipped with a sensor that detects falls and impacts. When the user falls, the device will make an emergency call to the police, fire department, or family members that have been registered in advance. This function is implemented, for example, using an acceleration sensor.

[0740] Warning notice

[0741] When the user approaches a known danger point, the device will issue a warning using its built-in speaker, such as "There is a step ahead, please be careful." If the emotion engine detects the user's anxiety or fear, it will increase the intensity of the warning or provide more detailed instructions.

[0742] Specific examples

[0743] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[0744] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0745] 3. The recorded data is sent to the server via the terminal's communication module.

[0746] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0747] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[0748] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[0749] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps." Furthermore, if the emotion engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[0750] As a concrete example, it is possible to simulate the system by inputting the following prompts into the generative AI model:

[0751] Example prompt: "A user discovers a steep step while walking through a park and presses the danger detection button on the Silver Guide. Please explain in detail how this information is sent to the server and how repair work is subsequently carried out."

[0752] This system allows users to go out safely and enables local governments to efficiently manage the safety of their cities. The introduction of an emotion engine enables flexible responses according to the individual conditions of each user, providing an even higher level of safety.

[0753] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0754] Step 1:

[0755] When a user starts walking around town with the Silver Guide, the device uses the GPS module to obtain real-time location information. The GPS module outputs longitude and latitude data as input. The device temporarily stores this location information in its internal memory.

[0756] Specific behavior:

[0757] The device acquires longitude and latitude data every 10 seconds and stores it in memory.

[0758] Step 2:

[0759] When a user presses the danger detection button at a location where they sense danger, the device records the location information and timestamp at that time. The input is the button press signal, longitude, latitude, and timestamp, and the device outputs it.

[0760] Specific behavior:

[0761] When the user presses the button, the device displays the message "Danger button has been pressed" and stores the acquired longitude, latitude and timestamp in memory.

[0762] Step 3:

[0763] The recorded location information and timestamp are sent to the server using the device's communication module. The input is the acquired longitude, latitude, and timestamp, and the output is AES encrypted to ensure data security.

[0764] Specific behavior:

[0765] The device encrypts the data within 5 seconds and sends it to the server.

[0766] Step 4:

[0767] The server receives the data sent from the device and stores it in a database. The input is the encrypted longitude, latitude, and timestamp. The data is decrypted before being stored in the database.

[0768] Specific behavior:

[0769] The server decrypts the received data and adds it to the PostgreSQL database.

[0770] Step 5:

[0771] The server periodically analyzes the data of dangerous locations stored in the database. It takes as input the collected location data and outputs it. It runs a Python script and applies cross-tabulation and anomaly detection algorithms to report information on locations that are deemed dangerous to local authorities.

[0772] Specific behavior:

[0773] The server cross-tabulates data from the past week to identify areas where the same location has been reported multiple times.

[0774] Step 6:

[0775] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. The input is voice data captured by the microphone and camera, and facial image data is output. Data analysis is performed using the Google Cloud Speech-to-Text API and OpenCV. Alerts are adjusted based on the emotional state detected.

[0776] Specific behavior:

[0777] If the device determines that the user is feeling anxious, it will increase the intensity of the warning.

[0778] Step 7:

[0779] The server generates a machine learning model based on the accumulated data and predicts future dangerous areas. The collected location information data is output as input. The machine learning model is trained using TensorFlow and Scikit-learn.

[0780] Specific behavior:

[0781] The server retrains the model every time new data is collected, maintaining prediction accuracy.

[0782] Step 8:

[0783] The device is equipped with sensors to detect falls and impacts, and if the user falls, it will make an emergency call to the police, fire department, or family members. Data from the accelerometer and gyroscope is output as input.

[0784] Specific behavior:

[0785] When the device detects a fall, it will send an SMS or an automated call to a pre-set emergency number.

[0786] Step 9:

[0787] When the user approaches a known danger point, the device will issue an audio warning using the built-in speaker. Location data and emotional state data are output as inputs.

[0788] Specific behavior:

[0789] The device will announce, "Be careful, there is a step ahead," and provide additional instructions if necessary.

[0790] Through the specific processing flow described above, the system supports users in moving safely around the city and enables the rapid identification and repair of dangerous areas.

[0791] (Application example 2)

[0792] 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."

[0793] Ensuring safety when walking around town is an extremely important issue these days. Detecting and responding to potential dangers is especially important for the elderly and physically frail. Users may feel anxious or scared in certain places, and a means to respond quickly to these situations is needed. However, current systems have difficulty detecting these emotions in real time and issuing appropriate warnings immediately. Furthermore, they lack the ability to predict future dangers.

[0794] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing received location information and providing information on places determined to be dangerous to the local government, means for issuing an audio warning to a user who approaches a place determined to be dangerous, and an emotion analysis engine for analyzing the emotional state of the user and adjusting the content of the warning notification if the user feels anxiety or fear. This supports users to move around town more safely and comfortably, and enables the local government to effectively manage dangerous areas and respond quickly.

[0795] A "location measurement module" is a device for acquiring the current location of a user and outputs data including location information.

[0796] The "information transmission module" is a communication device for transmitting the acquired location information to a server, and transmits and receives data.

[0797] An "emotion analysis engine" is software or hardware that analyzes a user's voice, facial expressions, etc. to detect their emotional state, making it possible to grasp the anxiety or fear the user is feeling in real time.

[0798] A "machine learning model" is an algorithm that performs statistical analysis and predictions based on collected data, and is a system that can predict future dangerous areas.

[0799] "Warning notification means" refers to devices or software that issue audio or visual warnings when a user approaches a dangerous area.

[0800] "Users" refers to people who use the system to get around town, especially elderly people and other pedestrians.

[0801] A "server" is a computer system that receives, stores, and analyzes location information and emotional data, thereby providing appropriate information to local governments and users.

[0802] The "danger detection button" is a means that users can press when they sense danger in the city, and this records their current location information.

[0803] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion analysis engine that recognizes the user's emotions, a high level of safety and comfort is achieved.

[0804] System configuration

[0805] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0806] 2. Terminal (Silver Guide): An intelligent accessory equipped with a location measurement module, information transmission module, danger detection button, emotion analysis engine, sensors (voice and facial expressions), and voice notification function.

[0807] 3. Server: A computer system that receives, stores, and analyzes data sent from terminals and provides appropriate information to local governments and users.

[0808] Program processing overview

[0809] 1. User location tracking

[0810] We use your device's built-in location measurement module (e.g., GPS) to track your location in real time, allowing us to accurately track your movements.

[0811] 2. Detecting dangerous areas

[0812] The location information acquired through the device's information transmission module is sent to a server, which then identifies dangerous areas and automatically stores them in a database. Information on dangerous areas reported by store employees and other customers is also incorporated.

[0813] 3. Analysis using a sentiment analysis engine

[0814] The device uses a microphone and camera to analyze the user's voice and facial expressions in real time, and an emotion analysis engine is used to detect their emotional state (anxiety or fear), allowing the device to understand their mental state and provide appropriate warnings and support.

[0815] 4. Warning notice

[0816] When a user approaches a known dangerous spot, the device's voice notification function will issue an audible warning, and if the emotion analysis engine detects anxiety or fear in the user, the strength and content of the warning will be adjusted.

[0817] 5. Data transmission and analysis

[0818] The device encrypts the collected data and sends it to a server, which stores it in a database and periodically analyzes the data to generate a machine learning model for predicting future risk areas.

[0819] Specific examples

[0820] 1. A user discovers a steep step on a path in a park they regularly walk through. They press the danger detection button on the spot. The device records the location information and timestamp at that time and sends them to the server.

[0821] 2. The recorded data is received by a server and stored in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0822] 3. The server uses this information to notify the local government that repairs are necessary, and the local government uses the information provided to promptly begin repair work on the steps.

[0823] 4. When the user returns to the park, the device will issue a voice warning saying, "Be careful, there are steps." If the emotion analysis engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[0824] This system allows users to go out safely and enables local governments to efficiently manage safety in their cities. The introduction of an emotion analysis engine enables flexible responses according to the individual state of each user, providing an even higher level of safety.

[0825] *Example of a prompt to input to the generative AI model:

[0826] Design an AI system that monitors users' facial expressions in real time as they move through a physical store, and issues audio and visual warnings to ensure safety. The system also issues warnings when users approach known hazards or crowded areas. The system manages the user's location and adapts to their emotional state.

[0827] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0828] Step 1:

[0829] The user walks around the city

[0830] Input: User's location, voice, facial expression

[0831] Processing: The device acquires real-time location information using a location measurement module (GPS) and captures voice and facial expressions using a camera and microphone.

[0832] Specific operation: While the user is walking, the device's sensors continuously collect data. The device collects this data in real time and performs initial processing in its internal processor.

[0833] Output: Real-time location information, audio data, facial expression data

[0834] Step 2:

[0835] The danger detection button is pressed

[0836] Input: Button press event, current location, timestamp

[0837] Processing: When the button is pressed, the device records the current location and a timestamp.

[0838] Specific operation: When the user senses danger and presses the button, the device acquires data from the location information measurement module and temporarily stores it in memory along with a timestamp.

[0839] Output: Recorded location information, timestamp

[0840] Step 3:

[0841] Sending data

[0842] Input: Recorded location information, timestamp

[0843] Processing: The device sends the recorded location information and timestamp to the server via the information transmission module. The data is encrypted before transmission.

[0844] Specific operation: Data packets sent from the device are sent to the server using a communication protocol. The data is protected by encryption technology such as SSL / TLS.

[0845] Output: Location information received by the server, timestamp

[0846] Step 4:

[0847] Analyzing incoming data

[0848] Input: Location information stored on the server, timestamp

[0849] Processing: The server analyzes the received data and decides whether to mark a hotspot. If there are multiple reports, they are prioritized according to a specific algorithm.

[0850] Specific operation: The analysis engine on the server retrieves and analyzes the received data from the database. If there are multiple reports, the risk level is evaluated based on frequency and degree of agreement. For example, cluster analysis of data surrounding the reporting location can be performed to ensure that risk areas are identified.

[0851] Output: Location information and details of locations that are deemed dangerous

[0852] Step 5:

[0853] Warning notice

[0854] Input: Server analysis results (location information and details of dangerous areas)

[0855] Processing: The server sends information about the danger zone back to the device, which then issues a voice warning to the user. An emotion analysis engine evaluates the user's real-time emotional state and adjusts the warning accordingly.

[0856] Specific operation: The device that receives the data sent by the server uses its voice notification function to play a message such as "There is a step ahead, please be careful." If the emotion analysis engine detects the user's anxiety, it provides additional instructions such as "Please walk slowly."

[0857] Output: Audio alert, adjust notification content based on emotion

[0858] Through these steps, the system will help users move safely around the city and enable local governments to efficiently manage dangerous areas and respond quickly.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] [Third embodiment]

[0863] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0864] 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.

[0865] 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).

[0866] 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.

[0867] 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.

[0868] 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).

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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."

[0875] The system for carrying out this invention is designed to create an environment in which users can move safely around town. The specific configuration of this system and the processing of the program will be described below.

[0876] System configuration

[0877] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[0878] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[0879] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[0880] Program processing overview

[0881] Use in the city

[0882] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[0883] Sending and Receiving Data

[0884] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. Encryption technology is generally used to ensure security.

[0885] Analyzing the data

[0886] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if there is a specific pattern.The server then provides information on locations that are deemed dangerous to local governments, facilitating repairs.

[0887] Creating a predictive model

[0888] The server generates a machine learning model based on the collected data to predict future danger zones. This prediction model is updated regularly. When a danger zone is predicted, local governments are notified in advance so that preventive measures can be taken.

[0889] Warning notice

[0890] When the user approaches a known dangerous spot, the device will issue a warning using the built-in speaker. For example, it may announce, "There is a step ahead, so be careful." This function allows the user to recognize danger in advance and move safely.

[0891] Specific examples

[0892] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[0893] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0894] 3. The recorded data is sent to the server via the terminal's communication module.

[0895] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[0896] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[0897] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[0898] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps."

[0899] This system will enable users to go out safely and local governments to efficiently manage safety in their cities. This invention will contribute to creating an environment where pedestrians, including the elderly, can go out with peace of mind.

[0900] The processing flow will be explained below.

[0901] Step 1:

[0902] The user launches Silver Guide.

[0903] The device will initialize the GPS module and begin obtaining current location information.

[0904] Step 2:

[0905] As users walk around town, the device periodically updates its GPS data to track their location.

[0906] Step 3:

[0907] When the user reaches a location where he or she feels danger, he or she presses the danger detection button on the terminal.

[0908] Step 4:

[0909] The device records the GPS data and timestamp of the location where the button was pressed. For example, the data is generated in the format location_data = {timestamp: current time, latitude: latitude, longitude: longitude}.

[0910] Step 5:

[0911] The device sends the recorded location information and a timestamp to the server using a POST request via the REST API.

[0912] Step 6:

[0913] The server receives the data sent from the device and stores it in a database, for example using an SQL query such as INSERT INTO danger_points (timestamp, latitude, longitude) VALUES (current time, latitude, longitude).

[0914] Step 7:

[0915] The server periodically retrieves the data on danger points from the database and analyzes it. Specifically, it counts the number of reports at common points using an SQL query. Example: SELECT latitude, longitude, COUNT() FROM danger_points GROUP BY latitude, longitude HAVING COUNT() > n

[0916] Step 8:

[0917] The server identifies locations that have been reported a certain number of times and marks them as dangerous.

[0918] Step 9:

[0919] The server prepares to provide details of locations marked as dangerous to local authorities. It generates a list of danger points and sends it to the municipal system via API or notification system. Example: POST / api / municipalities / danger_points {dangerous_locations: [location1, location2,...]}

[0920] Step 10:

[0921] The server uses the collected data to train a machine learning model to predict future hazards, and this predictive model is updated regularly.

[0922] Step 11:

[0923] When the user approaches a known danger point, the device will use its built-in speaker to issue an audible warning, such as "There is a step ahead, so be careful."

[0924] Example 1

[0925] 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."

[0926] The present invention relates to a system for creating an environment in which elderly people and other pedestrians can move around town safely. Conventional systems have the drawback of being time-consuming to detect and report dangerous areas, making it difficult to take measures before danger actually occurs. Furthermore, information on dangerous areas is not properly managed, which can delay the response of local governments. There is a need to solve these problems by more quickly and accurately predicting dangerous areas, providing warnings to users, and promoting the provision of appropriate information to local governments.

[0927] 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.

[0928] In this invention, the server includes means for analyzing the received location information and providing information on locations determined to be dangerous to local governments, means for predicting future dangerous locations using a machine learning library, and means for periodically analyzing the location information stored in the database using a statistical anomaly detection algorithm.As a result, when a user senses danger in a city, the location information is quickly obtained and sent to a computer system, thereby providing accurate information to local governments, predicting future dangerous locations, and enabling them to take preventative measures.

[0929] "Users" refers to elderly people and pedestrians who use the system to get around town.

[0930] A "button" refers to an input device that a user presses when they sense danger to notify the system of the danger.

[0931] A "Global Positioning System module" refers to a device that measures its location on Earth using satellite signals, commonly known as a GPS module.

[0932] A "communication module" is a communication device for transmitting recorded data to other devices or systems.

[0933] "Computer system" refers to a computing device for receiving, storing, analyzing, and communicating data.

[0934] A "hazardous location" is a location that the system has analyzed multiple data points and deemed dangerous because it exceeded certain criteria.

[0935] "Local government" refers to a regional administrative unit such as a city, town, or village, and is an organization responsible for managing public safety.

[0936] "Audio notification means" refers to a device or technology that generates audio to alert the user to a danger.

[0937] "Encryption" is the process of converting information to protect it from external interference or unauthorized access.

[0938] "Database" refers to a software system for systematically storing and managing collected data.

[0939] A "statistical anomaly detection algorithm" is a mathematical method used to identify patterns and outliers in data.

[0940] "Machine learning library" refers to software tools and libraries used to build and train machine learning models.

[0941] A "machine learning model" is an algorithm that predicts future data and patterns based on past data.

[0942] This invention relates to a system for providing an environment in which elderly people and other pedestrians can move around safely in the city. This system consists of a user, a terminal (Silver Guide), and a server. The specific processing of each component and program is explained below.

[0943] System configuration

[0944] 1. Users: Elderly people and other pedestrians who use the system. Users move around the city with the Silver Guide.

[0945] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[0946] 3. Server: A computer system that receives, stores, and analyzes data sent from terminals and provides appropriate information to local governments and users.

[0947] Program processing overview

[0948] Initial setup and data acquisition

[0949] When a user launches Silver Guide, the device initializes the GPS module and acquires real-time location information. Specifically, the device receives signals from GPS satellites and calculates the current location's longitude and latitude. This process uses the NMEA protocol.

[0950] Recording of dangerous areas

[0951] When a user presses the danger detection button at a location where they sense danger, the device records the location information and timestamp at that moment. For example, if a user discovers a large step on the sidewalk, they press the danger detection button on the spot and the device records the location information.

[0952] Sending and Receiving Data

[0953] The recorded location information and timestamp are sent to the server via the device's communication module (e.g., 4G LTE module). The sent data is AES encrypted to ensure security. The server receives the data, stores it in temporary memory, and then saves it in a database (e.g., MySQL or PostgreSQL).

[0954] Analyzing the data

[0955] The server periodically analyzes the received data, and if multiple users report the same location or if a specific pattern is found, it determines that location as a "danger zone." The data is analyzed using a statistical anomaly detection algorithm using Python and the Pandas library.

[0956] Notification to local governments

[0957] If the server determines that a location is at risk, it will notify the local government using an automated email system (e.g., SendGrid). The email notification will include specific location information (e.g., longitude and latitude), a timestamp, and the number of reports.

[0958] Prediction using machine learning models

[0959] The server uses machine learning libraries (e.g., TensorFlow) to train a predictive model based on the collected data to predict future hazards. The model is periodically updated with new data and notifies local governments in advance.

[0960] User warning notification

[0961] When the user approaches a known dangerous spot, the device will issue a voice warning using the built-in speaker. For example, it will make an announcement such as, "There is a step ahead, so please be careful." This function allows the user to recognize danger in advance and move safely.

[0962] Specific examples

[0963] 1. The user discovers a steep step on a path in a park they usually walk through and presses the danger detection button on the spot.

[0964] 2. The device records its current location (e.g., longitude: 35.6895, latitude: 139.6917) and a timestamp.

[0965] 3. The recorded data is sent to the server via the terminal's communication module.

[0966] 4. The server receives the data and stores it in a database.

[0967] 5. The server analyzes the incident and determines that similar reports have been made multiple times by other users of the same park.

[0968] 6. The server provides this information to local authorities, notifying them that repairs are needed.

[0969] 7. Local governments will use the information provided to promptly begin repair work on the steps.

[0970] 8. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps."

[0971] Examples of prompt statements

[0972] "Record and send the GPS information of your current location"

[0973] "Analyze the patterns in the data that report hot spots at this location."

[0974] "Generate a model that predicts future danger spots based on the collected data."

[0975] "Generate an audio message to warn users when they approach this location"

[0976] In this way, this system provides an environment in which users can move around safely, and enables local governments to efficiently manage the safety of their cities.

[0977] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0978] Step 1:

[0979] Initial setup and data acquisition

[0980] The user starts Silver Guide. The input is a start command from the user. The device first initializes the GPS module (e.g., u-blox module) and receives signals from GPS satellites to collect current location information. For data calculation, the device analyzes the received data using the NMEA protocol and calculates the current longitude and latitude. The output is the current location information (longitude, latitude).

[0981] Step 2:

[0982] Recording of dangerous areas

[0983] When a user senses danger, they press the danger detection button. The input is the user pressing the button event. The device records the location information and timestamp at that moment. As data processing, the longitude, latitude, and time information of the current location are saved in memory as a single data set. The output is the recorded location data (longitude, latitude, timestamp).

[0984] Step 3:

[0985] Sending data

[0986] The device sends the recorded location information and timestamp to the server via a communication module (e.g., 4G LTE module). The input is the recorded location data. The data operation protects the data using AES encryption and sends it to the server using a transmission protocol (e.g., HTTP or MQTT). The output is the encrypted data transmission result.

[0987] Step 4:

[0988] Receiving and storing data

[0989] The server stores the received data in memory. The input is the encrypted data sent from the device. The data is then processed by decrypting it using AES encryption and checking the integrity of the data. An SQL query is created to store the data in a database (e.g., MySQL, PostgreSQL). The output is the location data stored in the database.

[0990] Step 5:

[0991] Analyzing the data

[0992] The server periodically analyzes the location data in the database. The input is the location data in the database. For data processing, Python and the Pandas library are used to analyze the frequency and consistency of data points based on statistical anomaly detection algorithms. The output is a list of locations that are determined to be dangerous.

[0993] Step 6:

[0994] Notification to local governments

[0995] The server provides information on identified dangerous locations to local governments. The input is the analysis results of the dangerous location data. Data is processed using an automated email system (e.g., SendGrid) to generate a notification email about the dangerous location. The output is a notification email sent to the local government.

[0996] Step 7:

[0997] Prediction using machine learning models

[0998] The server uses a machine learning library (e.g., TensorFlow) to train a model based on the collected data and predict future hazardous locations. The inputs are past location data and hazardous location data. Data calculations include data preprocessing, model training, and evaluation. The output is a prediction model for future hazardous locations and the prediction results.

[0999] Step 8:

[1000] User warning notification

[1001] When the user approaches a known dangerous spot, the device issues a voice warning through its built-in speaker. The inputs are current location information and dangerous spot data. Data calculations compare the current location information with known dangerous spot data and generate a voice message if a warning is necessary. The output is a voice warning such as "There is a step ahead, so be careful."

[1002] (Application example 1)

[1003] 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."

[1004] Modern society demands support systems to help elderly people and those with walking difficulties navigate safely around town. However, current systems are limited in their scope of effectiveness, and lack of coordination with autonomous vehicles in particular makes it difficult to fully ensure pedestrian safety. In addition, the detection and improvement of dangerous areas is often delayed, requiring rapid action by local governments and related organizations.

[1005] 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.

[1006] In this invention, the server includes: a means for a user to press a button when they sense danger in a city; a satellite positioning system that acquires location information of the location when the button is pressed; a communication means for transmitting the acquired location information to the server; a means for the server to analyze the received location information and provide information on locations determined to be dangerous to public institutions; a means for issuing an audio warning to a user approaching a location determined to be dangerous by the server; a means for the autonomous vehicle to adjust or stop its speed when approaching a dangerous location; and a means for the autonomous vehicle to acquire data on dangerous locations from the server. This enables the autonomous vehicle to take appropriate action in real time while ensuring the safety of pedestrians. It also provides information to local governments so that they can quickly improve dangerous locations.

[1007] "Users" refers to elderly people and people who have difficulty walking who use the system to move safely around the city.

[1008] "City" refers to areas where pedestrians frequently come and go, such as urban areas and public places.

[1009] "Means for pressing a button when danger is sensed" refers to an interface that a user can physically press when they sense danger, in order to notify the system of the presence of danger.

[1010] "Satellite Positioning System" means a satellite technology used to precisely determine location on Earth, and typically includes GPS.

[1011] "Communication Method" refers to the process of using the Internet or other network technology to transmit data to a server.

[1012] A "server" is a computer system that receives, stores, and analyzes data and provides appropriate information to users and public institutions.

[1013] "Public agency" refers to a government or administrative organization responsible for managing public safety, such as a local government, police, or fire department.

[1014] An "autonomous vehicle" refers to a vehicle that can drive itself without human intervention.

[1015] "Danger points" refer to specific locations that the server determines pose a high risk to users or autonomous vehicles.

[1016] "Means of issuing audio warnings" refers to a system that uses speakers or voice synthesis technology to issue audio warnings to alert users to danger.

[1017] "Means to adjust speed or stop" refers to a control system that takes appropriate action when an autonomous vehicle approaches a hazard.

[1018] "Means for obtaining data" refers to the communication process by which an autonomous vehicle obtains the necessary data from a server.

[1019] The system for implementing this invention ensures the safety of pedestrians while cooperating with autonomous vehicles to share and utilize safety information in real time. The specific configuration and operation of this system are described below.

[1020] 1. System Configuration

[1021] Users: Elderly people and other pedestrians who use the system. They carry a stick-shaped device (Silver Guide) and move around the city.

[1022] Device (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[1023] Autonomous vehicle: A vehicle that can drive itself without human intervention, equipped with a communication module and control system.

[1024] Server: A computer system that receives, stores, and analyzes data sent from terminals and autonomous vehicles, and provides appropriate information to local governments, users, and autonomous vehicles.

[1025] 2. Program Processing

[1026] Program Overview

[1027] The server receives and analyzes the location information of the device and the autonomous vehicle, identifies and predicts dangerous areas, and provides this information to public institutions, users, and autonomous vehicles in real time.

[1028] User's walking movements

[1029] When a user walks around town with the stick-shaped device, the device acquires GPS data in real time and tracks the user's current location. When the user presses the danger detection button at a point where they sense danger, the location information and timestamp at that time are recorded.

[1030] Sending and Receiving Data

[1031] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database, using encryption technology to ensure security.

[1032] Analyzing data and identifying hot spots

[1033] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is identified. Furthermore, it generates a machine learning model based on the collected data to predict future dangerous locations.

[1034] Collaboration with autonomous vehicles

[1035] The autonomous vehicle periodically retrieves data on dangerous locations from the server and calculates the distance between its current location and the dangerous location in real time. When approaching a dangerous location, the autonomous vehicle will adjust its speed or stop appropriately to ensure the safety of pedestrians.

[1036] Warning notice

[1037] Users approaching known danger points will receive a voice warning using the device's built-in speaker. Similarly, autonomous vehicles will issue warnings to pedestrians when approaching danger points.

[1038] 3. Adding specific examples

[1039] Usage example 1:

[1040] A user discovers a steep step on a path in a park they regularly walk through. They press the danger detection button on the spot. The device records its current location information (e.g., longitude 35.6895, latitude 139.6917) and a timestamp, and sends them to a server. The server then confirms similar reports from other pedestrians and notifies the local government. The local government quickly repairs the step, and when the user returns, a voice message is sent to the user saying, "Please be careful as there is a step ahead."

[1041] Usage example 2:

[1042] A self-driving vehicle approaches while a user is walking in a city. The self-driving vehicle receives the danger point data from the server, detects that the user is approaching a danger point, and adjusts its speed appropriately as it proceeds. This ensures the user's safety.

[1043] Prompt Sentence Examples

[1044] "Please develop a system that allows elderly people to move around safely using a smart cane. The system will acquire GPS data, record dangerous locations, and send them to a server. It will also provide autonomous vehicles with the ability to detect danger in real time based on this data and adjust their speed or stop."

[1045] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1046] Step 1:

[1047] The user starts walking around town. The device acquires the user's current location (GPS data) in real time using the built-in satellite positioning system. The input at this point is the user's current longitude and latitude. The device continues to record this GPS data. The output is the user's current location information.

[1048] Step 2:

[1049] When a user senses danger, they press the danger detection button on their device. This causes the device to acquire location information (longitude and latitude) and a timestamp at that time. The inputs are the signal that the button was pressed, current location information, and the current time. The output is the location information and timestamp of the danger area.

[1050] Step 3:

[1051] The terminal transmits the acquired location information and timestamp of the dangerous spot to the server via the communication module. The input is the location information and timestamp of the dangerous spot. The output is the result of data transmission to the server (success or failure).

[1052] Step 4:

[1053] The server stores the data received from the device in a database. This database also includes information on previously reported dangerous locations. The input is the location information and timestamp of the dangerous location sent from the device. The output is the result of storing the data in the database (success or failure).

[1054] Step 5:

[1055] The server periodically analyzes the data stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is present. The input is the past data of dangerous locations in the database. The output is a list of dangerous locations as a result of the analysis.

[1056] Step 6:

[1057] To ensure safety, the server predicts future dangerous locations by incorporating information about dangerous locations into a prediction model. The collected data is processed using a machine learning model to generate prediction results. The input is data on past dangerous locations. The output is a list of predicted dangerous locations.

[1058] Step 7:

[1059] The server provides information on predicted dangerous locations to public institutions and autonomous vehicles. It retrieves data from its own database and sends it to the necessary entities. The input is a list of predicted dangerous locations. The output is the result of sending the data to the public institutions or autonomous vehicles (success or failure).

[1060] Step 8:

[1061] The autonomous vehicle receives the hazard location data sent from the server in real time and calculates the distance between its current location and the hazard location. The input is the autonomous vehicle's current location information and the hazard location data. The output is the distance information to the hazard location.

[1062] Step 9:

[1063] When an autonomous vehicle approaches a dangerous spot, it automatically adjusts its speed or stops. The input is information about the distance to the dangerous spot and the autonomous vehicle's control system. The output is the speed adjustment or stopping action.

[1064] Step 10:

[1065] The server issues an audio warning to users approaching dangerous locations. The server checks the user's current location information and issues a warning based on a list of dangerous locations. The input is the user's current location information and a list of dangerous locations. The output is an audio warning notification.

[1066] 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.

[1067] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion engine that recognizes the user's emotions, a high level of safety and comfort is achieved. The specific configuration of this system and the program processing are described below.

[1068] System configuration

[1069] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[1070] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, emotion engine, sensors (voice and facial expressions), and voice notification function.

[1071] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[1072] Program processing overview

[1073] Use in the city

[1074] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[1075] Sending and Receiving Data

[1076] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. Encryption technology is generally used to ensure security.

[1077] Analyzing the data

[1078] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if there is a specific pattern.The server then provides information on locations that are deemed dangerous to local governments, facilitating repairs.

[1079] Emotion Engine Functions

[1080] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. For example, it is equipped with a camera and microphone to detect when the user is feeling anxious or scared. It also adjusts the intensity and content of warnings depending on the user's emotional state.

[1081] Creating a predictive model

[1082] The server generates a machine learning model based on the collected data to predict future danger zones. This prediction model is updated regularly. When a danger zone is predicted, local governments are notified in advance so that preventive measures can be taken.

[1083] Emergency reporting

[1084] The device is equipped with a sensor that detects the user's fall or impact, and if the user falls, it will make an emergency call to the police, fire department, or family members.

[1085] Warning notice

[1086] When the user approaches a known danger point, the device will issue a warning using its built-in speaker, such as "There is a step ahead, please be careful." If the emotion engine detects the user's anxiety or fear, it will increase the intensity of the warning or provide more detailed instructions.

[1087] Specific examples

[1088] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[1089] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[1090] 3. The recorded data is sent to the server via the terminal's communication module.

[1091] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[1092] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[1093] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[1094] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps." Furthermore, if the emotion engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[1095] This system allows users to go out safely and enables local governments to efficiently manage the safety of their cities. The introduction of an emotion engine enables flexible responses according to the individual conditions of each user, providing an even higher level of safety.

[1096] The processing flow will be explained below.

[1097] Step 1:

[1098] The user launches Silver Guide.

[1099] The device will initialize the GPS module and begin obtaining current location information.

[1100] Step 2:

[1101] As users walk around town, the device periodically updates its GPS data to track their location.

[1102] Step 3:

[1103] The device's emotion engine analyzes the user's voice and facial expressions to assess their emotional state in real time. Specifically, the camera captures facial expression data and the microphone captures voice data.

[1104] Step 4:

[1105] When the user reaches a location where he or she feels danger, he or she presses the danger detection button on the terminal.

[1106] Step 5:

[1107] The device records the GPS data and timestamp of the location where the button was pressed. For example, the data is generated in the format location_data = {timestamp: current time, latitude: latitude, longitude: longitude}.

[1108] Step 6:

[1109] The device sends the recorded location information, timestamp, and emotion data (e.g., anxiety score) generated by the emotion engine to the server using a POST request via the REST API.

[1110] Step 7:

[1111] The server receives the data sent from the device and stores it in a database, for example, using an SQL query such as INSERT INTO danger_points (timestamp, latitude, longitude, emotion_score) VALUES (current time, latitude, longitude, emotion_score).

[1112] Step 8:

[1113] The server periodically retrieves the danger point data from the database and analyzes it. Specifically, it counts the number of reports and emotion scores for common points using an SQL query. Example: SELECT latitude, longitude, COUNT(), AVG(emotion_score) FROM danger_points GROUP BY latitude, longitude HAVING COUNT() > n

[1114] Step 9:

[1115] The server identifies locations that have been reported more than a certain number of times or have a high emotional score and marks them as dangerous locations.

[1116] Step 10:

[1117] The server prepares to provide details of locations marked as dangerous to local authorities. It generates a list of danger points and sends it to the municipal system via API or notification system. Example: POST / api / municipalities / danger_points {dangerous_locations: [location1, location2,...]}

[1118] Step 11:

[1119] The server uses the collected data to train a machine learning model to predict future hazards, and this predictive model is updated regularly.

[1120] Step 12:

[1121] When the user approaches a known danger point, the device will issue a warning using the built-in speaker, such as "Be careful, there is a step ahead." If the emotion engine detects anxiety or fear, the device will issue an additional instruction such as "Walk slowly."

[1122] Step 13:

[1123] When the device's fall and shock sensors detect that the user has fallen, the device automatically makes an emergency call to the police, fire department, or family members. The call includes latitude and longitude information and emotional data.

[1124] In this way, the Silver Guide increases the safety of users and enables local governments to respond quickly. Furthermore, the introduction of an emotion engine allows for flexible responses according to individual conditions, providing an even higher level of safety.

[1125] Example 2

[1126] 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."

[1127] There is a need for effective methods to ensure safe urban mobility for elderly people and pedestrians, and to quickly identify and repair potential hazards. There is also a need for flexible warning functions that respond to the user's emotional state, and for systems that instantly report falls and impacts.

[1128] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing the user's voice and facial expression to detect the user's emotional state, a means for adjusting the strength and content of the warning depending on the user's emotional state, and a means for generating a machine learning model using collected location information data to predict future dangerous locations. This allows users to move safely around town, provides a flexible warning function according to the user's emotional state, and enables potential dangerous locations to be quickly identified and repaired. Furthermore, an emergency reporting function is also provided, further improving user safety.

[1129] "Users" refers to elderly people and other pedestrians who use the system to get around town.

[1130] "Means for pressing a button" refers to a button device that a user can press when they sense danger.

[1131] "Location information acquisition device" refers to a device that acquires location information in real time, such as a GPS module.

[1132] "Communication device" refers to a device that uses wireless communication technology to transmit acquired location information to a server.

[1133] "Server" refers to the computer system that analyzes received location information and stores and processes the data.

[1134] "Municipality" refers to local public bodies such as cities, towns, villages, and wards.

[1135] "Means for notifying the user by voice" refers to a device that uses a built-in speaker to issue a voice warning to the user.

[1136] "Means for detecting emotional state" refers to algorithms or devices that analyze the user's voice and facial expressions to determine their emotions in real time.

[1137] "Means for adjusting the intensity and content of warnings" refers to the ability to dynamically change the content and intensity of warnings based on the user's emotional state.

[1138] "Means for generating a machine learning model" refers to a process of using a machine learning algorithm to predict future hot spots using collected data.

[1139] "Devices that detect falls and impacts" refers to devices that use acceleration sensors, gyroscopes, etc. to detect falls and impacts by users.

[1140] "Means for making emergency calls" refers to a system that automatically notifies the police, fire department, or family members when the user experiences an emergency such as a fall.

[1141] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion engine that recognizes the user's emotions, a high level of safety and comfort is achieved. The specific configuration of this system and the program processing are described below.

[1142] System configuration

[1143] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[1144] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, emotion engine, sensors (voice and facial expressions), and voice notification function.

[1145] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[1146] Program processing overview

[1147] Use in the city

[1148] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[1149] Sending and Receiving Data

[1150] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. To ensure security, encryption technology is generally used. Specifically, AES (Advanced Encryption Standard) encryption technology is used.

[1151] Analyzing the data

[1152] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is identified. For example, it runs scripts using Python to cross-tabulate the data and apply anomaly detection algorithms. The server then provides information on dangerous locations to local governments to facilitate repairs.

[1153] Emotion Engine Functions

[1154] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. For example, it uses the Google Cloud Speech-to-Text API to analyze audio recorded by the microphone, and OpenCV and facial recognition APIs to analyze facial images captured by the camera. The emotion engine detects when the user feels anxiety or fear, and adjusts the intensity and content of warnings depending on the user's emotional state.

[1155] Creating a predictive model

[1156] The server generates a machine learning model based on the collected data to predict future dangerous areas. This predictive model is created using machine learning libraries such as TensorFlow and Scikit-learn. New data is periodically imported and the model is updated to maintain the accuracy of the predictions. When dangerous areas are predicted, local governments are notified in advance so that preventive measures can be taken.

[1157] Emergency reporting

[1158] The device is equipped with a sensor that detects falls and impacts. When the user falls, the device will make an emergency call to the police, fire department, or family members that have been registered in advance. This function is implemented, for example, using an acceleration sensor.

[1159] Warning notice

[1160] When the user approaches a known danger point, the device will issue a warning using its built-in speaker, such as "There is a step ahead, please be careful." If the emotion engine detects the user's anxiety or fear, it will increase the intensity of the warning or provide more detailed instructions.

[1161] Specific examples

[1162] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[1163] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[1164] 3. The recorded data is sent to the server via the terminal's communication module.

[1165] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[1166] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[1167] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[1168] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps." Furthermore, if the emotion engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[1169] As a concrete example, it is possible to simulate the system by inputting the following prompts into the generative AI model:

[1170] Example prompt: "A user discovers a steep step while walking through a park and presses the danger detection button on the Silver Guide. Please explain in detail how this information is sent to the server and how repair work is subsequently carried out."

[1171] This system allows users to go out safely and enables local governments to efficiently manage the safety of their cities. The introduction of an emotion engine enables flexible responses according to the individual conditions of each user, providing an even higher level of safety.

[1172] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1173] Step 1:

[1174] When a user starts walking around town with the Silver Guide, the device uses the GPS module to obtain real-time location information. The GPS module outputs longitude and latitude data as input. The device temporarily stores this location information in its internal memory.

[1175] Specific behavior:

[1176] The device acquires longitude and latitude data every 10 seconds and stores it in memory.

[1177] Step 2:

[1178] When a user presses the danger detection button at a location where they sense danger, the device records the location information and timestamp at that time. The input is the button press signal, longitude, latitude, and timestamp, and the device outputs it.

[1179] Specific behavior:

[1180] When the user presses the button, the device displays the message "Danger button has been pressed" and stores the acquired longitude, latitude and timestamp in memory.

[1181] Step 3:

[1182] The recorded location information and timestamp are sent to the server using the device's communication module. The input is the acquired longitude, latitude, and timestamp, and the output is AES encrypted to ensure data security.

[1183] Specific behavior:

[1184] The device encrypts the data within 5 seconds and sends it to the server.

[1185] Step 4:

[1186] The server receives the data sent from the device and stores it in a database. The input is the encrypted longitude, latitude, and timestamp. The data is decrypted before being stored in the database.

[1187] Specific behavior:

[1188] The server decrypts the received data and adds it to the PostgreSQL database.

[1189] Step 5:

[1190] The server periodically analyzes the data of dangerous locations stored in the database. It takes as input the collected location data and outputs it. It runs a Python script and applies cross-tabulation and anomaly detection algorithms to report information on locations that are deemed dangerous to local authorities.

[1191] Specific behavior:

[1192] The server cross-tabulates data from the past week to identify areas where the same location has been reported multiple times.

[1193] Step 6:

[1194] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. The input is voice data captured by the microphone and camera, and facial image data is output. Data analysis is performed using the Google Cloud Speech-to-Text API and OpenCV. Alerts are adjusted based on the emotional state detected.

[1195] Specific behavior:

[1196] If the device determines that the user is feeling anxious, it will increase the intensity of the warning.

[1197] Step 7:

[1198] The server generates a machine learning model based on the accumulated data and predicts future dangerous areas. The collected location information data is output as input. The machine learning model is trained using TensorFlow and Scikit-learn.

[1199] Specific behavior:

[1200] The server retrains the model every time new data is collected, maintaining prediction accuracy.

[1201] Step 8:

[1202] The device is equipped with sensors to detect falls and impacts, and if the user falls, it will make an emergency call to the police, fire department, or family members. Data from the accelerometer and gyroscope is output as input.

[1203] Specific behavior:

[1204] When the device detects a fall, it will send an SMS or an automated call to a pre-set emergency number.

[1205] Step 9:

[1206] When the user approaches a known danger point, the device will issue an audio warning using the built-in speaker. Location data and emotional state data are output as inputs.

[1207] Specific behavior:

[1208] The device will announce, "Be careful, there is a step ahead," and provide additional instructions if necessary.

[1209] Through the specific processing flow described above, the system supports users in moving safely around the city and enables the rapid identification and repair of dangerous areas.

[1210] (Application example 2)

[1211] 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."

[1212] Ensuring safety when walking around town is an extremely important issue these days. Detecting and responding to potential dangers is especially important for the elderly and physically frail. Users may feel anxious or scared in certain places, and a means to respond quickly to these situations is needed. However, current systems have difficulty detecting these emotions in real time and issuing appropriate warnings immediately. Furthermore, they lack the ability to predict future dangers.

[1213] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing received location information and providing information on places determined to be dangerous to the local government, means for issuing an audio warning to a user who approaches a place determined to be dangerous, and an emotion analysis engine for analyzing the emotional state of the user and adjusting the content of the warning notification if the user feels anxiety or fear. This supports users to move around town more safely and comfortably, and enables the local government to effectively manage dangerous areas and respond quickly.

[1214] A "location measurement module" is a device for acquiring the current location of a user and outputs data including location information.

[1215] The "information transmission module" is a communication device for transmitting the acquired location information to a server, and transmits and receives data.

[1216] An "emotion analysis engine" is software or hardware that analyzes a user's voice, facial expressions, etc. to detect their emotional state, making it possible to grasp the anxiety or fear the user is feeling in real time.

[1217] A "machine learning model" is an algorithm that performs statistical analysis and predictions based on collected data, and is a system that can predict future dangerous areas.

[1218] "Warning notification means" refers to devices or software that issue audio or visual warnings when a user approaches a dangerous area.

[1219] "Users" refers to people who use the system to get around town, especially elderly people and other pedestrians.

[1220] A "server" is a computer system that receives, stores, and analyzes location information and emotional data, thereby providing appropriate information to local governments and users.

[1221] The "danger detection button" is a means that users can press when they sense danger in the city, and this records their current location information.

[1222] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion analysis engine that recognizes the user's emotions, a high level of safety and comfort is achieved.

[1223] System configuration

[1224] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[1225] 2. Terminal (Silver Guide): An intelligent accessory equipped with a location measurement module, information transmission module, danger detection button, emotion analysis engine, sensors (voice and facial expressions), and voice notification function.

[1226] 3. Server: A computer system that receives, stores, and analyzes data sent from terminals and provides appropriate information to local governments and users.

[1227] Program processing overview

[1228] 1. User location tracking

[1229] We use your device's built-in location measurement module (e.g., GPS) to track your location in real time, allowing us to accurately track your movements.

[1230] 2. Detecting dangerous areas

[1231] The location information acquired through the device's information transmission module is sent to a server, which then identifies dangerous areas and automatically stores them in a database. Information on dangerous areas reported by store employees and other customers is also incorporated.

[1232] 3. Analysis using a sentiment analysis engine

[1233] The device uses a microphone and camera to analyze the user's voice and facial expressions in real time, and an emotion analysis engine is used to detect their emotional state (anxiety or fear), allowing the device to understand their mental state and provide appropriate warnings and support.

[1234] 4. Warning notice

[1235] When a user approaches a known dangerous spot, the device's voice notification function will issue an audible warning, and if the emotion analysis engine detects anxiety or fear in the user, the strength and content of the warning will be adjusted.

[1236] 5. Data transmission and analysis

[1237] The device encrypts the collected data and sends it to a server, which stores it in a database and periodically analyzes the data to generate a machine learning model for predicting future risk areas.

[1238] Specific examples

[1239] 1. A user discovers a steep step on a path in a park they regularly walk through. They press the danger detection button on the spot. The device records the location information and timestamp at that time and sends them to the server.

[1240] 2. The recorded data is received by a server and stored in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[1241] 3. The server uses this information to notify the local government that repairs are necessary, and the local government uses the information provided to promptly begin repair work on the steps.

[1242] 4. When the user returns to the park, the device will issue a voice warning saying, "Be careful, there are steps." If the emotion analysis engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[1243] This system allows users to go out safely and enables local governments to efficiently manage safety in their cities. The introduction of an emotion analysis engine enables flexible responses according to the individual state of each user, providing an even higher level of safety.

[1244] *Example of a prompt to input to the generative AI model:

[1245] Design an AI system that monitors users' facial expressions in real time as they move through a physical store, and issues audio and visual warnings to ensure safety. The system also issues warnings when users approach known hazards or crowded areas. The system manages the user's location and adapts to their emotional state.

[1246] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1247] Step 1:

[1248] The user walks around the city

[1249] Input: User's location, voice, facial expression

[1250] Processing: The device acquires real-time location information using a location measurement module (GPS) and captures voice and facial expressions using a camera and microphone.

[1251] Specific operation: While the user is walking, the device's sensors continuously collect data. The device collects this data in real time and performs initial processing in its internal processor.

[1252] Output: Real-time location information, audio data, facial expression data

[1253] Step 2:

[1254] The danger detection button is pressed

[1255] Input: Button press event, current location, timestamp

[1256] Processing: When the button is pressed, the device records the current location and a timestamp.

[1257] Specific operation: When the user senses danger and presses the button, the device acquires data from the location information measurement module and temporarily stores it in memory along with a timestamp.

[1258] Output: Recorded location information, timestamp

[1259] Step 3:

[1260] Sending data

[1261] Input: Recorded location information, timestamp

[1262] Processing: The device sends the recorded location information and timestamp to the server via the information transmission module. The data is encrypted before transmission.

[1263] Specific operation: Data packets sent from the device are sent to the server using a communication protocol. The data is protected by encryption technology such as SSL / TLS.

[1264] Output: Location information received by the server, timestamp

[1265] Step 4:

[1266] Analyzing incoming data

[1267] Input: Location information stored on the server, timestamp

[1268] Processing: The server analyzes the received data and decides whether to mark a hotspot. If there are multiple reports, they are prioritized according to a specific algorithm.

[1269] Specific operation: The analysis engine on the server retrieves and analyzes the received data from the database. If there are multiple reports, the risk level is evaluated based on frequency and degree of agreement. For example, cluster analysis of data surrounding the reporting location can be performed to ensure that risk areas are identified.

[1270] Output: Location information and details of locations that are deemed dangerous

[1271] Step 5:

[1272] Warning notice

[1273] Input: Server analysis results (location information and details of dangerous areas)

[1274] Processing: The server sends information about the danger zone back to the device, which then issues a voice warning to the user. An emotion analysis engine evaluates the user's real-time emotional state and adjusts the warning accordingly.

[1275] Specific operation: The device that receives the data sent by the server uses its voice notification function to play a message such as "There is a step ahead, please be careful." If the emotion analysis engine detects the user's anxiety, it provides additional instructions such as "Please walk slowly."

[1276] Output: Audio alert, adjust notification content based on emotion

[1277] Through these steps, the system will help users move safely around the city and enable local governments to efficiently manage dangerous areas and respond quickly.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] [Fourth embodiment]

[1282] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1283] 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.

[1284] 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).

[1285] 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.

[1286] 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.

[1287] 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).

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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.

[1292] 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.

[1293] 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.

[1294] 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."

[1295] The system for carrying out this invention is designed to create an environment in which users can move safely around town. The specific configuration of this system and the processing of the program will be described below.

[1296] System configuration

[1297] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[1298] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[1299] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[1300] Program processing overview

[1301] Use in the city

[1302] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[1303] Sending and Receiving Data

[1304] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. Encryption technology is generally used to ensure security.

[1305] Analyzing the data

[1306] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if there is a specific pattern.The server then provides information on locations that are deemed dangerous to local governments, facilitating repairs.

[1307] Creating a predictive model

[1308] The server generates a machine learning model based on the collected data to predict future danger zones. This prediction model is updated regularly. When a danger zone is predicted, local governments are notified in advance so that preventive measures can be taken.

[1309] Warning notice

[1310] When the user approaches a known dangerous spot, the device will issue a warning using the built-in speaker. For example, it may announce, "There is a step ahead, so be careful." This function allows the user to recognize danger in advance and move safely.

[1311] Specific examples

[1312] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[1313] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[1314] 3. The recorded data is sent to the server via the terminal's communication module.

[1315] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[1316] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[1317] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[1318] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps."

[1319] This system will enable users to go out safely and local governments to efficiently manage safety in their cities. This invention will contribute to creating an environment where pedestrians, including the elderly, can go out with peace of mind.

[1320] The processing flow will be explained below.

[1321] Step 1:

[1322] The user launches Silver Guide.

[1323] The device will initialize the GPS module and begin obtaining current location information.

[1324] Step 2:

[1325] As users walk around town, the device periodically updates its GPS data to track their location.

[1326] Step 3:

[1327] When the user reaches a location where he or she feels danger, he or she presses the danger detection button on the terminal.

[1328] Step 4:

[1329] The device records the GPS data and timestamp of the location where the button was pressed. For example, the data is generated in the format location_data = {timestamp: current time, latitude: latitude, longitude: longitude}.

[1330] Step 5:

[1331] The device sends the recorded location information and a timestamp to the server using a POST request via the REST API.

[1332] Step 6:

[1333] The server receives the data sent from the device and stores it in a database, for example using an SQL query such as INSERT INTO danger_points (timestamp, latitude, longitude) VALUES (current time, latitude, longitude).

[1334] Step 7:

[1335] The server periodically retrieves the data on danger points from the database and analyzes it. Specifically, it counts the number of reports at common points using an SQL query. Example: SELECT latitude, longitude, COUNT() FROM danger_points GROUP BY latitude, longitude HAVING COUNT() > n

[1336] Step 8:

[1337] The server identifies locations that have been reported a certain number of times and marks them as dangerous.

[1338] Step 9:

[1339] The server prepares to provide details of locations marked as dangerous to local authorities. It generates a list of danger points and sends it to the municipal system via API or notification system. Example: POST / api / municipalities / danger_points {dangerous_locations: [location1, location2,...]}

[1340] Step 10:

[1341] The server uses the collected data to train a machine learning model to predict future hazards, and this predictive model is updated regularly.

[1342] Step 11:

[1343] When the user approaches a known danger point, the device will use its built-in speaker to issue an audible warning, such as "There is a step ahead, so be careful."

[1344] Example 1

[1345] 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."

[1346] The present invention relates to a system for creating an environment in which elderly people and other pedestrians can move around town safely. Conventional systems have the drawback of being time-consuming to detect and report dangerous areas, making it difficult to take measures before danger actually occurs. Furthermore, information on dangerous areas is not properly managed, which can delay the response of local governments. There is a need to solve these problems by more quickly and accurately predicting dangerous areas, providing warnings to users, and promoting the provision of appropriate information to local governments.

[1347] 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.

[1348] In this invention, the server includes means for analyzing the received location information and providing information on locations determined to be dangerous to local governments, means for predicting future dangerous locations using a machine learning library, and means for periodically analyzing the location information stored in the database using a statistical anomaly detection algorithm.As a result, when a user senses danger in a city, the location information is quickly obtained and sent to a computer system, thereby providing accurate information to local governments, predicting future dangerous locations, and enabling them to take preventative measures.

[1349] "Users" refers to elderly people and pedestrians who use the system to get around town.

[1350] A "button" refers to an input device that a user presses when they sense danger to notify the system of the danger.

[1351] A "Global Positioning System module" refers to a device that measures its location on Earth using satellite signals, commonly known as a GPS module.

[1352] A "communication module" is a communication device for transmitting recorded data to other devices or systems.

[1353] "Computer system" refers to a computing device for receiving, storing, analyzing, and communicating data.

[1354] A "hazardous location" is a location that the system has analyzed multiple data points and deemed dangerous because it exceeded certain criteria.

[1355] "Local government" refers to a regional administrative unit such as a city, town, or village, and is an organization responsible for managing public safety.

[1356] "Audio notification means" refers to a device or technology that generates audio to alert the user to a danger.

[1357] "Encryption" is the process of converting information to protect it from external interference or unauthorized access.

[1358] "Database" refers to a software system for systematically storing and managing collected data.

[1359] A "statistical anomaly detection algorithm" is a mathematical method used to identify patterns and outliers in data.

[1360] "Machine learning library" refers to software tools and libraries used to build and train machine learning models.

[1361] A "machine learning model" is an algorithm that predicts future data and patterns based on past data.

[1362] This invention relates to a system for providing an environment in which elderly people and other pedestrians can move around safely in the city. This system consists of a user, a terminal (Silver Guide), and a server. The specific processing of each component and program is explained below.

[1363] System configuration

[1364] 1. Users: Elderly people and other pedestrians who use the system. Users move around the city with the Silver Guide.

[1365] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[1366] 3. Server: A computer system that receives, stores, and analyzes data sent from terminals and provides appropriate information to local governments and users.

[1367] Program processing overview

[1368] Initial setup and data acquisition

[1369] When a user launches Silver Guide, the device initializes the GPS module and acquires real-time location information. Specifically, the device receives signals from GPS satellites and calculates the current location's longitude and latitude. This process uses the NMEA protocol.

[1370] Recording of dangerous areas

[1371] When a user presses the danger detection button at a location where they sense danger, the device records the location information and timestamp at that moment. For example, if a user discovers a large step on the sidewalk, they press the danger detection button on the spot and the device records the location information.

[1372] Sending and Receiving Data

[1373] The recorded location information and timestamp are sent to the server via the device's communication module (e.g., 4G LTE module). The sent data is AES encrypted to ensure security. The server receives the data, stores it in temporary memory, and then saves it in a database (e.g., MySQL or PostgreSQL).

[1374] Analyzing the data

[1375] The server periodically analyzes the received data, and if multiple users report the same location or if a specific pattern is found, it determines that location as a "danger zone." The data is analyzed using a statistical anomaly detection algorithm using Python and the Pandas library.

[1376] Notification to local governments

[1377] If the server determines that a location is at risk, it will notify the local government using an automated email system (e.g., SendGrid). The email notification will include specific location information (e.g., longitude and latitude), a timestamp, and the number of reports.

[1378] Prediction using machine learning models

[1379] The server uses machine learning libraries (e.g., TensorFlow) to train a predictive model based on the collected data to predict future hazards. The model is periodically updated with new data and notifies local governments in advance.

[1380] User warning notification

[1381] When the user approaches a known dangerous spot, the device will issue a voice warning using the built-in speaker. For example, it will make an announcement such as, "There is a step ahead, so please be careful." This function allows the user to recognize danger in advance and move safely.

[1382] Specific examples

[1383] 1. The user discovers a steep step on a path in a park they usually walk through and presses the danger detection button on the spot.

[1384] 2. The device records its current location (e.g., longitude: 35.6895, latitude: 139.6917) and a timestamp.

[1385] 3. The recorded data is sent to the server via the terminal's communication module.

[1386] 4. The server receives the data and stores it in a database.

[1387] 5. The server analyzes the incident and determines that similar reports have been made multiple times by other users of the same park.

[1388] 6. The server provides this information to local authorities, notifying them that repairs are needed.

[1389] 7. Local governments will use the information provided to promptly begin repair work on the steps.

[1390] 8. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps."

[1391] Examples of prompt statements

[1392] "Record and send the GPS information of your current location"

[1393] "Analyze the patterns in the data that report hot spots at this location."

[1394] "Generate a model that predicts future danger spots based on the collected data."

[1395] "Generate an audio message to warn users when they approach this location"

[1396] In this way, this system provides an environment in which users can move around safely, and enables local governments to efficiently manage the safety of their cities.

[1397] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1398] Step 1:

[1399] Initial setup and data acquisition

[1400] The user starts Silver Guide. The input is a start command from the user. The device first initializes the GPS module (e.g., u-blox module) and receives signals from GPS satellites to collect current location information. For data calculation, the device analyzes the received data using the NMEA protocol and calculates the current longitude and latitude. The output is the current location information (longitude, latitude).

[1401] Step 2:

[1402] Recording of dangerous areas

[1403] When a user senses danger, they press the danger detection button. The input is the user pressing the button event. The device records the location information and timestamp at that moment. As data processing, the longitude, latitude, and time information of the current location are saved in memory as a single data set. The output is the recorded location data (longitude, latitude, timestamp).

[1404] Step 3:

[1405] Sending data

[1406] The device sends the recorded location information and timestamp to the server via a communication module (e.g., 4G LTE module). The input is the recorded location data. The data operation protects the data using AES encryption and sends it to the server using a transmission protocol (e.g., HTTP or MQTT). The output is the encrypted data transmission result.

[1407] Step 4:

[1408] Receiving and storing data

[1409] The server stores the received data in memory. The input is the encrypted data sent from the device. The data is then processed by decrypting it using AES encryption and checking the integrity of the data. An SQL query is created to store the data in a database (e.g., MySQL, PostgreSQL). The output is the location data stored in the database.

[1410] Step 5:

[1411] Analyzing the data

[1412] The server periodically analyzes the location data in the database. The input is the location data in the database. For data processing, Python and the Pandas library are used to analyze the frequency and consistency of data points based on statistical anomaly detection algorithms. The output is a list of locations that are determined to be dangerous.

[1413] Step 6:

[1414] Notification to local governments

[1415] The server provides information on identified dangerous locations to local governments. The input is the analysis results of the dangerous location data. Data is processed using an automated email system (e.g., SendGrid) to generate a notification email about the dangerous location. The output is a notification email sent to the local government.

[1416] Step 7:

[1417] Prediction using machine learning models

[1418] The server uses a machine learning library (e.g., TensorFlow) to train a model based on the collected data and predict future hazardous locations. The inputs are past location data and hazardous location data. Data calculations include data preprocessing, model training, and evaluation. The output is a prediction model for future hazardous locations and the prediction results.

[1419] Step 8:

[1420] User warning notification

[1421] When the user approaches a known dangerous spot, the device issues a voice warning through its built-in speaker. The inputs are current location information and dangerous spot data. Data calculations compare the current location information with known dangerous spot data and generate a voice message if a warning is necessary. The output is a voice warning such as "There is a step ahead, so be careful."

[1422] (Application example 1)

[1423] 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."

[1424] Modern society demands support systems to help elderly people and those with walking difficulties navigate safely around town. However, current systems are limited in their scope of effectiveness, and lack of coordination with autonomous vehicles in particular makes it difficult to fully ensure pedestrian safety. In addition, the detection and improvement of dangerous areas is often delayed, requiring rapid action by local governments and related organizations.

[1425] 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.

[1426] In this invention, the server includes: a means for a user to press a button when they sense danger in a city; a satellite positioning system that acquires location information of the location when the button is pressed; a communication means for transmitting the acquired location information to the server; a means for the server to analyze the received location information and provide information on locations determined to be dangerous to public institutions; a means for issuing an audio warning to a user approaching a location determined to be dangerous by the server; a means for the autonomous vehicle to adjust or stop its speed when approaching a dangerous location; and a means for the autonomous vehicle to acquire data on dangerous locations from the server. This enables the autonomous vehicle to take appropriate action in real time while ensuring the safety of pedestrians. It also provides information to local governments so that they can quickly improve dangerous locations.

[1427] "Users" refers to elderly people and people who have difficulty walking who use the system to move safely around the city.

[1428] "City" refers to areas where pedestrians frequently come and go, such as urban areas and public places.

[1429] "Means for pressing a button when danger is sensed" refers to an interface that a user can physically press when they sense danger, in order to notify the system of the presence of danger.

[1430] "Satellite Positioning System" means a satellite technology used to precisely determine location on Earth, and typically includes GPS.

[1431] "Communication Method" refers to the process of using the Internet or other network technology to transmit data to a server.

[1432] A "server" is a computer system that receives, stores, and analyzes data and provides appropriate information to users and public institutions.

[1433] "Public agency" refers to a government or administrative organization responsible for managing public safety, such as a local government, police, or fire department.

[1434] An "autonomous vehicle" refers to a vehicle that can drive itself without human intervention.

[1435] "Danger points" refer to specific locations that the server determines pose a high risk to users or autonomous vehicles.

[1436] "Means of issuing audio warnings" refers to a system that uses speakers or voice synthesis technology to issue audio warnings to alert users to danger.

[1437] "Means to adjust speed or stop" refers to a control system that takes appropriate action when an autonomous vehicle approaches a hazard.

[1438] "Means for obtaining data" refers to the communication process by which an autonomous vehicle obtains the necessary data from a server.

[1439] The system for implementing this invention ensures the safety of pedestrians while cooperating with autonomous vehicles to share and utilize safety information in real time. The specific configuration and operation of this system are described below.

[1440] 1. System Configuration

[1441] Users: Elderly people and other pedestrians who use the system. They carry a stick-shaped device (Silver Guide) and move around the city.

[1442] Device (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, and voice notification function.

[1443] Autonomous vehicle: A vehicle that can drive itself without human intervention, equipped with a communication module and control system.

[1444] Server: A computer system that receives, stores, and analyzes data sent from terminals and autonomous vehicles, and provides appropriate information to local governments, users, and autonomous vehicles.

[1445] 2. Program Processing

[1446] Program Overview

[1447] The server receives and analyzes the location information of the device and the autonomous vehicle, identifies and predicts dangerous areas, and provides this information to public institutions, users, and autonomous vehicles in real time.

[1448] User's walking movements

[1449] When a user walks around town with the stick-shaped device, the device acquires GPS data in real time and tracks the user's current location. When the user presses the danger detection button at a point where they sense danger, the location information and timestamp at that time are recorded.

[1450] Sending and Receiving Data

[1451] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database, using encryption technology to ensure security.

[1452] Analyzing data and identifying hot spots

[1453] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is identified. Furthermore, it generates a machine learning model based on the collected data to predict future dangerous locations.

[1454] Collaboration with autonomous vehicles

[1455] The autonomous vehicle periodically retrieves data on dangerous locations from the server and calculates the distance between its current location and the dangerous location in real time. When approaching a dangerous location, the autonomous vehicle will adjust its speed or stop appropriately to ensure the safety of pedestrians.

[1456] Warning notice

[1457] Users approaching known danger points will receive a voice warning using the device's built-in speaker. Similarly, autonomous vehicles will issue warnings to pedestrians when approaching danger points.

[1458] 3. Adding specific examples

[1459] Usage example 1:

[1460] A user discovers a steep step on a path in a park they regularly walk through. They press the danger detection button on the spot. The device records its current location information (e.g., longitude 35.6895, latitude 139.6917) and a timestamp, and sends them to a server. The server then confirms similar reports from other pedestrians and notifies the local government. The local government quickly repairs the step, and when the user returns, a voice message is sent to the user saying, "Please be careful as there is a step ahead."

[1461] Usage example 2:

[1462] A self-driving vehicle approaches while a user is walking in a city. The self-driving vehicle receives the danger point data from the server, detects that the user is approaching a danger point, and adjusts its speed appropriately as it proceeds. This ensures the user's safety.

[1463] Prompt Sentence Examples

[1464] "Please develop a system that allows elderly people to move around safely using a smart cane. The system will acquire GPS data, record dangerous locations, and send them to a server. It will also provide autonomous vehicles with the ability to detect danger in real time based on this data and adjust their speed or stop."

[1465] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1466] Step 1:

[1467] The user starts walking around town. The device acquires the user's current location (GPS data) in real time using the built-in satellite positioning system. The input at this point is the user's current longitude and latitude. The device continues to record this GPS data. The output is the user's current location information.

[1468] Step 2:

[1469] When a user senses danger, they press the danger detection button on their device. This causes the device to acquire location information (longitude and latitude) and a timestamp at that time. The inputs are the signal that the button was pressed, current location information, and the current time. The output is the location information and timestamp of the danger area.

[1470] Step 3:

[1471] The terminal transmits the acquired location information and timestamp of the dangerous spot to the server via the communication module. The input is the location information and timestamp of the dangerous spot. The output is the result of data transmission to the server (success or failure).

[1472] Step 4:

[1473] The server stores the data received from the device in a database. This database also includes information on previously reported dangerous locations. The input is the location information and timestamp of the dangerous location sent from the device. The output is the result of storing the data in the database (success or failure).

[1474] Step 5:

[1475] The server periodically analyzes the data stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is present. The input is the past data of dangerous locations in the database. The output is a list of dangerous locations as a result of the analysis.

[1476] Step 6:

[1477] To ensure safety, the server predicts future dangerous locations by incorporating information about dangerous locations into a prediction model. The collected data is processed using a machine learning model to generate prediction results. The input is data on past dangerous locations. The output is a list of predicted dangerous locations.

[1478] Step 7:

[1479] The server provides information on predicted dangerous locations to public institutions and autonomous vehicles. It retrieves data from its own database and sends it to the necessary entities. The input is a list of predicted dangerous locations. The output is the result of sending the data to the public institutions or autonomous vehicles (success or failure).

[1480] Step 8:

[1481] The autonomous vehicle receives the hazard location data sent from the server in real time and calculates the distance between its current location and the hazard location. The input is the autonomous vehicle's current location information and the hazard location data. The output is the distance information to the hazard location.

[1482] Step 9:

[1483] When an autonomous vehicle approaches a dangerous spot, it automatically adjusts its speed or stops. The input is information about the distance to the dangerous spot and the autonomous vehicle's control system. The output is the speed adjustment or stopping action.

[1484] Step 10:

[1485] The server issues an audio warning to users approaching dangerous locations. The server checks the user's current location information and issues a warning based on a list of dangerous locations. The input is the user's current location information and a list of dangerous locations. The output is an audio warning notification.

[1486] 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.

[1487] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion engine that recognizes the user's emotions, a high level of safety and comfort is achieved. The specific configuration of this system and the program processing are described below.

[1488] System configuration

[1489] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[1490] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, emotion engine, sensors (voice and facial expressions), and voice notification function.

[1491] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[1492] Program processing overview

[1493] Use in the city

[1494] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[1495] Sending and Receiving Data

[1496] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. Encryption technology is generally used to ensure security.

[1497] Analyzing the data

[1498] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if there is a specific pattern.The server then provides information on locations that are deemed dangerous to local governments, facilitating repairs.

[1499] Emotion Engine Functions

[1500] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. For example, it is equipped with a camera and microphone to detect when the user is feeling anxious or scared. It also adjusts the intensity and content of warnings depending on the user's emotional state.

[1501] Creating a predictive model

[1502] The server generates a machine learning model based on the collected data to predict future danger zones. This prediction model is updated regularly. When a danger zone is predicted, local governments are notified in advance so that preventive measures can be taken.

[1503] Emergency reporting

[1504] The device is equipped with a sensor that detects the user's fall or impact, and if the user falls, it will make an emergency call to the police, fire department, or family members.

[1505] Warning notice

[1506] When the user approaches a known danger point, the device will issue a warning using its built-in speaker, such as "There is a step ahead, please be careful." If the emotion engine detects the user's anxiety or fear, it will increase the intensity of the warning or provide more detailed instructions.

[1507] Specific examples

[1508] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[1509] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[1510] 3. The recorded data is sent to the server via the terminal's communication module.

[1511] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[1512] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[1513] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[1514] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps." Furthermore, if the emotion engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[1515] This system allows users to go out safely and enables local governments to efficiently manage the safety of their cities. The introduction of an emotion engine enables flexible responses according to the individual conditions of each user, providing an even higher level of safety.

[1516] The processing flow will be explained below.

[1517] Step 1:

[1518] The user launches Silver Guide.

[1519] The device will initialize the GPS module and begin obtaining current location information.

[1520] Step 2:

[1521] As users walk around town, the device periodically updates its GPS data to track their location.

[1522] Step 3:

[1523] The device's emotion engine analyzes the user's voice and facial expressions to assess their emotional state in real time. Specifically, the camera captures facial expression data and the microphone captures voice data.

[1524] Step 4:

[1525] When the user reaches a location where he or she feels danger, he or she presses the danger detection button on the terminal.

[1526] Step 5:

[1527] The device records the GPS data and timestamp of the location where the button was pressed. For example, the data is generated in the format location_data = {timestamp: current time, latitude: latitude, longitude: longitude}.

[1528] Step 6:

[1529] The device sends the recorded location information, timestamp, and emotion data (e.g., anxiety score) generated by the emotion engine to the server using a POST request via the REST API.

[1530] Step 7:

[1531] The server receives the data sent from the device and stores it in a database, for example, using an SQL query such as INSERT INTO danger_points (timestamp, latitude, longitude, emotion_score) VALUES (current time, latitude, longitude, emotion_score).

[1532] Step 8:

[1533] The server periodically retrieves the danger point data from the database and analyzes it. Specifically, it counts the number of reports and emotion scores for common points using an SQL query. Example: SELECT latitude, longitude, COUNT(), AVG(emotion_score) FROM danger_points GROUP BY latitude, longitude HAVING COUNT() > n

[1534] Step 9:

[1535] The server identifies locations that have been reported more than a certain number of times or have a high emotional score and marks them as dangerous locations.

[1536] Step 10:

[1537] The server prepares to provide details of locations marked as dangerous to local authorities. It generates a list of danger points and sends it to the municipal system via API or notification system. Example: POST / api / municipalities / danger_points {dangerous_locations: [location1, location2,...]}

[1538] Step 11:

[1539] The server uses the collected data to train a machine learning model to predict future hazards, and this predictive model is updated regularly.

[1540] Step 12:

[1541] When the user approaches a known danger point, the device will issue a warning using the built-in speaker, such as "Be careful, there is a step ahead." If the emotion engine detects anxiety or fear, the device will issue an additional instruction such as "Walk slowly."

[1542] Step 13:

[1543] When the device's fall and shock sensors detect that the user has fallen, the device automatically makes an emergency call to the police, fire department, or family members. The call includes latitude and longitude information and emotional data.

[1544] In this way, the Silver Guide increases the safety of users and enables local governments to respond quickly. Furthermore, the introduction of an emotion engine allows for flexible responses according to individual conditions, providing an even higher level of safety.

[1545] Example 2

[1546] 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."

[1547] There is a need for effective methods to ensure safe urban mobility for elderly people and pedestrians, and to quickly identify and repair potential hazards. There is also a need for flexible warning functions that respond to the user's emotional state, and for systems that instantly report falls and impacts.

[1548] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing the user's voice and facial expression to detect the user's emotional state, a means for adjusting the strength and content of the warning depending on the user's emotional state, and a means for generating a machine learning model using collected location information data to predict future dangerous locations. This allows users to move safely around town, provides a flexible warning function according to the user's emotional state, and enables potential dangerous locations to be quickly identified and repaired. Furthermore, an emergency reporting function is also provided, further improving user safety.

[1549] "Users" refers to elderly people and other pedestrians who use the system to get around town.

[1550] "Means for pressing a button" refers to a button device that a user can press when they sense danger.

[1551] "Location information acquisition device" refers to a device that acquires location information in real time, such as a GPS module.

[1552] "Communication device" refers to a device that uses wireless communication technology to transmit acquired location information to a server.

[1553] "Server" refers to the computer system that analyzes received location information and stores and processes the data.

[1554] "Municipality" refers to local public bodies such as cities, towns, villages, and wards.

[1555] "Means for notifying the user by voice" refers to a device that uses a built-in speaker to issue a voice warning to the user.

[1556] "Means for detecting emotional state" refers to algorithms or devices that analyze the user's voice and facial expressions to determine their emotions in real time.

[1557] "Means for adjusting the intensity and content of warnings" refers to the ability to dynamically change the content and intensity of warnings based on the user's emotional state.

[1558] "Means for generating a machine learning model" refers to a process of using a machine learning algorithm to predict future hot spots using collected data.

[1559] "Devices that detect falls and impacts" refers to devices that use acceleration sensors, gyroscopes, etc. to detect falls and impacts by users.

[1560] "Means for making emergency calls" refers to a system that automatically notifies the police, fire department, or family members when the user experiences an emergency such as a fall.

[1561] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion engine that recognizes the user's emotions, a high level of safety and comfort is achieved. The specific configuration of this system and the program processing are described below.

[1562] System configuration

[1563] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[1564] 2. Terminal (Silver Guide): A smart walking stick equipped with a GPS module, communication module, danger detection button, emotion engine, sensors (voice and facial expressions), and voice notification function.

[1565] 3. Server: A computer system that receives, stores, and analyzes data sent from the terminal and provides appropriate information to local governments and users.

[1566] Program processing overview

[1567] Use in the city

[1568] When a user starts walking around town with the Silver Guide, the device acquires GPS data in real time and tracks the user's current location. When the user senses danger and presses the danger detection button, the device records the location information and timestamp at that time.

[1569] Sending and Receiving Data

[1570] The recorded location information is sent to a server via the device's communication module. The server receives this data and stores it in a database. To ensure security, encryption technology is generally used. Specifically, AES (Advanced Encryption Standard) encryption technology is used.

[1571] Analyzing the data

[1572] The server periodically analyzes the data on dangerous locations stored in the database and determines whether a location is dangerous if multiple users report the same location or if a specific pattern is identified. For example, it runs scripts using Python to cross-tabulate the data and apply anomaly detection algorithms. The server then provides information on dangerous locations to local governments to facilitate repairs.

[1573] Emotion Engine Functions

[1574] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. For example, it uses the Google Cloud Speech-to-Text API to analyze audio recorded by the microphone, and OpenCV and facial recognition APIs to analyze facial images captured by the camera. The emotion engine detects when the user feels anxiety or fear, and adjusts the intensity and content of warnings depending on the user's emotional state.

[1575] Creating a predictive model

[1576] The server generates a machine learning model based on the collected data to predict future dangerous areas. This predictive model is created using machine learning libraries such as TensorFlow and Scikit-learn. New data is periodically imported and the model is updated to maintain the accuracy of the predictions. When dangerous areas are predicted, local governments are notified in advance so that preventive measures can be taken.

[1577] Emergency reporting

[1578] The device is equipped with a sensor that detects falls and impacts. When the user falls, the device will make an emergency call to the police, fire department, or family members that have been registered in advance. This function is implemented, for example, using an acceleration sensor.

[1579] Warning notice

[1580] When the user approaches a known danger point, the device will issue a warning using its built-in speaker, such as "There is a step ahead, please be careful." If the emotion engine detects the user's anxiety or fear, it will increase the intensity of the warning or provide more detailed instructions.

[1581] Specific examples

[1582] 1. The user discovers a steep step on a park path they usually walk through and presses the danger detection button on the spot.

[1583] 2. The device records its current location (longitude: 35.6895, latitude: 139.6917) and a timestamp.

[1584] 3. The recorded data is sent to the server via the terminal's communication module.

[1585] 4. The server receives the data and stores it in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[1586] 5. The server provides this information to local authorities and notifies them that repairs are needed.

[1587] 6. Local governments will use the information provided to promptly begin repair work on the steps.

[1588] 7. When the user passes through the park again, the device will issue a voice warning saying, "Be careful, there are steps." Furthermore, if the emotion engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[1589] As a concrete example, it is possible to simulate the system by inputting the following prompts into the generative AI model:

[1590] Example prompt: "A user discovers a steep step while walking through a park and presses the danger detection button on the Silver Guide. Please explain in detail how this information is sent to the server and how repair work is subsequently carried out."

[1591] This system allows users to go out safely and enables local governments to efficiently manage the safety of their cities. The introduction of an emotion engine enables flexible responses according to the individual conditions of each user, providing an even higher level of safety.

[1592] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1593] Step 1:

[1594] When a user starts walking around town with the Silver Guide, the device uses the GPS module to obtain real-time location information. The GPS module outputs longitude and latitude data as input. The device temporarily stores this location information in its internal memory.

[1595] Specific behavior:

[1596] The device acquires longitude and latitude data every 10 seconds and stores it in memory.

[1597] Step 2:

[1598] When a user presses the danger detection button at a location where they sense danger, the device records the location information and timestamp at that time. The input is the button press signal, longitude, latitude, and timestamp, and the device outputs it.

[1599] Specific behavior:

[1600] When the user presses the button, the device displays the message "Danger button has been pressed" and stores the acquired longitude, latitude and timestamp in memory.

[1601] Step 3:

[1602] The recorded location information and timestamp are sent to the server using the device's communication module. The input is the acquired longitude, latitude, and timestamp, and the output is AES encrypted to ensure data security.

[1603] Specific behavior:

[1604] The device encrypts the data within 5 seconds and sends it to the server.

[1605] Step 4:

[1606] The server receives the data sent from the device and stores it in a database. The input is the encrypted longitude, latitude, and timestamp. The data is decrypted before being stored in the database.

[1607] Specific behavior:

[1608] The server decrypts the received data and adds it to the PostgreSQL database.

[1609] Step 5:

[1610] The server periodically analyzes the data of dangerous locations stored in the database. It takes as input the collected location data and outputs it. It runs a Python script and applies cross-tabulation and anomaly detection algorithms to report information on locations that are deemed dangerous to local authorities.

[1611] Specific behavior:

[1612] The server cross-tabulates data from the past week to identify areas where the same location has been reported multiple times.

[1613] Step 6:

[1614] The device uses an emotion engine to analyze the user's voice and facial expressions in real time. The input is voice data captured by the microphone and camera, and facial image data is output. Data analysis is performed using the Google Cloud Speech-to-Text API and OpenCV. Alerts are adjusted based on the emotional state detected.

[1615] Specific behavior:

[1616] If the device determines that the user is feeling anxious, it will increase the intensity of the warning.

[1617] Step 7:

[1618] The server generates a machine learning model based on the accumulated data and predicts future dangerous areas. The collected location information data is output as input. The machine learning model is trained using TensorFlow and Scikit-learn.

[1619] Specific behavior:

[1620] The server retrains the model every time new data is collected, maintaining prediction accuracy.

[1621] Step 8:

[1622] The device is equipped with sensors to detect falls and impacts, and if the user falls, it will make an emergency call to the police, fire department, or family members. Data from the accelerometer and gyroscope is output as input.

[1623] Specific behavior:

[1624] When the device detects a fall, it will send an SMS or an automated call to a pre-set emergency number.

[1625] Step 9:

[1626] When the user approaches a known danger point, the device will issue an audio warning using the built-in speaker. Location data and emotional state data are output as inputs.

[1627] Specific behavior:

[1628] The device will announce, "Be careful, there is a step ahead," and provide additional instructions if necessary.

[1629] Through the specific processing flow described above, the system supports users in moving safely around the city and enables the rapid identification and repair of dangerous areas.

[1630] (Application example 2)

[1631] 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."

[1632] Ensuring safety when walking around town is an extremely important issue these days. Detecting and responding to potential dangers is especially important for the elderly and physically frail. Users may feel anxious or scared in certain places, and a means to respond quickly to these situations is needed. However, current systems have difficulty detecting these emotions in real time and issuing appropriate warnings immediately. Furthermore, they lack the ability to predict future dangers.

[1633] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing received location information and providing information on places determined to be dangerous to the local government, means for issuing an audio warning to a user who approaches a place determined to be dangerous, and an emotion analysis engine for analyzing the emotional state of the user and adjusting the content of the warning notification if the user feels anxiety or fear. This supports users to move around town more safely and comfortably, and enables the local government to effectively manage dangerous areas and respond quickly.

[1634] A "location measurement module" is a device for acquiring the current location of a user and outputs data including location information.

[1635] The "information transmission module" is a communication device for transmitting the acquired location information to a server, and transmits and receives data.

[1636] An "emotion analysis engine" is software or hardware that analyzes a user's voice, facial expressions, etc. to detect their emotional state, making it possible to grasp the anxiety or fear the user is feeling in real time.

[1637] A "machine learning model" is an algorithm that performs statistical analysis and predictions based on collected data, and is a system that can predict future dangerous areas.

[1638] "Warning notification means" refers to devices or software that issue audio or visual warnings when a user approaches a dangerous area.

[1639] "Users" refers to people who use the system to get around town, especially elderly people and other pedestrians.

[1640] A "server" is a computer system that receives, stores, and analyzes location information and emotional data, thereby providing appropriate information to local governments and users.

[1641] The "danger detection button" is a means that users can press when they sense danger in the city, and this records their current location information.

[1642] The system for implementing this invention is designed to create an environment where users can move safely around town and quickly identify and repair potential hazards. In particular, by combining it with an emotion analysis engine that recognizes the user's emotions, a high level of safety and comfort is achieved.

[1643] System configuration

[1644] 1. Users: Elderly people and other pedestrians who use the system. They carry a Silver Guide (smart cane) and walk around the city.

[1645] 2. Terminal (Silver Guide): An intelligent accessory equipped with a location measurement module, information transmission module, danger detection button, emotion analysis engine, sensors (voice and facial expressions), and voice notification function.

[1646] 3. Server: A computer system that receives, stores, and analyzes data sent from terminals and provides appropriate information to local governments and users.

[1647] Program processing overview

[1648] 1. User location tracking

[1649] We use your device's built-in location measurement module (e.g., GPS) to track your location in real time, allowing us to accurately track your movements.

[1650] 2. Detecting dangerous areas

[1651] The location information acquired through the device's information transmission module is sent to a server, which then identifies dangerous areas and automatically stores them in a database. Information on dangerous areas reported by store employees and other customers is also incorporated.

[1652] 3. Analysis using a sentiment analysis engine

[1653] The device uses a microphone and camera to analyze the user's voice and facial expressions in real time, and an emotion analysis engine is used to detect their emotional state (anxiety or fear), allowing the device to understand their mental state and provide appropriate warnings and support.

[1654] 4. Warning notice

[1655] When a user approaches a known dangerous spot, the device's voice notification function will issue an audible warning, and if the emotion analysis engine detects anxiety or fear in the user, the strength and content of the warning will be adjusted.

[1656] 5. Data transmission and analysis

[1657] The device encrypts the collected data and sends it to a server, which stores it in a database and periodically analyzes the data to generate a machine learning model for predicting future risk areas.

[1658] Specific examples

[1659] 1. A user discovers a steep step on a path in a park they regularly walk through. They press the danger detection button on the spot. The device records the location information and timestamp at that time and sends them to the server.

[1660] 2. The recorded data is received by a server and stored in a database. Analysis reveals that similar reports have been made multiple times by other users of the same park.

[1661] 3. The server uses this information to notify the local government that repairs are necessary, and the local government uses the information provided to promptly begin repair work on the steps.

[1662] 4. When the user returns to the park, the device will issue a voice warning saying, "Be careful, there are steps." If the emotion analysis engine detects the user's anxiety, the device will issue an additional instruction saying, "Walk slowly."

[1663] This system allows users to go out safely and enables local governments to efficiently manage safety in their cities. The introduction of an emotion analysis engine enables flexible responses according to the individual state of each user, providing an even higher level of safety.

[1664] *Example of a prompt to input to the generative AI model:

[1665] Design an AI system that monitors users' facial expressions in real time as they move through a physical store, and issues audio and visual warnings to ensure safety. The system also issues warnings when users approach known hazards or crowded areas. The system manages the user's location and adapts to their emotional state.

[1666] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1667] Step 1:

[1668] The user walks around the city

[1669] Input: User's location, voice, facial expression

[1670] Processing: The device acquires real-time location information using a location measurement module (GPS) and captures voice and facial expressions using a camera and microphone.

[1671] Specific operation: While the user is walking, the device's sensors continuously collect data. The device collects this data in real time and performs initial processing in its internal processor.

[1672] Output: Real-time location information, audio data, facial expression data

[1673] Step 2:

[1674] The danger detection button is pressed

[1675] Input: Button press event, current location, timestamp

[1676] Processing: When the button is pressed, the device records the current location and a timestamp.

[1677] Specific operation: When the user senses danger and presses the button, the device acquires data from the location information measurement module and temporarily stores it in memory along with a timestamp.

[1678] Output: Recorded location information, timestamp

[1679] Step 3:

[1680] Sending data

[1681] Input: Recorded location information, timestamp

[1682] Processing: The device sends the recorded location information and timestamp to the server via the information transmission module. The data is encrypted before transmission.

[1683] Specific operation: Data packets sent from the device are sent to the server using a communication protocol. The data is protected by encryption technology such as SSL / TLS.

[1684] Output: Location information received by the server, timestamp

[1685] Step 4:

[1686] Analyzing incoming data

[1687] Input: Location information stored on the server, timestamp

[1688] Processing: The server analyzes the received data and decides whether to mark a hotspot. If there are multiple reports, they are prioritized according to a specific algorithm.

[1689] Specific operation: The analysis engine on the server retrieves and analyzes the received data from the database. If there are multiple reports, the risk level is evaluated based on frequency and degree of agreement. For example, cluster analysis of data surrounding the reporting location can be performed to ensure that risk areas are identified.

[1690] Output: Location information and details of locations that are deemed dangerous

[1691] Step 5:

[1692] Warning notice

[1693] Input: Server analysis results (location information and details of dangerous areas)

[1694] Processing: The server sends information about the danger zone back to the device, which then issues a voice warning to the user. An emotion analysis engine evaluates the user's real-time emotional state and adjusts the warning accordingly.

[1695] Specific operation: The device that receives the data sent by the server uses its voice notification function to play a message such as "There is a step ahead, please be careful." If the emotion analysis engine detects the user's anxiety, it provides additional instructions such as "Please walk slowly."

[1696] Output: Audio alert, adjust notification content based on emotion

[1697] Through these steps, the system will help users move safely around the city and enable local governments to efficiently manage dangerous areas and respond quickly.

[1698] 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.

[1699] 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.

[1700] 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.

[1701] 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.

[1702] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1703] 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.

[1704] 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).

[1705] 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.

[1706] 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."

[1707] 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.

[1708] 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).

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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.

[1714] 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.

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] The following is further disclosed regarding the above embodiment.

[1720] (Claim 1)

[1721] A way for users to press a button when they feel unsafe in the city,

[1722] A GPS module that acquires location information when the button is pressed,

[1723] a communication module that transmits the acquired location information to a server;

[1724] A means for the server to analyze the received location information and provide information on locations that are deemed dangerous to local governments;

[1725] A system including a means for issuing an audio warning to a user approaching a location that the server judges to be dangerous.

[1726] (Claim 2)

[1727] 10. The system according to claim 1, further comprising a sensor for detecting a fall or impact of the user, and means for making an emergency call to the police, fire department, or family members upon detection.

[1728] (Claim 3)

[1729] The system according to claim 1, further comprising means for generating a machine learning model using location information data collected by the server and predicting future dangerous locations.

[1730] "Example 1"

[1731] (Claim 1)

[1732] A way for users to press a button when they feel unsafe in the city,

[1733] a global positioning system module that acquires location information when the button is pressed;

[1734] a communication module for transmitting the acquired location information to a computer system;

[1735] a means for the computer system to analyze the received location information and provide information on locations determined to be dangerous to local authorities;

[1736] a means for issuing a voice warning to a user who is approaching a place that the computer system has determined to be dangerous;

[1737] means for encrypting and transmitting location information using a communication module;

[1738] a means for the computer system to periodically analyze the location information stored in the database using a statistical anomaly detection algorithm;

[1739] A system including a means for predicting future dangerous locations using a machine learning library.

[1740] (Claim 2)

[1741] 10. The system according to claim 1, further comprising a sensor for detecting a fall or impact of the user, and means for making an emergency call when the sensor detects the fall or impact.

[1742] (Claim 3)

[1743] The system of claim 1, further comprising means for notifying local governments of future danger spots in advance using a machine learning model generated based on the data.

[1744] "Application Example 1"

[1745] (Claim 1)

[1746] A way for users to press a button when they feel unsafe in the city,

[1747] A satellite positioning system that acquires location information when the button is pressed;

[1748] a communication means for transmitting the acquired location information to a server;

[1749] A means for the server to analyze the received location information and provide information on locations that are determined to be dangerous to public institutions;

[1750] a means for issuing an audio warning to a user who is approaching a place that the server has determined to be dangerous;

[1751] a means for adjusting the speed or stopping the automated vehicle when it approaches a hazard;

[1752] A means for the autonomous vehicle to acquire data on dangerous locations from a server;

[1753] A system including:

[1754] (Claim 2)

[1755] 10. The system according to claim 1, further comprising a sensor for detecting a fall or impact of the user, and means for making an emergency call to the police, an ambulance, or a family member upon detection.

[1756] (Claim 3)

[1757] The system according to claim 1, further comprising means for generating a machine learning model using location information data collected by the server and predicting future dangerous locations.

[1758] "Example 2: Combining Emotion Engines"

[1759] (Claim 1)

[1760] A way for users to press a button when they feel unsafe in the city,

[1761] a location information acquisition device that acquires location information of a location when the button is pressed;

[1762] a communication device that transmits the acquired location information to a server;

[1763] A means for the server to analyze the received location information and provide information on locations that are deemed dangerous to local governments;

[1764] a means for issuing an audio warning to a user who is approaching a place that the server has determined to be dangerous;

[1765] A means for detecting the emotional state of a user by analyzing the user's voice and facial expressions;

[1766] The system includes a means for adjusting the intensity and content of warnings depending on emotional state.

[1767] (Claim 2)

[1768] 2. The system according to claim 1, further comprising a device for detecting a fall or impact of the user, and means for making an emergency call to the police, fire department, or family members upon detection.

[1769] (Claim 3)

[1770] The system according to claim 1, further comprising means for generating a machine learning model using location information data collected by the server and predicting future dangerous locations.

[1771] "Application example 2 when combining emotion engines"

[1772] (Claim 1)

[1773] A way for users to press a button when they feel unsafe in the city,

[1774] a location measurement module that acquires location information of a location when the button is pressed;

[1775] an information transmission module that transmits the acquired location information to a server;

[1776] A means for the server to analyze the received location information and provide information on locations that are deemed dangerous to local governments;

[1777] a means for issuing an audio warning to a user who is approaching a place that the server has determined to be dangerous;

[1778] An emotion analysis engine that analyzes the user's emotional state and adjusts the content of warning notifications if the user feels anxious or scared;

[1779] A system including:

[1780] (Claim 2)

[1781] 10. The system according to claim 1, further comprising a sensor for detecting a fall or impact of the user, and means for making an emergency call to the police, fire department, or family members upon detection.

[1782] (Claim 3)

[1783] The system according to claim 1, further comprising means for generating a machine learning model using location information data collected by the server and predicting future dangerous locations. [Explanation of symbols]

[1784] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A way for users to press a button when they feel unsafe in the city, A GPS module that acquires location information when the button is pressed, a communication module that transmits the acquired location information to a server; A means for the server to analyze the received location information and provide information on locations that are deemed dangerous to local governments; A system including a means for issuing an audio warning to a user approaching a location that the server judges to be dangerous.

2. 2. The system according to claim 1, further comprising a sensor for detecting a fall or impact of the user, and means for making an emergency call to the police, fire department, or family members upon detection.

3. The system according to claim 1 , further comprising means for generating a machine learning model using location information data collected by the server and predicting future dangerous locations.

Images