System

Abstract

A system is provided.SOLUTION: A system including means for periodically acquiring location information, means for transmitting the acquired location information to a server, means for the server to store the location information in a database, means for an artificial intelligence module mounted on the server to analyze the location information and learn a daily behavior pattern of a target person, means for comparing current location information with the learned behavior pattern to detect an abnormality, and means for issuing an alert to a user terminal when the abnormality is detected.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] This invention relates to a monitoring system for ensuring the safety of children and the elderly. Specifically, the objective is to provide a system that can prevent risks such as childcare accidents and elderly wandering and disappearances by detecting abnormalities in real time. Another objective is to solve the social issue of reducing the workload of childcare workers and caregivers. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means: A system including a means for periodically acquiring location information and a means for transmitting the acquired location information to a server. The server includes a means for saving the location information in a database, and further includes a means for an artificial intelligence module to analyze the location information and learn the target person's daily behavior patterns. A system including a means for comparing the current location information with the learned behavior patterns to detect abnormalities and a means for issuing an alert to the user terminal when an abnormality is detected can effectively monitor the safety of children and the elderly.

[0006] "Location information" is data that includes latitude and longitude to identify the subject's current location.

[0007] The "acquisition means" is a device or method that periodically collects location information of a subject.

[0008] The "transmitting means" is a device or method for transferring the acquired location information to the server.

[0009] A "server" is a computer system that receives location information, stores it in a database, and further analyzes it using an artificial intelligence module.

[0010] A "database" is a digital storage system for recording and managing location information.

[0011] An "artificial intelligence module" is software or algorithms that analyze location information and learn the subject's daily behavioral patterns.

[0012] A "behavioral pattern" is a collection of data including the subject's usual travel route, length of stay, location, etc.

[0013] An "anomaly detection means" is a device or method that compares current location information with learned behavioral patterns to identify anomalies.

[0014] An "alert" is a warning message that notifies the user when an abnormality is detected.

[0015] "User terminal" refers to a device for receiving and displaying alerts, including smartphones and tablets. [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 present invention relates to a monitoring system that acquires location information of a target person, detects an abnormality, and issues an alert. Hereinafter, specific embodiments of the present invention will be described.

[0038] System configuration

[0039] The system mainly consists of the following elements:

[0040] 1. A GPS device that periodically acquires location information.

[0041] 2. A device that sends the acquired location information to a server.

[0042] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[0043] 4. A function that sends an alert to the user's device when an abnormality is detected.

[0044] Program processing

[0045] 1. Obtaining location information

[0046] The terminal periodically (for example, every minute) acquires the target person's location information from the GPS device. This location information includes latitude, longitude, and timestamp.

[0047] 2. Data transmission

[0048] The terminal transmits the acquired location information to the server.

[0049] 3. Data storage

[0050] The server stores the received location information in a database, accumulating and managing past location information as well.

[0051] 4. Learning behavioral patterns

[0052] An artificial intelligence module installed on the server analyzes the accumulated location information and learns the target person's daily behavioral patterns, for example, identifying a child's route to school or an elderly person's walking route and time of day.

[0053] 5. Location Comparison

[0054] The terminal obtains the current real-time location information and transmits it to the server.

[0055] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0056] 6. Anomaly Detection

[0057] The AI ​​module detects any deviations from the current location from normal behavioral patterns, such as straying from a specific route or staying in an unspecified area for an extended period of time.

[0058] 7. Alerts

[0059] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location and the reason for the anomaly.

[0060] Specific examples

[0061] Watching over children going to school

[0062] 1. The user gives their child a GPS device.

[0063] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[0064] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[0065] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[0066] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[0067] 6. The user receives an alert and immediately checks on the safety of the child.

[0068] Preventing elderly people from wandering

[0069] 1. The user gives the elderly person a GPS device.

[0070] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[0071] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[0072] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[0073] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[0074] 6. The user receives an alert, checks the elderly person's condition, and takes action.

[0075] This system allows users to monitor the safety of children and the elderly in real time, and responds quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] The user attaches a GPS device to the subject (child or elderly person).

[0079] Step 2:

[0080] The device (smartphone or tablet) registers the GPS device through the app and enters the target person's information (name, age, contact details, etc.).

[0081] Step 3:

[0082] The terminal periodically (for example, every minute) acquires location information (latitude, longitude, timestamp) from the GPS device.

[0083] Step 4:

[0084] The terminal transmits the acquired location information to the server in real time.

[0085] Step 5:

[0086] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[0087] Step 6:

[0088] The AI ​​module installed on the server periodically analyzes the location information in the database and learns the subject's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[0089] Step 7:

[0090] The terminal transmits the current location information obtained in real time to the server.

[0091] Step 8:

[0092] The server passes the received current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0093] Step 9:

[0094] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended period of time in an unplanned location.

[0095] Step 10:

[0096] If an abnormality is detected, the server immediately sends an alert to the user's (guardian's or caregiver's) device.

[0097] Step 11:

[0098] The server includes in the alert message the current location information, the reason why the anomaly was detected, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[0099] Step 12:

[0100] The user checks the alert notification displayed on the device and takes appropriate action, such as contacting the child to check on their safety or heading to the scene.

[0101] Example 1

[0102] 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."

[0103] Conventional monitoring systems not only acquire the target's location information and transmit it to a server, but also analyze that location information, learn the target's daily behavioral patterns, and detect abnormalities. However, existing systems have difficulty detecting abnormalities in real time, and it takes a long time to issue an appropriate alert in an emergency. Furthermore, security during data transmission is insufficient, creating a risk of location information leaks. The present invention aims to solve these problems by providing a system that detects abnormalities more accurately and quickly, ensuring user safety.

[0104] 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.

[0105] In this invention, the server includes means for periodically acquiring location information of a target person, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and perform machine learning on the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, means for encrypting and transmitting the target person's location information, and means for sending an alert to the user terminal using push notification or SMS in an emergency. This enables highly accurate abnormality detection in real time, prompt alert issuance, and safe data transmission.

[0106] "Location information" is data about a subject's current location, including latitude, longitude, and timestamp.

[0107] "Means of acquisition" refers to the means of periodically collecting the subject's location information using a GPS device or terminal.

[0108] A "server" is a remote computer system that receives, stores, processes, etc. data.

[0109] The "transmitting means" is a means for sending data from the terminal to the server.

[0110] A "database" is a data management system that stores location information and allows it to be searched and updated as needed.

[0111] The "artificial intelligence module" is a software module that analyzes location information and learns daily behavior patterns.

[0112] "Machine learning" refers to algorithms and techniques that automatically learn patterns and trends based on large amounts of data.

[0113] The "means for detecting anomalies" is a means for determining whether the current location information deviates from the normal behavioral pattern.

[0114] The "means for issuing an alert" is a means for sending a notification to a user terminal when an abnormality is detected.

[0115] "Means for encryption and transmission" refers to means for encrypting data to protect location information from third parties and transmitting it securely to a server.

[0116] "Push notification" is a method for sending messages from a server to a user terminal in real time.

[0117] "SMS" stands for Short Message Service, a means of sending short text messages via mobile phones.

[0118] The present invention relates to a monitoring system that acquires location information of a target person, detects an abnormality, and issues an alert. A specific embodiment of this system will be described below.

[0119] Hardware and Software Configuration

[0120] Terminal

[0121] The device communicates with the subject's GPS device to obtain location information. The device periodically obtains latitude, longitude, and timestamps from the GPS device using Bluetooth or Wi-Fi connections. HTTPS is used to encrypt the obtained location information and send it securely to the server.

[0122] server

[0123] The server is a device that stores the received location information in a database and analyzes it using an artificial intelligence module. The server uses a relational database such as MySQL or PostgreSQL, and indexes the location information to enable efficient searches. The server is equipped with an artificial intelligence module using Python's Scikit-learn and TensorFlow, which uses machine learning to learn daily behavior patterns based on the accumulated location information.

[0124] Specific actions

[0125] 1. Acquisition and transmission of location information

[0126] The terminal communicates with a GPS device and periodically acquires location information (latitude, longitude, timestamp).

[0127] The device encrypts the acquired location information and sends it to the server using HTTPS.

[0128] 2. Location information storage and analysis

[0129] The server stores the received location information in a database.

[0130] The server's artificial intelligence module analyzes the accumulated location information and learns the subject's daily behavioral patterns, for example, by using K-Means clustering to identify the person's commute route, walking route, and time of day.

[0131] 3. Detecting anomalies and issuing alerts

[0132] The terminal again acquires the current real-time location information and transmits it to the server.

[0133] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0134] The artificial intelligence module detects any deviations in current location information from normal behavioral patterns as an anomaly.

[0135] When an anomaly is detected, the server immediately sends an alert to the user's device via push notification or SMS, and the notification includes the user's current location and the reason why the anomaly was detected.

[0136] Specific examples

[0137] Watching over children going to school

[0138] 1. The user gives their child a GPS device.

[0139] 2. The device will receive the child's location information from the GPS device via Bluetooth every minute. The location information includes latitude, longitude, and a timestamp.

[0140] 3. The device sends the encrypted location information to the server via HTTPS.

[0141] 4. The server stores the location information in a database, and the artificial intelligence module uses the data to learn the school route using K-Means clustering.

[0142] 5. If a child deviates from their usual route to school in real time, the artificial intelligence module will detect this as an anomaly.

[0143] 6. The server immediately sends a push notification to the user's smartphone, alerting them to the location. The notification includes information such as, "Your child has deviated from their normal route. Their current location is latitude x, longitude y."

[0144] Preventing elderly people from wandering

[0145] 1. The user gives the elderly person a GPS device.

[0146] 2. The device receives the elderly person's location information from the GPS device via Bluetooth every minute. The location information includes latitude, longitude, and timestamp.

[0147] 3. The device sends the encrypted location information to the server via HTTPS.

[0148] 4. The server stores the location information in a database, and the artificial intelligence module learns daily behavior patterns using K-Means clustering.

[0149] 5. If an elderly person is out and about and stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[0150] 6. The server immediately sends an alert to the user's smartphone via push notification or SMS. The notification contains information such as, "An elderly person has been outside their usual living area for an extended period of time. Their current location is latitude x, longitude y."

[0151] Example prompts for generative AI models

[0152] Prompt statement:

[0153] Describe a system that sends an alert if a child deviates from their usual route to school. This system uses a GPS device, a server, an artificial intelligence module, etc.

[0154] Prompt statement:

[0155] Describe a system that alerts elderly people if they are outside their usual living area for an extended period of time. The system uses GPS devices, a server, and an artificial intelligence module.

[0156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0157] Step 1:

[0158] Obtaining location information

[0159] The terminal communicates with the subject's GPS device and periodically (e.g., every minute) obtains location information. The input is the latitude, longitude, and timestamp from the GPS device, and the output is the obtained location information. Specifically, the terminal reads information from the device via Bluetooth or Wi-Fi connection.

[0160] Step 2:

[0161] Location encryption

[0162] The device encrypts the acquired location information. The input is the location information acquired in step 1, and the output is the encrypted location information. Specifically, the data is secured using encryption algorithms such as AES or RSA.

[0163] Step 3:

[0164] Sending location information

[0165] The device sends encrypted location information to the server using HTTPS. The input is the encrypted location information, and the output is a notification to the server that the location information has been sent. Specifically, the data is sent to a RESTful API endpoint using a POST request.

[0166] Step 4:

[0167] Save location information

[0168] The server stores the received location information in a database. The input is the location information sent from the device, and the output is a notification that the information has been saved to the database. Specifically, the server uses an INSERT statement to store the location information in the database.

[0169] Step 5:

[0170] Learning behavioral patterns

[0171] The artificial intelligence module installed on the server analyzes the accumulated location information and performs machine learning to learn daily behavior patterns. The input is past location information obtained from a database, and the output is the learned behavior pattern. Specifically, it applies machine learning algorithms such as K-Means clustering.

[0172] Step 6:

[0173] Acquiring and sending real-time location information

[0174] The device again acquires the latest real-time location information and sends it to the server. The input is the current location information from the GPS device, and the output is a notification to the server that transmission has been completed. Specifically, the device again collects location information from the GPS device via Bluetooth or Wi-Fi, encrypts it, and sends it to the server.

[0175] Step 7:

[0176] Real-time location analysis

[0177] The server receives real-time location information and passes it on to an artificial intelligence module for analysis. The input is real-time location information, and the output is the analysis results. Specifically, it compares learned behavioral patterns with real-time location information to detect anomalies.

[0178] Step 8:

[0179] Anomaly detection

[0180] The AI ​​module detects anomalies by identifying deviations from normal behavioral patterns in real-time location information. The input is real-time location information and learned patterns, and the output is the anomaly detection result. Specific operations include using support vector machines (SVM) and other anomaly detection algorithms.

[0181] Step 9:

[0182] Alert issuance

[0183] If an anomaly is detected, the server immediately sends an alert to the user device. The input is the anomaly detection result, and the output is an alert notification to the user device. Specifically, the server sends a push notification or SMS using Firebase Cloud Messaging (FCM) or Twilio.

[0184] Through the technology and specific actions used at each step, the system can monitor the safety of the subject in real time, allowing for quick response in emergencies and greatly reducing the risk of accidents or disappearances.

[0185] (Application example 1)

[0186] 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."

[0187] In the food delivery industry, the safety of delivery staff and efficient operation management are important issues. Conventional methods lack a system that can track delivery staff's location information in real time and immediately detect deviations from the planned route or abnormal behavior. As a result, it is difficult to respond quickly to delays or problems. This can lead to a decline in service quality and a decrease in customer satisfaction.

[0188] 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.

[0189] In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the behavioral patterns of the target person (daily behavior patterns), means for comparing the current location information with the learned behavioral patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, and means for tracking the location information of delivery staff, detecting abnormalities, and notifying an administrator in real time for delivery services. This makes it possible to track the location information of delivery staff in real time in the food delivery industry, quickly detect delays and route deviations, and immediately take appropriate measures.

[0190] "Location information" is data indicating the subject's current location, such as latitude, longitude, and timestamp.

[0191] "Server" means a computing device for receiving, storing, and analyzing location information.

[0192] A "database" is a system that systematically stores and manages acquired location information and related data.

[0193] The "artificial intelligence module" is a group of programs and algorithms that analyze location information and learn the subject's daily behavioral patterns.

[0194] A "user terminal" is a communication device such as a smartphone or dedicated device for receiving alerts.

[0195] A "delivery service" is a business service that delivers meals or goods to a specified location.

[0196] "Delivery staff" refers to personnel whose job is to transport goods and food to provide delivery services.

[0197] "Administrator" refers to the person responsible for supervising and managing delivery staff and the overall system in the delivery service.

[0198] "Real-time tracking" refers to monitoring the location of delivery staff in real time with almost no delay.

[0199] An "alert" is a warning notification sent to a user terminal when an abnormality is detected.

[0200] The present invention relates to a system for tracking the location information of delivery staff in the food delivery industry in real time, detecting abnormalities, and notifying an administrator of an alert. Specific embodiments of the present invention will be described below.

[0201] System Configuration

[0202] The system consists of the following elements:

[0203] 1. Terminal

[0204] The smartphone functions as a GPS device, periodically obtaining the location information of the delivery staff (for example, every minute).

[0205] The acquired location information (latitude, longitude, timestamp) is sent to a server via the Internet.

[0206] 2. Server

[0207] The received location information is stored in a database and managed, including past data.

[0208] The server is equipped with an artificial intelligence module that analyzes the accumulated location information to learn the delivery staff's daily delivery routes and behavioral patterns.

[0209] 3. Database

[0210] Systematically manage location information, delivery route data, etc. stored on the server.

[0211] 4. Artificial Intelligence Module

[0212] It includes software algorithms for analyzing location data and learning the behavioral patterns of subjects.

[0213] 5. User device (administrator smartphone)

[0214] Receive alerts from the server in real time.

[0215] Processing flow

[0216] The server stores the location information acquired by the smartphone in a database and analyzes behavioral patterns using an artificial intelligence module. If an abnormality is detected, the server immediately sends an alert to the administrator's smartphone (user device).

[0217] Hardware and software used

[0218] Hardware

[0219] Smartphone: Obtains the location information of delivery staff and sends it to the server.

[0220] Server: Stores and analyzes data.

[0221] software

[0222] Python-based server application: manages, stores, and analyzes location information.

[0223] Python machine learning libraries (e.g., scikit-learn and TensorFlow): Implement programs that learn behavioral patterns and detect anomalies.

[0224] Mobile application: An app for delivery service managers to receive alerts.

[0225] Specific examples

[0226] For example, if a delivery staff member deviates significantly from their normal delivery route and begins heading out into the suburbs, the system will detect the anomaly and send an alert to the administrator stating, "A delivery staff member has deviated from the standard route. Their current location is latitude 35.5, longitude 135.8." In this way, abnormal behavior can be detected early, allowing for appropriate action to be taken promptly.

[0227] Prompt Sentence Examples

[0228] Here are some example prompts you can give to your generative AI model:

[0229] "Generate Python code for an algorithm that detects anomalous delivery staff routes, such as the following."

[0230] This prompt statement can be used to help generate specific program code.

[0231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0232] Step 1:

[0233] The terminal periodically obtains the location information of the delivery staff. Specifically, it uses the smartphone's GPS function to obtain the current latitude, longitude, and timestamp every minute. The input is GPS data, and the output is location information.

[0234] Step 2:

[0235] The device sends the acquired location information to the server. The location information is sent via the Internet in JSON format. The input is the acquired location information, and the output is the data sent to the server.

[0236] Step 3:

[0237] The server stores the received location information in a database. The location information is accumulated and managed in the database along with past data. The input is the received location information, and the output is the data stored in the database.

[0238] Step 4:

[0239] The server uses the stored location information to learn the delivery staff's daily delivery routes and behavioral patterns. Specifically, it uses Python's machine learning library to analyze time periods and delivery route patterns. The input is the location information in the database, and the output is the learned behavioral patterns.

[0240] Step 5:

[0241] The device transmits the current location information acquired in real time to the server. The input is the real-time location information, and the output is the data transmitted to the server.

[0242] Step 6:

[0243] The server compares the current location with the learned behavioral patterns. It uses an artificial intelligence module to perform pattern matching and determine if the current location matches the learned behavioral patterns. The input is the current location and the learned behavioral patterns, and the output is the anomaly detection results.

[0244] Step 7:

[0245] If the server detects an anomaly, it immediately sends an alert to the administrator's user device. The alert includes the current location information and the reason for the anomaly. The input is the anomaly detection result, and the output is the alert message sent to the administrator's smartphone.

[0246] 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.

[0247] The present invention relates to a monitoring system that collects location information of subjects (children and elderly people) and detects abnormalities, and further optimizes alerts by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention are described below.

[0248] System configuration

[0249] The system mainly consists of the following elements:

[0250] 1. A GPS device that periodically acquires location information.

[0251] 2. A device that sends the acquired location information to a server.

[0252] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[0253] 4. A function that sends an alert to the user's device when an abnormality is detected.

[0254] 5. An emotion engine that recognizes user emotions and collects responses.

[0255] Program processing

[0256] 1. Obtaining location information

[0257] The terminal periodically (for example, every minute) acquires the target person's location information from the GPS device. This location information includes latitude, longitude, and timestamp.

[0258] 2. Data transmission

[0259] The terminal transmits the acquired location information to the server.

[0260] 3. Data storage

[0261] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[0262] 4. Learning behavioral patterns

[0263] An artificial intelligence module installed on the server analyzes the accumulated location information and learns the target person's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[0264] 5. Location Comparison

[0265] The terminal obtains the current real-time location information and transmits it to the server.

[0266] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0267] 6. Anomaly Detection

[0268] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended period of time in an unplanned location.

[0269] 7. Alerts

[0270] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location, the reason for the anomaly, and recommended countermeasures (e.g., contacting the user for confirmation, heading to the site, etc.).

[0271] 8. Emotional Recognition

[0272] Upon receiving the alert, the user's device uses an emotion engine to recognize the user's emotional response, which includes extracting emotions from the user's facial expressions, voice, or text data.

[0273] 9. Collecting and analyzing emotional responses

[0274] The server collects and stores in a database the user's emotional responses to the alerts.

[0275] The emotion engine analyzes the collected emotion data and optimizes the content and notification method of the next alert.

[0276] Specific examples

[0277] Watching over children going to school

[0278] 1. The user gives their child a GPS device.

[0279] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[0280] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[0281] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[0282] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[0283] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0284] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[0285] Preventing elderly people from wandering

[0286] 1. The user gives the elderly person a GPS device.

[0287] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[0288] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[0289] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[0290] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[0291] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0292] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[0293] This system allows users to monitor the safety of children and the elderly in real time, and can respond quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances. In addition, by combining it with an emotion engine, it becomes possible to issue alerts that take into account the user's emotional reactions, which is expected to lead to more appropriate and efficient responses.

[0294] The processing flow will be explained below.

[0295] Step 1:

[0296] The user attaches a GPS device to the subject (child or elderly person).

[0297] Step 2:

[0298] The device (smartphone or tablet) registers the GPS device through the app and inputs the target person's information, including name, age, and contact details.

[0299] Step 3:

[0300] The terminal periodically (for example, every minute) acquires location information (latitude, longitude, timestamp) from the GPS device.

[0301] Step 4:

[0302] The terminal transmits the acquired location information to the server.

[0303] Step 5:

[0304] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[0305] Step 6:

[0306] The AI ​​module installed on the server periodically analyzes the location information in the database and learns the subject's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[0307] Step 7:

[0308] The terminal transmits the current location information obtained in real time to the server.

[0309] Step 8:

[0310] The server passes the received current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0311] Step 9:

[0312] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended amount of time in an unplanned location.

[0313] Step 10:

[0314] If an abnormality is detected, the server immediately sends an alert to the user's (guardian's or caregiver's) device.

[0315] Step 11:

[0316] The server includes in the alert message the current location information, the reason why the anomaly was detected, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[0317] Step 12:

[0318] When receiving an alert, the user's device recognizes the user's emotion using an emotion engine, which extracts emotions from the user's facial expressions, voice, or text data.

[0319] Step 13:

[0320] The server collects and stores in a database the user's emotional responses to the alerts.

[0321] Step 14:

[0322] The emotion engine analyzes the collected emotion data and optimizes the content and notification method of the next alert, enabling more appropriate alerts to be issued that take the user's emotions into consideration.

[0323] Specific examples

[0324] Watching over children going to school

[0325] Step 1:

[0326] The user gives the child a GPS device.

[0327] Step 2:

[0328] The device obtains the child's location information from the GPS device every minute and sends it to the server.

[0329] Step 3:

[0330] The server stores the location information in a database, and an artificial intelligence module learns the student's route to school.

[0331] Step 4:

[0332] If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[0333] Step 5:

[0334] The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[0335] Step 6:

[0336] When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0337] Step 7:

[0338] The server collects the user's emotional responses and optimizes the content of the next alert.

[0339] Preventing elderly people from wandering

[0340] Step 1:

[0341] The user provides the elderly person with a GPS device.

[0342] Step 2:

[0343] The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[0344] Step 3:

[0345] The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[0346] Step 4:

[0347] If an elderly person stays outside their usual living area for an extended period of time, the artificial intelligence module will detect this as an abnormality.

[0348] Step 5:

[0349] The server detects any abnormality and immediately sends an alert to the user's (family member's) smartphone.

[0350] Step 6:

[0351] When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0352] Step 7:

[0353] The server collects the user's emotional responses and optimizes the content of the next alert.

[0354] This system allows users to monitor the safety of children and the elderly in real time, and can respond quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances. In addition, by combining it with an emotion engine, it becomes possible to issue alerts that take into account the user's emotional reactions, which is expected to lead to more appropriate and efficient responses.

[0355] Example 2

[0356] 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."

[0357] Conventional monitoring systems have a problem in that, despite acquiring the target's location information, they do not optimize alerts to take into account the target's emotional state or the user's reaction. This can lead to false alerts and delayed appropriate responses. The present invention aims to solve these problems and improve alert accuracy and user satisfaction.

[0358] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to the user terminal when an abnormality is detected, means for collecting the user's emotional response using an emotion engine that recognizes the user's emotions, and means for analyzing the user's emotional response to the alert and optimizing the content of the next alert and the notification method. This makes it possible to issue an alert that takes into account not only the target person's location information but also the user's emotional state, thereby reducing false alarms and enabling prompt and appropriate responses.

[0359] "Location information" is data indicating the subject's current location, and includes latitude, longitude, and a timestamp.

[0360] A "server" is a computer system that aggregates, stores, and processes acquired data.

[0361] A "database" is a system for systematically storing, searching, and managing information.

[0362] The "artificial intelligence module" is software that analyzes collected data and performs pattern recognition and anomaly detection.

[0363] "Behavioral patterns" refer to specific patterns of a subject's daily travel routes and behavior.

[0364] "Abnormal" refers to a significant deviation from learned patterns of behavior, including a subject leaving their usual route or staying in an unexpected location for an extended period of time.

[0365] An "alert" is a warning message that is sent to the user when an abnormality is detected.

[0366] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0367] An "emotion engine" is software for recognizing and analyzing a user's emotional state.

[0368] "Emotional response" refers to the emotional reaction a user shows when receiving an alert, and is extracted from facial expressions, voice, and text data.

[0369] The present invention relates to a monitoring system that mainly acquires location information, detects abnormalities, issues alerts, and recognizes emotions. Specific embodiments of the present invention are described below.

[0370] System configuration

[0371] The system mainly consists of the following elements:

[0372] 1. GPS devices that periodically acquire location information

[0373] 2. The device that sends the acquired location information to the server

[0374] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[0375] 4. A function that issues an alert to the user device when an abnormality is detected

[0376] 5. Emotion engine that recognizes user emotions and collects responses

[0377] Details of each element

[0378] GPS devices and terminals

[0379] The device periodically obtains location information from the target person's GPS device. This location information includes latitude, longitude, and a timestamp. For example, the device obtains location information from the GPS device every minute on the way to school.

[0380] Servers and Databases

[0381] The server receives the location information sent from the device and stores it in a database. The database is used to accumulate and manage the location history for each subject, making it possible to analyze the subject's behavioral patterns over a long period of time.

[0382] Artificial Intelligence Module

[0383] The AI ​​module installed on the server analyzes the location information stored in the database and learns the subject's daily behavioral patterns. For example, it identifies a child's route to school or an elderly person's walking route and the time of day. This creates a foundation for determining the subject's normal behavior range and abnormal behavior.

[0384] Anomaly detection and alert generation

[0385] The device again acquires its current real-time location information and sends it to the server. The server then passes the current location information to an AI module, which compares it with the learned behavioral patterns. If the current location information significantly deviates from the learned behavioral patterns, it detects this as an anomaly. For example, this could include a child straying from their usual school route or an elderly person staying in an unplanned location for an extended period of time.

[0386] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location, the reason for the anomaly, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[0387] Emotion Engine

[0388] When receiving an alert, the user's device uses an emotion engine to recognize the user's emotional response. The emotion engine extracts emotions from the user's facial expressions, voice, or text data. For example, after receiving an alert message, the emotion engine analyzes the user's facial expressions and voice using the smartphone's camera and microphone.

[0389] Collecting and analyzing emotional responses

[0390] The server collects the user's emotional response to the alert and stores it in a database. The emotion engine analyzes the collected emotional data and optimizes the content and notification method of the next alert. For example, if the user feels anxious about the alert, the next alert notification will include more specific countermeasures.

[0391] Specific examples

[0392] Watching over children going to school

[0393] 1. The user gives their child a GPS device.

[0394] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[0395] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[0396] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[0397] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[0398] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0399] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[0400] Preventing elderly people from wandering

[0401] 1. The user gives the elderly person a GPS device.

[0402] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[0403] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[0404] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[0405] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[0406] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0407] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[0408] Examples of prompt statements

[0409] Prompt: "Please explain how parents are notified when their child deviates from their normal school route and how to recognize their emotions and optimize responses."

[0410] As a result, this system can monitor the location information of the target person in real time and respond quickly when an abnormality is detected.In addition, by combining it with an emotion engine, it is possible to issue alerts that take the user's emotional response into consideration, which is expected to lead to more appropriate and efficient responses.

[0411] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0412] Step 1: Obtaining location information

[0413] The device obtains location information every minute from the subject's GPS device, including latitude, longitude, and a timestamp.

[0414] (Input): Location data (latitude, longitude, timestamp) obtained from a GPS device

[0415] (Output): Data packet containing the obtained location information

[0416] (Specific operation): The device automatically obtains location data from the GPS device every minute and temporarily stores the data.

[0417] Step 2: Sending data

[0418] The device automatically transmits the acquired location information to the server immediately after the location information is acquired.

[0419] (Input): Location data stored on the device

[0420] (Output): Location data sent to the server

[0421] (Specific operation): The device uses Wi-Fi or mobile data communication to send a data packet containing location information to the server's fixed IP address.

[0422] Step 3: Save your data

[0423] The server stores the received location information in a database, and a location history is accumulated for each subject.

[0424] (Input): Location data received by the server

[0425] (Output): Location information stored in the database

[0426] (Specific operation): The server analyzes the received location data and adds new location information to the corresponding subject's database entry.

[0427] Step 4: Learning behavioral patterns

[0428] An artificial intelligence module installed on the server analyzes the accumulated location information, learns the target person's daily behavior patterns, and generates a predictive model.

[0429] (Input): Past location data stored in the database

[0430] (Output): Learned behavioral pattern model

[0431] (Specific operation): The AI ​​module applies machine learning algorithms to analyze past behavioral data to identify the subject's daily route and time of day, and update the behavioral pattern model.

[0432] Step 5: Compare locations

[0433] The terminal again acquires the current real-time location information and transmits it to the server.

[0434] The server compares the current location information with the learned behavioral patterns.

[0435] (Input): Real-time location data, learned behavioral pattern model

[0436] (Output): The result of determining whether the location information is normal or abnormal

[0437] (Specific operation): The device sends newly acquired real-time location information to the server, which then passes this data to the AI ​​module and compares it with the learned model.

[0438] Step 6: Detect anomalies

[0439] The artificial intelligence module detects an anomaly if the current location information deviates from the learned behavioral patterns.

[0440] (Input): Current location information, learned behavior patterns

[0441] (Output): Anomaly detection flag

[0442] (Specific operation): The AI ​​module evaluates whether the current location information deviates from the learned pattern by more than a certain threshold, and sets an anomaly detection flag if an anomaly is detected.

[0443] Step 7: Triggering an alert

[0444] When an anomaly is detected, the server immediately sends an alert to the user's device, which includes the user's current location, the reason for the anomaly, and recommended countermeasures.

[0445] (Input): Anomaly detection flag, current location information

[0446] (Output): Alert notification to user device

[0447] (Specific operation): When an abnormality is detected, the server generates an alert message and sends it to the user's smartphone as a push notification. The alert message contains specific content such as "Your child has deviated from their normal route. Please contact us to check or go to the location."

[0448] Step 8: Recognize emotions

[0449] When the user's device receives an alert, it activates an emotion engine and recognizes emotions from the user's facial expressions and voice.

[0450] (Input): Alert message, user's real-time facial expression and voice data

[0451] (Output): Recognized user emotion data

[0452] (Specific operation): After receiving an alert, the smartphone's camera and microphone are used to collect the user's facial expressions and voice, which are then analyzed by the emotion engine to recognize the user's emotional state.

[0453] Step 9: Collect and analyze emotional responses

[0454] The server collects the user's emotional response to the alert and stores it in a database. The emotion engine uses this information to optimize the content and notification method of the next alert.

[0455] (Input): Recognized user emotion data

[0456] (Output): Optimized alert content and notification method

[0457] (Specific operation): The server receives data from the emotion engine and stores it in a database. For subsequent alerts, the content and method of notifications (for example, more detailed instructions or reassuring messages) are optimized to take into account the user's emotional response.

[0458] (Application example 2)

[0459] 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."

[0460] While conventional monitoring systems are capable of acquiring location information of the target and detecting abnormalities, they have problems optimizing alerts to take appropriate action when an abnormality occurs. In particular, notifications are sent uniformly without considering the emotional state of the alert recipient, which can cause excessive stress to the recipient. In addition, false positives can cause anxiety due to meaningless alerts. The present invention aims to solve these problems and provide a more appropriate and efficient monitoring system.

[0461] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0462] In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, means for installing an emotion recognition engine in the user terminal to recognize the user's emotion when an alert is received, and means for collecting the user's emotional reactions and optimizing the alert content and notification method. This makes it possible to issue an alert that reflects the user's emotional state when an abnormality occurs, reducing the burden on the recipient and enabling a quick and appropriate response.

[0463] "Means for periodically obtaining location information" refers to means for obtaining location information such as GPS from equipment or devices carried by the subject at regular intervals.

[0464] The "means for transmitting the acquired location information to a server" refers to a means for transmitting the target person's location information to a server via the Internet or a communication network.

[0465] "Means for the server to store location information in a database" refers to a means for storing received location information on the server for a long period of time, making it possible to refer to and analyze it later.

[0466] "Means for an artificial intelligence module installed on a server to analyze location information and learn the target person's daily behavioral patterns" refers to a means for analyzing received location information and using a machine learning algorithm to extract and learn the target person's usual behavioral patterns.

[0467] "Means for detecting abnormalities by comparing current location information with learned behavioral patterns" refers to means for comparing location information acquired in real time with already learned behavioral patterns, and determining that an abnormality exists if there is any deviation.

[0468] The "means for issuing an alert to a user terminal when an abnormality is detected" refers to a means for sending a notification or warning to a device held by a user when an abnormality is detected.

[0469] "Means of equipping a user device with an emotion recognition engine and recognizing the user's emotion when an alert is received" refers to a means of equipping a user device with an engine that recognizes and analyzes the user's emotional state when an alert is notified.

[0470] "Means for collecting users' emotional responses and optimizing alert content and notification methods" refers to means for collecting and analyzing users' emotional data and adjusting the alert content and notification methods from the next time onwards based on the results.

[0471] The system of the present invention collects and analyzes the location information of a target person, and optimizes alerts by taking into account the user's emotions when an abnormality is detected. This system is composed of the following internal components and their respective functions.

[0472] System configuration

[0473] 1. Periodic acquisition of location information

[0474] The equipment or device carried by the subject uses GPS to acquire location information at regular intervals (e.g., every minute), which includes latitude, longitude, and a timestamp.

[0475] 2. Sending location information to the server

[0476] The acquired location information is sent to a server via a network. The Internet is used for communication, and encryption technology (e.g., SSL / TLS) is preferably used as needed.

[0477] 3. Saving to the database

[0478] The server stores the received location information in a database, which manages data in chronological order and also keeps a history of past events.

[0479] 4. Learning behavioral patterns using an artificial intelligence module

[0480] The server's installed artificial intelligence module analyzes the accumulated location data and learns the subject's normal daily behavior patterns. For example, a machine learning model can be built using TensorFlow or Keras.

[0481] 5. Anomaly Detection

[0482] The system compares location information acquired in real time with learned behavioral patterns and detects any deviations as an anomaly. This makes it possible to immediately detect deviations, such as when a person deviates from their usual school route.

[0483] 6. Alerts

[0484] When an anomaly is detected, the server immediately sends an alert to the user's device, which includes the current location, the reason for the anomaly, and a recommended course of action (e.g., contacting the user for confirmation, visiting the site, etc.).

[0485] 7. Emotion Recognition Engine

[0486] When an alert is issued, the user device uses an emotion recognition engine to analyze the user's emotional response, using facial expression recognition (e.g., OpenCV, DeepFace) and voice recognition (e.g., Google Cloud Speech-to-Text) technologies.

[0487] 8. Collecting and optimizing emotional responses

[0488] The recognized emotion data is sent to the server and stored in a database, and the content and notification method for future alerts are optimized based on this data.

[0489] Specific hardware and software names to be used

[0490] Hardware: GPS devices, smartphones or mobile communication devices, servers

[0491] Software: TensorFlow, Keras, OpenCV, DeepFace, Google Cloud Speech-to-Text, Flask or FastAPI, SSL / TLS encryption technology

[0492] Examples of concrete examples and prompts

[0493] Specific examples

[0494] If an elderly person stays outside their usual living area for an extended period of time, the system detects this as an abnormality and immediately sends an alert to the family member's smartphone. The alert includes the family member's current location and details of the abnormality. When the user checks the alert, the smartphone's camera is used to capture facial expressions and analyze them with an emotion recognition engine. The recognized emotion data is sent to a server and used to optimize the content of future notifications.

[0495] Prompt Sentence Examples

[0496] "My father has been in an unusual location for an extended period of time. Please suggest ways to check on him."

[0497] This embodiment of the present invention not only ensures the safety of the subject in real time, but also enables appropriate responses that take into account the user's emotions.

[0498] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0499] Step 1:

[0500] The terminal uses a GPS device to obtain the subject's latitude, longitude, and timestamp. The input is raw data from the GPS device, and the output is analyzed location information. Specifically, the terminal queries the GPS device for location information every minute and obtains the data.

[0501] Step 2:

[0502] The device sends the acquired location information to the server. The input is the location information acquired in step 1, and the output is data transfer to the server. Specifically, the device uses an HTTP POST request to send the location information to the server in JSON format.

[0503] Step 3:

[0504] The server stores the received location information in a database. The input is the location information sent from the device, and the output is storage in the database. Specifically, it formats the location data appropriately and executes an INSERT statement into a database such as MySQL or PostgreSQL.

[0505] Step 4:

[0506] The artificial intelligence module installed on the server analyzes the accumulated location information and learns the subject's normal daily behavior patterns. The input is past location information data, and the output is a learned behavior pattern model. Specifically, it uses TensorFlow and Keras to train a machine learning model based on the location information data.

[0507] Step 5:

[0508] The server compares location information acquired in real time with learned behavioral patterns to detect anomalies. The input is real-time location information and the learned model, and the output is the presence or absence of anomalies. Specifically, newly acquired location information is input into the learned model and classified as normal or abnormal.

[0509] Step 6:

[0510] If the server detects an anomaly, it immediately sends an alert to the user device. The input is the fact that an anomaly has been detected and detailed information about it, and the output is an alert notification to the user device. Specifically, the server uses an HTTP POST request to send the alert information to the user device.

[0511] Step 7:

[0512] The user device uses an emotion recognition engine to recognize the user's emotions when receiving an alert. The input is the user's facial expression or voice data, and the output is the recognized emotion data. Specifically, OpenCV and DeepFace are used to analyze the facial expression data obtained from the camera.

[0513] Step 8:

[0514] The user device sends the recognized emotion data to the server. The input is the emotion data obtained from the emotion recognition engine, and the output is the data transfer to the server. Specifically, the emotion data is sent to the server in JSON format using an HTTP POST request.

[0515] Step 9:

[0516] The server stores the collected emotion data in a database and optimizes the alert content and notification method. The input is the emotion data sent from the user's device, and the output is the optimization of the alert content from the next time onwards. Specifically, the server accumulates emotion data and uses this data to adaptively change the notification method when the next alert is generated.

[0517] 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.

[0518] 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.

[0519] 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.

[0520] [Second embodiment]

[0521] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0522] 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.

[0523] 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).

[0524] 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.

[0525] 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.

[0526] 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).

[0527] 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.

[0528] 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.

[0529] 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.

[0530] 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.

[0531] 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.

[0532] 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."

[0533] The present invention relates to a monitoring system that acquires location information of a target person, detects an abnormality, and issues an alert. Hereinafter, specific embodiments of the present invention will be described.

[0534] System configuration

[0535] The system mainly consists of the following elements:

[0536] 1. A GPS device that periodically acquires location information.

[0537] 2. A device that sends the acquired location information to a server.

[0538] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[0539] 4. A function that sends an alert to the user's device when an abnormality is detected.

[0540] Program processing

[0541] 1. Obtaining location information

[0542] The terminal periodically (for example, every minute) acquires the target person's location information from the GPS device. This location information includes latitude, longitude, and timestamp.

[0543] 2. Data transmission

[0544] The terminal transmits the acquired location information to the server.

[0545] 3. Data storage

[0546] The server stores the received location information in a database, accumulating and managing past location information as well.

[0547] 4. Learning behavioral patterns

[0548] An artificial intelligence module installed on the server analyzes the accumulated location information and learns the target person's daily behavioral patterns, for example, identifying a child's route to school or an elderly person's walking route and time of day.

[0549] 5. Location Comparison

[0550] The terminal obtains the current real-time location information and transmits it to the server.

[0551] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0552] 6. Anomaly Detection

[0553] The AI ​​module detects any deviations from the current location from normal behavioral patterns, such as straying from a specific route or staying in an unspecified area for an extended period of time.

[0554] 7. Alerts

[0555] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location and the reason for the anomaly.

[0556] Specific examples

[0557] Watching over children going to school

[0558] 1. The user gives their child a GPS device.

[0559] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[0560] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[0561] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[0562] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[0563] 6. The user receives an alert and immediately checks on the safety of the child.

[0564] Preventing elderly people from wandering

[0565] 1. The user gives the elderly person a GPS device.

[0566] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[0567] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[0568] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[0569] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[0570] 6. The user receives an alert, checks the elderly person's condition, and takes action.

[0571] This system allows users to monitor the safety of children and the elderly in real time, and responds quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances.

[0572] The processing flow will be explained below.

[0573] Step 1:

[0574] The user attaches a GPS device to the subject (child or elderly person).

[0575] Step 2:

[0576] The device (smartphone or tablet) registers the GPS device through the app and enters the target person's information (name, age, contact details, etc.).

[0577] Step 3:

[0578] The terminal periodically (for example, every minute) acquires location information (latitude, longitude, timestamp) from the GPS device.

[0579] Step 4:

[0580] The terminal transmits the acquired location information to the server in real time.

[0581] Step 5:

[0582] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[0583] Step 6:

[0584] The AI ​​module installed on the server periodically analyzes the location information in the database and learns the subject's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[0585] Step 7:

[0586] The terminal transmits the current location information obtained in real time to the server.

[0587] Step 8:

[0588] The server passes the received current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0589] Step 9:

[0590] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended period of time in an unplanned location.

[0591] Step 10:

[0592] If an abnormality is detected, the server immediately sends an alert to the user's (guardian's or caregiver's) device.

[0593] Step 11:

[0594] The server includes in the alert message the current location information, the reason why the anomaly was detected, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[0595] Step 12:

[0596] The user checks the alert notification displayed on the device and takes appropriate action, such as contacting the child to check on their safety or heading to the scene.

[0597] Example 1

[0598] 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."

[0599] Conventional monitoring systems not only acquire the target's location information and transmit it to a server, but also analyze that location information, learn the target's daily behavioral patterns, and detect abnormalities. However, existing systems have difficulty detecting abnormalities in real time, and it takes a long time to issue an appropriate alert in an emergency. Furthermore, security during data transmission is insufficient, creating a risk of location information leaks. The present invention aims to solve these problems by providing a system that detects abnormalities more accurately and quickly, ensuring user safety.

[0600] 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.

[0601] In this invention, the server includes means for periodically acquiring location information of a target person, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and perform machine learning on the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, means for encrypting and transmitting the target person's location information, and means for sending an alert to the user terminal using push notification or SMS in an emergency. This enables highly accurate abnormality detection in real time, prompt alert issuance, and safe data transmission.

[0602] "Location information" is data about a subject's current location, including latitude, longitude, and timestamp.

[0603] "Means of acquisition" refers to the means of periodically collecting the subject's location information using a GPS device or terminal.

[0604] A "server" is a remote computer system that receives, stores, processes, etc. data.

[0605] The "transmitting means" is a means for sending data from the terminal to the server.

[0606] A "database" is a data management system that stores location information and allows it to be searched and updated as needed.

[0607] The "artificial intelligence module" is a software module that analyzes location information and learns daily behavior patterns.

[0608] "Machine learning" refers to algorithms and techniques that automatically learn patterns and trends based on large amounts of data.

[0609] The "means for detecting anomalies" is a means for determining whether the current location information deviates from the normal behavioral pattern.

[0610] The "means for issuing an alert" is a means for sending a notification to a user terminal when an abnormality is detected.

[0611] "Means for encryption and transmission" refers to means for encrypting data to protect location information from third parties and transmitting it securely to a server.

[0612] "Push notification" is a method for sending messages from a server to a user terminal in real time.

[0613] "SMS" stands for Short Message Service, a means of sending short text messages via mobile phones.

[0614] The present invention relates to a monitoring system that acquires location information of a target person, detects an abnormality, and issues an alert. A specific embodiment of this system will be described below.

[0615] Hardware and Software Configuration

[0616] Terminal

[0617] The device communicates with the subject's GPS device to obtain location information. The device periodically obtains latitude, longitude, and timestamps from the GPS device using Bluetooth or Wi-Fi connections. HTTPS is used to encrypt the obtained location information and send it securely to the server.

[0618] server

[0619] The server is a device that stores the received location information in a database and analyzes it using an artificial intelligence module. The server uses a relational database such as MySQL or PostgreSQL, and indexes the location information to enable efficient searches. The server is equipped with an artificial intelligence module using Python's Scikit-learn and TensorFlow, which uses machine learning to learn daily behavior patterns based on the accumulated location information.

[0620] Specific actions

[0621] 1. Acquisition and transmission of location information

[0622] The terminal communicates with a GPS device and periodically acquires location information (latitude, longitude, timestamp).

[0623] The device encrypts the acquired location information and sends it to the server using HTTPS.

[0624] 2. Location information storage and analysis

[0625] The server stores the received location information in a database.

[0626] The server's artificial intelligence module analyzes the accumulated location information and learns the subject's daily behavioral patterns, for example, by using K-Means clustering to identify the person's commute route, walking route, and time of day.

[0627] 3. Detecting anomalies and issuing alerts

[0628] The terminal again acquires the current real-time location information and transmits it to the server.

[0629] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0630] The artificial intelligence module detects any deviations in current location information from normal behavioral patterns as an anomaly.

[0631] When an anomaly is detected, the server immediately sends an alert to the user's device via push notification or SMS, and the notification includes the user's current location and the reason why the anomaly was detected.

[0632] Specific examples

[0633] Watching over children going to school

[0634] 1. The user gives their child a GPS device.

[0635] 2. The device will receive the child's location information from the GPS device via Bluetooth every minute. The location information includes latitude, longitude, and a timestamp.

[0636] 3. The device sends the encrypted location information to the server via HTTPS.

[0637] 4. The server stores the location information in a database, and the artificial intelligence module uses the data to learn the school route using K-Means clustering.

[0638] 5. If a child deviates from their usual route to school in real time, the artificial intelligence module will detect this as an anomaly.

[0639] 6. The server immediately sends a push notification to the user's smartphone, alerting them to the location. The notification includes information such as, "Your child has deviated from their normal route. Their current location is latitude x, longitude y."

[0640] Preventing elderly people from wandering

[0641] 1. The user gives the elderly person a GPS device.

[0642] 2. The device receives the elderly person's location information from the GPS device via Bluetooth every minute. The location information includes latitude, longitude, and timestamp.

[0643] 3. The device sends the encrypted location information to the server via HTTPS.

[0644] 4. The server stores the location information in a database, and the artificial intelligence module learns daily behavior patterns using K-Means clustering.

[0645] 5. If an elderly person is out and about and stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[0646] 6. The server immediately sends an alert to the user's smartphone via push notification or SMS. The notification contains information such as, "An elderly person has been outside their usual living area for an extended period of time. Their current location is latitude x, longitude y."

[0647] Example prompts for generative AI models

[0648] Prompt statement:

[0649] Describe a system that sends an alert if a child deviates from their usual route to school. This system uses a GPS device, a server, an artificial intelligence module, etc.

[0650] Prompt statement:

[0651] Describe a system that alerts elderly people if they are outside their usual living area for an extended period of time. The system uses GPS devices, a server, and an artificial intelligence module.

[0652] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0653] Step 1:

[0654] Obtaining location information

[0655] The terminal communicates with the subject's GPS device and periodically (e.g., every minute) obtains location information. The input is the latitude, longitude, and timestamp from the GPS device, and the output is the obtained location information. Specifically, the terminal reads information from the device via Bluetooth or Wi-Fi connection.

[0656] Step 2:

[0657] Location encryption

[0658] The device encrypts the acquired location information. The input is the location information acquired in step 1, and the output is the encrypted location information. Specifically, the data is secured using encryption algorithms such as AES or RSA.

[0659] Step 3:

[0660] Sending location information

[0661] The device sends encrypted location information to the server using HTTPS. The input is the encrypted location information, and the output is a notification to the server that the location information has been sent. Specifically, the data is sent to a RESTful API endpoint using a POST request.

[0662] Step 4:

[0663] Save location information

[0664] The server stores the received location information in a database. The input is the location information sent from the device, and the output is a notification that the information has been saved to the database. Specifically, the server uses an INSERT statement to store the location information in the database.

[0665] Step 5:

[0666] Learning behavioral patterns

[0667] The artificial intelligence module installed on the server analyzes the accumulated location information and performs machine learning to learn daily behavior patterns. The input is past location information obtained from a database, and the output is the learned behavior pattern. Specifically, it applies machine learning algorithms such as K-Means clustering.

[0668] Step 6:

[0669] Acquiring and sending real-time location information

[0670] The device again acquires the latest real-time location information and sends it to the server. The input is the current location information from the GPS device, and the output is a notification to the server that transmission has been completed. Specifically, the device again collects location information from the GPS device via Bluetooth or Wi-Fi, encrypts it, and sends it to the server.

[0671] Step 7:

[0672] Real-time location analysis

[0673] The server receives real-time location information and passes it on to an artificial intelligence module for analysis. The input is real-time location information, and the output is the analysis results. Specifically, it compares learned behavioral patterns with real-time location information to detect anomalies.

[0674] Step 8:

[0675] Anomaly detection

[0676] The AI ​​module detects anomalies by identifying deviations from normal behavioral patterns in real-time location information. The input is real-time location information and learned patterns, and the output is the anomaly detection result. Specific operations include using support vector machines (SVM) and other anomaly detection algorithms.

[0677] Step 9:

[0678] Alert issuance

[0679] If an anomaly is detected, the server immediately sends an alert to the user device. The input is the anomaly detection result, and the output is an alert notification to the user device. Specifically, the server sends a push notification or SMS using Firebase Cloud Messaging (FCM) or Twilio.

[0680] Through the technology and specific actions used at each step, the system can monitor the safety of the subject in real time, allowing for quick response in emergencies and greatly reducing the risk of accidents or disappearances.

[0681] (Application example 1)

[0682] 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."

[0683] In the food delivery industry, the safety of delivery staff and efficient operation management are important issues. Conventional methods lack a system that can track delivery staff's location information in real time and immediately detect deviations from the planned route or abnormal behavior. As a result, it is difficult to respond quickly to delays or problems. This can lead to a decline in service quality and a decrease in customer satisfaction.

[0684] 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.

[0685] In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the behavioral patterns of the target person (daily behavior patterns), means for comparing the current location information with the learned behavioral patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, and means for tracking the location information of delivery staff, detecting abnormalities, and notifying an administrator in real time for delivery services. This makes it possible to track the location information of delivery staff in real time in the food delivery industry, quickly detect delays and route deviations, and immediately take appropriate measures.

[0686] "Location information" is data indicating the subject's current location, such as latitude, longitude, and timestamp.

[0687] "Server" means a computing device for receiving, storing, and analyzing location information.

[0688] A "database" is a system that systematically stores and manages acquired location information and related data.

[0689] The "artificial intelligence module" is a group of programs and algorithms that analyze location information and learn the subject's daily behavioral patterns.

[0690] A "user terminal" is a communication device such as a smartphone or dedicated device for receiving alerts.

[0691] A "delivery service" is a business service that delivers meals or goods to a specified location.

[0692] "Delivery staff" refers to personnel whose job is to transport goods and food to provide delivery services.

[0693] "Administrator" refers to the person responsible for supervising and managing delivery staff and the overall system in the delivery service.

[0694] "Real-time tracking" refers to monitoring the location of delivery staff in real time with almost no delay.

[0695] An "alert" is a warning notification sent to a user terminal when an abnormality is detected.

[0696] The present invention relates to a system for tracking the location information of delivery staff in the food delivery industry in real time, detecting abnormalities, and notifying an administrator of an alert. Specific embodiments of the present invention will be described below.

[0697] System Configuration

[0698] The system consists of the following elements:

[0699] 1. Terminal

[0700] The smartphone functions as a GPS device, periodically obtaining the location information of the delivery staff (for example, every minute).

[0701] The acquired location information (latitude, longitude, timestamp) is sent to a server via the Internet.

[0702] 2. Server

[0703] The received location information is stored in a database and managed, including past data.

[0704] The server is equipped with an artificial intelligence module that analyzes the accumulated location information to learn the delivery staff's daily delivery routes and behavioral patterns.

[0705] 3. Database

[0706] Systematically manage location information, delivery route data, etc. stored on the server.

[0707] 4. Artificial Intelligence Module

[0708] It includes software algorithms for analyzing location data and learning the behavioral patterns of subjects.

[0709] 5. User device (administrator smartphone)

[0710] Receive alerts from the server in real time.

[0711] Processing flow

[0712] The server stores the location information acquired by the smartphone in a database and analyzes behavioral patterns using an artificial intelligence module. If an abnormality is detected, the server immediately sends an alert to the administrator's smartphone (user device).

[0713] Hardware and software used

[0714] Hardware

[0715] Smartphone: Obtains the location information of delivery staff and sends it to the server.

[0716] Server: Stores and analyzes data.

[0717] software

[0718] Python-based server application: manages, stores, and analyzes location information.

[0719] Python machine learning libraries (e.g., scikit-learn and TensorFlow): Implement programs that learn behavioral patterns and detect anomalies.

[0720] Mobile application: An app for delivery service managers to receive alerts.

[0721] Specific examples

[0722] For example, if a delivery staff member deviates significantly from their normal delivery route and begins heading out into the suburbs, the system will detect the anomaly and send an alert to the administrator stating, "A delivery staff member has deviated from the standard route. Their current location is latitude 35.5, longitude 135.8." In this way, abnormal behavior can be detected early, allowing for appropriate action to be taken promptly.

[0723] Prompt Sentence Examples

[0724] Here are some example prompts you can give to your generative AI model:

[0725] "Generate Python code for an algorithm that detects anomalous delivery staff routes, such as the following."

[0726] This prompt statement can be used to help generate specific program code.

[0727] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0728] Step 1:

[0729] The terminal periodically obtains the location information of the delivery staff. Specifically, it uses the smartphone's GPS function to obtain the current latitude, longitude, and timestamp every minute. The input is GPS data, and the output is location information.

[0730] Step 2:

[0731] The device sends the acquired location information to the server. The location information is sent via the Internet in JSON format. The input is the acquired location information, and the output is the data sent to the server.

[0732] Step 3:

[0733] The server stores the received location information in a database. The location information is accumulated and managed in the database along with past data. The input is the received location information, and the output is the data stored in the database.

[0734] Step 4:

[0735] The server uses the stored location information to learn the delivery staff's daily delivery routes and behavioral patterns. Specifically, it uses Python's machine learning library to analyze time periods and delivery route patterns. The input is the location information in the database, and the output is the learned behavioral patterns.

[0736] Step 5:

[0737] The device transmits the current location information acquired in real time to the server. The input is the real-time location information, and the output is the data transmitted to the server.

[0738] Step 6:

[0739] The server compares the current location with the learned behavioral patterns. It uses an artificial intelligence module to perform pattern matching and determine if the current location matches the learned behavioral patterns. The input is the current location and the learned behavioral patterns, and the output is the anomaly detection results.

[0740] Step 7:

[0741] If the server detects an anomaly, it immediately sends an alert to the administrator's user device. The alert includes the current location information and the reason for the anomaly. The input is the anomaly detection result, and the output is the alert message sent to the administrator's smartphone.

[0742] 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.

[0743] The present invention relates to a monitoring system that collects location information of subjects (children and elderly people) and detects abnormalities, and further optimizes alerts by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention are described below.

[0744] System configuration

[0745] The system mainly consists of the following elements:

[0746] 1. A GPS device that periodically acquires location information.

[0747] 2. A device that sends the acquired location information to a server.

[0748] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[0749] 4. A function that sends an alert to the user's device when an abnormality is detected.

[0750] 5. An emotion engine that recognizes user emotions and collects responses.

[0751] Program processing

[0752] 1. Obtaining location information

[0753] The terminal periodically (for example, every minute) acquires the target person's location information from the GPS device. This location information includes latitude, longitude, and timestamp.

[0754] 2. Data transmission

[0755] The terminal transmits the acquired location information to the server.

[0756] 3. Data storage

[0757] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[0758] 4. Learning behavioral patterns

[0759] An artificial intelligence module installed on the server analyzes the accumulated location information and learns the target person's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[0760] 5. Location Comparison

[0761] The terminal obtains the current real-time location information and transmits it to the server.

[0762] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0763] 6. Anomaly Detection

[0764] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended period of time in an unplanned location.

[0765] 7. Alerts

[0766] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location, the reason for the anomaly, and recommended countermeasures (e.g., contacting the user for confirmation, heading to the site, etc.).

[0767] 8. Emotional Recognition

[0768] Upon receiving the alert, the user's device uses an emotion engine to recognize the user's emotional response, which includes extracting emotions from the user's facial expressions, voice, or text data.

[0769] 9. Collecting and analyzing emotional responses

[0770] The server collects and stores in a database the user's emotional responses to the alerts.

[0771] The emotion engine analyzes the collected emotion data and optimizes the content and notification method of the next alert.

[0772] Specific examples

[0773] Watching over children going to school

[0774] 1. The user gives their child a GPS device.

[0775] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[0776] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[0777] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[0778] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[0779] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0780] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[0781] Preventing elderly people from wandering

[0782] 1. The user gives the elderly person a GPS device.

[0783] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[0784] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[0785] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[0786] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[0787] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0788] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[0789] This system allows users to monitor the safety of children and the elderly in real time, and can respond quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances. In addition, by combining it with an emotion engine, it becomes possible to issue alerts that take into account the user's emotional reactions, which is expected to lead to more appropriate and efficient responses.

[0790] The processing flow will be explained below.

[0791] Step 1:

[0792] The user attaches a GPS device to the subject (child or elderly person).

[0793] Step 2:

[0794] The device (smartphone or tablet) registers the GPS device through the app and inputs the target person's information, including name, age, and contact details.

[0795] Step 3:

[0796] The terminal periodically (for example, every minute) acquires location information (latitude, longitude, timestamp) from the GPS device.

[0797] Step 4:

[0798] The terminal transmits the acquired location information to the server.

[0799] Step 5:

[0800] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[0801] Step 6:

[0802] The AI ​​module installed on the server periodically analyzes the location information in the database and learns the subject's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[0803] Step 7:

[0804] The terminal transmits the current location information obtained in real time to the server.

[0805] Step 8:

[0806] The server passes the received current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[0807] Step 9:

[0808] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended amount of time in an unplanned location.

[0809] Step 10:

[0810] If an abnormality is detected, the server immediately sends an alert to the user's (guardian's or caregiver's) device.

[0811] Step 11:

[0812] The server includes in the alert message the current location information, the reason why the anomaly was detected, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[0813] Step 12:

[0814] When receiving an alert, the user's device recognizes the user's emotion using an emotion engine, which extracts emotions from the user's facial expressions, voice, or text data.

[0815] Step 13:

[0816] The server collects and stores in a database the user's emotional responses to the alerts.

[0817] Step 14:

[0818] The emotion engine analyzes the collected emotion data and optimizes the content and notification method of the next alert, enabling more appropriate alerts to be issued that take the user's emotions into consideration.

[0819] Specific examples

[0820] Watching over children going to school

[0821] Step 1:

[0822] The user gives the child a GPS device.

[0823] Step 2:

[0824] The device obtains the child's location information from the GPS device every minute and sends it to the server.

[0825] Step 3:

[0826] The server stores the location information in a database, and an artificial intelligence module learns the student's route to school.

[0827] Step 4:

[0828] If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[0829] Step 5:

[0830] The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[0831] Step 6:

[0832] When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0833] Step 7:

[0834] The server collects the user's emotional responses and optimizes the content of the next alert.

[0835] Preventing elderly people from wandering

[0836] Step 1:

[0837] The user provides the elderly person with a GPS device.

[0838] Step 2:

[0839] The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[0840] Step 3:

[0841] The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[0842] Step 4:

[0843] If an elderly person stays outside their usual living area for an extended period of time, the artificial intelligence module will detect this as an abnormality.

[0844] Step 5:

[0845] The server detects any abnormality and immediately sends an alert to the user's (family member's) smartphone.

[0846] Step 6:

[0847] When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0848] Step 7:

[0849] The server collects the user's emotional responses and optimizes the content of the next alert.

[0850] This system allows users to monitor the safety of children and the elderly in real time, and can respond quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances. In addition, by combining it with an emotion engine, it becomes possible to issue alerts that take into account the user's emotional reactions, which is expected to lead to more appropriate and efficient responses.

[0851] Example 2

[0852] 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."

[0853] Conventional monitoring systems have a problem in that, despite acquiring the target's location information, they do not optimize alerts to take into account the target's emotional state or the user's reaction. This can lead to false alerts and delayed appropriate responses. The present invention aims to solve these problems and improve alert accuracy and user satisfaction.

[0854] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to the user terminal when an abnormality is detected, means for collecting the user's emotional response using an emotion engine that recognizes the user's emotions, and means for analyzing the user's emotional response to the alert and optimizing the content of the next alert and the notification method. This makes it possible to issue an alert that takes into account not only the target person's location information but also the user's emotional state, thereby reducing false alarms and enabling prompt and appropriate responses.

[0855] "Location information" is data indicating the subject's current location, and includes latitude, longitude, and a timestamp.

[0856] A "server" is a computer system that aggregates, stores, and processes acquired data.

[0857] A "database" is a system for systematically storing, searching, and managing information.

[0858] The "artificial intelligence module" is software that analyzes collected data and performs pattern recognition and anomaly detection.

[0859] "Behavioral patterns" refer to specific patterns of a subject's daily travel routes and behavior.

[0860] "Abnormal" refers to a significant deviation from learned patterns of behavior, including a subject leaving their usual route or staying in an unexpected location for an extended period of time.

[0861] An "alert" is a warning message that is sent to the user when an abnormality is detected.

[0862] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0863] An "emotion engine" is software for recognizing and analyzing a user's emotional state.

[0864] "Emotional response" refers to the emotional reaction a user shows when receiving an alert, and is extracted from facial expressions, voice, and text data.

[0865] The present invention relates to a monitoring system that mainly acquires location information, detects abnormalities, issues alerts, and recognizes emotions. Specific embodiments of the present invention are described below.

[0866] System configuration

[0867] The system mainly consists of the following elements:

[0868] 1. GPS devices that periodically acquire location information

[0869] 2. The device that sends the acquired location information to the server

[0870] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[0871] 4. A function that issues an alert to the user device when an abnormality is detected

[0872] 5. Emotion engine that recognizes user emotions and collects responses

[0873] Details of each element

[0874] GPS devices and terminals

[0875] The device periodically obtains location information from the target person's GPS device. This location information includes latitude, longitude, and a timestamp. For example, the device obtains location information from the GPS device every minute on the way to school.

[0876] Servers and Databases

[0877] The server receives the location information sent from the device and stores it in a database. The database is used to accumulate and manage the location history for each subject, making it possible to analyze the subject's behavioral patterns over a long period of time.

[0878] Artificial Intelligence Module

[0879] The AI ​​module installed on the server analyzes the location information stored in the database and learns the subject's daily behavioral patterns. For example, it identifies a child's route to school or an elderly person's walking route and the time of day. This creates a foundation for determining the subject's normal behavior range and abnormal behavior.

[0880] Anomaly detection and alert generation

[0881] The device again acquires its current real-time location information and sends it to the server. The server then passes the current location information to an AI module, which compares it with the learned behavioral patterns. If the current location information significantly deviates from the learned behavioral patterns, it detects this as an anomaly. For example, this could include a child straying from their usual school route or an elderly person staying in an unplanned location for an extended period of time.

[0882] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location, the reason for the anomaly, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[0883] Emotion Engine

[0884] When receiving an alert, the user's device uses an emotion engine to recognize the user's emotional response. The emotion engine extracts emotions from the user's facial expressions, voice, or text data. For example, after receiving an alert message, the emotion engine analyzes the user's facial expressions and voice using the smartphone's camera and microphone.

[0885] Collecting and analyzing emotional responses

[0886] The server collects the user's emotional response to the alert and stores it in a database. The emotion engine analyzes the collected emotional data and optimizes the content and notification method of the next alert. For example, if the user feels anxious about the alert, the next alert notification will include more specific countermeasures.

[0887] Specific examples

[0888] Watching over children going to school

[0889] 1. The user gives their child a GPS device.

[0890] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[0891] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[0892] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[0893] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[0894] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0895] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[0896] Preventing elderly people from wandering

[0897] 1. The user gives the elderly person a GPS device.

[0898] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[0899] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[0900] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[0901] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[0902] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[0903] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[0904] Examples of prompt statements

[0905] Prompt: "Please explain how parents are notified when their child deviates from their normal school route and how to recognize their emotions and optimize responses."

[0906] As a result, this system can monitor the location information of the target person in real time and respond quickly when an abnormality is detected.In addition, by combining it with an emotion engine, it is possible to issue alerts that take the user's emotional response into consideration, which is expected to lead to more appropriate and efficient responses.

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

[0908] Step 1: Obtaining location information

[0909] The device obtains location information every minute from the subject's GPS device, including latitude, longitude, and a timestamp.

[0910] (Input): Location data (latitude, longitude, timestamp) obtained from a GPS device

[0911] (Output): Data packet containing the obtained location information

[0912] (Specific operation): The device automatically obtains location data from the GPS device every minute and temporarily stores the data.

[0913] Step 2: Sending data

[0914] The device automatically transmits the acquired location information to the server immediately after the location information is acquired.

[0915] (Input): Location data stored on the device

[0916] (Output): Location data sent to the server

[0917] (Specific operation): The device uses Wi-Fi or mobile data communication to send a data packet containing location information to the server's fixed IP address.

[0918] Step 3: Save your data

[0919] The server stores the received location information in a database, and a location history is accumulated for each subject.

[0920] (Input): Location data received by the server

[0921] (Output): Location information stored in the database

[0922] (Specific operation): The server analyzes the received location data and adds new location information to the corresponding subject's database entry.

[0923] Step 4: Learning behavioral patterns

[0924] An artificial intelligence module installed on the server analyzes the accumulated location information, learns the target person's daily behavior patterns, and generates a predictive model.

[0925] (Input): Past location data stored in the database

[0926] (Output): Learned behavioral pattern model

[0927] (Specific operation): The AI ​​module applies machine learning algorithms to analyze past behavioral data to identify the subject's daily route and time of day, and update the behavioral pattern model.

[0928] Step 5: Compare locations

[0929] The terminal again acquires the current real-time location information and transmits it to the server.

[0930] The server compares the current location information with the learned behavioral patterns.

[0931] (Input): Real-time location data, learned behavioral pattern model

[0932] (Output): The result of determining whether the location information is normal or abnormal

[0933] (Specific operation): The device sends newly acquired real-time location information to the server, which then passes this data to the AI ​​module and compares it with the learned model.

[0934] Step 6: Detect anomalies

[0935] The artificial intelligence module detects an anomaly if the current location information deviates from the learned behavioral patterns.

[0936] (Input): Current location information, learned behavior patterns

[0937] (Output): Anomaly detection flag

[0938] (Specific operation): The AI ​​module evaluates whether the current location information deviates from the learned pattern by more than a certain threshold, and sets an anomaly detection flag if an anomaly is detected.

[0939] Step 7: Triggering an alert

[0940] When an anomaly is detected, the server immediately sends an alert to the user's device, which includes the user's current location, the reason for the anomaly, and recommended countermeasures.

[0941] (Input): Anomaly detection flag, current location information

[0942] (Output): Alert notification to user device

[0943] (Specific operation): When an abnormality is detected, the server generates an alert message and sends it to the user's smartphone as a push notification. The alert message contains specific content such as "Your child has deviated from their normal route. Please contact us to check or go to the location."

[0944] Step 8: Recognize emotions

[0945] When the user's device receives an alert, it activates an emotion engine and recognizes emotions from the user's facial expressions and voice.

[0946] (Input): Alert message, user's real-time facial expression and voice data

[0947] (Output): Recognized user emotion data

[0948] (Specific operation): After receiving an alert, the smartphone's camera and microphone are used to collect the user's facial expressions and voice, which are then analyzed by the emotion engine to recognize the user's emotional state.

[0949] Step 9: Collect and analyze emotional responses

[0950] The server collects the user's emotional response to the alert and stores it in a database. The emotion engine uses this information to optimize the content and notification method of the next alert.

[0951] (Input): Recognized user emotion data

[0952] (Output): Optimized alert content and notification method

[0953] (Specific operation): The server receives data from the emotion engine and stores it in a database. For subsequent alerts, the content and method of notifications (for example, more detailed instructions or reassuring messages) are optimized to take into account the user's emotional response.

[0954] (Application example 2)

[0955] 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."

[0956] While conventional monitoring systems are capable of acquiring location information of the target and detecting abnormalities, they have problems optimizing alerts to take appropriate action when an abnormality occurs. In particular, notifications are sent uniformly without considering the emotional state of the alert recipient, which can cause excessive stress to the recipient. In addition, false positives can cause anxiety due to meaningless alerts. The present invention aims to solve these problems and provide a more appropriate and efficient monitoring system.

[0957] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0958] In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, means for installing an emotion recognition engine in the user terminal to recognize the user's emotion when an alert is received, and means for collecting the user's emotional reactions and optimizing the alert content and notification method. This makes it possible to issue an alert that reflects the user's emotional state when an abnormality occurs, reducing the burden on the recipient and enabling a quick and appropriate response.

[0959] "Means for periodically obtaining location information" refers to means for obtaining location information such as GPS from equipment or devices carried by the subject at regular intervals.

[0960] The "means for transmitting the acquired location information to a server" refers to a means for transmitting the target person's location information to a server via the Internet or a communication network.

[0961] "Means for the server to store location information in a database" refers to a means for storing received location information on the server for a long period of time, making it possible to refer to and analyze it later.

[0962] "Means for an artificial intelligence module installed on a server to analyze location information and learn the target person's daily behavioral patterns" refers to a means for analyzing received location information and using a machine learning algorithm to extract and learn the target person's usual behavioral patterns.

[0963] "Means for detecting abnormalities by comparing current location information with learned behavioral patterns" refers to means for comparing location information acquired in real time with already learned behavioral patterns, and determining that an abnormality exists if there is any deviation.

[0964] The "means for issuing an alert to a user terminal when an abnormality is detected" refers to a means for sending a notification or warning to a device held by a user when an abnormality is detected.

[0965] "Means of equipping a user device with an emotion recognition engine and recognizing the user's emotion when an alert is received" refers to a means of equipping a user device with an engine that recognizes and analyzes the user's emotional state when an alert is notified.

[0966] "Means for collecting users' emotional responses and optimizing alert content and notification methods" refers to means for collecting and analyzing users' emotional data and adjusting the alert content and notification methods from the next time onwards based on the results.

[0967] The system of the present invention collects and analyzes the location information of a target person, and optimizes alerts by taking into account the user's emotions when an abnormality is detected. This system is composed of the following internal components and their respective functions.

[0968] System configuration

[0969] 1. Periodic acquisition of location information

[0970] The equipment or device carried by the subject uses GPS to acquire location information at regular intervals (e.g., every minute), which includes latitude, longitude, and a timestamp.

[0971] 2. Sending location information to the server

[0972] The acquired location information is sent to a server via a network. The Internet is used for communication, and encryption technology (e.g., SSL / TLS) is preferably used as needed.

[0973] 3. Saving to the database

[0974] The server stores the received location information in a database, which manages data in chronological order and also keeps a history of past events.

[0975] 4. Learning behavioral patterns using an artificial intelligence module

[0976] The server's installed artificial intelligence module analyzes the accumulated location data and learns the subject's normal daily behavior patterns. For example, a machine learning model can be built using TensorFlow or Keras.

[0977] 5. Anomaly Detection

[0978] The system compares location information acquired in real time with learned behavioral patterns and detects any deviations as an anomaly. This makes it possible to immediately detect deviations, such as when a person deviates from their usual school route.

[0979] 6. Alerts

[0980] When an anomaly is detected, the server immediately sends an alert to the user's device, which includes the current location, the reason for the anomaly, and a recommended course of action (e.g., contacting the user for confirmation, visiting the site, etc.).

[0981] 7. Emotion Recognition Engine

[0982] When an alert is issued, the user device uses an emotion recognition engine to analyze the user's emotional response, using facial expression recognition (e.g., OpenCV, DeepFace) and voice recognition (e.g., Google Cloud Speech-to-Text) technologies.

[0983] 8. Collecting and optimizing emotional responses

[0984] The recognized emotion data is sent to the server and stored in a database, and the content and notification method for future alerts are optimized based on this data.

[0985] Specific hardware and software names to be used

[0986] Hardware: GPS devices, smartphones or mobile communication devices, servers

[0987] Software: TensorFlow, Keras, OpenCV, DeepFace, Google Cloud Speech-to-Text, Flask or FastAPI, SSL / TLS encryption technology

[0988] Examples of concrete examples and prompts

[0989] Specific examples

[0990] If an elderly person stays outside their usual living area for an extended period of time, the system detects this as an abnormality and immediately sends an alert to the family member's smartphone. The alert includes the family member's current location and details of the abnormality. When the user checks the alert, the smartphone's camera is used to capture facial expressions and analyze them with an emotion recognition engine. The recognized emotion data is sent to a server and used to optimize the content of future notifications.

[0991] Prompt Sentence Examples

[0992] "My father has been in an unusual location for an extended period of time. Please suggest ways to check on him."

[0993] This embodiment of the present invention not only ensures the safety of the subject in real time, but also enables appropriate responses that take into account the user's emotions.

[0994] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0995] Step 1:

[0996] The terminal uses a GPS device to obtain the subject's latitude, longitude, and timestamp. The input is raw data from the GPS device, and the output is analyzed location information. Specifically, the terminal queries the GPS device for location information every minute and obtains the data.

[0997] Step 2:

[0998] The device sends the acquired location information to the server. The input is the location information acquired in step 1, and the output is data transfer to the server. Specifically, the device uses an HTTP POST request to send the location information to the server in JSON format.

[0999] Step 3:

[1000] The server stores the received location information in a database. The input is the location information sent from the device, and the output is storage in the database. Specifically, it formats the location data appropriately and executes an INSERT statement into a database such as MySQL or PostgreSQL.

[1001] Step 4:

[1002] The artificial intelligence module installed on the server analyzes the accumulated location information and learns the subject's normal daily behavior patterns. The input is past location information data, and the output is a learned behavior pattern model. Specifically, it uses TensorFlow and Keras to train a machine learning model based on the location information data.

[1003] Step 5:

[1004] The server compares location information acquired in real time with learned behavioral patterns to detect anomalies. The input is real-time location information and the learned model, and the output is the presence or absence of anomalies. Specifically, newly acquired location information is input into the learned model and classified as normal or abnormal.

[1005] Step 6:

[1006] If the server detects an anomaly, it immediately sends an alert to the user device. The input is the fact that an anomaly has been detected and detailed information about it, and the output is an alert notification to the user device. Specifically, the server uses an HTTP POST request to send the alert information to the user device.

[1007] Step 7:

[1008] The user device uses an emotion recognition engine to recognize the user's emotions when receiving an alert. The input is the user's facial expression or voice data, and the output is the recognized emotion data. Specifically, OpenCV and DeepFace are used to analyze the facial expression data obtained from the camera.

[1009] Step 8:

[1010] The user device sends the recognized emotion data to the server. The input is the emotion data obtained from the emotion recognition engine, and the output is the data transfer to the server. Specifically, the emotion data is sent to the server in JSON format using an HTTP POST request.

[1011] Step 9:

[1012] The server stores the collected emotion data in a database and optimizes the alert content and notification method. The input is the emotion data sent from the user's device, and the output is the optimization of the alert content from the next time onwards. Specifically, the server accumulates emotion data and uses this data to adaptively change the notification method when the next alert is generated.

[1013] 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.

[1014] 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.

[1015] 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.

[1016] [Third embodiment]

[1017] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1018] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1019] 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).

[1020] 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.

[1021] 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.

[1022] 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).

[1023] 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.

[1024] 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.

[1025] 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.

[1026] 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.

[1027] 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.

[1028] 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."

[1029] The present invention relates to a monitoring system that acquires location information of a target person, detects an abnormality, and issues an alert. Hereinafter, specific embodiments of the present invention will be described.

[1030] System configuration

[1031] The system mainly consists of the following elements:

[1032] 1. A GPS device that periodically acquires location information.

[1033] 2. A device that sends the acquired location information to a server.

[1034] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[1035] 4. A function that sends an alert to the user's device when an abnormality is detected.

[1036] Program processing

[1037] 1. Obtaining location information

[1038] The terminal periodically (for example, every minute) acquires the target person's location information from the GPS device. This location information includes latitude, longitude, and timestamp.

[1039] 2. Data transmission

[1040] The terminal transmits the acquired location information to the server.

[1041] 3. Data storage

[1042] The server stores the received location information in a database, accumulating and managing past location information as well.

[1043] 4. Learning behavioral patterns

[1044] An artificial intelligence module installed on the server analyzes the accumulated location information and learns the target person's daily behavioral patterns, for example, identifying a child's route to school or an elderly person's walking route and time of day.

[1045] 5. Location Comparison

[1046] The terminal obtains the current real-time location information and transmits it to the server.

[1047] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1048] 6. Anomaly Detection

[1049] The AI ​​module detects any deviations from the current location from normal behavioral patterns, such as straying from a specific route or staying in an unspecified area for an extended period of time.

[1050] 7. Alerts

[1051] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location and the reason for the anomaly.

[1052] Specific examples

[1053] Watching over children going to school

[1054] 1. The user gives their child a GPS device.

[1055] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[1056] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[1057] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[1058] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[1059] 6. The user receives an alert and immediately checks on the safety of the child.

[1060] Preventing elderly people from wandering

[1061] 1. The user gives the elderly person a GPS device.

[1062] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[1063] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[1064] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[1065] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[1066] 6. The user receives an alert, checks the elderly person's condition, and takes action.

[1067] This system allows users to monitor the safety of children and the elderly in real time, and responds quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances.

[1068] The processing flow will be explained below.

[1069] Step 1:

[1070] The user attaches a GPS device to the subject (child or elderly person).

[1071] Step 2:

[1072] The device (smartphone or tablet) registers the GPS device through the app and enters the target person's information (name, age, contact details, etc.).

[1073] Step 3:

[1074] The terminal periodically (for example, every minute) acquires location information (latitude, longitude, timestamp) from the GPS device.

[1075] Step 4:

[1076] The terminal transmits the acquired location information to the server in real time.

[1077] Step 5:

[1078] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[1079] Step 6:

[1080] The AI ​​module installed on the server periodically analyzes the location information in the database and learns the subject's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[1081] Step 7:

[1082] The terminal transmits the current location information obtained in real time to the server.

[1083] Step 8:

[1084] The server passes the received current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1085] Step 9:

[1086] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended period of time in an unplanned location.

[1087] Step 10:

[1088] If an abnormality is detected, the server immediately sends an alert to the user's (guardian's or caregiver's) device.

[1089] Step 11:

[1090] The server includes in the alert message the current location information, the reason why the anomaly was detected, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[1091] Step 12:

[1092] The user checks the alert notification displayed on the device and takes appropriate action, such as contacting the child to check on their safety or heading to the scene.

[1093] Example 1

[1094] 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."

[1095] Conventional monitoring systems not only acquire the target's location information and transmit it to a server, but also analyze that location information, learn the target's daily behavioral patterns, and detect abnormalities. However, existing systems have difficulty detecting abnormalities in real time, and it takes a long time to issue an appropriate alert in an emergency. Furthermore, security during data transmission is insufficient, creating a risk of location information leaks. The present invention aims to solve these problems by providing a system that detects abnormalities more accurately and quickly, ensuring user safety.

[1096] 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.

[1097] In this invention, the server includes means for periodically acquiring location information of a target person, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and perform machine learning on the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, means for encrypting and transmitting the target person's location information, and means for sending an alert to the user terminal using push notification or SMS in an emergency. This enables highly accurate abnormality detection in real time, prompt alert issuance, and safe data transmission.

[1098] "Location information" is data about a subject's current location, including latitude, longitude, and timestamp.

[1099] "Means of acquisition" refers to the means of periodically collecting the subject's location information using a GPS device or terminal.

[1100] A "server" is a remote computer system that receives, stores, processes, etc. data.

[1101] The "transmitting means" is a means for sending data from the terminal to the server.

[1102] A "database" is a data management system that stores location information and allows it to be searched and updated as needed.

[1103] The "artificial intelligence module" is a software module that analyzes location information and learns daily behavior patterns.

[1104] "Machine learning" refers to algorithms and techniques that automatically learn patterns and trends based on large amounts of data.

[1105] The "means for detecting anomalies" is a means for determining whether the current location information deviates from the normal behavioral pattern.

[1106] The "means for issuing an alert" is a means for sending a notification to a user terminal when an abnormality is detected.

[1107] "Means for encryption and transmission" refers to means for encrypting data to protect location information from third parties and transmitting it securely to a server.

[1108] "Push notification" is a method for sending messages from a server to a user terminal in real time.

[1109] "SMS" stands for Short Message Service, a means of sending short text messages via mobile phones.

[1110] The present invention relates to a monitoring system that acquires location information of a target person, detects an abnormality, and issues an alert. A specific embodiment of this system will be described below.

[1111] Hardware and Software Configuration

[1112] Terminal

[1113] The device communicates with the subject's GPS device to obtain location information. The device periodically obtains latitude, longitude, and timestamps from the GPS device using Bluetooth or Wi-Fi connections. HTTPS is used to encrypt the obtained location information and send it securely to the server.

[1114] server

[1115] The server is a device that stores the received location information in a database and analyzes it using an artificial intelligence module. The server uses a relational database such as MySQL or PostgreSQL, and indexes the location information to enable efficient searches. The server is equipped with an artificial intelligence module using Python's Scikit-learn and TensorFlow, which uses machine learning to learn daily behavior patterns based on the accumulated location information.

[1116] Specific actions

[1117] 1. Acquisition and transmission of location information

[1118] The terminal communicates with a GPS device and periodically acquires location information (latitude, longitude, timestamp).

[1119] The device encrypts the acquired location information and sends it to the server using HTTPS.

[1120] 2. Location information storage and analysis

[1121] The server stores the received location information in a database.

[1122] The server's artificial intelligence module analyzes the accumulated location information and learns the subject's daily behavioral patterns, for example, by using K-Means clustering to identify the person's commute route, walking route, and time of day.

[1123] 3. Detecting anomalies and issuing alerts

[1124] The terminal again acquires the current real-time location information and transmits it to the server.

[1125] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1126] The artificial intelligence module detects any deviations in current location information from normal behavioral patterns as an anomaly.

[1127] When an anomaly is detected, the server immediately sends an alert to the user's device via push notification or SMS, and the notification includes the user's current location and the reason why the anomaly was detected.

[1128] Specific examples

[1129] Watching over children going to school

[1130] 1. The user gives their child a GPS device.

[1131] 2. The device will receive the child's location information from the GPS device via Bluetooth every minute. The location information includes latitude, longitude, and a timestamp.

[1132] 3. The device sends the encrypted location information to the server via HTTPS.

[1133] 4. The server stores the location information in a database, and the artificial intelligence module uses the data to learn the school route using K-Means clustering.

[1134] 5. If a child deviates from their usual route to school in real time, the artificial intelligence module will detect this as an anomaly.

[1135] 6. The server immediately sends a push notification to the user's smartphone, alerting them to the location. The notification includes information such as, "Your child has deviated from their normal route. Their current location is latitude x, longitude y."

[1136] Preventing elderly people from wandering

[1137] 1. The user gives the elderly person a GPS device.

[1138] 2. The device receives the elderly person's location information from the GPS device via Bluetooth every minute. The location information includes latitude, longitude, and timestamp.

[1139] 3. The device sends the encrypted location information to the server via HTTPS.

[1140] 4. The server stores the location information in a database, and the artificial intelligence module learns daily behavior patterns using K-Means clustering.

[1141] 5. If an elderly person is out and about and stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[1142] 6. The server immediately sends an alert to the user's smartphone via push notification or SMS. The notification contains information such as, "An elderly person has been outside their usual living area for an extended period of time. Their current location is latitude x, longitude y."

[1143] Example prompts for generative AI models

[1144] Prompt statement:

[1145] Describe a system that sends an alert if a child deviates from their usual route to school. This system uses a GPS device, a server, an artificial intelligence module, etc.

[1146] Prompt statement:

[1147] Describe a system that alerts elderly people if they are outside their usual living area for an extended period of time. The system uses GPS devices, a server, and an artificial intelligence module.

[1148] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1149] Step 1:

[1150] Obtaining location information

[1151] The terminal communicates with the subject's GPS device and periodically (e.g., every minute) obtains location information. The input is the latitude, longitude, and timestamp from the GPS device, and the output is the obtained location information. Specifically, the terminal reads information from the device via Bluetooth or Wi-Fi connection.

[1152] Step 2:

[1153] Location encryption

[1154] The device encrypts the acquired location information. The input is the location information acquired in step 1, and the output is the encrypted location information. Specifically, the data is secured using encryption algorithms such as AES or RSA.

[1155] Step 3:

[1156] Sending location information

[1157] The device sends encrypted location information to the server using HTTPS. The input is the encrypted location information, and the output is a notification to the server that the location information has been sent. Specifically, the data is sent to a RESTful API endpoint using a POST request.

[1158] Step 4:

[1159] Save location information

[1160] The server stores the received location information in a database. The input is the location information sent from the device, and the output is a notification that the information has been saved to the database. Specifically, the server uses an INSERT statement to store the location information in the database.

[1161] Step 5:

[1162] Learning behavioral patterns

[1163] The artificial intelligence module installed on the server analyzes the accumulated location information and performs machine learning to learn daily behavior patterns. The input is past location information obtained from a database, and the output is the learned behavior pattern. Specifically, it applies machine learning algorithms such as K-Means clustering.

[1164] Step 6:

[1165] Acquiring and sending real-time location information

[1166] The device again acquires the latest real-time location information and sends it to the server. The input is the current location information from the GPS device, and the output is a notification to the server that transmission has been completed. Specifically, the device again collects location information from the GPS device via Bluetooth or Wi-Fi, encrypts it, and sends it to the server.

[1167] Step 7:

[1168] Real-time location analysis

[1169] The server receives real-time location information and passes it on to an artificial intelligence module for analysis. The input is real-time location information, and the output is the analysis results. Specifically, it compares learned behavioral patterns with real-time location information to detect anomalies.

[1170] Step 8:

[1171] Anomaly detection

[1172] The AI ​​module detects anomalies by identifying deviations from normal behavioral patterns in real-time location information. The input is real-time location information and learned patterns, and the output is the anomaly detection result. Specific operations include using support vector machines (SVM) and other anomaly detection algorithms.

[1173] Step 9:

[1174] Alert issuance

[1175] If an anomaly is detected, the server immediately sends an alert to the user device. The input is the anomaly detection result, and the output is an alert notification to the user device. Specifically, the server sends a push notification or SMS using Firebase Cloud Messaging (FCM) or Twilio.

[1176] Through the technology and specific actions used at each step, the system can monitor the safety of the subject in real time, allowing for quick response in emergencies and greatly reducing the risk of accidents or disappearances.

[1177] (Application example 1)

[1178] 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."

[1179] In the food delivery industry, the safety of delivery staff and efficient operation management are important issues. Conventional methods lack a system that can track delivery staff's location information in real time and immediately detect deviations from the planned route or abnormal behavior. As a result, it is difficult to respond quickly to delays or problems. This can lead to a decline in service quality and a decrease in customer satisfaction.

[1180] 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.

[1181] In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the behavioral patterns of the target person (daily behavior patterns), means for comparing the current location information with the learned behavioral patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, and means for tracking the location information of delivery staff, detecting abnormalities, and notifying an administrator in real time for delivery services. This makes it possible to track the location information of delivery staff in real time in the food delivery industry, quickly detect delays and route deviations, and immediately take appropriate measures.

[1182] "Location information" is data indicating the subject's current location, such as latitude, longitude, and timestamp.

[1183] "Server" means a computing device for receiving, storing, and analyzing location information.

[1184] A "database" is a system that systematically stores and manages acquired location information and related data.

[1185] The "artificial intelligence module" is a group of programs and algorithms that analyze location information and learn the subject's daily behavioral patterns.

[1186] A "user terminal" is a communication device such as a smartphone or dedicated device for receiving alerts.

[1187] A "delivery service" is a business service that delivers meals or goods to a specified location.

[1188] "Delivery staff" refers to personnel whose job is to transport goods and food to provide delivery services.

[1189] "Administrator" refers to the person responsible for supervising and managing delivery staff and the overall system in the delivery service.

[1190] "Real-time tracking" refers to monitoring the location of delivery staff in real time with almost no delay.

[1191] An "alert" is a warning notification sent to a user terminal when an abnormality is detected.

[1192] The present invention relates to a system for tracking the location information of delivery staff in the food delivery industry in real time, detecting abnormalities, and notifying an administrator of an alert. Specific embodiments of the present invention will be described below.

[1193] System Configuration

[1194] The system consists of the following elements:

[1195] 1. Terminal

[1196] The smartphone functions as a GPS device, periodically obtaining the location information of the delivery staff (for example, every minute).

[1197] The acquired location information (latitude, longitude, timestamp) is sent to a server via the Internet.

[1198] 2. Server

[1199] The received location information is stored in a database and managed, including past data.

[1200] The server is equipped with an artificial intelligence module that analyzes the accumulated location information to learn the delivery staff's daily delivery routes and behavioral patterns.

[1201] 3. Database

[1202] Systematically manage location information, delivery route data, etc. stored on the server.

[1203] 4. Artificial Intelligence Module

[1204] It includes software algorithms for analyzing location data and learning the behavioral patterns of subjects.

[1205] 5. User device (administrator smartphone)

[1206] Receive alerts from the server in real time.

[1207] Processing flow

[1208] The server stores the location information acquired by the smartphone in a database and analyzes behavioral patterns using an artificial intelligence module. If an abnormality is detected, the server immediately sends an alert to the administrator's smartphone (user device).

[1209] Hardware and software used

[1210] Hardware

[1211] Smartphone: Obtains the location information of delivery staff and sends it to the server.

[1212] Server: Stores and analyzes data.

[1213] software

[1214] Python-based server application: manages, stores, and analyzes location information.

[1215] Python machine learning libraries (e.g., scikit-learn and TensorFlow): Implement programs that learn behavioral patterns and detect anomalies.

[1216] Mobile application: An app for delivery service managers to receive alerts.

[1217] Specific examples

[1218] For example, if a delivery staff member deviates significantly from their normal delivery route and begins heading out into the suburbs, the system will detect the anomaly and send an alert to the administrator stating, "A delivery staff member has deviated from the standard route. Their current location is latitude 35.5, longitude 135.8." In this way, abnormal behavior can be detected early, allowing for appropriate action to be taken promptly.

[1219] Prompt Sentence Examples

[1220] Here are some example prompts you can give to your generative AI model:

[1221] "Generate Python code for an algorithm that detects anomalous delivery staff routes, such as the following."

[1222] This prompt statement can be used to help generate specific program code.

[1223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1224] Step 1:

[1225] The terminal periodically obtains the location information of the delivery staff. Specifically, it uses the smartphone's GPS function to obtain the current latitude, longitude, and timestamp every minute. The input is GPS data, and the output is location information.

[1226] Step 2:

[1227] The device sends the acquired location information to the server. The location information is sent via the Internet in JSON format. The input is the acquired location information, and the output is the data sent to the server.

[1228] Step 3:

[1229] The server stores the received location information in a database. The location information is accumulated and managed in the database along with past data. The input is the received location information, and the output is the data stored in the database.

[1230] Step 4:

[1231] The server uses the stored location information to learn the delivery staff's daily delivery routes and behavioral patterns. Specifically, it uses Python's machine learning library to analyze time periods and delivery route patterns. The input is the location information in the database, and the output is the learned behavioral patterns.

[1232] Step 5:

[1233] The device transmits the current location information acquired in real time to the server. The input is the real-time location information, and the output is the data transmitted to the server.

[1234] Step 6:

[1235] The server compares the current location with the learned behavioral patterns. It uses an artificial intelligence module to perform pattern matching and determine if the current location matches the learned behavioral patterns. The input is the current location and the learned behavioral patterns, and the output is the anomaly detection results.

[1236] Step 7:

[1237] If the server detects an anomaly, it immediately sends an alert to the administrator's user device. The alert includes the current location information and the reason for the anomaly. The input is the anomaly detection result, and the output is the alert message sent to the administrator's smartphone.

[1238] 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.

[1239] The present invention relates to a monitoring system that collects location information of subjects (children and elderly people) and detects abnormalities, and further optimizes alerts by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention are described below.

[1240] System configuration

[1241] The system mainly consists of the following elements:

[1242] 1. A GPS device that periodically acquires location information.

[1243] 2. A device that sends the acquired location information to a server.

[1244] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[1245] 4. A function that sends an alert to the user's device when an abnormality is detected.

[1246] 5. An emotion engine that recognizes user emotions and collects responses.

[1247] Program processing

[1248] 1. Obtaining location information

[1249] The terminal periodically (for example, every minute) acquires the target person's location information from the GPS device. This location information includes latitude, longitude, and timestamp.

[1250] 2. Data transmission

[1251] The terminal transmits the acquired location information to the server.

[1252] 3. Data storage

[1253] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[1254] 4. Learning behavioral patterns

[1255] An artificial intelligence module installed on the server analyzes the accumulated location information and learns the target person's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[1256] 5. Location Comparison

[1257] The terminal obtains the current real-time location information and transmits it to the server.

[1258] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1259] 6. Anomaly Detection

[1260] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended period of time in an unplanned location.

[1261] 7. Alerts

[1262] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location, the reason for the anomaly, and recommended countermeasures (e.g., contacting the user for confirmation, heading to the site, etc.).

[1263] 8. Emotional Recognition

[1264] Upon receiving the alert, the user's device uses an emotion engine to recognize the user's emotional response, which includes extracting emotions from the user's facial expressions, voice, or text data.

[1265] 9. Collecting and analyzing emotional responses

[1266] The server collects and stores in a database the user's emotional responses to the alerts.

[1267] The emotion engine analyzes the collected emotion data and optimizes the content and notification method of the next alert.

[1268] Specific examples

[1269] Watching over children going to school

[1270] 1. The user gives their child a GPS device.

[1271] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[1272] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[1273] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[1274] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[1275] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1276] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[1277] Preventing elderly people from wandering

[1278] 1. The user gives the elderly person a GPS device.

[1279] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[1280] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[1281] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[1282] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[1283] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1284] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[1285] This system allows users to monitor the safety of children and the elderly in real time, and can respond quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances. In addition, by combining it with an emotion engine, it becomes possible to issue alerts that take into account the user's emotional reactions, which is expected to lead to more appropriate and efficient responses.

[1286] The processing flow will be explained below.

[1287] Step 1:

[1288] The user attaches a GPS device to the subject (child or elderly person).

[1289] Step 2:

[1290] The device (smartphone or tablet) registers the GPS device through the app and inputs the target person's information, including name, age, and contact details.

[1291] Step 3:

[1292] The terminal periodically (for example, every minute) acquires location information (latitude, longitude, timestamp) from the GPS device.

[1293] Step 4:

[1294] The terminal transmits the acquired location information to the server.

[1295] Step 5:

[1296] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[1297] Step 6:

[1298] The AI ​​module installed on the server periodically analyzes the location information in the database and learns the subject's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[1299] Step 7:

[1300] The terminal transmits the current location information obtained in real time to the server.

[1301] Step 8:

[1302] The server passes the received current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1303] Step 9:

[1304] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended amount of time in an unplanned location.

[1305] Step 10:

[1306] If an abnormality is detected, the server immediately sends an alert to the user's (guardian's or caregiver's) device.

[1307] Step 11:

[1308] The server includes in the alert message the current location information, the reason why the anomaly was detected, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[1309] Step 12:

[1310] When receiving an alert, the user's device recognizes the user's emotion using an emotion engine, which extracts emotions from the user's facial expressions, voice, or text data.

[1311] Step 13:

[1312] The server collects and stores in a database the user's emotional responses to the alerts.

[1313] Step 14:

[1314] The emotion engine analyzes the collected emotion data and optimizes the content and notification method of the next alert, enabling more appropriate alerts to be issued that take the user's emotions into consideration.

[1315] Specific examples

[1316] Watching over children going to school

[1317] Step 1:

[1318] The user gives the child a GPS device.

[1319] Step 2:

[1320] The device obtains the child's location information from the GPS device every minute and sends it to the server.

[1321] Step 3:

[1322] The server stores the location information in a database, and an artificial intelligence module learns the student's route to school.

[1323] Step 4:

[1324] If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[1325] Step 5:

[1326] The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[1327] Step 6:

[1328] When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1329] Step 7:

[1330] The server collects the user's emotional responses and optimizes the content of the next alert.

[1331] Preventing elderly people from wandering

[1332] Step 1:

[1333] The user provides the elderly person with a GPS device.

[1334] Step 2:

[1335] The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[1336] Step 3:

[1337] The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[1338] Step 4:

[1339] If an elderly person stays outside their usual living area for an extended period of time, the artificial intelligence module will detect this as an abnormality.

[1340] Step 5:

[1341] The server detects any abnormality and immediately sends an alert to the user's (family member's) smartphone.

[1342] Step 6:

[1343] When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1344] Step 7:

[1345] The server collects the user's emotional responses and optimizes the content of the next alert.

[1346] This system allows users to monitor the safety of children and the elderly in real time, and can respond quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances. In addition, by combining it with an emotion engine, it becomes possible to issue alerts that take into account the user's emotional reactions, which is expected to lead to more appropriate and efficient responses.

[1347] Example 2

[1348] 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."

[1349] Conventional monitoring systems have a problem in that, despite acquiring the target's location information, they do not optimize alerts to take into account the target's emotional state or the user's reaction. This can lead to false alerts and delayed appropriate responses. The present invention aims to solve these problems and improve alert accuracy and user satisfaction.

[1350] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to the user terminal when an abnormality is detected, means for collecting the user's emotional response using an emotion engine that recognizes the user's emotions, and means for analyzing the user's emotional response to the alert and optimizing the content of the next alert and the notification method. This makes it possible to issue an alert that takes into account not only the target person's location information but also the user's emotional state, thereby reducing false alarms and enabling prompt and appropriate responses.

[1351] "Location information" is data indicating the subject's current location, and includes latitude, longitude, and a timestamp.

[1352] A "server" is a computer system that aggregates, stores, and processes acquired data.

[1353] A "database" is a system for systematically storing, searching, and managing information.

[1354] The "artificial intelligence module" is software that analyzes collected data and performs pattern recognition and anomaly detection.

[1355] "Behavioral patterns" refer to specific patterns of a subject's daily travel routes and behavior.

[1356] "Abnormal" refers to a significant deviation from learned patterns of behavior, including a subject leaving their usual route or staying in an unexpected location for an extended period of time.

[1357] An "alert" is a warning message that is sent to the user when an abnormality is detected.

[1358] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[1359] An "emotion engine" is software for recognizing and analyzing a user's emotional state.

[1360] "Emotional response" refers to the emotional reaction a user shows when receiving an alert, and is extracted from facial expressions, voice, and text data.

[1361] The present invention relates to a monitoring system that mainly acquires location information, detects abnormalities, issues alerts, and recognizes emotions. Specific embodiments of the present invention are described below.

[1362] System configuration

[1363] The system mainly consists of the following elements:

[1364] 1. GPS devices that periodically acquire location information

[1365] 2. The device that sends the acquired location information to the server

[1366] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[1367] 4. A function that issues an alert to the user device when an abnormality is detected

[1368] 5. Emotion engine that recognizes user emotions and collects responses

[1369] Details of each element

[1370] GPS devices and terminals

[1371] The device periodically obtains location information from the target person's GPS device. This location information includes latitude, longitude, and a timestamp. For example, the device obtains location information from the GPS device every minute on the way to school.

[1372] Servers and Databases

[1373] The server receives the location information sent from the device and stores it in a database. The database is used to accumulate and manage the location history for each subject, making it possible to analyze the subject's behavioral patterns over a long period of time.

[1374] Artificial Intelligence Module

[1375] The AI ​​module installed on the server analyzes the location information stored in the database and learns the subject's daily behavioral patterns. For example, it identifies a child's route to school or an elderly person's walking route and the time of day. This creates a foundation for determining the subject's normal behavior range and abnormal behavior.

[1376] Anomaly detection and alert generation

[1377] The device again acquires its current real-time location information and sends it to the server. The server then passes the current location information to an AI module, which compares it with the learned behavioral patterns. If the current location information significantly deviates from the learned behavioral patterns, it detects this as an anomaly. For example, this could include a child straying from their usual school route or an elderly person staying in an unplanned location for an extended period of time.

[1378] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location, the reason for the anomaly, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[1379] Emotion Engine

[1380] When receiving an alert, the user's device uses an emotion engine to recognize the user's emotional response. The emotion engine extracts emotions from the user's facial expressions, voice, or text data. For example, after receiving an alert message, the emotion engine analyzes the user's facial expressions and voice using the smartphone's camera and microphone.

[1381] Collecting and analyzing emotional responses

[1382] The server collects the user's emotional response to the alert and stores it in a database. The emotion engine analyzes the collected emotional data and optimizes the content and notification method of the next alert. For example, if the user feels anxious about the alert, the next alert notification will include more specific countermeasures.

[1383] Specific examples

[1384] Watching over children going to school

[1385] 1. The user gives their child a GPS device.

[1386] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[1387] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[1388] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[1389] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[1390] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1391] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[1392] Preventing elderly people from wandering

[1393] 1. The user gives the elderly person a GPS device.

[1394] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[1395] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[1396] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[1397] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[1398] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1399] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[1400] Examples of prompt statements

[1401] Prompt: "Please explain how parents are notified when their child deviates from their normal school route and how to recognize their emotions and optimize responses."

[1402] As a result, this system can monitor the location information of the target person in real time and respond quickly when an abnormality is detected.In addition, by combining it with an emotion engine, it is possible to issue alerts that take the user's emotional response into consideration, which is expected to lead to more appropriate and efficient responses.

[1403] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1404] Step 1: Obtaining location information

[1405] The device obtains location information every minute from the subject's GPS device, including latitude, longitude, and a timestamp.

[1406] (Input): Location data (latitude, longitude, timestamp) obtained from a GPS device

[1407] (Output): Data packet containing the obtained location information

[1408] (Specific operation): The device automatically obtains location data from the GPS device every minute and temporarily stores the data.

[1409] Step 2: Sending data

[1410] The device automatically transmits the acquired location information to the server immediately after the location information is acquired.

[1411] (Input): Location data stored on the device

[1412] (Output): Location data sent to the server

[1413] (Specific operation): The device uses Wi-Fi or mobile data communication to send a data packet containing location information to the server's fixed IP address.

[1414] Step 3: Save your data

[1415] The server stores the received location information in a database, and a location history is accumulated for each subject.

[1416] (Input): Location data received by the server

[1417] (Output): Location information stored in the database

[1418] (Specific operation): The server analyzes the received location data and adds new location information to the corresponding subject's database entry.

[1419] Step 4: Learning behavioral patterns

[1420] An artificial intelligence module installed on the server analyzes the accumulated location information, learns the target person's daily behavior patterns, and generates a predictive model.

[1421] (Input): Past location data stored in the database

[1422] (Output): Learned behavioral pattern model

[1423] (Specific operation): The AI ​​module applies machine learning algorithms to analyze past behavioral data to identify the subject's daily route and time of day, and update the behavioral pattern model.

[1424] Step 5: Compare locations

[1425] The terminal again acquires the current real-time location information and transmits it to the server.

[1426] The server compares the current location information with the learned behavioral patterns.

[1427] (Input): Real-time location data, learned behavioral pattern model

[1428] (Output): The result of determining whether the location information is normal or abnormal

[1429] (Specific operation): The device sends newly acquired real-time location information to the server, which then passes this data to the AI ​​module and compares it with the learned model.

[1430] Step 6: Detect anomalies

[1431] The artificial intelligence module detects an anomaly if the current location information deviates from the learned behavioral patterns.

[1432] (Input): Current location information, learned behavior patterns

[1433] (Output): Anomaly detection flag

[1434] (Specific operation): The AI ​​module evaluates whether the current location information deviates from the learned pattern by more than a certain threshold, and sets an anomaly detection flag if an anomaly is detected.

[1435] Step 7: Triggering an alert

[1436] When an anomaly is detected, the server immediately sends an alert to the user's device, which includes the user's current location, the reason for the anomaly, and recommended countermeasures.

[1437] (Input): Anomaly detection flag, current location information

[1438] (Output): Alert notification to user device

[1439] (Specific operation): When an abnormality is detected, the server generates an alert message and sends it to the user's smartphone as a push notification. The alert message contains specific content such as "Your child has deviated from their normal route. Please contact us to check or go to the location."

[1440] Step 8: Recognize emotions

[1441] When the user's device receives an alert, it activates an emotion engine and recognizes emotions from the user's facial expressions and voice.

[1442] (Input): Alert message, user's real-time facial expression and voice data

[1443] (Output): Recognized user emotion data

[1444] (Specific operation): After receiving an alert, the smartphone's camera and microphone are used to collect the user's facial expressions and voice, which are then analyzed by the emotion engine to recognize the user's emotional state.

[1445] Step 9: Collect and analyze emotional responses

[1446] The server collects the user's emotional response to the alert and stores it in a database. The emotion engine uses this information to optimize the content and notification method of the next alert.

[1447] (Input): Recognized user emotion data

[1448] (Output): Optimized alert content and notification method

[1449] (Specific operation): The server receives data from the emotion engine and stores it in a database. For subsequent alerts, the content and method of notifications (for example, more detailed instructions or reassuring messages) are optimized to take into account the user's emotional response.

[1450] (Application example 2)

[1451] 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."

[1452] While conventional monitoring systems are capable of acquiring location information of the target and detecting abnormalities, they have problems optimizing alerts to take appropriate action when an abnormality occurs. In particular, notifications are sent uniformly without considering the emotional state of the alert recipient, which can cause excessive stress to the recipient. In addition, false positives can cause anxiety due to meaningless alerts. The present invention aims to solve these problems and provide a more appropriate and efficient monitoring system.

[1453] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1454] In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, means for installing an emotion recognition engine in the user terminal to recognize the user's emotion when an alert is received, and means for collecting the user's emotional reactions and optimizing the alert content and notification method. This makes it possible to issue an alert that reflects the user's emotional state when an abnormality occurs, reducing the burden on the recipient and enabling a quick and appropriate response.

[1455] "Means for periodically obtaining location information" refers to means for obtaining location information such as GPS from equipment or devices carried by the subject at regular intervals.

[1456] The "means for transmitting the acquired location information to a server" refers to a means for transmitting the target person's location information to a server via the Internet or a communication network.

[1457] "Means for the server to store location information in a database" refers to a means for storing received location information on the server for a long period of time, making it possible to refer to and analyze it later.

[1458] "Means for an artificial intelligence module installed on a server to analyze location information and learn the target person's daily behavioral patterns" refers to a means for analyzing received location information and using a machine learning algorithm to extract and learn the target person's usual behavioral patterns.

[1459] "Means for detecting abnormalities by comparing current location information with learned behavioral patterns" refers to means for comparing location information acquired in real time with already learned behavioral patterns, and determining that an abnormality exists if there is any deviation.

[1460] The "means for issuing an alert to a user terminal when an abnormality is detected" refers to a means for sending a notification or warning to a device held by a user when an abnormality is detected.

[1461] "Means of equipping a user device with an emotion recognition engine and recognizing the user's emotion when an alert is received" refers to a means of equipping a user device with an engine that recognizes and analyzes the user's emotional state when an alert is notified.

[1462] "Means for collecting users' emotional responses and optimizing alert content and notification methods" refers to means for collecting and analyzing users' emotional data and adjusting the alert content and notification methods from the next time onwards based on the results.

[1463] The system of the present invention collects and analyzes the location information of a target person, and optimizes alerts by taking into account the user's emotions when an abnormality is detected. This system is composed of the following internal components and their respective functions.

[1464] System configuration

[1465] 1. Periodic acquisition of location information

[1466] The equipment or device carried by the subject uses GPS to acquire location information at regular intervals (e.g., every minute), which includes latitude, longitude, and a timestamp.

[1467] 2. Sending location information to the server

[1468] The acquired location information is sent to a server via a network. The Internet is used for communication, and encryption technology (e.g., SSL / TLS) is preferably used as needed.

[1469] 3. Saving to the database

[1470] The server stores the received location information in a database, which manages data in chronological order and also keeps a history of past events.

[1471] 4. Learning behavioral patterns using an artificial intelligence module

[1472] The server's installed artificial intelligence module analyzes the accumulated location data and learns the subject's normal daily behavior patterns. For example, a machine learning model can be built using TensorFlow or Keras.

[1473] 5. Anomaly Detection

[1474] The system compares location information acquired in real time with learned behavioral patterns and detects any deviations as an anomaly. This makes it possible to immediately detect deviations, such as when a person deviates from their usual school route.

[1475] 6. Alerts

[1476] When an anomaly is detected, the server immediately sends an alert to the user's device, which includes the current location, the reason for the anomaly, and a recommended course of action (e.g., contacting the user for confirmation, visiting the site, etc.).

[1477] 7. Emotion Recognition Engine

[1478] When an alert is issued, the user device uses an emotion recognition engine to analyze the user's emotional response, using facial expression recognition (e.g., OpenCV, DeepFace) and voice recognition (e.g., Google Cloud Speech-to-Text) technologies.

[1479] 8. Collecting and optimizing emotional responses

[1480] The recognized emotion data is sent to the server and stored in a database, and the content and notification method for future alerts are optimized based on this data.

[1481] Specific hardware and software names to be used

[1482] Hardware: GPS devices, smartphones or mobile communication devices, servers

[1483] Software: TensorFlow, Keras, OpenCV, DeepFace, Google Cloud Speech-to-Text, Flask or FastAPI, SSL / TLS encryption technology

[1484] Examples of concrete examples and prompts

[1485] Specific examples

[1486] If an elderly person stays outside their usual living area for an extended period of time, the system detects this as an abnormality and immediately sends an alert to the family member's smartphone. The alert includes the family member's current location and details of the abnormality. When the user checks the alert, the smartphone's camera is used to capture facial expressions and analyze them with an emotion recognition engine. The recognized emotion data is sent to a server and used to optimize the content of future notifications.

[1487] Prompt Sentence Examples

[1488] "My father has been in an unusual location for an extended period of time. Please suggest ways to check on him."

[1489] This embodiment of the present invention not only ensures the safety of the subject in real time, but also enables appropriate responses that take into account the user's emotions.

[1490] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1491] Step 1:

[1492] The terminal uses a GPS device to obtain the subject's latitude, longitude, and timestamp. The input is raw data from the GPS device, and the output is analyzed location information. Specifically, the terminal queries the GPS device for location information every minute and obtains the data.

[1493] Step 2:

[1494] The device sends the acquired location information to the server. The input is the location information acquired in step 1, and the output is data transfer to the server. Specifically, the device uses an HTTP POST request to send the location information to the server in JSON format.

[1495] Step 3:

[1496] The server stores the received location information in a database. The input is the location information sent from the device, and the output is storage in the database. Specifically, it formats the location data appropriately and executes an INSERT statement into a database such as MySQL or PostgreSQL.

[1497] Step 4:

[1498] The artificial intelligence module installed on the server analyzes the accumulated location information and learns the subject's normal daily behavior patterns. The input is past location information data, and the output is a learned behavior pattern model. Specifically, it uses TensorFlow and Keras to train a machine learning model based on the location information data.

[1499] Step 5:

[1500] The server compares location information acquired in real time with learned behavioral patterns to detect anomalies. The input is real-time location information and the learned model, and the output is the presence or absence of anomalies. Specifically, newly acquired location information is input into the learned model and classified as normal or abnormal.

[1501] Step 6:

[1502] If the server detects an anomaly, it immediately sends an alert to the user device. The input is the fact that an anomaly has been detected and detailed information about it, and the output is an alert notification to the user device. Specifically, the server uses an HTTP POST request to send the alert information to the user device.

[1503] Step 7:

[1504] The user device uses an emotion recognition engine to recognize the user's emotions when receiving an alert. The input is the user's facial expression or voice data, and the output is the recognized emotion data. Specifically, OpenCV and DeepFace are used to analyze the facial expression data obtained from the camera.

[1505] Step 8:

[1506] The user device sends the recognized emotion data to the server. The input is the emotion data obtained from the emotion recognition engine, and the output is the data transfer to the server. Specifically, the emotion data is sent to the server in JSON format using an HTTP POST request.

[1507] Step 9:

[1508] The server stores the collected emotion data in a database and optimizes the alert content and notification method. The input is the emotion data sent from the user's device, and the output is the optimization of the alert content from the next time onwards. Specifically, the server accumulates emotion data and uses this data to adaptively change the notification method when the next alert is generated.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] [Fourth embodiment]

[1513] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1514] 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.

[1515] 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).

[1516] 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.

[1517] 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.

[1518] 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).

[1519] 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.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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."

[1526] The present invention relates to a monitoring system that acquires location information of a target person, detects an abnormality, and issues an alert. Hereinafter, specific embodiments of the present invention will be described.

[1527] System configuration

[1528] The system mainly consists of the following elements:

[1529] 1. A GPS device that periodically acquires location information.

[1530] 2. A device that sends the acquired location information to a server.

[1531] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[1532] 4. A function that sends an alert to the user's device when an abnormality is detected.

[1533] Program processing

[1534] 1. Obtaining location information

[1535] The terminal periodically (for example, every minute) acquires the target person's location information from the GPS device. This location information includes latitude, longitude, and timestamp.

[1536] 2. Data transmission

[1537] The terminal transmits the acquired location information to the server.

[1538] 3. Data storage

[1539] The server stores the received location information in a database, accumulating and managing past location information as well.

[1540] 4. Learning behavioral patterns

[1541] An artificial intelligence module installed on the server analyzes the accumulated location information and learns the target person's daily behavioral patterns, for example, identifying a child's route to school or an elderly person's walking route and time of day.

[1542] 5. Location Comparison

[1543] The terminal obtains the current real-time location information and transmits it to the server.

[1544] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1545] 6. Anomaly Detection

[1546] The AI ​​module detects any deviations from the current location from normal behavioral patterns, such as straying from a specific route or staying in an unspecified area for an extended period of time.

[1547] 7. Alerts

[1548] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location and the reason for the anomaly.

[1549] Specific examples

[1550] Watching over children going to school

[1551] 1. The user gives their child a GPS device.

[1552] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[1553] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[1554] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[1555] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[1556] 6. The user receives an alert and immediately checks on the safety of the child.

[1557] Preventing elderly people from wandering

[1558] 1. The user gives the elderly person a GPS device.

[1559] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[1560] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[1561] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[1562] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[1563] 6. The user receives an alert, checks the elderly person's condition, and takes action.

[1564] This system allows users to monitor the safety of children and the elderly in real time, and responds quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances.

[1565] The processing flow will be explained below.

[1566] Step 1:

[1567] The user attaches a GPS device to the subject (child or elderly person).

[1568] Step 2:

[1569] The device (smartphone or tablet) registers the GPS device through the app and enters the target person's information (name, age, contact details, etc.).

[1570] Step 3:

[1571] The terminal periodically (for example, every minute) acquires location information (latitude, longitude, timestamp) from the GPS device.

[1572] Step 4:

[1573] The terminal transmits the acquired location information to the server in real time.

[1574] Step 5:

[1575] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[1576] Step 6:

[1577] The AI ​​module installed on the server periodically analyzes the location information in the database and learns the subject's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[1578] Step 7:

[1579] The terminal transmits the current location information obtained in real time to the server.

[1580] Step 8:

[1581] The server passes the received current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1582] Step 9:

[1583] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended period of time in an unplanned location.

[1584] Step 10:

[1585] If an abnormality is detected, the server immediately sends an alert to the user's (guardian's or caregiver's) device.

[1586] Step 11:

[1587] The server includes in the alert message the current location information, the reason why the anomaly was detected, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[1588] Step 12:

[1589] The user checks the alert notification displayed on the device and takes appropriate action, such as contacting the child to check on their safety or heading to the scene.

[1590] Example 1

[1591] 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."

[1592] Conventional monitoring systems not only acquire the target's location information and transmit it to a server, but also analyze that location information, learn the target's daily behavioral patterns, and detect abnormalities. However, existing systems have difficulty detecting abnormalities in real time, and it takes a long time to issue an appropriate alert in an emergency. Furthermore, security during data transmission is insufficient, creating a risk of location information leaks. The present invention aims to solve these problems by providing a system that detects abnormalities more accurately and quickly, ensuring user safety.

[1593] 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.

[1594] In this invention, the server includes means for periodically acquiring location information of a target person, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and perform machine learning on the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, means for encrypting and transmitting the target person's location information, and means for sending an alert to the user terminal using push notification or SMS in an emergency. This enables highly accurate abnormality detection in real time, prompt alert issuance, and safe data transmission.

[1595] "Location information" is data about a subject's current location, including latitude, longitude, and timestamp.

[1596] "Means of acquisition" refers to the means of periodically collecting the subject's location information using a GPS device or terminal.

[1597] A "server" is a remote computer system that receives, stores, processes, etc. data.

[1598] The "transmitting means" is a means for sending data from the terminal to the server.

[1599] A "database" is a data management system that stores location information and allows it to be searched and updated as needed.

[1600] The "artificial intelligence module" is a software module that analyzes location information and learns daily behavior patterns.

[1601] "Machine learning" refers to algorithms and techniques that automatically learn patterns and trends based on large amounts of data.

[1602] The "means for detecting anomalies" is a means for determining whether the current location information deviates from the normal behavioral pattern.

[1603] The "means for issuing an alert" is a means for sending a notification to a user terminal when an abnormality is detected.

[1604] "Means for encryption and transmission" refers to means for encrypting data to protect location information from third parties and transmitting it securely to a server.

[1605] "Push notification" is a method for sending messages from a server to a user terminal in real time.

[1606] "SMS" stands for Short Message Service, a means of sending short text messages via mobile phones.

[1607] The present invention relates to a monitoring system that acquires location information of a target person, detects an abnormality, and issues an alert. A specific embodiment of this system will be described below.

[1608] Hardware and Software Configuration

[1609] Terminal

[1610] The device communicates with the subject's GPS device to obtain location information. The device periodically obtains latitude, longitude, and timestamps from the GPS device using Bluetooth or Wi-Fi connections. HTTPS is used to encrypt the obtained location information and send it securely to the server.

[1611] server

[1612] The server is a device that stores the received location information in a database and analyzes it using an artificial intelligence module. The server uses a relational database such as MySQL or PostgreSQL, and indexes the location information to enable efficient searches. The server is equipped with an artificial intelligence module using Python's Scikit-learn and TensorFlow, which uses machine learning to learn daily behavior patterns based on the accumulated location information.

[1613] Specific actions

[1614] 1. Acquisition and transmission of location information

[1615] The terminal communicates with a GPS device and periodically acquires location information (latitude, longitude, timestamp).

[1616] The device encrypts the acquired location information and sends it to the server using HTTPS.

[1617] 2. Location information storage and analysis

[1618] The server stores the received location information in a database.

[1619] The server's artificial intelligence module analyzes the accumulated location information and learns the subject's daily behavioral patterns, for example, by using K-Means clustering to identify the person's commute route, walking route, and time of day.

[1620] 3. Detecting anomalies and issuing alerts

[1621] The terminal again acquires the current real-time location information and transmits it to the server.

[1622] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1623] The artificial intelligence module detects any deviations in current location information from normal behavioral patterns as an anomaly.

[1624] When an anomaly is detected, the server immediately sends an alert to the user's device via push notification or SMS, and the notification includes the user's current location and the reason why the anomaly was detected.

[1625] Specific examples

[1626] Watching over children going to school

[1627] 1. The user gives their child a GPS device.

[1628] 2. The device will receive the child's location information from the GPS device via Bluetooth every minute. The location information includes latitude, longitude, and a timestamp.

[1629] 3. The device sends the encrypted location information to the server via HTTPS.

[1630] 4. The server stores the location information in a database, and the artificial intelligence module uses the data to learn the school route using K-Means clustering.

[1631] 5. If a child deviates from their usual route to school in real time, the artificial intelligence module will detect this as an anomaly.

[1632] 6. The server immediately sends a push notification to the user's smartphone, alerting them to the location. The notification includes information such as, "Your child has deviated from their normal route. Their current location is latitude x, longitude y."

[1633] Preventing elderly people from wandering

[1634] 1. The user gives the elderly person a GPS device.

[1635] 2. The device receives the elderly person's location information from the GPS device via Bluetooth every minute. The location information includes latitude, longitude, and timestamp.

[1636] 3. The device sends the encrypted location information to the server via HTTPS.

[1637] 4. The server stores the location information in a database, and the artificial intelligence module learns daily behavior patterns using K-Means clustering.

[1638] 5. If an elderly person is out and about and stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[1639] 6. The server immediately sends an alert to the user's smartphone via push notification or SMS. The notification contains information such as, "An elderly person has been outside their usual living area for an extended period of time. Their current location is latitude x, longitude y."

[1640] Example prompts for generative AI models

[1641] Prompt statement:

[1642] Describe a system that sends an alert if a child deviates from their usual route to school. This system uses a GPS device, a server, an artificial intelligence module, etc.

[1643] Prompt statement:

[1644] Describe a system that alerts elderly people if they are outside their usual living area for an extended period of time. The system uses GPS devices, a server, and an artificial intelligence module.

[1645] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1646] Step 1:

[1647] Obtaining location information

[1648] The terminal communicates with the subject's GPS device and periodically (e.g., every minute) obtains location information. The input is the latitude, longitude, and timestamp from the GPS device, and the output is the obtained location information. Specifically, the terminal reads information from the device via Bluetooth or Wi-Fi connection.

[1649] Step 2:

[1650] Location encryption

[1651] The device encrypts the acquired location information. The input is the location information acquired in step 1, and the output is the encrypted location information. Specifically, the data is secured using encryption algorithms such as AES or RSA.

[1652] Step 3:

[1653] Sending location information

[1654] The device sends encrypted location information to the server using HTTPS. The input is the encrypted location information, and the output is a notification to the server that the location information has been sent. Specifically, the data is sent to a RESTful API endpoint using a POST request.

[1655] Step 4:

[1656] Save location information

[1657] The server stores the received location information in a database. The input is the location information sent from the device, and the output is a notification that the information has been saved to the database. Specifically, the server uses an INSERT statement to store the location information in the database.

[1658] Step 5:

[1659] Learning behavioral patterns

[1660] The artificial intelligence module installed on the server analyzes the accumulated location information and performs machine learning to learn daily behavior patterns. The input is past location information obtained from a database, and the output is the learned behavior pattern. Specifically, it applies machine learning algorithms such as K-Means clustering.

[1661] Step 6:

[1662] Acquiring and sending real-time location information

[1663] The device again acquires the latest real-time location information and sends it to the server. The input is the current location information from the GPS device, and the output is a notification to the server that transmission has been completed. Specifically, the device again collects location information from the GPS device via Bluetooth or Wi-Fi, encrypts it, and sends it to the server.

[1664] Step 7:

[1665] Real-time location analysis

[1666] The server receives real-time location information and passes it on to an artificial intelligence module for analysis. The input is real-time location information, and the output is the analysis results. Specifically, it compares learned behavioral patterns with real-time location information to detect anomalies.

[1667] Step 8:

[1668] Anomaly detection

[1669] The AI ​​module detects anomalies by identifying deviations from normal behavioral patterns in real-time location information. The input is real-time location information and learned patterns, and the output is the anomaly detection result. Specific operations include using support vector machines (SVM) and other anomaly detection algorithms.

[1670] Step 9:

[1671] Alert issuance

[1672] If an anomaly is detected, the server immediately sends an alert to the user device. The input is the anomaly detection result, and the output is an alert notification to the user device. Specifically, the server sends a push notification or SMS using Firebase Cloud Messaging (FCM) or Twilio.

[1673] Through the technology and specific actions used at each step, the system can monitor the safety of the subject in real time, allowing for quick response in emergencies and greatly reducing the risk of accidents or disappearances.

[1674] (Application example 1)

[1675] 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."

[1676] In the food delivery industry, the safety of delivery staff and efficient operation management are important issues. Conventional methods lack a system that can track delivery staff's location information in real time and immediately detect deviations from the planned route or abnormal behavior. As a result, it is difficult to respond quickly to delays or problems. This can lead to a decline in service quality and a decrease in customer satisfaction.

[1677] 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.

[1678] In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the behavioral patterns of the target person (daily behavior patterns), means for comparing the current location information with the learned behavioral patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, and means for tracking the location information of delivery staff, detecting abnormalities, and notifying an administrator in real time for delivery services. This makes it possible to track the location information of delivery staff in real time in the food delivery industry, quickly detect delays and route deviations, and immediately take appropriate measures.

[1679] "Location information" is data indicating the subject's current location, such as latitude, longitude, and timestamp.

[1680] "Server" means a computing device for receiving, storing, and analyzing location information.

[1681] A "database" is a system that systematically stores and manages acquired location information and related data.

[1682] The "artificial intelligence module" is a group of programs and algorithms that analyze location information and learn the subject's daily behavioral patterns.

[1683] A "user terminal" is a communication device such as a smartphone or dedicated device for receiving alerts.

[1684] A "delivery service" is a business service that delivers meals or goods to a specified location.

[1685] "Delivery staff" refers to personnel whose job is to transport goods and food to provide delivery services.

[1686] "Administrator" refers to the person responsible for supervising and managing delivery staff and the overall system in the delivery service.

[1687] "Real-time tracking" refers to monitoring the location of delivery staff in real time with almost no delay.

[1688] An "alert" is a warning notification sent to a user terminal when an abnormality is detected.

[1689] The present invention relates to a system for tracking the location information of delivery staff in the food delivery industry in real time, detecting abnormalities, and notifying an administrator of an alert. Specific embodiments of the present invention will be described below.

[1690] System Configuration

[1691] The system consists of the following elements:

[1692] 1. Terminal

[1693] The smartphone functions as a GPS device, periodically obtaining the location information of the delivery staff (for example, every minute).

[1694] The acquired location information (latitude, longitude, timestamp) is sent to a server via the Internet.

[1695] 2. Server

[1696] The received location information is stored in a database and managed, including past data.

[1697] The server is equipped with an artificial intelligence module that analyzes the accumulated location information to learn the delivery staff's daily delivery routes and behavioral patterns.

[1698] 3. Database

[1699] Systematically manage location information, delivery route data, etc. stored on the server.

[1700] 4. Artificial Intelligence Module

[1701] It includes software algorithms for analyzing location data and learning the behavioral patterns of subjects.

[1702] 5. User device (administrator smartphone)

[1703] Receive alerts from the server in real time.

[1704] Processing flow

[1705] The server stores the location information acquired by the smartphone in a database and analyzes behavioral patterns using an artificial intelligence module. If an abnormality is detected, the server immediately sends an alert to the administrator's smartphone (user device).

[1706] Hardware and software used

[1707] Hardware

[1708] Smartphone: Obtains the location information of delivery staff and sends it to the server.

[1709] Server: Stores and analyzes data.

[1710] software

[1711] Python-based server application: manages, stores, and analyzes location information.

[1712] Python machine learning libraries (e.g., scikit-learn and TensorFlow): Implement programs that learn behavioral patterns and detect anomalies.

[1713] Mobile application: An app for delivery service managers to receive alerts.

[1714] Specific examples

[1715] For example, if a delivery staff member deviates significantly from their normal delivery route and begins heading out into the suburbs, the system will detect the anomaly and send an alert to the administrator stating, "A delivery staff member has deviated from the standard route. Their current location is latitude 35.5, longitude 135.8." In this way, abnormal behavior can be detected early, allowing for appropriate action to be taken promptly.

[1716] Prompt Sentence Examples

[1717] Here are some example prompts you can give to your generative AI model:

[1718] "Generate Python code for an algorithm that detects anomalous delivery staff routes, such as the following."

[1719] This prompt statement can be used to help generate specific program code.

[1720] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1721] Step 1:

[1722] The terminal periodically obtains the location information of the delivery staff. Specifically, it uses the smartphone's GPS function to obtain the current latitude, longitude, and timestamp every minute. The input is GPS data, and the output is location information.

[1723] Step 2:

[1724] The device sends the acquired location information to the server. The location information is sent via the Internet in JSON format. The input is the acquired location information, and the output is the data sent to the server.

[1725] Step 3:

[1726] The server stores the received location information in a database. The location information is accumulated and managed in the database along with past data. The input is the received location information, and the output is the data stored in the database.

[1727] Step 4:

[1728] The server uses the stored location information to learn the delivery staff's daily delivery routes and behavioral patterns. Specifically, it uses Python's machine learning library to analyze time periods and delivery route patterns. The input is the location information in the database, and the output is the learned behavioral patterns.

[1729] Step 5:

[1730] The device transmits the current location information acquired in real time to the server. The input is the real-time location information, and the output is the data transmitted to the server.

[1731] Step 6:

[1732] The server compares the current location with the learned behavioral patterns. It uses an artificial intelligence module to perform pattern matching and determine if the current location matches the learned behavioral patterns. The input is the current location and the learned behavioral patterns, and the output is the anomaly detection results.

[1733] Step 7:

[1734] If the server detects an anomaly, it immediately sends an alert to the administrator's user device. The alert includes the current location information and the reason for the anomaly. The input is the anomaly detection result, and the output is the alert message sent to the administrator's smartphone.

[1735] 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.

[1736] The present invention relates to a monitoring system that collects location information of subjects (children and elderly people) and detects abnormalities, and further optimizes alerts by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the present invention are described below.

[1737] System configuration

[1738] The system mainly consists of the following elements:

[1739] 1. A GPS device that periodically acquires location information.

[1740] 2. A device that sends the acquired location information to a server.

[1741] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[1742] 4. A function that sends an alert to the user's device when an abnormality is detected.

[1743] 5. An emotion engine that recognizes user emotions and collects responses.

[1744] Program processing

[1745] 1. Obtaining location information

[1746] The terminal periodically (for example, every minute) acquires the target person's location information from the GPS device. This location information includes latitude, longitude, and timestamp.

[1747] 2. Data transmission

[1748] The terminal transmits the acquired location information to the server.

[1749] 3. Data storage

[1750] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[1751] 4. Learning behavioral patterns

[1752] An artificial intelligence module installed on the server analyzes the accumulated location information and learns the target person's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[1753] 5. Location Comparison

[1754] The terminal obtains the current real-time location information and transmits it to the server.

[1755] The server passes the current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1756] 6. Anomaly Detection

[1757] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended period of time in an unplanned location.

[1758] 7. Alerts

[1759] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location, the reason for the anomaly, and recommended countermeasures (e.g., contacting the user for confirmation, heading to the site, etc.).

[1760] 8. Emotional Recognition

[1761] Upon receiving the alert, the user's device uses an emotion engine to recognize the user's emotional response, which includes extracting emotions from the user's facial expressions, voice, or text data.

[1762] 9. Collecting and analyzing emotional responses

[1763] The server collects and stores in a database the user's emotional responses to the alerts.

[1764] The emotion engine analyzes the collected emotion data and optimizes the content and notification method of the next alert.

[1765] Specific examples

[1766] Watching over children going to school

[1767] 1. The user gives their child a GPS device.

[1768] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[1769] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[1770] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[1771] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[1772] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1773] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[1774] Preventing elderly people from wandering

[1775] 1. The user gives the elderly person a GPS device.

[1776] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[1777] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[1778] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[1779] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[1780] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1781] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[1782] This system allows users to monitor the safety of children and the elderly in real time, and can respond quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances. In addition, by combining it with an emotion engine, it becomes possible to issue alerts that take into account the user's emotional reactions, which is expected to lead to more appropriate and efficient responses.

[1783] The processing flow will be explained below.

[1784] Step 1:

[1785] The user attaches a GPS device to the subject (child or elderly person).

[1786] Step 2:

[1787] The device (smartphone or tablet) registers the GPS device through the app and inputs the target person's information, including name, age, and contact details.

[1788] Step 3:

[1789] The terminal periodically (for example, every minute) acquires location information (latitude, longitude, timestamp) from the GPS device.

[1790] Step 4:

[1791] The terminal transmits the acquired location information to the server.

[1792] Step 5:

[1793] The server stores the received location information in a database, which manages location data for each individual and accumulates past history as well.

[1794] Step 6:

[1795] The AI ​​module installed on the server periodically analyzes the location information in the database and learns the subject's daily behavioral patterns, for example, identifying the route a child takes to school or the walking route and time of day an elderly person takes.

[1796] Step 7:

[1797] The terminal transmits the current location information obtained in real time to the server.

[1798] Step 8:

[1799] The server passes the received current location information to an artificial intelligence module, which compares it with learned behavioral patterns.

[1800] Step 9:

[1801] The AI ​​module detects anomalies when the current location significantly deviates from learned behavioral patterns, such as a child straying from their usual school route or an elderly person spending an extended amount of time in an unplanned location.

[1802] Step 10:

[1803] If an abnormality is detected, the server immediately sends an alert to the user's (guardian's or caregiver's) device.

[1804] Step 11:

[1805] The server includes in the alert message the current location information, the reason why the anomaly was detected, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[1806] Step 12:

[1807] When receiving an alert, the user's device recognizes the user's emotion using an emotion engine, which extracts emotions from the user's facial expressions, voice, or text data.

[1808] Step 13:

[1809] The server collects and stores in a database the user's emotional responses to the alerts.

[1810] Step 14:

[1811] The emotion engine analyzes the collected emotion data and optimizes the content and notification method of the next alert, enabling more appropriate alerts to be issued that take the user's emotions into consideration.

[1812] Specific examples

[1813] Watching over children going to school

[1814] Step 1:

[1815] The user gives the child a GPS device.

[1816] Step 2:

[1817] The device obtains the child's location information from the GPS device every minute and sends it to the server.

[1818] Step 3:

[1819] The server stores the location information in a database, and an artificial intelligence module learns the student's route to school.

[1820] Step 4:

[1821] If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[1822] Step 5:

[1823] The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[1824] Step 6:

[1825] When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1826] Step 7:

[1827] The server collects the user's emotional responses and optimizes the content of the next alert.

[1828] Preventing elderly people from wandering

[1829] Step 1:

[1830] The user provides the elderly person with a GPS device.

[1831] Step 2:

[1832] The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[1833] Step 3:

[1834] The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[1835] Step 4:

[1836] If an elderly person stays outside their usual living area for an extended period of time, the artificial intelligence module will detect this as an abnormality.

[1837] Step 5:

[1838] The server detects any abnormality and immediately sends an alert to the user's (family member's) smartphone.

[1839] Step 6:

[1840] When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1841] Step 7:

[1842] The server collects the user's emotional responses and optimizes the content of the next alert.

[1843] This system allows users to monitor the safety of children and the elderly in real time, and can respond quickly if an abnormality is detected, significantly reducing the risk of accidents or disappearances. In addition, by combining it with an emotion engine, it becomes possible to issue alerts that take into account the user's emotional reactions, which is expected to lead to more appropriate and efficient responses.

[1844] Example 2

[1845] 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."

[1846] Conventional monitoring systems have a problem in that, despite acquiring the target's location information, they do not optimize alerts to take into account the target's emotional state or the user's reaction. This can lead to false alerts and delayed appropriate responses. The present invention aims to solve these problems and improve alert accuracy and user satisfaction.

[1847] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to the user terminal when an abnormality is detected, means for collecting the user's emotional response using an emotion engine that recognizes the user's emotions, and means for analyzing the user's emotional response to the alert and optimizing the content of the next alert and the notification method. This makes it possible to issue an alert that takes into account not only the target person's location information but also the user's emotional state, thereby reducing false alarms and enabling prompt and appropriate responses.

[1848] "Location information" is data indicating the subject's current location, and includes latitude, longitude, and a timestamp.

[1849] A "server" is a computer system that aggregates, stores, and processes acquired data.

[1850] A "database" is a system for systematically storing, searching, and managing information.

[1851] The "artificial intelligence module" is software that analyzes collected data and performs pattern recognition and anomaly detection.

[1852] "Behavioral patterns" refer to specific patterns of a subject's daily travel routes and behavior.

[1853] "Abnormal" refers to a significant deviation from learned patterns of behavior, including a subject leaving their usual route or staying in an unexpected location for an extended period of time.

[1854] An "alert" is a warning message that is sent to the user when an abnormality is detected.

[1855] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[1856] An "emotion engine" is software for recognizing and analyzing a user's emotional state.

[1857] "Emotional response" refers to the emotional reaction a user shows when receiving an alert, and is extracted from facial expressions, voice, and text data.

[1858] The present invention relates to a monitoring system that mainly acquires location information, detects abnormalities, issues alerts, and recognizes emotions. Specific embodiments of the present invention are described below.

[1859] System configuration

[1860] The system mainly consists of the following elements:

[1861] 1. GPS devices that periodically acquire location information

[1862] 2. The device that sends the acquired location information to the server

[1863] 3. A server that stores the received location information in a database and analyzes it using an artificial intelligence module.

[1864] 4. A function that issues an alert to the user device when an abnormality is detected

[1865] 5. Emotion engine that recognizes user emotions and collects responses

[1866] Details of each element

[1867] GPS devices and terminals

[1868] The device periodically obtains location information from the target person's GPS device. This location information includes latitude, longitude, and a timestamp. For example, the device obtains location information from the GPS device every minute on the way to school.

[1869] Servers and Databases

[1870] The server receives the location information sent from the device and stores it in a database. The database is used to accumulate and manage the location history for each subject, making it possible to analyze the subject's behavioral patterns over a long period of time.

[1871] Artificial Intelligence Module

[1872] The AI ​​module installed on the server analyzes the location information stored in the database and learns the subject's daily behavioral patterns. For example, it identifies a child's route to school or an elderly person's walking route and the time of day. This creates a foundation for determining the subject's normal behavior range and abnormal behavior.

[1873] Anomaly detection and alert generation

[1874] The device again acquires its current real-time location information and sends it to the server. The server then passes the current location information to an AI module, which compares it with the learned behavioral patterns. If the current location information significantly deviates from the learned behavioral patterns, it detects this as an anomaly. For example, this could include a child straying from their usual school route or an elderly person staying in an unplanned location for an extended period of time.

[1875] When an anomaly is detected, the server immediately sends an alert to the user's device. The alert message includes the user's current location, the reason for the anomaly, and recommended actions to take (e.g., contacting the device for confirmation, heading to the location, etc.).

[1876] Emotion Engine

[1877] When receiving an alert, the user's device uses an emotion engine to recognize the user's emotional response. The emotion engine extracts emotions from the user's facial expressions, voice, or text data. For example, after receiving an alert message, the emotion engine analyzes the user's facial expressions and voice using the smartphone's camera and microphone.

[1878] Collecting and analyzing emotional responses

[1879] The server collects the user's emotional response to the alert and stores it in a database. The emotion engine analyzes the collected emotional data and optimizes the content and notification method of the next alert. For example, if the user feels anxious about the alert, the next alert notification will include more specific countermeasures.

[1880] Specific examples

[1881] Watching over children going to school

[1882] 1. The user gives their child a GPS device.

[1883] 2. The device obtains the child's location information from the GPS device every minute and sends it to the server.

[1884] 3. The server stores the location information in a database, and the artificial intelligence module learns the school route.

[1885] 4. If a child takes a route that differs from their usual route to school, the artificial intelligence module will detect this as an anomaly.

[1886] 5. The server detects the abnormality and immediately sends an alert to the user's (guardian's) smartphone.

[1887] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1888] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[1889] Preventing elderly people from wandering

[1890] 1. The user gives the elderly person a GPS device.

[1891] 2. The terminal obtains the elderly person's location information from the GPS device every minute and sends it to the server.

[1892] 3. The server stores the location information in a database, and an artificial intelligence module learns daily behavior patterns.

[1893] 4. If an elderly person stays outside their usual living area for a long period of time, the artificial intelligence module will detect this as an abnormality.

[1894] 5. The server detects the abnormality and immediately sends an alert to the user's (family member's) smartphone.

[1895] 6. When an alert is received, the user's device uses an emotion engine to recognize the user's emotion.

[1896] 7. The server collects the user's emotional response and optimizes the content of the next alert.

[1897] Examples of prompt statements

[1898] Prompt: "Please explain how parents are notified when their child deviates from their normal school route and how to recognize their emotions and optimize responses."

[1899] As a result, this system can monitor the location information of the target person in real time and respond quickly when an abnormality is detected.In addition, by combining it with an emotion engine, it is possible to issue alerts that take the user's emotional response into consideration, which is expected to lead to more appropriate and efficient responses.

[1900] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1901] Step 1: Obtaining location information

[1902] The device obtains location information every minute from the subject's GPS device, including latitude, longitude, and a timestamp.

[1903] (Input): Location data (latitude, longitude, timestamp) obtained from a GPS device

[1904] (Output): Data packet containing the obtained location information

[1905] (Specific operation): The device automatically obtains location data from the GPS device every minute and temporarily stores the data.

[1906] Step 2: Sending data

[1907] The device automatically transmits the acquired location information to the server immediately after the location information is acquired.

[1908] (Input): Location data stored on the device

[1909] (Output): Location data sent to the server

[1910] (Specific operation): The device uses Wi-Fi or mobile data communication to send a data packet containing location information to the server's fixed IP address.

[1911] Step 3: Save your data

[1912] The server stores the received location information in a database, and a location history is accumulated for each subject.

[1913] (Input): Location data received by the server

[1914] (Output): Location information stored in the database

[1915] (Specific operation): The server analyzes the received location data and adds new location information to the corresponding subject's database entry.

[1916] Step 4: Learning behavioral patterns

[1917] An artificial intelligence module installed on the server analyzes the accumulated location information, learns the target person's daily behavior patterns, and generates a predictive model.

[1918] (Input): Past location data stored in the database

[1919] (Output): Learned behavioral pattern model

[1920] (Specific operation): The AI ​​module applies machine learning algorithms to analyze past behavioral data to identify the subject's daily route and time of day, and update the behavioral pattern model.

[1921] Step 5: Compare locations

[1922] The terminal again acquires the current real-time location information and transmits it to the server.

[1923] The server compares the current location information with the learned behavioral patterns.

[1924] (Input): Real-time location data, learned behavioral pattern model

[1925] (Output): The result of determining whether the location information is normal or abnormal

[1926] (Specific operation): The device sends newly acquired real-time location information to the server, which then passes this data to the AI ​​module and compares it with the learned model.

[1927] Step 6: Detect anomalies

[1928] The artificial intelligence module detects an anomaly if the current location information deviates from the learned behavioral patterns.

[1929] (Input): Current location information, learned behavior patterns

[1930] (Output): Anomaly detection flag

[1931] (Specific operation): The AI ​​module evaluates whether the current location information deviates from the learned pattern by more than a certain threshold, and sets an anomaly detection flag if an anomaly is detected.

[1932] Step 7: Triggering an alert

[1933] When an anomaly is detected, the server immediately sends an alert to the user's device, which includes the user's current location, the reason for the anomaly, and recommended countermeasures.

[1934] (Input): Anomaly detection flag, current location information

[1935] (Output): Alert notification to user device

[1936] (Specific operation): When an abnormality is detected, the server generates an alert message and sends it to the user's smartphone as a push notification. The alert message contains specific content such as "Your child has deviated from their normal route. Please contact us to check or go to the location."

[1937] Step 8: Recognize emotions

[1938] When the user's device receives an alert, it activates an emotion engine and recognizes emotions from the user's facial expressions and voice.

[1939] (Input): Alert message, user's real-time facial expression and voice data

[1940] (Output): Recognized user emotion data

[1941] (Specific operation): After receiving an alert, the smartphone's camera and microphone are used to collect the user's facial expressions and voice, which are then analyzed by the emotion engine to recognize the user's emotional state.

[1942] Step 9: Collect and analyze emotional responses

[1943] The server collects the user's emotional response to the alert and stores it in a database. The emotion engine uses this information to optimize the content and notification method of the next alert.

[1944] (Input): Recognized user emotion data

[1945] (Output): Optimized alert content and notification method

[1946] (Specific operation): The server receives data from the emotion engine and stores it in a database. For subsequent alerts, the content and method of notifications (for example, more detailed instructions or reassuring messages) are optimized to take into account the user's emotional response.

[1947] (Application example 2)

[1948] 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."

[1949] While conventional monitoring systems are capable of acquiring location information of the target and detecting abnormalities, they have problems optimizing alerts to take appropriate action when an abnormality occurs. In particular, notifications are sent uniformly without considering the emotional state of the alert recipient, which can cause excessive stress to the recipient. In addition, false positives can cause anxiety due to meaningless alerts. The present invention aims to solve these problems and provide a more appropriate and efficient monitoring system.

[1950] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1951] In this invention, the server includes means for periodically acquiring location information, means for transmitting the acquired location information to the server, means for the server to store the location information in a database, means for an artificial intelligence module installed in the server to analyze the location information and learn the target person's daily behavior patterns, means for comparing the current location information with the learned behavior patterns to detect abnormalities, means for issuing an alert to a user terminal when an abnormality is detected, means for installing an emotion recognition engine in the user terminal to recognize the user's emotion when an alert is received, and means for collecting the user's emotional reactions and optimizing the alert content and notification method. This makes it possible to issue an alert that reflects the user's emotional state when an abnormality occurs, reducing the burden on the recipient and enabling a quick and appropriate response.

[1952] "Means for periodically obtaining location information" refers to means for obtaining location information such as GPS from equipment or devices carried by the subject at regular intervals.

[1953] The "means for transmitting the acquired location information to a server" refers to a means for transmitting the target person's location information to a server via the Internet or a communication network.

[1954] "Means for the server to store location information in a database" refers to a means for storing received location information on the server for a long period of time, making it possible to refer to and analyze it later.

[1955] "Means for an artificial intelligence module installed on a server to analyze location information and learn the target person's daily behavioral patterns" refers to a means for analyzing received location information and using a machine learning algorithm to extract and learn the target person's usual behavioral patterns.

[1956] "Means for detecting abnormalities by comparing current location information with learned behavioral patterns" refers to means for comparing location information acquired in real time with already learned behavioral patterns, and determining that an abnormality exists if there is any deviation.

[1957] The "means for issuing an alert to a user terminal when an abnormality is detected" refers to a means for sending a notification or warning to a device held by a user when an abnormality is detected.

[1958] "Means of equipping a user device with an emotion recognition engine and recognizing the user's emotion when an alert is received" refers to a means of equipping a user device with an engine that recognizes and analyzes the user's emotional state when an alert is notified.

[1959] "Means for collecting users' emotional responses and optimizing alert content and notification methods" refers to means for collecting and analyzing users' emotional data and adjusting the alert content and notification methods from the next time onwards based on the results.

[1960] The system of the present invention collects and analyzes the location information of a target person, and optimizes alerts by taking into account the user's emotions when an abnormality is detected. This system is composed of the following internal components and their respective functions.

[1961] System configuration

[1962] 1. Periodic acquisition of location information

[1963] The equipment or device carried by the subject uses GPS to acquire location information at regular intervals (e.g., every minute), which includes latitude, longitude, and a timestamp.

[1964] 2. Sending location information to the server

[1965] The acquired location information is sent to a server via a network. The Internet is used for communication, and encryption technology (e.g., SSL / TLS) is preferably used as needed.

[1966] 3. Saving to the database

[1967] The server stores the received location information in a database, which manages data in chronological order and also keeps a history of past events.

[1968] 4. Learning behavioral patterns using an artificial intelligence module

[1969] The server's installed artificial intelligence module analyzes the accumulated location data and learns the subject's normal daily behavior patterns. For example, a machine learning model can be built using TensorFlow or Keras.

[1970] 5. Anomaly Detection

[1971] The system compares location information acquired in real time with learned behavioral patterns and detects any deviations as an anomaly. This makes it possible to immediately detect deviations, such as when a person deviates from their usual school route.

[1972] 6. Alerts

[1973] When an anomaly is detected, the server immediately sends an alert to the user's device, which includes the current location, the reason for the anomaly, and a recommended course of action (e.g., contacting the user for confirmation, visiting the site, etc.).

[1974] 7. Emotion Recognition Engine

[1975] When an alert is issued, the user device uses an emotion recognition engine to analyze the user's emotional response, using facial expression recognition (e.g., OpenCV, DeepFace) and voice recognition (e.g., Google Cloud Speech-to-Text) technologies.

[1976] 8. Collecting and optimizing emotional responses

[1977] The recognized emotion data is sent to the server and stored in a database, and the content and notification method for future alerts are optimized based on this data.

[1978] Specific hardware and software names to be used

[1979] Hardware: GPS devices, smartphones or mobile communication devices, servers

[1980] Software: TensorFlow, Keras, OpenCV, DeepFace, Google Cloud Speech-to-Text, Flask or FastAPI, SSL / TLS encryption technology

[1981] Examples of concrete examples and prompts

[1982] Specific examples

[1983] If an elderly person stays outside their usual living area for an extended period of time, the system detects this as an abnormality and immediately sends an alert to the family member's smartphone. The alert includes the family member's current location and details of the abnormality. When the user checks the alert, the smartphone's camera is used to capture facial expressions and analyze them with an emotion recognition engine. The recognized emotion data is sent to a server and used to optimize the content of future notifications.

[1984] Prompt Sentence Examples

[1985] "My father has been in an unusual location for an extended period of time. Please suggest ways to check on him."

[1986] This embodiment of the present invention not only ensures the safety of the subject in real time, but also enables appropriate responses that take into account the user's emotions.

[1987] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1988] Step 1:

[1989] The terminal uses a GPS device to obtain the subject's latitude, longitude, and timestamp. The input is raw data from the GPS device, and the output is analyzed location information. Specifically, the terminal queries the GPS device for location information every minute and obtains the data.

[1990] Step 2:

[1991] The device sends the acquired location information to the server. The input is the location information acquired in step 1, and the output is data transfer to the server. Specifically, the device uses an HTTP POST request to send the location information to the server in JSON format.

[1992] Step 3:

[1993] The server stores the received location information in a database. The input is the location information sent from the device, and the output is storage in the database. Specifically, it formats the location data appropriately and executes an INSERT statement into a database such as MySQL or PostgreSQL.

[1994] Step 4:

[1995] The artificial intelligence module installed on the server analyzes the accumulated location information and learns the subject's normal daily behavior patterns. The input is past location information data, and the output is a learned behavior pattern model. Specifically, it uses TensorFlow and Keras to train a machine learning model based on the location information data.

[1996] Step 5:

[1997] The server compares location information acquired in real time with learned behavioral patterns to detect anomalies. The input is real-time location information and the learned model, and the output is the presence or absence of anomalies. Specifically, newly acquired location information is input into the learned model and classified as normal or abnormal.

[1998] Step 6:

[1999] If the server detects an anomaly, it immediately sends an alert to the user device. The input is the fact that an anomaly has been detected and detailed information about it, and the output is an alert notification to the user device. Specifically, the server uses an HTTP POST request to send the alert information to the user device.

[2000] Step 7:

[2001] The user device uses an emotion recognition engine to recognize the user's emotions when receiving an alert. The input is the user's facial expression or voice data, and the output is the recognized emotion data. Specifically, OpenCV and DeepFace are used to analyze the facial expression data obtained from the camera.

[2002] Step 8:

[2003] The user device sends the recognized emotion data to the server. The input is the emotion data obtained from the emotion recognition engine, and the output is the data transfer to the server. Specifically, the emotion data is sent to the server in JSON format using an HTTP POST request.

[2004] Step 9:

[2005] The server stores the collected emotion data in a database and optimizes the alert content and notification method. The input is the emotion data sent from the user's device, and the output is the optimization of the alert content from the next time onwards. Specifically, the server accumulates emotion data and uses this data to adaptively change the notification method when the next alert is generated.

[2006] 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.

[2007] 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.

[2008] 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.

[2009] 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.

[2010] 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.

[2011] 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.

[2012] 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).

[2013] 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.

[2014] 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."

[2015] 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.

[2016] 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...

Claims

1. A means for periodically obtaining location information; means for transmitting the acquired location information to a server; a means for the server to store the location information in a database; An artificial intelligence module installed on the server analyzes location information and learns the target person's daily behavior patterns; means for comparing current location information with learned behavioral patterns to detect anomalies; means for issuing an alert to a user terminal when an abnormality is detected; A system including:

2. The system of claim 1 , wherein the data including the location information is stored in a database.

3. The system according to claim 1 , wherein when an abnormality is detected, a countermeasure is included in the alert.

Images