system

Abstract

Provide a system. 【Solution means】 Means for acquiring activity data of organisms and suspicious persons from a plurality of detection devices installed within a protected area; Means for processing the acquired data and performing preprocessing; Means for accumulating the preprocessed data and storing it in a database including time-series information; Means for learning the normal behavior patterns of organisms based on the accumulated data; Means for monitoring newly acquired data in real time and detecting abnormal behavior; Means for generating an alarm based on the detected abnormal behavior and sending a notification; Means for push-notifying the alarm to terminals used by citizens and administrators to promote safety in parks and natural areas within the city; A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Monitoring the behavior of wild animals in their natural environment is difficult to perform efficiently to every corner of vast protected areas because human monitoring capabilities are limited. Also, these areas are often targeted by poaching and illegal activities, and a prompt response is required, but conventional methods have difficulty in immediate response and the effects are insufficient. Furthermore, there has been a lack of the ability to process a large amount of data in real time and quickly detect abnormal behavior of animals. The purpose of this invention is to solve these problems by utilizing AI technology and enable efficient and immediate protection activities.

Means for Solving the Problems

[0005] To solve the above problems, this invention provides a system that includes means for acquiring activity data of animals and suspicious persons from multiple detection devices installed within a protected area, and has a function for processing and pre-processing this data. Furthermore, the pre-processed data is stored in a database, enabling time-series analysis. This allows the system to learn the normal behavior patterns of animals and detect abnormal behavior in real time by comparing it with newly acquired data. When abnormal behavior is detected, the system generates an alarm, sends a notification to a designated terminal, and prompts immediate action, enabling efficient monitoring of protected areas over a wide area.

[0006] A "detection device" refers to devices such as sensors and cameras that are installed to detect the movement and activity of animals or suspicious individuals.

[0007] "Activity data" refers to data that includes location information, movement, audio, images, body temperature, and other information related to animals or suspicious individuals.

[0008] "Preprocessing" refers to the data processing steps involved in shaping acquired raw data into an analyzable format, including noise reduction and format conversion.

[0009] A "database" refers to a collection of information that allows for the efficient storage and retrieval of pre-processed data.

[0010] "Behavioral patterns" refer to models that show the regularity and tendencies of the normal movement and activity in a particular animal species or individual.

[0011] "Real-time monitoring" refers to a technology that monitors the movements of animals and suspicious individuals by immediately processing and analyzing newly acquired data at the present time.

[0012] "Abnormal behavior" refers to a condition in which an animal exhibits movements or activities that deviate from its normal behavioral patterns.

[0013] An "alarm" refers to a notification or warning message generated when abnormal or suspicious activity is detected.

[0014] "Terminal" refers to a computer, smartphone, or tablet device used to receive and display alarms.

[0015] "Notification" refers to a message sent to a device to convey information about detected abnormal behavior or circumstances. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention aims to protect wildlife and monitor poaching activities in extensive nature reserves, and provides an automated monitoring system utilizing AI technology. By installing multiple detection devices within the area and monitoring animal activity and suspicious activity, this system can efficiently detect anomalies in real time and take immediate countermeasures.

[0038] System Configuration

[0039] This system is designed to first use sensors and cameras as detection devices to sense animal movement and the presence of people, and to collect the data. The sensors collect temperature, vibration, and location data, while the cameras acquire still images and videos. This collected data is transmitted to a dedicated server.

[0040] Data processing and analysis

[0041] The server preprocesses the received data, removing noise and formatting it. The preprocessed data is stored in a database and structured as time-series information. This allows machine learning models to be applied to identify the animals' normal behavioral patterns. The server compares these models with newly acquired data in real time to detect abnormal behavior.

[0042] Anomaly detection and alarm generation

[0043] The server automatically generates an alarm when it detects abnormal behavior or suspicious activity. The alarm includes the type, time, location, and video data of the detected anomaly. This information is immediately sent as a push notification to the designated device.

[0044] Response and Management

[0045] The terminal receives notifications from the server and prompts the user to take appropriate action. The user, such as a ranger or administrator in a protected area, uses the received information to conduct an on-site investigation and respond to the alert as needed.

[0046] Specific example

[0047] For example, suppose a camera in a protected area captures a herd of animals deviating from their usual migration route one night. The server analyzes this unusual movement in real time and generates an alert as an anomaly detection. The terminal receives this alert and sends a push notification to the ranger. The ranger, as a user, can then rush to the scene, check on the animals, and investigate the cause of the unusual behavior.

[0048] In this way, the present invention enhances efficiency in animal protection and monitoring of illegal activities, enabling a rapid and accurate response.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] Data collection

[0052] The server periodically receives data on animal and intruder activity from each detection device within the protected area. This includes location, movement, and temperature data from sensors, as well as image and video data from cameras.

[0053] Step 2:

[0054] Data preprocessing

[0055] The server denoises the collected raw data and formats it into a standard format. This improves the quality of the data and makes it suitable for subsequent analysis.

[0056] Step 3:

[0057] Data storage

[0058] The server stores the pre-processed data as time-series information in the database. Here, metadata such as associated timestamps and location information is attached to the data.

[0059] Step 4:

[0060] Learning of normal behavioral patterns

[0061] The server uses accumulated data to learn the animals' typical behavioral patterns. This process employs machine learning algorithms to model the animals' habits and general movement tendencies.

[0062] Step 5:

[0063] Real-time monitoring and data analysis

[0064] The server constantly receives new data in real time and compares it with learned behavioral patterns. This makes it possible to quickly detect movements that deviate from normal behavior.

[0065] Step 6:

[0066] Anomaly detection and alarm generation

[0067] When the server detects unusual behavior or suspicious individuals, it generates an alert that includes the type, location, and time of the anomaly. This alert information is processed quickly, and the process moves to the next step.

[0068] Step 7:

[0069] Notification distribution

[0070] The terminal receives alerts sent from the server and distributes them as push notifications to rangers and administrators. The notifications include the alert details and information necessary for taking action.

[0071] Step 8:

[0072] Response and Action

[0073] Users can check notifications received on their devices and take necessary actions on-site. For example, they can quickly investigate suspicious individuals or rescue animals. Rangers can also request further investigation or assistance depending on the situation on the ground.

[0074] (Example 1)

[0075] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0076] Regarding wildlife conservation in extensive nature reserves, current monitoring systems face challenges such as insufficient real-time detection of abnormal behavior and difficulty in responding efficiently and quickly. Furthermore, problems such as wasted responses due to false alarms and the failure to transmit warnings when needed have been pointed out. It is necessary to resolve these challenges and achieve effective monitoring of wildlife and illegal activities.

[0077] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0078] In this invention, the server includes means for acquiring information on the activities of living organisms and humans, means for performing noise reduction and formatting, and means for storing the information in an information structure that includes time-series information. This enables real-time monitoring within nature reserves, allowing for early detection and prompt response to abnormal behavior.

[0079] A "detection device" is a device installed to detect information about the activity of living organisms or people within a specific area and to transmit that information to a server.

[0080] "Activity information" refers to data that shows physical changes such as the movement, location, vibration, and temperature of living organisms and people.

[0081] "Denoising and formatting" is the process of removing unnecessary data from acquired information and converting it into a consistent form.

[0082] "Information structure" refers to the format in which information is organized and stored chronologically within a database or other storage system.

[0083] A "biological behavior model" refers to data and algorithms that learn the normal behavioral patterns of organisms and use that to determine the abnormality of new behaviors.

[0084] An "alarm" is a notification or alert generated to inform of abnormal behavior or potential danger.

[0085] A "receiving device" is a device used to receive alarms and notifications transmitted from a server, and includes, for example, smartphones and tablets.

[0086] A "conservationist" refers to an individual or organization responsible for the protection and management of wildlife within a nature reserve.

[0087] In implementing this invention, the collaboration between a server, a terminal, and a user is primarily utilized. The terminal includes multiple sensors and cameras placed within an area. These devices detect biological and human activity information in real time and transmit this information to the server. The sensors can detect various physical changes such as temperature, vibration, and location data, while the cameras can acquire visual data.

[0088] The server receives information transmitted from these terminals and performs preprocessing, such as denoising and formatting the data, using a generative AI model. It then structures the information as time-series data and stores it. This process contributes to efficient information utilization and rapid detection of abnormal behavior.

[0089] For example, if a camera captures a group of animals deviating from their usual movement pattern at night, the server analyzes this information in real time to detect abnormal behavior. Based on the detected anomaly, it generates an alarm and sends it as a push notification to the device.

[0090] Conservation workers, as users, can take swift action based on notifications received via their devices and conduct direct on-site investigations. In this way, the present invention significantly improves the efficiency and accuracy of protecting wildlife and monitoring illegal activities within nature reserves.

[0091] An example of a prompt is, "What steps are necessary to detect abnormal behavioral patterns in animals?" This prompts the generative AI model to analyze specific behavioral patterns, enabling accurate detection.

[0092] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0093] Step 1:

[0094] Data collection by devices

[0095] The device uses sensors and cameras to detect information about the activity of living organisms and people within the protected area. Inputs include temperature, vibration, location data, and visual data. This data is collected and transmitted to a server via a communication module. Specifically, when a sensor instantly detects abnormal vibrations, the camera automatically rotates in that direction to capture video.

[0096] Step 2:

[0097] Server-based data preprocessing

[0098] The server receives raw data sent from the terminal and performs noise reduction and formatting. The data received as input may contain noise and redundant information. The server filters out these unnecessary parts and outputs a clear dataset. Specifically, the server detects abnormally high temperature changes and removes abnormal data.

[0099] Step 3:

[0100] Storing and structuring data in a database

[0101] The preprocessed data is structured as time-series data by the server and stored in a database. This serves as the foundation for subsequent analysis and anomaly detection. The output is a time-series dataset. The server then sorts the data chronologically based on its timestamps.

[0102] Step 4:

[0103] Analysis using generative AI models

[0104] The server uses stored time-series data as input to learn the normal behavioral patterns of organisms using a generative AI model. This prepares it to detect anomalies by comparing it with newly acquired data. The output is a baseline pattern of normal behavior. Specifically, the model analyzes trends from past data and updates its prediction algorithm.

[0105] Step 5:

[0106] Anomaly detection and alarm generation

[0107] The server analyzes newly acquired data in real time and automatically generates an alarm if abnormal behavior is detected. The input is newly acquired activity data. The output of the alarm includes the type of abnormality, the time of occurrence, location information, and related video footage. Specifically, an alarm is generated immediately upon detection of abnormal animal movement.

[0108] Step 6:

[0109] Alarm notifications via terminal

[0110] The terminal receives alarms from the server and pushes them to the user as notifications. The input is the alarm sent from the server. The output is the generation of notifications displayed on the user interface. Specifically, the terminal displays high-priority notifications as pop-ups on the user's device screen.

[0111] Step 7:

[0112] User response

[0113] The user takes appropriate action based on the alarm notification from the terminal. Detailed information about the alarm is provided as input. The user goes to the scene, investigates the cause of the abnormal behavior, and takes action. Specifically, the user uses a patrol vehicle to quickly reach the scene and perform a physical check.

[0114] (Application Example 1)

[0115] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0116] In urban parks and natural areas, there is a need to quickly and accurately detect and respond to anomalies while ensuring the safety of wildlife and citizens. In such environments, it is crucial to efficiently monitor unusual behavior of animals and suspicious individuals and to immediately notify relevant parties when problems occur. However, conventional technologies make it difficult to respond quickly and promptly, resulting in delays in appropriate responses to abnormal situations.

[0117] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0118] In this invention, the server includes means for acquiring activity data from multiple detection devices installed within a protected area, means for accumulating and learning from pre-processed data, and means for pushing alerts to terminals. This makes it possible to detect abnormal behavior of living organisms or suspicious individuals in real time and prompt citizens and administrators to take immediate action.

[0119] A "protected area" is an area where specific regulations are in place for the purpose of preserving nature and wildlife, and ensuring the safety of citizens.

[0120] A "detection device" is a device that includes sensors and cameras for detecting the activity of animals and suspicious individuals and converting it into data.

[0121] "Activity data" refers to data that records information such as the movements, locations, and temperatures of living organisms or suspicious individuals in a time-series format.

[0122] "Preprocessing" is the process of removing noise from acquired data and shaping it into a format that is easy to analyze.

[0123] A "database" is a recording system that structures and stores processed data as time-series information.

[0124] A "behavioral pattern" refers to the tendencies in movement and behavior that an organism exhibits at a specific time or in a particular situation.

[0125] "Abnormal behavior" refers to the actions of an organism or suspicious person that deviate from their normal behavioral patterns and require a swift response.

[0126] An "alarm" is a notification that is generated when an anomaly is detected, and its purpose is to prompt immediate action.

[0127] A "push notification" is a real-time alert message automatically sent to the user from the originating server.

[0128] A "terminal" refers to a portable information device or computer used to receive and display alarms.

[0129] To implement this invention, it is first necessary to install multiple detection devices in parks and natural areas within cities. These detection devices include sensors and cameras for detecting the movement of animals and suspicious individuals. The sensors acquire data such as temperature and vibration, and the cameras capture still images and videos.

[0130] The server receives data transmitted from these detection devices and performs data preprocessing. Preprocessing includes noise reduction and formatting. This process converts the data into a format that is easy to analyze.

[0131] The pre-processed data is stored in a database as time-series information. Based on this information, the server applies a generative AI model to learn the normal behavioral patterns of organisms. By comparing the learned behavioral patterns with newly acquired data, abnormal behavior is detected in real time.

[0132] When an anomaly is detected, the server immediately generates an alarm and sends this information as a push notification to the device. Citizens and administrators using the device can receive the push notification and check the details of the anomaly. This allows citizens to ensure their own safety and administrators to conduct on-site investigations as needed and respond quickly.

[0133] For example, if an animal exhibiting unusual behavior is observed in the park, the system will detect the anomaly and immediately send a notification to the administrator's terminal. The administrator can then receive the notification, confirm the situation, and take necessary measures.

[0134] An example of a prompt using a generative AI model is: "Explain how to analyze data detected by sensor and camera systems installed in urban parks to identify abnormal animal behavior and notify citizens in real time."

[0135] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0136] Step 1:

[0137] The server receives sensor and camera data from multiple detection devices installed in the protected area. Inputs include temperature, vibration, still images, and video data. This data is prepared for real-time processing by the server.

[0138] Step 2:

[0139] The server preprocesses the received data. This preprocessing includes noise removal and formatting. The data input is raw sensor and camera information, and the output is clean data suitable for analysis. Specific operations include, for example, removing outliers and converting the data into a time series.

[0140] Step 3:

[0141] The server stores pre-processed data in a database. The input is cleaned data, and the output is structured chronologically and stored in the database in a format that allows for quick access when needed. Specifically, this involves data indexing and tagging.

[0142] Step 4:

[0143] The server inputs accumulated data into a generating AI model to learn the normal behavioral patterns of organisms. In this step, a behavioral prediction model is trained using past data patterns. The input is structured data, and the output is the trained model. Specifically, the model's parameters are updated.

[0144] Step 5:

[0145] The server compares newly acquired data with existing models in real time to detect abnormal behavior. This allows for the rapid identification of behaviors defined as abnormal. The input is real-time data, and the output is information regarding the presence or absence of abnormalities. The server analyzes the results of model application and prepares a report.

[0146] Step 6:

[0147] When an anomaly is detected, the server generates an alarm and sends a notification to administrator and user terminals. The input is the result of the anomaly detection, and the output is an alarm in the form of a push notification. Specifically, the notification is formatted and sent.

[0148] Step 7:

[0149] The terminal receives push notifications from the server and displays their contents to the user. The input is notification information from the server, and the output is an alarm display on the terminal. Based on this information, the user can perform on-site checks and take safety measures.

[0150] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0151] This invention provides a system for streamlining wildlife conservation and monitoring poaching activities, and offers an applied technology that combines it with an emotion engine that recognizes the user's emotions. In addition to monitoring animal activity, detecting abnormal behavior, and generating alarms, this system can suggest more appropriate countermeasures by analyzing the user's emotional state.

[0152] System Configuration

[0153] This system consists of the aforementioned group of detection devices for monitoring animal behavior, a server, and user terminals. The server receives data from multiple sensors and cameras within the area and processes it in real time. The emotion engine analyzes the user's emotional state in real time and personalizes the received alarms and notifications based on the individual user's emotional response.

[0154] Data processing and sentiment analysis

[0155] While the server performs normal data preprocessing and behavioral pattern learning functions, it also acquires emotional data when the user receives a notification. This data is based on input from the camera and microphone on the user's device, and an emotion analysis algorithm is applied. This algorithm determines emotional states such as excitement, surprise, and stress, and stores this information in a database.

[0156] Alarm personalization

[0157] The emotion engine adjusts the content and method of alerts and notifications based on the user's emotional state. For example, if the user is feeling stressed, it can simplify the notification content and provide assistance in clarifying whether immediate action is required depending on the importance of the situation.

[0158] Specific example

[0159] One day, the server detects an animal's behavior deviating from its normal activity pattern within a protected area and generates an alert. When a notification is sent to the terminal, the emotion engine analyzes the user's facial expression data and detects surprise. The server receives this information and adjusts the alert content, allowing it to prioritize and present the user with necessary emergency response measures. In this way, the user can take appropriate action at the right time, improving the system's usefulness.

[0160] This invention enables wildlife conservation and anti-poaching measures to be operated with greater precision than before, while reducing user stress and emotional burden.

[0161] The following describes the processing flow.

[0162] Step 1:

[0163] Data collection

[0164] The server receives activity data on animals and suspicious individuals from detection devices installed within the protected area. This includes motion detection and temperature data from sensors, as well as image and video data from cameras.

[0165] Step 2:

[0166] Data preprocessing

[0167] The server analyzes the acquired data, removes noise, and formats the information into a consistent format. This ensures that the data is processed accurately and efficiently.

[0168] Step 3:

[0169] Save to database

[0170] The server stores the pre-processed data in a database. The data is organized chronologically so that it can be used for later analysis.

[0171] Step 4:

[0172] Learning behavioral patterns

[0173] The server analyzes the stored data to learn the animals' typical behavioral patterns. It then uses machine learning algorithms to model these patterns and create baseline data.

[0174] Step 5:

[0175] Real-time monitoring and anomaly detection

[0176] The server monitors new data in real time and compares it to learned normal behavior patterns. When it detects abnormal behavior or suspicious individuals, it processes the information immediately.

[0177] Step 6:

[0178] Alarm generation

[0179] The server generates an alarm based on the detected anomaly. The alarm includes the type of anomaly, location, time, and associated video data.

[0180] Step 7:

[0181] User sentiment analysis

[0182] Upon receiving an alarm notification, the device simultaneously analyzes the user's facial expressions and voice data using an emotion engine to understand the user's emotional state. This information is then returned to the server.

[0183] Step 8:

[0184] Alarm adjustment and notification

[0185] The server adjusts the alert content based on the user's emotional state. To reduce stress, it simplifies notifications and prioritizes displaying information appropriate to the urgency of the situation. The device then delivers the adjusted notifications to the user.

[0186] Step 9:

[0187] Immediate response

[0188] Users can review coordinated notifications and take appropriate action quickly in the field. They can also request further support or backup as needed.

[0189] (Example 2)

[0190] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0191] In wildlife conservation and poaching monitoring, there is a need for timely information and appropriate response measures when abnormal events are detected. However, information provision optimized for individual users has not yet been achieved, and appropriate responses may be difficult depending on the user's emotional state. This project aims to solve this problem.

[0192] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0193] In this invention, the server includes means for acquiring activity information of living organisms and suspicious persons from a plurality of detection devices installed within a protected area; means for processing and pre-processing the information; and means for analyzing the user's emotional state via a receiving terminal and personalizing the alarms and notifications based on individual emotional responses. This enables the provision of information optimized for the user's emotional state, allowing for a quick and effective response.

[0194] A "detection device" is a physical device installed within a protected area to collect information on surrounding activity.

[0195] "Activity information" refers to data about the movements and actions of living organisms or suspicious individuals, and is information acquired by detection devices.

[0196] "Preprocessing" refers to steps such as noise reduction and standardization of data formats that are performed to convert acquired activity information into a format that is easy to analyze.

[0197] A "database" is a collection of information that stores pre-processed information and is structured to be searchable and usable as needed.

[0198] A "behavioral pattern" is a model that shows the typical activity tendencies of an organism, and is constructed based on accumulated information.

[0199] "Abnormal behavior" refers to actions that deviate from normal behavioral patterns and are detected through real-time information monitoring.

[0200] An "alert" is information generated to warn users based on the detection of abnormal behavior, and it is the content that should be notified to the user.

[0201] "Emotional state" refers to the user's internal reactions and is analyzed based on data such as facial expressions and voice acquired through the receiving device.

[0202] "Personalization" refers to the process of adjusting information and notifications according to the user's emotional state and providing them in an individually optimized format.

[0203] This system is based on acquiring information about the activity of living organisms and suspicious individuals using detection devices installed within the protected area. It primarily collects data such as the movement of living organisms, heart rate, and body temperature, which is then processed on a server. The server applies appropriate algorithms to remove noise and standardize the data format during the data preprocessing stage. While industry-standard analytical tools are used for data analysis as a software platform, specific names are not mentioned here.

[0204] Next, the server runs the animal behavior analysis process, comparing the real-time data with normal behavioral patterns stored in the database. This allows for the detection of abnormal behavior.

[0205] Furthermore, the user's device collects emotional data through its built-in camera and microphone. A specialized algorithm is applied to analyze the user's facial expressions and changes in voice to determine emotional states such as excitement, surprise, and stress. The analysis results are sent to a server, which forms the basis for personalizing alarms and notifications.

[0206] For example, if the server detects abnormal behavior, it generates an alarm based on this information. If sentiment analysis reveals that the user is in a surprised state, the alarm content is adjusted, and a concise and clear notification is sent to encourage a quick response.

[0207] As an example of a specific prompt, we will use the following format: "Suggest a way to notify the user when abnormal behavior in wild animals is detected. How can the notification be effectively personalized if the user is startled?" This sentence is a fundamental Pro question for generating appropriate notification methods in a generative AI model.

[0208] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0209] Step 1:

[0210] The server collects activity information on living organisms and suspicious individuals from multiple detection devices installed within the protected area. Input data includes animal movement, body temperature, and heart rate. Based on this, the server compresses the data and converts it to a format necessary to improve communication efficiency. Output data is generated as a standardized dataset, facilitating subsequent processing.

[0211] Step 2:

[0212] The server preprocesses the collected data. The input is raw data obtained from the detection device. Based on this, the server performs filtering to remove noise and extract only meaningful information. As output, it generates a clean, analyzable dataset.

[0213] Step 3:

[0214] The server analyzes animal behavior patterns using pre-processed data. The input is a pre-processed dataset. Here, the server applies a machine learning model to identify typical animal behavior patterns. As output, the behavior pattern model is updated and stored in a database.

[0215] Step 4:

[0216] The device collects user emotion data using its camera and microphone. Input consists of the user's facial expressions and voice. Based on this, an emotion analysis algorithm is used to evaluate the emotional state. The output identifies emotions such as excitement, surprise, and stress, and the results are sent to a server as data.

[0217] Step 5:

[0218] The server monitors newly acquired data in real time and detects abnormal behavior. The input consists of an updated behavioral pattern model and real-time acquired data. This data is analyzed, and if an anomaly is found, an alarm is generated. The output is alarm data indicating the abnormal behavior, and the anomaly is identified.

[0219] Step 6:

[0220] The server personalizes alarms and notifications based on the user's emotional state. Inputs include alarm data related to abnormal behavior and the user's emotional analysis results. The server then adjusts the format and content of the notifications to make them more acceptable to the user. Personalized notification data is generated as output.

[0221] Step 7:

[0222] The server sends personalized notifications to the user's device. The input is personalized notification data. Based on this, the server immediately pushes the notification. As an output, the user receives appropriate action plans through their device, enabling quick decision-making.

[0223] (Application Example 2)

[0224] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0225] Conventional wildlife conservation and poaching monitoring systems can monitor animal behavior and detect anomalies, but they have the drawback of providing uniform alarms and notifications that cannot respond to the emotional state of individual users. As a result, users may experience excessive stress when receiving notifications, making it difficult to respond quickly and appropriately.

[0226] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0227] In this invention, the server includes means for acquiring activity data from multiple detection devices installed within a protected area; means for processing and pre-processing the acquired data; means for accumulating the pre-processed data and storing it in a database including time-series information; means for learning normal behavior patterns based on the accumulated data; means for monitoring newly acquired data in real time and detecting abnormal behavior; means for generating alarms and sending notifications based on the detected abnormal behavior; and means for analyzing the user's emotional state and personalizing the alarms and notifications. This makes it possible to send personalized notifications according to the user's emotional state, enabling the user to respond quickly and accurately without experiencing excessive stress.

[0228] A "detection device" is a hardware device installed within a protected area to monitor the activity of animals or other targets.

[0229] "Activity data" refers to information about the movements and behaviors of animals or targets acquired by detection devices.

[0230] "Preprocessing" refers to the process of appropriately processing acquired activity data and shaping it into a format that can be analyzed.

[0231] "Time-series information" refers to information that describes the state or changes in data collected over time.

[0232] "Typical behavioral patterns" refer to the typical behavioral tendencies or habits that an animal or subject exhibits over a long period of time.

[0233] "Abnormal behavior" refers to atypical behavior of an animal or subject that deviates from its normal behavioral patterns.

[0234] An "alert" is an alert generated based on detected abnormal behavior, indicating that a specified action is required.

[0235] A "notification" is a message or warning used to convey information to a user.

[0236] "Emotional state" refers to a user's psychological response or emotional state in response to a specific situation.

[0237] "Personalization" refers to adjusting something to suit the specific needs and circumstances of each individual user.

[0238] The system for carrying out this invention involves placing a detection device, including multiple sensors and cameras, within a protected area to acquire animal activity data. A server receives this data in real time, performs data preprocessing, and stores it in a database as time-series information.

[0239] The server learns normal behavior patterns and monitors newly acquired data in real time to detect abnormal behavior. Based on the detected abnormal behavior, it generates an alarm and sends notifications to various terminals. In this process, the server analyzes emotional data from the user's terminal and applies an emotional analysis algorithm to determine the user's emotional state. The analysis uses the smartphone's camera and microphone.

[0240] The device displays alarms and notifications sent from the server in a personalized manner based on the user's emotional state. For example, if the user is feeling stressed, the notification will be concise and clearly indicate whether immediate action is required.

[0241] For example, if a server detects unusual animal movement in a city park and sends a notification to the user's smartphone, and the user is startled, the server adjusts the alarm based on this information. This allows the user to respond effectively, improving the system's usefulness.

[0242] By using generative AI models, it is possible to analyze data on users' emotional states through deep learning and provide more precise and personalized responses. An example of a prompt would be: "I want to design an urban ecosystem monitoring app. I want to monitor the movements of wild animals and adjust the alert content based on the user's emotions. Please provide details of the emotion analysis algorithm along with specific examples of how it works."

[0243] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0244] Step 1:

[0245] The server acquires activity data from various sensors and cameras installed within the protected area. This data includes animal location, movement, and environmental conditions. Input is real-time data from each detection device, and output is in a data format that can be pre-processed internally by the server. The server aggregates this data and performs pre-processing to convert it into an appropriate format.

[0246] Step 2:

[0247] The server stores pre-processed data in a database as time-series information. Data is stored in JSON or CSV format, enabling historical data analysis. The input is pre-processed data, and the output is time-series data stored in the database.

[0248] Step 3:

[0249] The server learns typical behavioral patterns based on accumulated data. This process uses machine learning algorithms to model typical animal behavior. The input is historical time-series data, and the output is the learned behavioral model.

[0250] Step 4:

[0251] The server monitors newly acquired data in real time and detects abnormal behavior by comparing it with learned behavioral patterns. If an anomaly is detected, it generates an alarm. The input is real-time data and a behavioral model, and the output is an alarm for abnormal behavior.

[0252] Step 5:

[0253] The server notifies each terminal of an alarm generated based on abnormal behavior. At the same time, it acquires emotional data from the user's smartphone and analyzes it using an emotional analysis algorithm. The input is the alarm data and the user's emotional data, and the output is the analyzed emotional information.

[0254] Step 6:

[0255] The device uses the sentiment analysis results received from the server to personalize alarms and notifications. The content of notifications is concisely adjusted according to the user's emotional state. The input is sentiment information and alarm data, and the output is a personalized notification message.

[0256] Step 7:

[0257] Users receive personalized notifications displayed on their devices. They can review the notification content and take immediate action as needed. The input is the personalized notification, and the output is the user's response action.

[0258] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0259] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0260] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0261] [Second Embodiment]

[0262] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0263] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0264] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0265] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0266] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0267] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0268] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0269] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0270] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0271] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0272] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0273] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0274] This invention aims to protect wildlife and monitor poaching activities in extensive nature reserves, and provides an automated monitoring system utilizing AI technology. By installing multiple detection devices within the area and monitoring animal activity and suspicious activity, this system can efficiently detect anomalies in real time and take immediate countermeasures.

[0275] System Configuration

[0276] This system is designed to first use sensors and cameras as detection devices to sense animal movement and the presence of people, and to collect the data. The sensors collect temperature, vibration, and location data, while the cameras acquire still images and videos. This collected data is transmitted to a dedicated server.

[0277] Data processing and analysis

[0278] The server preprocesses the received data, removing noise and formatting it. The preprocessed data is stored in a database and structured as time-series information. This allows machine learning models to be applied to identify the animals' normal behavioral patterns. The server compares these models with newly acquired data in real time to detect abnormal behavior.

[0279] Anomaly detection and alarm generation

[0280] The server automatically generates an alarm when it detects abnormal behavior or suspicious activity. The alarm includes the type, time, location, and video data of the detected anomaly. This information is immediately sent as a push notification to the designated device.

[0281] Response and Management

[0282] The terminal receives notifications from the server and prompts the user to take appropriate action. The user, such as a ranger or administrator in a protected area, uses the received information to conduct an on-site investigation and respond to the alert as needed.

[0283] Specific example

[0284] For example, suppose that at a certain night, a camera in the protected area captures a group of animals that have deviated from their normal movement route. The server analyzes this abnormal movement in real time and generates an alarm as an anomaly detection. The terminal receives this alarm and sends a push notification to the ranger. The ranger, who is the user, can rush to the scene to check the situation of the animals and investigate the cause of the abnormal behavior.

[0285] In this way, the present invention enhances the efficiency in animal protection and illegal activity monitoring and enables quick and accurate responses.

[0286] The processing flow will be described below.

[0287] Step 1:

[0288] Data collection

[0289] The server regularly receives data on the activities of animals and suspicious persons from each detection device within the protected area. This includes position information, movement, temperature data, images and video data captured by sensors and cameras.

[0290] Step 2:

[0291] Data preprocessing

[0292] The server performs noise removal on the collected raw data and formats it into a standard form. This improves the quality of the data and makes it suitable for subsequent analysis processing.

[0293] Step 3:

[0294] Data storage

[0295] The server stores the preprocessed data in the database as time-series information. Here, metadata such as relevant timestamps and position information are attached to the data.

[0296] Step 4:

[0297] Learning of Normal Behavior Patterns

[0298] The server learns the normal behavior patterns of animals using the accumulated data. In this process, machine learning algorithms are used to model the habits and general movement tendencies of animals.

[0299] Step 5:

[0300] Real-time Monitoring and Data Analysis

[0301] The server constantly receives new data in real time and compares it with the learned behavior patterns. This makes it possible to quickly detect movements that are different from normal behavior.

[0302] Step 6:

[0303] Anomaly Detection and Alarm Generation

[0304] When the server detects behaviors or suspicious persons that are different from normal, it generates an alarm including the type, location, time, etc. of the anomaly. This alarm information is processed quickly and proceeds to the next step.

[0305] Step 7:

[0306] Notification Distribution

[0307] The terminal receives the alarm sent from the server and distributes it as a push notification to the ranger or administrator. The notification includes the warning content and the information necessary for response.

[0308] Step 8:

[0309] Response and Action

[0310] Users can check notifications received on their devices and take necessary actions on-site. For example, they can quickly investigate suspicious individuals or rescue animals. Rangers can also request further investigation or assistance depending on the situation on the ground.

[0311] (Example 1)

[0312] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0313] Regarding wildlife conservation in extensive nature reserves, current monitoring systems face challenges such as insufficient real-time detection of abnormal behavior and difficulty in responding efficiently and quickly. Furthermore, problems such as wasted responses due to false alarms and the failure to transmit warnings when needed have been pointed out. It is necessary to resolve these challenges and achieve effective monitoring of wildlife and illegal activities.

[0314] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0315] In this invention, the server includes means for acquiring information on the activities of living organisms and humans, means for performing noise reduction and formatting, and means for storing the information in an information structure that includes time-series information. This enables real-time monitoring within nature reserves, allowing for early detection and prompt response to abnormal behavior.

[0316] A "detection device" is a device installed to detect information about the activity of living organisms or people within a specific area and to transmit that information to a server.

[0317] "Activity information" refers to data that shows physical changes such as the movement, location, vibration, and temperature of living organisms and people.

[0318] "Denoising and formatting" is the process of removing unnecessary data from acquired information and converting it into a consistent form.

[0319] "Information structure" refers to the format in which information is organized and stored chronologically within a database or other storage system.

[0320] A "biological behavior model" refers to data and algorithms that learn the normal behavioral patterns of organisms and use that to determine the abnormality of new behaviors.

[0321] An "alarm" is a notification or alert generated to inform of abnormal behavior or potential danger.

[0322] A "receiving device" is a device used to receive alarms and notifications transmitted from a server, and includes, for example, smartphones and tablets.

[0323] A "conservationist" refers to an individual or organization responsible for the protection and management of wildlife within a nature reserve.

[0324] In implementing this invention, the collaboration between a server, a terminal, and a user is primarily utilized. The terminal includes multiple sensors and cameras placed within an area. These devices detect biological and human activity information in real time and transmit this information to the server. The sensors can detect various physical changes such as temperature, vibration, and location data, while the cameras can acquire visual data.

[0325] The server receives information transmitted from these terminals and performs preprocessing, such as denoising and formatting the data, using a generative AI model. It then structures the information as time-series data and stores it. This process contributes to efficient information utilization and rapid detection of abnormal behavior.

[0326] For example, if a camera captures a group of animals deviating from their usual movement pattern at night, the server analyzes this information in real time to detect abnormal behavior. Based on the detected anomaly, it generates an alarm and sends it as a push notification to the device.

[0327] Conservation workers, as users, can take swift action based on notifications received via their devices and conduct direct on-site investigations. In this way, the present invention significantly improves the efficiency and accuracy of protecting wildlife and monitoring illegal activities within nature reserves.

[0328] An example of a prompt is, "What steps are necessary to detect abnormal behavioral patterns in animals?" This prompts the generative AI model to analyze specific behavioral patterns, enabling accurate detection.

[0329] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0330] Step 1:

[0331] Data collection by devices

[0332] The device uses sensors and cameras to detect information about the activity of living organisms and people within the protected area. Inputs include temperature, vibration, location data, and visual data. This data is collected and transmitted to a server via a communication module. Specifically, when a sensor instantly detects abnormal vibrations, the camera automatically rotates in that direction to capture video.

[0333] Step 2:

[0334] Server-based data preprocessing

[0335] The server receives raw data sent from the terminal and performs noise reduction and formatting. The data received as input may contain noise and redundant information. The server filters out these unnecessary parts and outputs a clear dataset. Specifically, the server detects abnormally high temperature changes and removes abnormal data.

[0336] Step 3:

[0337] Storing and structuring data in a database

[0338] The preprocessed data is structured as time-series data by the server and stored in a database. This serves as the foundation for subsequent analysis and anomaly detection. The output is a time-series dataset. The server then sorts the data chronologically based on its timestamps.

[0339] Step 4:

[0340] Analysis using generative AI models

[0341] The server uses stored time-series data as input to learn the normal behavioral patterns of organisms using a generative AI model. This prepares it to detect anomalies by comparing it with newly acquired data. The output is a baseline pattern of normal behavior. Specifically, the model analyzes trends from past data and updates its prediction algorithm.

[0342] Step 5:

[0343] Anomaly detection and alarm generation

[0344] The server analyzes newly acquired data in real time and automatically generates an alarm if abnormal behavior is detected. The input is newly acquired activity data. The output of the alarm includes the type of abnormality, the time of occurrence, location information, and related video footage. Specifically, an alarm is generated immediately upon detection of abnormal animal movement.

[0345] Step 6:

[0346] Alarm notifications via terminal

[0347] The terminal receives alarms from the server and pushes them to the user as notifications. The input is the alarm sent from the server. The output is the generation of notifications displayed on the user interface. Specifically, the terminal displays high-priority notifications as pop-ups on the user's device screen.

[0348] Step 7:

[0349] User response

[0350] The user takes appropriate action based on the alarm notification from the terminal. Detailed information about the alarm is provided as input. The user goes to the scene, investigates the cause of the abnormal behavior, and takes action. Specifically, the user uses a patrol vehicle to quickly reach the scene and perform a physical check.

[0351] (Application Example 1)

[0352] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0353] In urban parks and natural areas, there is a need to quickly and accurately detect and respond to anomalies while ensuring the safety of wildlife and citizens. In such environments, it is crucial to efficiently monitor unusual behavior of animals and suspicious individuals and to immediately notify relevant parties when problems occur. However, conventional technologies make it difficult to respond quickly and promptly, resulting in delays in appropriate responses to abnormal situations.

[0354] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0355] In this invention, the server includes means for acquiring activity data from multiple detection devices installed within a protected area, means for accumulating and learning from pre-processed data, and means for pushing alerts to terminals. This makes it possible to detect abnormal behavior of living organisms or suspicious individuals in real time and prompt citizens and administrators to take immediate action.

[0356] A "protected area" is an area where specific regulations are in place for the purpose of preserving nature and wildlife, and ensuring the safety of citizens.

[0357] A "detection device" is a device that includes sensors and cameras for detecting the activity of animals and suspicious individuals and converting it into data.

[0358] "Activity data" refers to data that records information such as the movements, locations, and temperatures of living organisms or suspicious individuals in a time-series format.

[0359] "Preprocessing" is the process of removing noise from acquired data and shaping it into a format that is easy to analyze.

[0360] A "database" is a recording system that structures and stores processed data as time-series information.

[0361] A "behavioral pattern" refers to the tendencies in movement and behavior that an organism exhibits at a specific time or in a particular situation.

[0362] "Abnormal behavior" refers to the actions of an organism or suspicious person that deviate from their normal behavioral patterns and require a swift response.

[0363] An "alarm" is a notification that is generated when an anomaly is detected, and its purpose is to prompt immediate action.

[0364] A "push notification" is a real-time alert message automatically sent to the user from the originating server.

[0365] A "terminal" refers to a portable information device or computer used to receive and display alarms.

[0366] To implement this invention, it is first necessary to install multiple detection devices in parks and natural areas within cities. These detection devices include sensors and cameras for detecting the movement of animals and suspicious individuals. The sensors acquire data such as temperature and vibration, and the cameras capture still images and videos.

[0367] The server receives data transmitted from these detection devices and performs data preprocessing. Preprocessing includes noise reduction and formatting. This process converts the data into a format that is easy to analyze.

[0368] The pre-processed data is stored in a database as time-series information. Based on this information, the server applies a generative AI model to learn the normal behavioral patterns of organisms. By comparing the learned behavioral patterns with newly acquired data, abnormal behavior is detected in real time.

[0369] When an anomaly is detected, the server immediately generates an alarm and sends this information as a push notification to the device. Citizens and administrators using the device can receive the push notification and check the details of the anomaly. This allows citizens to ensure their own safety and administrators to conduct on-site investigations as needed and respond quickly.

[0370] For example, if an animal exhibiting unusual behavior is observed in the park, the system will detect the anomaly and immediately send a notification to the administrator's terminal. The administrator can then receive the notification, confirm the situation, and take necessary measures.

[0371] An example of a prompt using a generative AI model is: "Explain how to analyze data detected by sensor and camera systems installed in urban parks to identify abnormal animal behavior and notify citizens in real time."

[0372] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0373] Step 1:

[0374] The server receives sensor and camera data from multiple detection devices installed in the protected area. Inputs include temperature, vibration, still images, and video data. This data is prepared for real-time processing by the server.

[0375] Step 2:

[0376] The server preprocesses the received data. This preprocessing includes noise removal and formatting. The data input is raw sensor and camera information, and the output is clean data suitable for analysis. Specific operations include, for example, removing outliers and converting the data into a time series.

[0377] Step 3:

[0378] The server stores pre-processed data in a database. The input is cleaned data, and the output is structured chronologically and stored in the database in a format that allows for quick access when needed. Specifically, this involves data indexing and tagging.

[0379] Step 4:

[0380] The server inputs accumulated data into a generating AI model to learn the normal behavioral patterns of organisms. In this step, a behavioral prediction model is trained using past data patterns. The input is structured data, and the output is the trained model. Specifically, the model's parameters are updated.

[0381] Step 5:

[0382] The server compares newly acquired data with existing models in real time to detect abnormal behavior. This allows for the rapid identification of behaviors defined as abnormal. The input is real-time data, and the output is information regarding the presence or absence of abnormalities. The server analyzes the results of model application and prepares a report.

[0383] Step 6:

[0384] When an anomaly is detected, the server generates an alarm and sends a notification to administrator and user terminals. The input is the result of the anomaly detection, and the output is an alarm in the form of a push notification. Specifically, the notification is formatted and sent.

[0385] Step 7:

[0386] The terminal receives push notifications from the server and displays their contents to the user. The input is notification information from the server, and the output is an alarm display on the terminal. Based on this information, the user can perform on-site checks and take safety measures.

[0387] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0388] This invention provides a system for streamlining wildlife conservation and monitoring poaching activities, and offers an applied technology that combines it with an emotion engine that recognizes the user's emotions. In addition to monitoring animal activity, detecting abnormal behavior, and generating alarms, this system can suggest more appropriate countermeasures by analyzing the user's emotional state.

[0389] System Configuration

[0390] This system consists of the aforementioned group of detection devices for monitoring animal behavior, a server, and user terminals. The server receives data from multiple sensors and cameras within the area and processes it in real time. The emotion engine analyzes the user's emotional state in real time and personalizes the received alarms and notifications based on the individual user's emotional response.

[0391] Data processing and sentiment analysis

[0392] While the server performs normal data preprocessing and behavioral pattern learning functions, it also acquires emotional data when the user receives a notification. This data is based on input from the camera and microphone on the user's device, and an emotion analysis algorithm is applied. This algorithm determines emotional states such as excitement, surprise, and stress, and stores this information in a database.

[0393] Alarm personalization

[0394] The emotion engine adjusts the content and method of alerts and notifications based on the user's emotional state. For example, if the user is feeling stressed, it can simplify the notification content and provide assistance in clarifying whether immediate action is required depending on the importance of the situation.

[0395] Specific example

[0396] One day, the server detects an animal's behavior deviating from its normal activity pattern within a protected area and generates an alert. When a notification is sent to the terminal, the emotion engine analyzes the user's facial expression data and detects surprise. The server receives this information and adjusts the alert content, allowing it to prioritize and present the user with necessary emergency response measures. In this way, the user can take appropriate action at the right time, improving the system's usefulness.

[0397] This invention enables wildlife conservation and anti-poaching measures to be operated with greater precision than before, while reducing user stress and emotional burden.

[0398] The following describes the processing flow.

[0399] Step 1:

[0400] Data collection

[0401] The server receives activity data on animals and suspicious individuals from detection devices installed within the protected area. This includes motion detection and temperature data from sensors, as well as image and video data from cameras.

[0402] Step 2:

[0403] Data preprocessing

[0404] The server analyzes the acquired data, removes noise, and formats the information into a consistent format. This ensures that the data is processed accurately and efficiently.

[0405] Step 3:

[0406] Save to database

[0407] The server stores the pre-processed data in a database. The data is organized chronologically so that it can be used for later analysis.

[0408] Step 4:

[0409] Learning behavioral patterns

[0410] The server analyzes the stored data to learn the animals' typical behavioral patterns. It then uses machine learning algorithms to model these patterns and create baseline data.

[0411] Step 5:

[0412] Real-time monitoring and anomaly detection

[0413] The server monitors new data in real time and compares it to learned normal behavior patterns. When it detects abnormal behavior or suspicious individuals, it processes the information immediately.

[0414] Step 6:

[0415] Alarm generation

[0416] The server generates an alarm based on the detected anomaly. The alarm includes the type of anomaly, location, time, and associated video data.

[0417] Step 7:

[0418] User sentiment analysis

[0419] Upon receiving an alarm notification, the device simultaneously analyzes the user's facial expressions and voice data using an emotion engine to understand the user's emotional state. This information is then returned to the server.

[0420] Step 8:

[0421] Alarm adjustment and notification

[0422] The server adjusts the alert content based on the user's emotional state. To reduce stress, it simplifies notifications and prioritizes displaying information appropriate to the urgency of the situation. The device then delivers the adjusted notifications to the user.

[0423] Step 9:

[0424] Immediate response

[0425] Users can review coordinated notifications and take appropriate action quickly in the field. They can also request further support or backup as needed.

[0426] (Example 2)

[0427] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0428] In wildlife conservation and poaching monitoring, there is a need for timely information and appropriate response measures when abnormal events are detected. However, information provision optimized for individual users has not yet been achieved, and appropriate responses may be difficult depending on the user's emotional state. This project aims to solve this problem.

[0429] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0430] In this invention, the server includes means for acquiring activity information of living organisms and suspicious persons from a plurality of detection devices installed within a protected area; means for processing and pre-processing the information; and means for analyzing the user's emotional state via a receiving terminal and personalizing the alarms and notifications based on individual emotional responses. This enables the provision of information optimized for the user's emotional state, allowing for a quick and effective response.

[0431] A "detection device" is a physical device installed within a protected area to collect information on surrounding activity.

[0432] "Activity information" refers to data about the movements and actions of living organisms or suspicious individuals, and is information acquired by detection devices.

[0433] "Preprocessing" refers to steps such as noise reduction and standardization of data formats that are performed to convert acquired activity information into a format that is easy to analyze.

[0434] A "database" is a collection of information that stores pre-processed information and is structured to be searchable and usable as needed.

[0435] A "behavioral pattern" is a model that shows the typical activity tendencies of an organism, and is constructed based on accumulated information.

[0436] "Abnormal behavior" refers to actions that deviate from normal behavioral patterns and are detected through real-time information monitoring.

[0437] An "alert" is information generated to warn users based on the detection of abnormal behavior, and it is the content that should be notified to the user.

[0438] "Emotional state" refers to the user's internal reactions and is analyzed based on data such as facial expressions and voice acquired through the receiving device.

[0439] "Personalization" refers to the process of adjusting information and notifications according to the user's emotional state and providing them in an individually optimized format.

[0440] This system is based on acquiring information about the activity of living organisms and suspicious individuals using detection devices installed within the protected area. It primarily collects data such as the movement of living organisms, heart rate, and body temperature, which is then processed on a server. The server applies appropriate algorithms to remove noise and standardize the data format during the data preprocessing stage. While industry-standard analytical tools are used for data analysis as a software platform, specific names are not mentioned here.

[0441] Next, the server runs the animal behavior analysis process, comparing the real-time data with normal behavioral patterns stored in the database. This allows for the detection of abnormal behavior.

[0442] Furthermore, the user's device collects emotional data through its built-in camera and microphone. A specialized algorithm is applied to analyze the user's facial expressions and changes in voice to determine emotional states such as excitement, surprise, and stress. The analysis results are sent to a server, which forms the basis for personalizing alarms and notifications.

[0443] For example, if the server detects abnormal behavior, it generates an alarm based on this information. If sentiment analysis reveals that the user is in a surprised state, the alarm content is adjusted, and a concise and clear notification is sent to encourage a quick response.

[0444] As an example of a specific prompt, we will use the following format: "Suggest a way to notify the user when abnormal behavior in wild animals is detected. How can the notification be effectively personalized if the user is startled?" This sentence is a fundamental Pro question for generating appropriate notification methods in a generative AI model.

[0445] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0446] Step 1:

[0447] The server collects activity information on living organisms and suspicious individuals from multiple detection devices installed within the protected area. Input data includes animal movement, body temperature, and heart rate. Based on this, the server compresses the data and converts it to a format necessary to improve communication efficiency. Output data is generated as a standardized dataset, facilitating subsequent processing.

[0448] Step 2:

[0449] The server preprocesses the collected data. The input is raw data obtained from the detection device. Based on this, the server performs filtering to remove noise and extract only meaningful information. As output, it generates a clean, analyzable dataset.

[0450] Step 3:

[0451] The server analyzes animal behavior patterns using pre-processed data. The input is a pre-processed dataset. Here, the server applies a machine learning model to identify typical animal behavior patterns. As output, the behavior pattern model is updated and stored in a database.

[0452] Step 4:

[0453] The device collects user emotion data using its camera and microphone. Input consists of the user's facial expressions and voice. Based on this, an emotion analysis algorithm is used to evaluate the emotional state. The output identifies emotions such as excitement, surprise, and stress, and the results are sent to a server as data.

[0454] Step 5:

[0455] The server monitors newly acquired data in real time and detects abnormal behavior. The input consists of an updated behavioral pattern model and real-time acquired data. This data is analyzed, and if an anomaly is found, an alarm is generated. The output is alarm data indicating the abnormal behavior, and the anomaly is identified.

[0456] Step 6:

[0457] The server personalizes alarms and notifications based on the user's emotional state. Inputs include alarm data related to abnormal behavior and the user's emotional analysis results. The server then adjusts the format and content of the notifications to make them more acceptable to the user. Personalized notification data is generated as output.

[0458] Step 7:

[0459] The server sends personalized notifications to the user's device. The input is personalized notification data. Based on this, the server immediately pushes the notification. As an output, the user receives appropriate action plans through their device, enabling quick decision-making.

[0460] (Application Example 2)

[0461] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0462] Conventional wildlife conservation and poaching monitoring systems can monitor animal behavior and detect anomalies, but they have the drawback of providing uniform alarms and notifications that cannot respond to the emotional state of individual users. As a result, users may experience excessive stress when receiving notifications, making it difficult to respond quickly and appropriately.

[0463] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0464] In this invention, the server includes means for acquiring activity data from multiple detection devices installed within a protected area; means for processing and pre-processing the acquired data; means for accumulating the pre-processed data and storing it in a database including time-series information; means for learning normal behavior patterns based on the accumulated data; means for monitoring newly acquired data in real time and detecting abnormal behavior; means for generating alarms and sending notifications based on the detected abnormal behavior; and means for analyzing the user's emotional state and personalizing the alarms and notifications. This makes it possible to send personalized notifications according to the user's emotional state, enabling the user to respond quickly and accurately without experiencing excessive stress.

[0465] A "detection device" is a hardware device installed within a protected area to monitor the activity of animals or other targets.

[0466] "Activity data" refers to information about the movements and behaviors of animals or targets acquired by detection devices.

[0467] "Preprocessing" refers to the process of appropriately processing acquired activity data and shaping it into a format that can be analyzed.

[0468] "Time-series information" refers to information that describes the state or changes in data collected over time.

[0469] "Typical behavioral patterns" refer to the typical behavioral tendencies or habits that an animal or subject exhibits over a long period of time.

[0470] "Abnormal behavior" refers to atypical behavior of an animal or subject that deviates from its normal behavioral patterns.

[0471] An "alert" is an alert generated based on detected abnormal behavior, indicating that a specified action is required.

[0472] A "notification" is a message or warning used to convey information to a user.

[0473] "Emotional state" refers to a user's psychological response or emotional state in response to a specific situation.

[0474] "Personalization" refers to adjusting something to suit the specific needs and circumstances of each individual user.

[0475] The system for carrying out this invention involves placing a detection device, including multiple sensors and cameras, within a protected area to acquire animal activity data. A server receives this data in real time, performs data preprocessing, and stores it in a database as time-series information.

[0476] The server learns normal behavior patterns and monitors newly acquired data in real time to detect abnormal behavior. Based on the detected abnormal behavior, it generates an alarm and sends notifications to various terminals. In this process, the server analyzes emotional data from the user's terminal and applies an emotional analysis algorithm to determine the user's emotional state. The analysis uses the smartphone's camera and microphone.

[0477] The device displays alarms and notifications sent from the server in a personalized manner based on the user's emotional state. For example, if the user is feeling stressed, the notification will be concise and clearly indicate whether immediate action is required.

[0478] For example, if a server detects unusual animal movement in a city park and sends a notification to the user's smartphone, and the user is startled, the server adjusts the alarm based on this information. This allows the user to respond effectively, improving the system's usefulness.

[0479] By using generative AI models, it is possible to analyze data on users' emotional states through deep learning and provide more precise and personalized responses. An example of a prompt would be: "I want to design an urban ecosystem monitoring app. I want to monitor the movements of wild animals and adjust the alert content based on the user's emotions. Please provide details of the emotion analysis algorithm along with specific examples of how it works."

[0480] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0481] Step 1:

[0482] The server acquires activity data from various sensors and cameras installed within the protected area. This data includes animal location, movement, and environmental conditions. Input is real-time data from each detection device, and output is in a data format that can be pre-processed internally by the server. The server aggregates this data and performs pre-processing to convert it into an appropriate format.

[0483] Step 2:

[0484] The server stores pre-processed data in a database as time-series information. Data is stored in JSON or CSV format, enabling historical data analysis. The input is pre-processed data, and the output is time-series data stored in the database.

[0485] Step 3:

[0486] The server learns typical behavioral patterns based on accumulated data. This process uses machine learning algorithms to model typical animal behavior. The input is historical time-series data, and the output is the learned behavioral model.

[0487] Step 4:

[0488] The server monitors newly acquired data in real time and detects abnormal behavior by comparing it with learned behavioral patterns. If an anomaly is detected, it generates an alarm. The input is real-time data and a behavioral model, and the output is an alarm for abnormal behavior.

[0489] Step 5:

[0490] The server notifies each terminal of an alarm generated based on abnormal behavior. At the same time, it acquires emotional data from the user's smartphone and analyzes it using an emotional analysis algorithm. The input is the alarm data and the user's emotional data, and the output is the analyzed emotional information.

[0491] Step 6:

[0492] The device uses the sentiment analysis results received from the server to personalize alarms and notifications. The content of notifications is concisely adjusted according to the user's emotional state. The input is sentiment information and alarm data, and the output is a personalized notification message.

[0493] Step 7:

[0494] Users receive personalized notifications displayed on their devices. They can review the notification content and take immediate action as needed. The input is the personalized notification, and the output is the user's response action.

[0495] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0496] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0497] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0498] [Third Embodiment]

[0499] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0500] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0501] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0502] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0503] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0504] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0505] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0506] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0507] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0508] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0509] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0510] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0511] This invention aims to protect wildlife and monitor poaching activities in extensive nature reserves, and provides an automated monitoring system utilizing AI technology. By installing multiple detection devices within the area and monitoring animal activity and suspicious activity, this system can efficiently detect anomalies in real time and take immediate countermeasures.

[0512] System Configuration

[0513] This system is designed to first use sensors and cameras as detection devices to sense animal movement and the presence of people, and to collect the data. The sensors collect temperature, vibration, and location data, while the cameras acquire still images and videos. This collected data is transmitted to a dedicated server.

[0514] Data processing and analysis

[0515] The server preprocesses the received data, removing noise and formatting it. The preprocessed data is stored in a database and structured as time-series information. This allows machine learning models to be applied to identify the animals' normal behavioral patterns. The server compares these models with newly acquired data in real time to detect abnormal behavior.

[0516] Anomaly detection and alarm generation

[0517] The server automatically generates an alarm when it detects abnormal behavior or suspicious activity. The alarm includes the type, time, location, and video data of the detected anomaly. This information is immediately sent as a push notification to the designated device.

[0518] Response and Management

[0519] The terminal receives notifications from the server and prompts the user to take appropriate action. The user, such as a ranger or administrator in a protected area, uses the received information to conduct an on-site investigation and respond to the alert as needed.

[0520] Specific example

[0521] For example, suppose a camera in a protected area captures a herd of animals deviating from their usual migration route one night. The server analyzes this unusual movement in real time and generates an alert as an anomaly detection. The terminal receives this alert and sends a push notification to the ranger. The ranger, as a user, can then rush to the scene, check on the animals, and investigate the cause of the unusual behavior.

[0522] In this way, the present invention enhances efficiency in animal protection and monitoring of illegal activities, enabling a rapid and accurate response.

[0523] The following describes the processing flow.

[0524] Step 1:

[0525] Data collection

[0526] The server periodically receives data on animal and intruder activity from each detection device within the protected area. This includes location, movement, and temperature data from sensors, as well as image and video data from cameras.

[0527] Step 2:

[0528] Data preprocessing

[0529] The server denoises the collected raw data and formats it into a standard format. This improves the quality of the data and makes it suitable for subsequent analysis.

[0530] Step 3:

[0531] Data storage

[0532] The server stores the pre-processed data as time-series information in the database. Here, metadata such as associated timestamps and location information is attached to the data.

[0533] Step 4:

[0534] Learning of normal behavioral patterns

[0535] The server uses accumulated data to learn the animals' typical behavioral patterns. This process employs machine learning algorithms to model the animals' habits and general movement tendencies.

[0536] Step 5:

[0537] Real-time monitoring and data analysis

[0538] The server constantly receives new data in real time and compares it with learned behavioral patterns. This makes it possible to quickly detect movements that deviate from normal behavior.

[0539] Step 6:

[0540] Anomaly detection and alarm generation

[0541] When the server detects unusual behavior or suspicious individuals, it generates an alert that includes the type, location, and time of the anomaly. This alert information is processed quickly, and the process moves to the next step.

[0542] Step 7:

[0543] Notification distribution

[0544] The terminal receives alerts sent from the server and distributes them as push notifications to rangers and administrators. The notifications include the alert details and information necessary for taking action.

[0545] Step 8:

[0546] Response and Action

[0547] Users can check notifications received on their devices and take necessary actions on-site. For example, they can quickly investigate suspicious individuals or rescue animals. Rangers can also request further investigation or assistance depending on the situation on the ground.

[0548] (Example 1)

[0549] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0550] Regarding wildlife conservation in extensive nature reserves, current monitoring systems face challenges such as insufficient real-time detection of abnormal behavior and difficulty in responding efficiently and quickly. Furthermore, problems such as wasted responses due to false alarms and the failure to transmit warnings when needed have been pointed out. It is necessary to resolve these challenges and achieve effective monitoring of wildlife and illegal activities.

[0551] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0552] In this invention, the server includes means for acquiring information on the activities of living organisms and humans, means for performing noise reduction and formatting, and means for storing the information in an information structure that includes time-series information. This enables real-time monitoring within nature reserves, allowing for early detection and prompt response to abnormal behavior.

[0553] A "detection device" is a device installed to detect information about the activity of living organisms or people within a specific area and to transmit that information to a server.

[0554] "Activity information" refers to data that shows physical changes such as the movement, location, vibration, and temperature of living organisms and people.

[0555] "Denoising and formatting" is the process of removing unnecessary data from acquired information and converting it into a consistent form.

[0556] "Information structure" refers to the format in which information is organized and stored chronologically within a database or other storage system.

[0557] A "biological behavior model" refers to data and algorithms that learn the normal behavioral patterns of organisms and use that to determine the abnormality of new behaviors.

[0558] An "alarm" is a notification or alert generated to inform of abnormal behavior or potential danger.

[0559] A "receiving device" is a device used to receive alarms and notifications transmitted from a server, and includes, for example, smartphones and tablets.

[0560] A "conservationist" refers to an individual or organization responsible for the protection and management of wildlife within a nature reserve.

[0561] In implementing this invention, the collaboration between a server, a terminal, and a user is primarily utilized. The terminal includes multiple sensors and cameras placed within an area. These devices detect biological and human activity information in real time and transmit this information to the server. The sensors can detect various physical changes such as temperature, vibration, and location data, while the cameras can acquire visual data.

[0562] The server receives information transmitted from these terminals and performs preprocessing, such as denoising and formatting the data, using a generative AI model. It then structures the information as time-series data and stores it. This process contributes to efficient information utilization and rapid detection of abnormal behavior.

[0563] For example, if a camera captures a group of animals deviating from their usual movement pattern at night, the server analyzes this information in real time to detect abnormal behavior. Based on the detected anomaly, it generates an alarm and sends it as a push notification to the device.

[0564] Conservation workers, as users, can take swift action based on notifications received via their devices and conduct direct on-site investigations. In this way, the present invention significantly improves the efficiency and accuracy of protecting wildlife and monitoring illegal activities within nature reserves.

[0565] An example of a prompt is, "What steps are necessary to detect abnormal behavioral patterns in animals?" This prompts the generative AI model to analyze specific behavioral patterns, enabling accurate detection.

[0566] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0567] Step 1:

[0568] Data collection by devices

[0569] The device uses sensors and cameras to detect information about the activity of living organisms and people within the protected area. Inputs include temperature, vibration, location data, and visual data. This data is collected and transmitted to a server via a communication module. Specifically, when a sensor instantly detects abnormal vibrations, the camera automatically rotates in that direction to capture video.

[0570] Step 2:

[0571] Server-based data preprocessing

[0572] The server receives raw data sent from the terminal and performs noise reduction and formatting. The data received as input may contain noise and redundant information. The server filters out these unnecessary parts and outputs a clear dataset. Specifically, the server detects abnormally high temperature changes and removes abnormal data.

[0573] Step 3:

[0574] Storing and structuring data in a database

[0575] The preprocessed data is structured as time-series data by the server and stored in a database. This serves as the foundation for subsequent analysis and anomaly detection. The output is a time-series dataset. The server then sorts the data chronologically based on its timestamps.

[0576] Step 4:

[0577] Analysis using generative AI models

[0578] The server uses stored time-series data as input to learn the normal behavioral patterns of organisms using a generative AI model. This prepares it to detect anomalies by comparing it with newly acquired data. The output is a baseline pattern of normal behavior. Specifically, the model analyzes trends from past data and updates its prediction algorithm.

[0579] Step 5:

[0580] Anomaly detection and alarm generation

[0581] The server analyzes newly acquired data in real time and automatically generates an alarm if abnormal behavior is detected. The input is newly acquired activity data. The output of the alarm includes the type of abnormality, the time of occurrence, location information, and related video footage. Specifically, an alarm is generated immediately upon detection of abnormal animal movement.

[0582] Step 6:

[0583] Alarm notifications via terminal

[0584] The terminal receives alarms from the server and pushes them to the user as notifications. The input is the alarm sent from the server. The output is the generation of notifications displayed on the user interface. Specifically, the terminal displays high-priority notifications as pop-ups on the user's device screen.

[0585] Step 7:

[0586] User response

[0587] The user takes appropriate action based on the alarm notification from the terminal. Detailed information about the alarm is provided as input. The user goes to the scene, investigates the cause of the abnormal behavior, and takes action. Specifically, the user uses a patrol vehicle to quickly reach the scene and perform a physical check.

[0588] (Application Example 1)

[0589] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0590] In urban parks and natural areas, there is a need to quickly and accurately detect and respond to anomalies while ensuring the safety of wildlife and citizens. In such environments, it is crucial to efficiently monitor unusual behavior of animals and suspicious individuals and to immediately notify relevant parties when problems occur. However, conventional technologies make it difficult to respond quickly and promptly, resulting in delays in appropriate responses to abnormal situations.

[0591] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0592] In this invention, the server includes means for acquiring activity data from multiple detection devices installed within a protected area, means for accumulating and learning from pre-processed data, and means for pushing alerts to terminals. This makes it possible to detect abnormal behavior of living organisms or suspicious individuals in real time and prompt citizens and administrators to take immediate action.

[0593] A "protected area" is an area where specific regulations are in place for the purpose of preserving nature and wildlife, and ensuring the safety of citizens.

[0594] A "detection device" is a device that includes sensors and cameras for detecting the activity of animals and suspicious individuals and converting it into data.

[0595] "Activity data" refers to data that records information such as the movements, locations, and temperatures of living organisms or suspicious individuals in a time-series format.

[0596] "Preprocessing" is the process of removing noise from acquired data and shaping it into a format that is easy to analyze.

[0597] A "database" is a recording system that structures and stores processed data as time-series information.

[0598] A "behavioral pattern" refers to the tendencies in movement and behavior that an organism exhibits at a specific time or in a particular situation.

[0599] "Abnormal behavior" refers to the actions of an organism or suspicious person that deviate from their normal behavioral patterns and require a swift response.

[0600] An "alarm" is a notification that is generated when an anomaly is detected, and its purpose is to prompt immediate action.

[0601] A "push notification" is a real-time alert message automatically sent to the user from the originating server.

[0602] A "terminal" refers to a portable information device or computer used to receive and display alarms.

[0603] To implement this invention, it is first necessary to install multiple detection devices in parks and natural areas within cities. These detection devices include sensors and cameras for detecting the movement of animals and suspicious individuals. The sensors acquire data such as temperature and vibration, and the cameras capture still images and videos.

[0604] The server receives data transmitted from these detection devices and performs data preprocessing. Preprocessing includes noise reduction and formatting. This process converts the data into a format that is easy to analyze.

[0605] The pre-processed data is stored in a database as time-series information. Based on this information, the server applies a generative AI model to learn the normal behavioral patterns of organisms. By comparing the learned behavioral patterns with newly acquired data, abnormal behavior is detected in real time.

[0606] When an anomaly is detected, the server immediately generates an alarm and sends this information as a push notification to the device. Citizens and administrators using the device can receive the push notification and check the details of the anomaly. This allows citizens to ensure their own safety and administrators to conduct on-site investigations as needed and respond quickly.

[0607] For example, if an animal exhibiting unusual behavior is observed in the park, the system will detect the anomaly and immediately send a notification to the administrator's terminal. The administrator can then receive the notification, confirm the situation, and take necessary measures.

[0608] An example of a prompt using a generative AI model is: "Explain how to analyze data detected by sensor and camera systems installed in urban parks to identify abnormal animal behavior and notify citizens in real time."

[0609] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0610] Step 1:

[0611] The server receives sensor and camera data from multiple detection devices installed in the protected area. Inputs include temperature, vibration, still images, and video data. This data is prepared for real-time processing by the server.

[0612] Step 2:

[0613] The server preprocesses the received data. This preprocessing includes noise removal and formatting. The data input is raw sensor and camera information, and the output is clean data suitable for analysis. Specific operations include, for example, removing outliers and converting the data into a time series.

[0614] Step 3:

[0615] The server stores pre-processed data in a database. The input is cleaned data, and the output is structured chronologically and stored in the database in a format that allows for quick access when needed. Specifically, this involves data indexing and tagging.

[0616] Step 4:

[0617] The server inputs accumulated data into a generating AI model to learn the normal behavioral patterns of organisms. In this step, a behavioral prediction model is trained using past data patterns. The input is structured data, and the output is the trained model. Specifically, the model's parameters are updated.

[0618] Step 5:

[0619] The server compares newly acquired data with existing models in real time to detect abnormal behavior. This allows for the rapid identification of behaviors defined as abnormal. The input is real-time data, and the output is information regarding the presence or absence of abnormalities. The server analyzes the results of model application and prepares a report.

[0620] Step 6:

[0621] When an anomaly is detected, the server generates an alarm and sends a notification to administrator and user terminals. The input is the result of the anomaly detection, and the output is an alarm in the form of a push notification. Specifically, the notification is formatted and sent.

[0622] Step 7:

[0623] The terminal receives push notifications from the server and displays their contents to the user. The input is notification information from the server, and the output is an alarm display on the terminal. Based on this information, the user can perform on-site checks and take safety measures.

[0624] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0625] This invention provides a system for streamlining wildlife conservation and monitoring poaching activities, and offers an applied technology that combines it with an emotion engine that recognizes the user's emotions. In addition to monitoring animal activity, detecting abnormal behavior, and generating alarms, this system can suggest more appropriate countermeasures by analyzing the user's emotional state.

[0626] System Configuration

[0627] This system consists of the aforementioned group of detection devices for monitoring animal behavior, a server, and user terminals. The server receives data from multiple sensors and cameras within the area and processes it in real time. The emotion engine analyzes the user's emotional state in real time and personalizes the received alarms and notifications based on the individual user's emotional response.

[0628] Data processing and sentiment analysis

[0629] While the server performs normal data preprocessing and behavioral pattern learning functions, it also acquires emotional data when the user receives a notification. This data is based on input from the camera and microphone on the user's device, and an emotion analysis algorithm is applied. This algorithm determines emotional states such as excitement, surprise, and stress, and stores this information in a database.

[0630] Alarm personalization

[0631] The emotion engine adjusts the content and method of alerts and notifications based on the user's emotional state. For example, if the user is feeling stressed, it can simplify the notification content and provide assistance in clarifying whether immediate action is required depending on the importance of the situation.

[0632] Specific example

[0633] One day, the server detects an animal's behavior deviating from its normal activity pattern within a protected area and generates an alert. When a notification is sent to the terminal, the emotion engine analyzes the user's facial expression data and detects surprise. The server receives this information and adjusts the alert content, allowing it to prioritize and present the user with necessary emergency response measures. In this way, the user can take appropriate action at the right time, improving the system's usefulness.

[0634] This invention enables wildlife conservation and anti-poaching measures to be operated with greater precision than before, while reducing user stress and emotional burden.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] Data collection

[0638] The server receives activity data on animals and suspicious individuals from detection devices installed within the protected area. This includes motion detection and temperature data from sensors, as well as image and video data from cameras.

[0639] Step 2:

[0640] Data preprocessing

[0641] The server analyzes the acquired data, removes noise, and formats the information into a consistent format. This ensures that the data is processed accurately and efficiently.

[0642] Step 3:

[0643] Save to database

[0644] The server stores the pre-processed data in a database. The data is organized chronologically so that it can be used for later analysis.

[0645] Step 4:

[0646] Learning behavioral patterns

[0647] The server analyzes the stored data to learn the animals' typical behavioral patterns. It then uses machine learning algorithms to model these patterns and create baseline data.

[0648] Step 5:

[0649] Real-time monitoring and anomaly detection

[0650] The server monitors new data in real time and compares it to learned normal behavior patterns. When it detects abnormal behavior or suspicious individuals, it processes the information immediately.

[0651] Step 6:

[0652] Alarm generation

[0653] The server generates an alarm based on the detected anomaly. The alarm includes the type of anomaly, location, time, and associated video data.

[0654] Step 7:

[0655] User sentiment analysis

[0656] Upon receiving an alarm notification, the device simultaneously analyzes the user's facial expressions and voice data using an emotion engine to understand the user's emotional state. This information is then returned to the server.

[0657] Step 8:

[0658] Alarm adjustment and notification

[0659] The server adjusts the alert content based on the user's emotional state. To reduce stress, it simplifies notifications and prioritizes displaying information appropriate to the urgency of the situation. The device then delivers the adjusted notifications to the user.

[0660] Step 9:

[0661] Immediate response

[0662] Users can review coordinated notifications and take appropriate action quickly in the field. They can also request further support or backup as needed.

[0663] (Example 2)

[0664] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0665] In wildlife conservation and poaching monitoring, there is a need for timely information and appropriate response measures when abnormal events are detected. However, information provision optimized for individual users has not yet been achieved, and appropriate responses may be difficult depending on the user's emotional state. This project aims to solve this problem.

[0666] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0667] In this invention, the server includes means for acquiring activity information of living organisms and suspicious persons from a plurality of detection devices installed within a protected area; means for processing and pre-processing the information; and means for analyzing the user's emotional state via a receiving terminal and personalizing the alarms and notifications based on individual emotional responses. This enables the provision of information optimized for the user's emotional state, allowing for a quick and effective response.

[0668] A "detection device" is a physical device installed within a protected area to collect information on surrounding activity.

[0669] "Activity information" refers to data about the movements and actions of living organisms or suspicious individuals, and is information acquired by detection devices.

[0670] "Preprocessing" refers to steps such as noise reduction and standardization of data formats that are performed to convert acquired activity information into a format that is easy to analyze.

[0671] A "database" is a collection of information that stores pre-processed information and is structured to be searchable and usable as needed.

[0672] A "behavioral pattern" is a model that shows the typical activity tendencies of an organism, and is constructed based on accumulated information.

[0673] "Abnormal behavior" refers to actions that deviate from normal behavioral patterns and are detected through real-time information monitoring.

[0674] An "alert" is information generated to warn users based on the detection of abnormal behavior, and it is the content that should be notified to the user.

[0675] "Emotional state" refers to the user's internal reactions and is analyzed based on data such as facial expressions and voice acquired through the receiving device.

[0676] "Personalization" refers to the process of adjusting information and notifications according to the user's emotional state and providing them in an individually optimized format.

[0677] This system is based on acquiring information about the activity of living organisms and suspicious individuals using detection devices installed within the protected area. It primarily collects data such as the movement of living organisms, heart rate, and body temperature, which is then processed on a server. The server applies appropriate algorithms to remove noise and standardize the data format during the data preprocessing stage. While industry-standard analytical tools are used for data analysis as a software platform, specific names are not mentioned here.

[0678] Next, the server runs the animal behavior analysis process, comparing the real-time data with normal behavioral patterns stored in the database. This allows for the detection of abnormal behavior.

[0679] Furthermore, the user's device collects emotional data through its built-in camera and microphone. A specialized algorithm is applied to analyze the user's facial expressions and changes in voice to determine emotional states such as excitement, surprise, and stress. The analysis results are sent to a server, which forms the basis for personalizing alarms and notifications.

[0680] For example, if the server detects abnormal behavior, it generates an alarm based on this information. If sentiment analysis reveals that the user is in a surprised state, the alarm content is adjusted, and a concise and clear notification is sent to encourage a quick response.

[0681] As an example of a specific prompt, we will use the following format: "Suggest a way to notify the user when abnormal behavior in wild animals is detected. How can the notification be effectively personalized if the user is startled?" This sentence is a fundamental Pro question for generating appropriate notification methods in a generative AI model.

[0682] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0683] Step 1:

[0684] The server collects activity information on living organisms and suspicious individuals from multiple detection devices installed within the protected area. Input data includes animal movement, body temperature, and heart rate. Based on this, the server compresses the data and converts it to a format necessary to improve communication efficiency. Output data is generated as a standardized dataset, facilitating subsequent processing.

[0685] Step 2:

[0686] The server preprocesses the collected data. The input is raw data obtained from the detection device. Based on this, the server performs filtering to remove noise and extract only meaningful information. As output, it generates a clean, analyzable dataset.

[0687] Step 3:

[0688] The server analyzes animal behavior patterns using pre-processed data. The input is a pre-processed dataset. Here, the server applies a machine learning model to identify typical animal behavior patterns. As output, the behavior pattern model is updated and stored in a database.

[0689] Step 4:

[0690] The device collects user emotion data using its camera and microphone. Input consists of the user's facial expressions and voice. Based on this, an emotion analysis algorithm is used to evaluate the emotional state. The output identifies emotions such as excitement, surprise, and stress, and the results are sent to a server as data.

[0691] Step 5:

[0692] The server monitors newly acquired data in real time and detects abnormal behavior. The input consists of an updated behavioral pattern model and real-time acquired data. This data is analyzed, and if an anomaly is found, an alarm is generated. The output is alarm data indicating the abnormal behavior, and the anomaly is identified.

[0693] Step 6:

[0694] The server personalizes alarms and notifications based on the user's emotional state. Inputs include alarm data related to abnormal behavior and the user's emotional analysis results. The server then adjusts the format and content of the notifications to make them more acceptable to the user. Personalized notification data is generated as output.

[0695] Step 7:

[0696] The server sends personalized notifications to the user's device. The input is personalized notification data. Based on this, the server immediately pushes the notification. As an output, the user receives appropriate action plans through their device, enabling quick decision-making.

[0697] (Application Example 2)

[0698] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0699] Conventional wildlife conservation and poaching monitoring systems can monitor animal behavior and detect anomalies, but they have the drawback of providing uniform alarms and notifications that cannot respond to the emotional state of individual users. As a result, users may experience excessive stress when receiving notifications, making it difficult to respond quickly and appropriately.

[0700] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0701] In this invention, the server includes means for acquiring activity data from multiple detection devices installed within a protected area; means for processing and pre-processing the acquired data; means for accumulating the pre-processed data and storing it in a database including time-series information; means for learning normal behavior patterns based on the accumulated data; means for monitoring newly acquired data in real time and detecting abnormal behavior; means for generating alarms and sending notifications based on the detected abnormal behavior; and means for analyzing the user's emotional state and personalizing the alarms and notifications. This makes it possible to send personalized notifications according to the user's emotional state, enabling the user to respond quickly and accurately without experiencing excessive stress.

[0702] A "detection device" is a hardware device installed within a protected area to monitor the activity of animals or other targets.

[0703] "Activity data" refers to information about the movements and behaviors of animals or targets acquired by detection devices.

[0704] "Preprocessing" refers to the process of appropriately processing acquired activity data and shaping it into a format that can be analyzed.

[0705] "Time-series information" refers to information that describes the state or changes in data collected over time.

[0706] "Typical behavioral patterns" refer to the typical behavioral tendencies or habits that an animal or subject exhibits over a long period of time.

[0707] "Abnormal behavior" refers to atypical behavior of an animal or subject that deviates from its normal behavioral patterns.

[0708] An "alert" is an alert generated based on detected abnormal behavior, indicating that a specified action is required.

[0709] A "notification" is a message or warning used to convey information to a user.

[0710] "Emotional state" refers to a user's psychological response or emotional state in response to a specific situation.

[0711] "Personalization" refers to adjusting something to suit the specific needs and circumstances of each individual user.

[0712] The system for carrying out this invention involves placing a detection device, including multiple sensors and cameras, within a protected area to acquire animal activity data. A server receives this data in real time, performs data preprocessing, and stores it in a database as time-series information.

[0713] The server learns normal behavior patterns and monitors newly acquired data in real time to detect abnormal behavior. Based on the detected abnormal behavior, it generates an alarm and sends notifications to various terminals. In this process, the server analyzes emotional data from the user's terminal and applies an emotional analysis algorithm to determine the user's emotional state. The analysis uses the smartphone's camera and microphone.

[0714] The device displays alarms and notifications sent from the server in a personalized manner based on the user's emotional state. For example, if the user is feeling stressed, the notification will be concise and clearly indicate whether immediate action is required.

[0715] For example, if a server detects unusual animal movement in a city park and sends a notification to the user's smartphone, and the user is startled, the server adjusts the alarm based on this information. This allows the user to respond effectively, improving the system's usefulness.

[0716] By using generative AI models, it is possible to analyze data on users' emotional states through deep learning and provide more precise and personalized responses. An example of a prompt would be: "I want to design an urban ecosystem monitoring app. I want to monitor the movements of wild animals and adjust the alert content based on the user's emotions. Please provide details of the emotion analysis algorithm along with specific examples of how it works."

[0717] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0718] Step 1:

[0719] The server acquires activity data from various sensors and cameras installed within the protected area. This data includes animal location, movement, and environmental conditions. Input is real-time data from each detection device, and output is in a data format that can be pre-processed internally by the server. The server aggregates this data and performs pre-processing to convert it into an appropriate format.

[0720] Step 2:

[0721] The server stores pre-processed data in a database as time-series information. Data is stored in JSON or CSV format, enabling historical data analysis. The input is pre-processed data, and the output is time-series data stored in the database.

[0722] Step 3:

[0723] The server learns typical behavioral patterns based on accumulated data. This process uses machine learning algorithms to model typical animal behavior. The input is historical time-series data, and the output is the learned behavioral model.

[0724] Step 4:

[0725] The server monitors newly acquired data in real time and detects abnormal behavior by comparing it with learned behavioral patterns. If an anomaly is detected, it generates an alarm. The input is real-time data and a behavioral model, and the output is an alarm for abnormal behavior.

[0726] Step 5:

[0727] The server notifies each terminal of an alarm generated based on abnormal behavior. At the same time, it acquires emotional data from the user's smartphone and analyzes it using an emotional analysis algorithm. The input is the alarm data and the user's emotional data, and the output is the analyzed emotional information.

[0728] Step 6:

[0729] The device uses the sentiment analysis results received from the server to personalize alarms and notifications. The content of notifications is concisely adjusted according to the user's emotional state. The input is sentiment information and alarm data, and the output is a personalized notification message.

[0730] Step 7:

[0731] Users receive personalized notifications displayed on their devices. They can review the notification content and take immediate action as needed. The input is the personalized notification, and the output is the user's response action.

[0732] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0733] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0734] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0735] [Fourth Embodiment]

[0736] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0737] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0738] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0739] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0740] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0741] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0742] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0743] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0744] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0745] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0746] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0747] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0748] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0749] This invention aims to protect wildlife and monitor poaching activities in extensive nature reserves, and provides an automated monitoring system utilizing AI technology. By installing multiple detection devices within the area and monitoring animal activity and suspicious activity, this system can efficiently detect anomalies in real time and take immediate countermeasures.

[0750] System Configuration

[0751] This system is designed to first use sensors and cameras as detection devices to sense animal movement and the presence of people, and to collect the data. The sensors collect temperature, vibration, and location data, while the cameras acquire still images and videos. This collected data is transmitted to a dedicated server.

[0752] Data processing and analysis

[0753] The server preprocesses the received data, removing noise and formatting it. The preprocessed data is stored in a database and structured as time-series information. This allows machine learning models to be applied to identify the animals' normal behavioral patterns. The server compares these models with newly acquired data in real time to detect abnormal behavior.

[0754] Anomaly detection and alarm generation

[0755] The server automatically generates an alarm when it detects abnormal behavior or suspicious activity. The alarm includes the type, time, location, and video data of the detected anomaly. This information is immediately sent as a push notification to the designated device.

[0756] Response and Management

[0757] The terminal receives notifications from the server and prompts the user to take appropriate action. The user, such as a ranger or administrator in a protected area, uses the received information to conduct an on-site investigation and respond to the alert as needed.

[0758] Specific example

[0759] For example, suppose a camera in a protected area captures a herd of animals deviating from their usual migration route one night. The server analyzes this unusual movement in real time and generates an alert as an anomaly detection. The terminal receives this alert and sends a push notification to the ranger. The ranger, as a user, can then rush to the scene, check on the animals, and investigate the cause of the unusual behavior.

[0760] In this way, the present invention enhances efficiency in animal protection and monitoring of illegal activities, enabling a rapid and accurate response.

[0761] The following describes the processing flow.

[0762] Step 1:

[0763] Data collection

[0764] The server periodically receives data on animal and intruder activity from each detection device within the protected area. This includes location, movement, and temperature data from sensors, as well as image and video data from cameras.

[0765] Step 2:

[0766] Data preprocessing

[0767] The server denoises the collected raw data and formats it into a standard format. This improves the quality of the data and makes it suitable for subsequent analysis.

[0768] Step 3:

[0769] Data storage

[0770] The server stores the pre-processed data as time-series information in the database. Here, metadata such as associated timestamps and location information is attached to the data.

[0771] Step 4:

[0772] Learning of normal behavioral patterns

[0773] The server uses accumulated data to learn the animals' typical behavioral patterns. This process employs machine learning algorithms to model the animals' habits and general movement tendencies.

[0774] Step 5:

[0775] Real-time monitoring and data analysis

[0776] The server constantly receives new data in real time and compares it with learned behavioral patterns. This makes it possible to quickly detect movements that deviate from normal behavior.

[0777] Step 6:

[0778] Anomaly detection and alarm generation

[0779] When the server detects unusual behavior or suspicious individuals, it generates an alert that includes the type, location, and time of the anomaly. This alert information is processed quickly, and the process moves to the next step.

[0780] Step 7:

[0781] Notification distribution

[0782] The terminal receives alerts sent from the server and distributes them as push notifications to rangers and administrators. The notifications include the alert details and information necessary for taking action.

[0783] Step 8:

[0784] Response and Action

[0785] Users can check notifications received on their devices and take necessary actions on-site. For example, they can quickly investigate suspicious individuals or rescue animals. Rangers can also request further investigation or assistance depending on the situation on the ground.

[0786] (Example 1)

[0787] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0788] Regarding wildlife conservation in extensive nature reserves, current monitoring systems face challenges such as insufficient real-time detection of abnormal behavior and difficulty in responding efficiently and quickly. Furthermore, problems such as wasted responses due to false alarms and the failure to transmit warnings when needed have been pointed out. It is necessary to resolve these challenges and achieve effective monitoring of wildlife and illegal activities.

[0789] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0790] In this invention, the server includes means for acquiring information on the activities of living organisms and humans, means for performing noise reduction and formatting, and means for storing the information in an information structure that includes time-series information. This enables real-time monitoring within nature reserves, allowing for early detection and prompt response to abnormal behavior.

[0791] A "detection device" is a device installed to detect information about the activity of living organisms or people within a specific area and to transmit that information to a server.

[0792] "Activity information" refers to data that shows physical changes such as the movement, location, vibration, and temperature of living organisms and people.

[0793] "Denoising and formatting" is the process of removing unnecessary data from acquired information and converting it into a consistent form.

[0794] "Information structure" refers to the format in which information is organized and stored chronologically within a database or other storage system.

[0795] A "biological behavior model" refers to data and algorithms that learn the normal behavioral patterns of organisms and use that to determine the abnormality of new behaviors.

[0796] An "alarm" is a notification or alert generated to inform of abnormal behavior or potential danger.

[0797] A "receiving device" is a device used to receive alarms and notifications transmitted from a server, and includes, for example, smartphones and tablets.

[0798] A "conservationist" refers to an individual or organization responsible for the protection and management of wildlife within a nature reserve.

[0799] In implementing this invention, the collaboration between a server, a terminal, and a user is primarily utilized. The terminal includes multiple sensors and cameras placed within an area. These devices detect biological and human activity information in real time and transmit this information to the server. The sensors can detect various physical changes such as temperature, vibration, and location data, while the cameras can acquire visual data.

[0800] The server receives information transmitted from these terminals and performs preprocessing, such as denoising and formatting the data, using a generative AI model. It then structures the information as time-series data and stores it. This process contributes to efficient information utilization and rapid detection of abnormal behavior.

[0801] For example, if a camera captures a group of animals deviating from their usual movement pattern at night, the server analyzes this information in real time to detect abnormal behavior. Based on the detected anomaly, it generates an alarm and sends it as a push notification to the device.

[0802] Conservation workers, as users, can take swift action based on notifications received via their devices and conduct direct on-site investigations. In this way, the present invention significantly improves the efficiency and accuracy of protecting wildlife and monitoring illegal activities within nature reserves.

[0803] An example of a prompt is, "What steps are necessary to detect abnormal behavioral patterns in animals?" This prompts the generative AI model to analyze specific behavioral patterns, enabling accurate detection.

[0804] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0805] Step 1:

[0806] Data collection by devices

[0807] The device uses sensors and cameras to detect information about the activity of living organisms and people within the protected area. Inputs include temperature, vibration, location data, and visual data. This data is collected and transmitted to a server via a communication module. Specifically, when a sensor instantly detects abnormal vibrations, the camera automatically rotates in that direction to capture video.

[0808] Step 2:

[0809] Server-based data preprocessing

[0810] The server receives raw data sent from the terminal and performs noise reduction and formatting. The data received as input may contain noise and redundant information. The server filters out these unnecessary parts and outputs a clear dataset. Specifically, the server detects abnormally high temperature changes and removes abnormal data.

[0811] Step 3:

[0812] Storing and structuring data in a database

[0813] The preprocessed data is structured as time-series data by the server and stored in a database. This serves as the foundation for subsequent analysis and anomaly detection. The output is a time-series dataset. The server then sorts the data chronologically based on its timestamps.

[0814] Step 4:

[0815] Analysis using generative AI models

[0816] The server uses stored time-series data as input to learn the normal behavioral patterns of organisms using a generative AI model. This prepares it to detect anomalies by comparing it with newly acquired data. The output is a baseline pattern of normal behavior. Specifically, the model analyzes trends from past data and updates its prediction algorithm.

[0817] Step 5:

[0818] Anomaly detection and alarm generation

[0819] The server analyzes newly acquired data in real time and automatically generates an alarm if abnormal behavior is detected. The input is newly acquired activity data. The output of the alarm includes the type of abnormality, the time of occurrence, location information, and related video footage. Specifically, an alarm is generated immediately upon detection of abnormal animal movement.

[0820] Step 6:

[0821] Alarm notifications via terminal

[0822] The terminal receives alarms from the server and pushes them to the user as notifications. The input is the alarm sent from the server. The output is the generation of notifications displayed on the user interface. Specifically, the terminal displays high-priority notifications as pop-ups on the user's device screen.

[0823] Step 7:

[0824] User response

[0825] The user takes appropriate action based on the alarm notification from the terminal. Detailed information about the alarm is provided as input. The user goes to the scene, investigates the cause of the abnormal behavior, and takes action. Specifically, the user uses a patrol vehicle to quickly reach the scene and perform a physical check.

[0826] (Application Example 1)

[0827] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0828] In urban parks and natural areas, there is a need to quickly and accurately detect and respond to anomalies while ensuring the safety of wildlife and citizens. In such environments, it is crucial to efficiently monitor unusual behavior of animals and suspicious individuals and to immediately notify relevant parties when problems occur. However, conventional technologies make it difficult to respond quickly and promptly, resulting in delays in appropriate responses to abnormal situations.

[0829] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0830] In this invention, the server includes means for acquiring activity data from multiple detection devices installed within a protected area, means for accumulating and learning from pre-processed data, and means for pushing alerts to terminals. This makes it possible to detect abnormal behavior of living organisms or suspicious individuals in real time and prompt citizens and administrators to take immediate action.

[0831] A "protected area" is an area where specific regulations are in place for the purpose of preserving nature and wildlife, and ensuring the safety of citizens.

[0832] A "detection device" is a device that includes sensors and cameras for detecting the activity of animals and suspicious individuals and converting it into data.

[0833] "Activity data" refers to data that records information such as the movements, locations, and temperatures of living organisms or suspicious individuals in a time-series format.

[0834] "Preprocessing" is the process of removing noise from acquired data and shaping it into a format that is easy to analyze.

[0835] A "database" is a recording system that structures and stores processed data as time-series information.

[0836] A "behavioral pattern" refers to the tendencies in movement and behavior that an organism exhibits at a specific time or in a particular situation.

[0837] "Abnormal behavior" refers to the actions of an organism or suspicious person that deviate from their normal behavioral patterns and require a swift response.

[0838] An "alarm" is a notification that is generated when an anomaly is detected, and its purpose is to prompt immediate action.

[0839] A "push notification" is a real-time alert message automatically sent to the user from the originating server.

[0840] A "terminal" refers to a portable information device or computer used to receive and display alarms.

[0841] To implement this invention, it is first necessary to install multiple detection devices in parks and natural areas within cities. These detection devices include sensors and cameras for detecting the movement of animals and suspicious individuals. The sensors acquire data such as temperature and vibration, and the cameras capture still images and videos.

[0842] The server receives data transmitted from these detection devices and performs data preprocessing. Preprocessing includes noise reduction and formatting. This process converts the data into a format that is easy to analyze.

[0843] The pre-processed data is stored in a database as time-series information. Based on this information, the server applies a generative AI model to learn the normal behavioral patterns of organisms. By comparing the learned behavioral patterns with newly acquired data, abnormal behavior is detected in real time.

[0844] When an anomaly is detected, the server immediately generates an alarm and sends this information as a push notification to the device. Citizens and administrators using the device can receive the push notification and check the details of the anomaly. This allows citizens to ensure their own safety and administrators to conduct on-site investigations as needed and respond quickly.

[0845] For example, if an animal exhibiting unusual behavior is observed in the park, the system will detect the anomaly and immediately send a notification to the administrator's terminal. The administrator can then receive the notification, confirm the situation, and take necessary measures.

[0846] An example of a prompt using a generative AI model is: "Explain how to analyze data detected by sensor and camera systems installed in urban parks to identify abnormal animal behavior and notify citizens in real time."

[0847] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0848] Step 1:

[0849] The server receives sensor and camera data from multiple detection devices installed in the protected area. Inputs include temperature, vibration, still images, and video data. This data is prepared for real-time processing by the server.

[0850] Step 2:

[0851] The server preprocesses the received data. This preprocessing includes noise removal and formatting. The data input is raw sensor and camera information, and the output is clean data suitable for analysis. Specific operations include, for example, removing outliers and converting the data into a time series.

[0852] Step 3:

[0853] The server stores pre-processed data in a database. The input is cleaned data, and the output is structured chronologically and stored in the database in a format that allows for quick access when needed. Specifically, this involves data indexing and tagging.

[0854] Step 4:

[0855] The server inputs accumulated data into a generating AI model to learn the normal behavioral patterns of organisms. In this step, a behavioral prediction model is trained using past data patterns. The input is structured data, and the output is the trained model. Specifically, the model's parameters are updated.

[0856] Step 5:

[0857] The server compares newly acquired data with existing models in real time to detect abnormal behavior. This allows for the rapid identification of behaviors defined as abnormal. The input is real-time data, and the output is information regarding the presence or absence of abnormalities. The server analyzes the results of model application and prepares a report.

[0858] Step 6:

[0859] When an anomaly is detected, the server generates an alarm and sends a notification to administrator and user terminals. The input is the result of the anomaly detection, and the output is an alarm in the form of a push notification. Specifically, the notification is formatted and sent.

[0860] Step 7:

[0861] The terminal receives push notifications from the server and displays their contents to the user. The input is notification information from the server, and the output is an alarm display on the terminal. Based on this information, the user can perform on-site checks and take safety measures.

[0862] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0863] This invention provides a system for streamlining wildlife conservation and monitoring poaching activities, and offers an applied technology that combines it with an emotion engine that recognizes the user's emotions. In addition to monitoring animal activity, detecting abnormal behavior, and generating alarms, this system can suggest more appropriate countermeasures by analyzing the user's emotional state.

[0864] System Configuration

[0865] This system consists of the aforementioned group of detection devices for monitoring animal behavior, a server, and user terminals. The server receives data from multiple sensors and cameras within the area and processes it in real time. The emotion engine analyzes the user's emotional state in real time and personalizes the received alarms and notifications based on the individual user's emotional response.

[0866] Data processing and sentiment analysis

[0867] While the server performs normal data preprocessing and behavioral pattern learning functions, it also acquires emotional data when the user receives a notification. This data is based on input from the camera and microphone on the user's device, and an emotion analysis algorithm is applied. This algorithm determines emotional states such as excitement, surprise, and stress, and stores this information in a database.

[0868] Alarm personalization

[0869] The emotion engine adjusts the content and method of alerts and notifications based on the user's emotional state. For example, if the user is feeling stressed, it can simplify the notification content and provide assistance in clarifying whether immediate action is required depending on the importance of the situation.

[0870] Specific example

[0871] One day, the server detects an animal's behavior deviating from its normal activity pattern within a protected area and generates an alert. When a notification is sent to the terminal, the emotion engine analyzes the user's facial expression data and detects surprise. The server receives this information and adjusts the alert content, allowing it to prioritize and present the user with necessary emergency response measures. In this way, the user can take appropriate action at the right time, improving the system's usefulness.

[0872] This invention enables wildlife conservation and anti-poaching measures to be operated with greater precision than before, while reducing user stress and emotional burden.

[0873] The following describes the processing flow.

[0874] Step 1:

[0875] Data collection

[0876] The server receives activity data on animals and suspicious individuals from detection devices installed within the protected area. This includes motion detection and temperature data from sensors, as well as image and video data from cameras.

[0877] Step 2:

[0878] Data preprocessing

[0879] The server analyzes the acquired data, removes noise, and formats the information into a consistent format. This ensures that the data is processed accurately and efficiently.

[0880] Step 3:

[0881] Save to database

[0882] The server stores the pre-processed data in a database. The data is organized chronologically so that it can be used for later analysis.

[0883] Step 4:

[0884] Learning behavioral patterns

[0885] The server analyzes the stored data to learn the animals' typical behavioral patterns. It then uses machine learning algorithms to model these patterns and create baseline data.

[0886] Step 5:

[0887] Real-time monitoring and anomaly detection

[0888] The server monitors new data in real time and compares it to learned normal behavior patterns. When it detects abnormal behavior or suspicious individuals, it processes the information immediately.

[0889] Step 6:

[0890] Alarm generation

[0891] The server generates an alarm based on the detected anomaly. The alarm includes the type of anomaly, location, time, and associated video data.

[0892] Step 7:

[0893] User sentiment analysis

[0894] Upon receiving an alarm notification, the device simultaneously analyzes the user's facial expressions and voice data using an emotion engine to understand the user's emotional state. This information is then returned to the server.

[0895] Step 8:

[0896] Alarm adjustment and notification

[0897] The server adjusts the alert content based on the user's emotional state. To reduce stress, it simplifies notifications and prioritizes displaying information appropriate to the urgency of the situation. The device then delivers the adjusted notifications to the user.

[0898] Step 9:

[0899] Immediate response

[0900] Users can review coordinated notifications and take appropriate action quickly in the field. They can also request further support or backup as needed.

[0901] (Example 2)

[0902] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0903] In wildlife conservation and poaching monitoring, there is a need for timely information and appropriate response measures when abnormal events are detected. However, information provision optimized for individual users has not yet been achieved, and appropriate responses may be difficult depending on the user's emotional state. This project aims to solve this problem.

[0904] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0905] In this invention, the server includes means for acquiring activity information of living organisms and suspicious persons from a plurality of detection devices installed within a protected area; means for processing and pre-processing the information; and means for analyzing the user's emotional state via a receiving terminal and personalizing the alarms and notifications based on individual emotional responses. This enables the provision of information optimized for the user's emotional state, allowing for a quick and effective response.

[0906] A "detection device" is a physical device installed within a protected area to collect information on surrounding activity.

[0907] "Activity information" refers to data about the movements and actions of living organisms or suspicious individuals, and is information acquired by detection devices.

[0908] "Preprocessing" refers to steps such as noise reduction and standardization of data formats that are performed to convert acquired activity information into a format that is easy to analyze.

[0909] A "database" is a collection of information that stores pre-processed information and is structured to be searchable and usable as needed.

[0910] A "behavioral pattern" is a model that shows the typical activity tendencies of an organism, and is constructed based on accumulated information.

[0911] "Abnormal behavior" refers to actions that deviate from normal behavioral patterns and are detected through real-time information monitoring.

[0912] An "alert" is information generated to warn users based on the detection of abnormal behavior, and it is the content that should be notified to the user.

[0913] "Emotional state" refers to the user's internal reactions and is analyzed based on data such as facial expressions and voice acquired through the receiving device.

[0914] "Personalization" refers to the process of adjusting information and notifications according to the user's emotional state and providing them in an individually optimized format.

[0915] This system is based on acquiring information about the activity of living organisms and suspicious individuals using detection devices installed within the protected area. It primarily collects data such as the movement of living organisms, heart rate, and body temperature, which is then processed on a server. The server applies appropriate algorithms to remove noise and standardize the data format during the data preprocessing stage. While industry-standard analytical tools are used for data analysis as a software platform, specific names are not mentioned here.

[0916] Next, the server runs the animal behavior analysis process, comparing the real-time data with normal behavioral patterns stored in the database. This allows for the detection of abnormal behavior.

[0917] Furthermore, the user's device collects emotional data through its built-in camera and microphone. A specialized algorithm is applied to analyze the user's facial expressions and changes in voice to determine emotional states such as excitement, surprise, and stress. The analysis results are sent to a server, which forms the basis for personalizing alarms and notifications.

[0918] For example, if the server detects abnormal behavior, it generates an alarm based on this information. If sentiment analysis reveals that the user is in a surprised state, the alarm content is adjusted, and a concise and clear notification is sent to encourage a quick response.

[0919] As an example of a specific prompt, we will use the following format: "Suggest a way to notify the user when abnormal behavior in wild animals is detected. How can the notification be effectively personalized if the user is startled?" This sentence is a fundamental Pro question for generating appropriate notification methods in a generative AI model.

[0920] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0921] Step 1:

[0922] The server collects activity information on living organisms and suspicious individuals from multiple detection devices installed within the protected area. Input data includes animal movement, body temperature, and heart rate. Based on this, the server compresses the data and converts it to a format necessary to improve communication efficiency. Output data is generated as a standardized dataset, facilitating subsequent processing.

[0923] Step 2:

[0924] The server preprocesses the collected data. The input is raw data obtained from the detection device. Based on this, the server performs filtering to remove noise and extract only meaningful information. As output, it generates a clean, analyzable dataset.

[0925] Step 3:

[0926] The server analyzes animal behavior patterns using pre-processed data. The input is a pre-processed dataset. Here, the server applies a machine learning model to identify typical animal behavior patterns. As output, the behavior pattern model is updated and stored in a database.

[0927] Step 4:

[0928] The device collects user emotion data using its camera and microphone. Input consists of the user's facial expressions and voice. Based on this, an emotion analysis algorithm is used to evaluate the emotional state. The output identifies emotions such as excitement, surprise, and stress, and the results are sent to a server as data.

[0929] Step 5:

[0930] The server monitors newly acquired data in real time and detects abnormal behavior. The input consists of an updated behavioral pattern model and real-time acquired data. This data is analyzed, and if an anomaly is found, an alarm is generated. The output is alarm data indicating the abnormal behavior, and the anomaly is identified.

[0931] Step 6:

[0932] The server personalizes alarms and notifications based on the user's emotional state. Inputs include alarm data related to abnormal behavior and the user's emotional analysis results. The server then adjusts the format and content of the notifications to make them more acceptable to the user. Personalized notification data is generated as output.

[0933] Step 7:

[0934] The server sends personalized notifications to the user's device. The input is personalized notification data. Based on this, the server immediately pushes the notification. As an output, the user receives appropriate action plans through their device, enabling quick decision-making.

[0935] (Application Example 2)

[0936] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0937] Conventional wildlife conservation and poaching monitoring systems can monitor animal behavior and detect anomalies, but they have the drawback of providing uniform alarms and notifications that cannot respond to the emotional state of individual users. As a result, users may experience excessive stress when receiving notifications, making it difficult to respond quickly and appropriately.

[0938] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0939] In this invention, the server includes means for acquiring activity data from multiple detection devices installed within a protected area; means for processing and pre-processing the acquired data; means for accumulating the pre-processed data and storing it in a database including time-series information; means for learning normal behavior patterns based on the accumulated data; means for monitoring newly acquired data in real time and detecting abnormal behavior; means for generating alarms and sending notifications based on the detected abnormal behavior; and means for analyzing the user's emotional state and personalizing the alarms and notifications. This makes it possible to send personalized notifications according to the user's emotional state, enabling the user to respond quickly and accurately without experiencing excessive stress.

[0940] A "detection device" is a hardware device installed within a protected area to monitor the activity of animals or other targets.

[0941] "Activity data" refers to information about the movements and behaviors of animals or targets acquired by detection devices.

[0942] "Preprocessing" refers to the process of appropriately processing acquired activity data and shaping it into a format that can be analyzed.

[0943] "Time-series information" refers to information that describes the state or changes in data collected over time.

[0944] "Typical behavioral patterns" refer to the typical behavioral tendencies or habits that an animal or subject exhibits over a long period of time.

[0945] "Abnormal behavior" refers to atypical behavior of an animal or subject that deviates from its normal behavioral patterns.

[0946] An "alert" is an alert generated based on detected abnormal behavior, indicating that a specified action is required.

[0947] A "notification" is a message or warning used to convey information to a user.

[0948] "Emotional state" refers to a user's psychological response or emotional state in response to a specific situation.

[0949] "Personalization" refers to adjusting something to suit the specific needs and circumstances of each individual user.

[0950] The system for carrying out this invention involves placing a detection device, including multiple sensors and cameras, within a protected area to acquire animal activity data. A server receives this data in real time, performs data preprocessing, and stores it in a database as time-series information.

[0951] The server learns normal behavior patterns and monitors newly acquired data in real time to detect abnormal behavior. Based on the detected abnormal behavior, it generates an alarm and sends notifications to various terminals. In this process, the server analyzes emotional data from the user's terminal and applies an emotional analysis algorithm to determine the user's emotional state. The analysis uses the smartphone's camera and microphone.

[0952] The device displays alarms and notifications sent from the server in a personalized manner based on the user's emotional state. For example, if the user is feeling stressed, the notification will be concise and clearly indicate whether immediate action is required.

[0953] For example, if a server detects unusual animal movement in a city park and sends a notification to the user's smartphone, and the user is startled, the server adjusts the alarm based on this information. This allows the user to respond effectively, improving the system's usefulness.

[0954] By using generative AI models, it is possible to analyze data on users' emotional states through deep learning and provide more precise and personalized responses. An example of a prompt would be: "I want to design an urban ecosystem monitoring app. I want to monitor the movements of wild animals and adjust the alert content based on the user's emotions. Please provide details of the emotion analysis algorithm along with specific examples of how it works."

[0955] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0956] Step 1:

[0957] The server acquires activity data from various sensors and cameras installed within the protected area. This data includes animal location, movement, and environmental conditions. Input is real-time data from each detection device, and output is in a data format that can be pre-processed internally by the server. The server aggregates this data and performs pre-processing to convert it into an appropriate format.

[0958] Step 2:

[0959] The server stores pre-processed data in a database as time-series information. Data is stored in JSON or CSV format, enabling historical data analysis. The input is pre-processed data, and the output is time-series data stored in the database.

[0960] Step 3:

[0961] The server learns typical behavioral patterns based on accumulated data. This process uses machine learning algorithms to model typical animal behavior. The input is historical time-series data, and the output is the learned behavioral model.

[0962] Step 4:

[0963] The server monitors newly acquired data in real time and detects abnormal behavior by comparing it with learned behavioral patterns. If an anomaly is detected, it generates an alarm. The input is real-time data and a behavioral model, and the output is an alarm for abnormal behavior.

[0964] Step 5:

[0965] The server notifies each terminal of an alarm generated based on abnormal behavior. At the same time, it acquires emotional data from the user's smartphone and analyzes it using an emotional analysis algorithm. The input is the alarm data and the user's emotional data, and the output is the analyzed emotional information.

[0966] Step 6:

[0967] The device uses the sentiment analysis results received from the server to personalize alarms and notifications. The content of notifications is concisely adjusted according to the user's emotional state. The input is sentiment information and alarm data, and the output is a personalized notification message.

[0968] Step 7:

[0969] Users receive personalized notifications displayed on their devices. They can review the notification content and take immediate action as needed. The input is the personalized notification, and the output is the user's response action.

[0970] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0971] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0972] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0973] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0974] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0975] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0976] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0977] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0978] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0979] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0980] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0981] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0982] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0983] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0984] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0985] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0986] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0987] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0988] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0989] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0990] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0991] The following is further disclosed regarding the embodiments described above.

[0992] (Claim 1)

[0993] A means of acquiring activity data of animals and suspicious individuals from multiple detection devices installed within the protected area,

[0994] A means for processing and pre-processing the acquired data,

[0995] A means for accumulating the aforementioned preprocessed data and storing it in a database including time-series information,

[0996] A means for learning the normal behavioral patterns of animals based on the aforementioned accumulated data,

[0997] A means to monitor newly acquired data in real time and detect abnormal behavior,

[0998] A means for generating an alarm and sending a notification based on the detected abnormal behavior,

[0999] A system that includes this.

[1000] (Claim 2)

[1001] The system according to claim 1, further comprising means for identifying abnormalities by comparing them with a model of the animal's behavioral patterns when detecting the abnormal behavior.

[1002] (Claim 3)

[1003] The system according to claim 1, further comprising means for prompting a protection worker to take immediate action by push notification to a receiving terminal.

[1004] "Example 1"

[1005] (Claim 1)

[1006] A means of acquiring information on the activity of living organisms and people from multiple detection devices installed within a protected area,

[1007] A means for processing the acquired information and performing noise reduction and formatting,

[1008] Means for storing the processed information and saving it in an information structure including time-series information,

[1009] A means for learning the normal behavioral patterns of organisms based on the accumulated information,

[1010] A means to monitor newly acquired information in real time and detect abnormal behavior,

[1011] A means for generating an alarm and sending a notification based on the detected abnormal behavior,

[1012] The aforementioned alarm is transmitted to a receiving device, and means are provided to prompt the appropriate action.

[1013] A system that includes this.

[1014] (Claim 2)

[1015] The system according to claim 1, further comprising means for identifying abnormalities by comparing them with a biological behavior model when detecting the abnormal behavior.

[1016] (Claim 3)

[1017] The system according to claim 1, further comprising means for prompting a protection worker to take immediate action by push notification to a receiving device.

[1018] "Application Example 1"

[1019] (Claim 1)

[1020] A means of acquiring activity data of living organisms and suspicious individuals from multiple detection devices installed within the protected area,

[1021] A means for processing and pre-processing the acquired data,

[1022] A means for accumulating the aforementioned preprocessed data and storing it in a database including time-series information,

[1023] A means for learning the normal behavioral patterns of organisms based on the aforementioned accumulated data,

[1024] A means to monitor newly acquired data in real time and detect abnormal behavior,

[1025] A means for generating an alarm and sending a notification based on the detected abnormal behavior,

[1026] The aforementioned warning is sent as a push notification to terminals used by citizens and administrators, and is a means of promoting safety in parks and natural areas within the city.

[1027] A system that includes this.

[1028] (Claim 2)

[1029] The system according to claim 1, further comprising means for identifying abnormalities by comparing them with a model of the behavioral patterns of the organism when detecting the abnormal behavior.

[1030] (Claim 3)

[1031] The system according to claim 1, further comprising means for prompting a safety officer to take immediate action by push notification to a receiving terminal.

[1032] "Example 2 of combining an emotion engine"

[1033] (Claim 1)

[1034] A means of obtaining information on the activity of living organisms and suspicious individuals from multiple detection devices installed within the protected area,

[1035] Means for processing and pre-processing the acquired information,

[1036] A means for accumulating the pre-processed information and storing it in a database that includes time-series information,

[1037] A means for learning the normal behavioral patterns of organisms based on the accumulated information,

[1038] A means to monitor newly acquired information in real time and detect abnormal behavior,

[1039] A means for generating an alarm and sending a notification based on the detected abnormal behavior,

[1040] A means for analyzing the user's emotional state via a receiving terminal and personalizing the alarms and notifications based on individual emotional responses,

[1041] A system that includes this.

[1042] (Claim 2)

[1043] The system according to claim 1, further comprising means for identifying abnormalities by comparing them with a model of the behavioral patterns of the organism when detecting the abnormal behavior.

[1044] (Claim 3)

[1045] The system according to claim 1, further comprising means for sending the notification as a push notification to a receiving terminal, adjusting the notification content based on the user's emotional state, and prompting immediate action.

[1046] "Application example 2 when combining with an emotional engine"

[1047] (Claim 1)

[1048] A means of acquiring activity data from multiple detection devices installed within the protected area,

[1049] A means for processing and pre-processing the acquired data,

[1050] A means for accumulating the aforementioned preprocessed data and storing it in a database including time-series information,

[1051] A means for learning normal behavioral patterns based on the aforementioned accumulated data,

[1052] A means to monitor newly acquired data in real time and detect abnormal behavior,

[1053] A means for generating an alarm and sending a notification based on the detected abnormal behavior,

[1054] A means for analyzing the user's emotional state and personalizing the aforementioned alarms and notifications,

[1055] A system that includes this.

[1056] (Claim 2)

[1057] The system according to claim 1, further comprising means for identifying abnormalities by comparing them with a model of the animal's behavioral patterns when detecting the abnormal behavior.

[1058] (Claim 3)

[1059] The system according to claim 1, further comprising means for prompting the responding person to take immediate action by sending the notification as a push notification to the receiving terminal. [Explanation of Symbols]

[1060] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring activity data of living organisms and suspicious individuals from multiple detection devices installed within the protected area, A means for processing and pre-processing the acquired data, A means for accumulating the aforementioned preprocessed data and storing it in a database including time-series information, A means for learning the normal behavioral patterns of organisms based on the aforementioned accumulated data, A means to monitor newly acquired data in real time and detect abnormal behavior, A means for generating an alarm and sending a notification based on the detected abnormal behavior, The aforementioned warning is sent as a push notification to terminals used by citizens and administrators, and is a means of promoting safety in parks and natural areas within the city. A system that includes this.

2. The system according to claim 1, further comprising means for identifying abnormalities by comparing them with a model of the behavioral patterns of the organism when detecting the abnormal behavior.

3. The system according to claim 1, further comprising means for prompting a safety officer to take immediate action by push notification to a receiving terminal.

Images