system

Abstract

We provide the system. [Solution] A means for collecting animal activity data and human activity data from a data acquisition device, An artificial intelligence module means for analyzing collected data to identify animal species and behavioral patterns, An anomaly detection module means for identifying abnormal activity or abnormal animal behavior from analyzed data, A communication module means for generating an alarm based on detected anomalies and notifying the user of information necessary for monitoring activities, A feedback processing unit means for receiving user feedback and updating model learning, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a wide range of wildlife protection areas, it is difficult to monitor poaching and illegal activities with limited personnel, and real-time monitoring and prompt response are required. With conventional methods, it has been difficult to immediately detect abnormal animal behavior or the intrusion of poachers and for rangers and conservation groups to respond effectively. For this reason, there is a need for a system that can detect abnormalities at an early stage and autonomously monitor a wide area.

Means for Solving the Problems

[0005] This invention includes means for collecting animal activity data and human activity data from a data acquisition device, and employs an artificial intelligence module to analyze the collected data and identify animal species and behavioral patterns. It also incorporates an anomaly detection module to identify abnormal activity or abnormal animal behavior from the analyzed data, and provides a communication module to generate alarms based on the detected anomalies and notify users of information necessary for monitoring activities. Furthermore, it includes a feedback processing unit to receive feedback from users and update the learning of the artificial intelligence model. This enables efficient and accurate support for wide-ranging nature conservation activities.

[0006] A "data acquisition device" is a device equipped with the function of collecting animal activity data and human activity data.

[0007] "Animal activity data" refers to electronic data that includes information on the movement, behavioral patterns, and species of wild animals.

[0008] "Human activity data" refers to data that includes information related to human movement and behavior within protected areas.

[0009] An "artificial intelligence module" is a group of programs that includes algorithms for analyzing and identifying animal species and behavioral patterns.

[0010] An "anomaly detection module" is a program that compares normal behavioral standards with collected data to identify abnormal behaviors or patterns.

[0011] A "communication module" is a device or system that generates alarms about detected anomalies and provides a means of communication to notify users of that information.

[0012] A "feedback processing unit" is a module that receives opinions and confirmation information from users and updates the learning process of the artificial intelligence model based on that information.

[0013] An "alert" is a notification that is generated when the system identifies abnormal activity or behavior, and is used to alert users. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention relates to a system that supports the monitoring of large-scale wildlife protection areas by collecting and analyzing animal activity data and human activity data in real time and detecting anomalies. This system consists of devices that perform the following operations.

[0036] First, a terminal is used to collect animal activity data and human activity data from local sensors and cameras as a data acquisition device. This data is collected in real time and transmitted to a server in a compressed format.

[0037] The server decompresses the received data and analyzes it using an artificial intelligence module. This module includes a pre-trained model to identify animal species and behavioral patterns. If the server detects unusual animal behavior or anomalies in human activity data, it immediately identifies the anomaly using an anomaly detection module.

[0038] When an anomaly is detected, the server generates an alarm and notifies the user using the communication module. This notification includes detailed information such as the nature of the anomaly, its location, and the time it occurred, allowing the user to take prompt action.

[0039] Furthermore, users can input their on-site observations into the system as feedback. The server receives this feedback through a feedback processing unit, retrains the model, and improves the accuracy of anomaly detection.

[0040] For example, if an animal is detected moving to a location where it doesn't normally appear at night, the server will determine that its behavior is abnormal and issue an alarm. The same applies when suspicious human activity is detected in areas of a protected zone where there is normally no human activity. This enables a swift and efficient response, contributing to the suppression of poaching and illegal activities.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The device collects animal and human activity data in real time from sensors and cameras installed within the wildlife sanctuary. This includes audio, video, and location information. The device temporarily stores this data locally.

[0044] Step 2:

[0045] The terminal compresses the collected data and sends it to the server based on a predetermined time interval or trigger event. Compression improves the efficiency of data transfer.

[0046] Step 3:

[0047] The server receives data from the terminal and performs decompression. The data is then input into an artificial intelligence module to identify the animal species and behavioral patterns. The AI ​​module performs this analysis using a pre-trained model.

[0048] Step 4:

[0049] The server evaluates the analyzed data using an anomaly detection module. This module compares the data to normal data to determine if there is any abnormal animal behavior or human activity.

[0050] Step 5:

[0051] The server generates an alarm when an anomaly is detected. The alarm includes the type, location, time, and possible cause of the anomaly.

[0052] Step 6:

[0053] The server notifies the user of an alarm via a communication module. This notification is sent via email, SMS, or a dedicated app. The user can then take action upon receiving this notification.

[0054] Step 7:

[0055] Users can check the situation on-site and input feedback into the system. This feedback includes information about the validity of the alarm and the actual situation.

[0056] Step 8:

[0057] The server receives feedback from users and performs analysis in the feedback processing unit. Based on this information, the artificial intelligence model is updated to further improve the accuracy of anomaly detection.

[0058] (Example 1)

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

[0060] Conventional monitoring systems for biological and human activities have problems with efficient real-time data collection and analysis across a wide range of data, making rapid detection and response to anomalies difficult. Furthermore, the lack of mechanisms to effectively utilize user feedback and continuously improve analytical accuracy sometimes results in insufficient system accuracy and reliability.

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

[0062] In this invention, the server includes means for collecting biological activity information and human activity information from a data collection device, knowledge processing module means for analyzing the collected information to identify the species and behavioral patterns of organisms, and an anomaly detection unit means for identifying abnormal activity or abnormal biological behavior from the analyzed information. This makes it possible to monitor a wide range of activities in real time and to quickly detect and respond to anomalies. Furthermore, since the accuracy of the entire system can be improved by utilizing evaluation information from users, long-term reliability is improved.

[0063] A "data collection device" refers to devices such as sensors and cameras used to collect information on biological and human activities in the field.

[0064] "Biological activity information" refers to information about the behavior and migration patterns of organisms, especially wild animals, in a specific region.

[0065] "Human activity information" refers to data on human movement and behavior, particularly information used to monitor human activity in natural environments and protected areas.

[0066] A "knowledge processing module" is a software configuration equipped with artificial intelligence technology used to analyze collected information and identify species and their behavioral patterns.

[0067] An "anomaly detection unit" is a device or software that has the function of identifying unusual activity or biological behavior from analyzed information.

[0068] A "transmission unit" is a communication device that notifies users of alarms generated based on detected anomalies, along with necessary information.

[0069] An "evaluation processing configuration" is a configuration that receives feedback information from users, updates the knowledge base based on this information, and has functions to improve the overall analysis accuracy of the system.

[0070] The "information transmission function" is a function that efficiently compresses collected information and transmits it via a communication network.

[0071] A "reference comparison configuration" is a configuration that has the function of comparing acquired data with pre-set reference values ​​or conditions when detecting abnormal activity.

[0072] The embodiments for carrying out this invention are shown below.

[0073] First, the terminal functions as a data collection device, utilizing sensors (e.g., infrared sensors) and high-resolution cameras installed on-site to collect information on biological and human activity. This information is aggregated in real time on the terminal and compressed for efficient data transfer. For example, the H.264 codec is commonly used for video compression.

[0074] Next, the terminal sends the compressed information to the server. The server receives it and first decompresses the information to make it analyzable. At this stage, the decompression technique to be used is selected according to the compression format of the received data.

[0075] Next, the server analyzes the information using a knowledge processing module. This module includes a generative AI model built using deep learning frameworks such as TENSORFLOW® and PyTorch, and is pre-trained to identify species and behavioral patterns of organisms. Based on the analysis results, the server uses an anomaly detection unit to identify unusual activities and behaviors. In this process, a reference comparison configuration is used to compare the observed behavior with a set baseline value.

[0076] If an anomaly is detected, the server generates an alarm via a transmission unit and notifies the user. This notification includes information such as the type of anomaly, its location, and the time it occurred. Based on this information, the user can take prompt action.

[0077] Furthermore, users can feed back their on-site observation results into the system as evaluation information. The server receives this feedback through the evaluation processing configuration and updates its knowledge base to improve the accuracy of anomaly detection.

[0078] As a concrete example, a possible prompt message might be, "Analyze the behavior of animals detected off animal trails at night." This invention enables efficient monitoring of a wide range of biological and human activities, allowing for rapid detection and response to anomalies, and is expected to deter illegal activities in protected areas.

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

[0080] Step 1:

[0081] The terminal collects information on biological and human activity from infrared sensors and high-resolution cameras installed on-site as data acquisition devices. In this collection stage, the input is raw data obtained from sensors and cameras, and the output is information compiled from that data in a unified manner. Specifically, a program that runs at regular intervals acquires scan results from each device and stores the data.

[0082] Step 2:

[0083] The terminal compresses the collected data to efficiently transmit it to the server. The input is a collection of raw data, and the output is compressed data generated using a compression algorithm (e.g., H.264 codec). The compressed data is then transferred to the server over the network. Specifically, a compression processor operates on the terminal side to generate a compressed file.

[0084] Step 3:

[0085] The server receives compressed data sent from the terminal and starts the decompression process. The input is compressed data, and the output is the original data in a parseable format. Decompression uses an algorithm that is the reverse of the compression algorithm. Specifically, decompression software installed on the server reads the data stream and decompresses it.

[0086] Step 4:

[0087] The server uses a knowledge processing module to analyze the decompressed data. The input is decompressed biological activity information and human activity information, and the output is information on the identified species and behavioral patterns of organisms. A generative AI model is used for this analysis, for example, a model pre-trained using TensorFlow. Specifically, the model component scans the data and extracts anomalous patterns and features.

[0088] Step 5:

[0089] If an anomaly is detected based on the analysis results, the server uses an anomaly detection unit to identify the anomaly. The input is the analysis results, and the output is identified information such as the type and location of the anomaly. A baseline comparison configuration is used at this stage and compared with normal operating data. Specifically, the anomaly detection algorithm retrieves baseline values ​​from the database and performs a comparative analysis.

[0090] Step 6:

[0091] If an anomaly is detected, the server generates an alarm through a transmission unit and notifies the user. The input is information from the anomaly detection unit, and the output is the alarm message sent to the user. Transmission is done via email or a dedicated application over the internet. Specifically, the notification software creates a message containing detailed information, including the time and location of the incident, and adds it to the transmission queue.

[0092] Step 7:

[0093] Users can provide feedback to the server based on on-site observations. The input is user feedback, and the output is an updated knowledge base reflecting that feedback. The server uses an evaluation processing configuration to incorporate new information into the system. Specifically, the feedback interface receives the information and automatically updates the knowledge base.

[0094] (Application Example 1)

[0095] 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."

[0096] There is a need for a system that can accurately monitor wildlife and human activity in large protected areas in real time and respond immediately if anomalies are detected. This system is expected to strengthen the suppression of poaching and illegal activities, as well as wildlife protection.

[0097] 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.

[0098] In this invention, the server includes means for collecting biological activity information and human activity information from a data acquisition device; artificial intelligence processor means for analyzing the collected information to identify the species and behavioral tendencies of organisms; anomaly detection process means for identifying abnormal activity or abnormal biological behavior from the analyzed information; and means for transmitting notifications in real time to user terminals to support rapid response at the site. This enables instantaneous detection of anomalies, rapid response, and increased efficiency of protection activities.

[0099] An "information acquisition device" is a hardware or software component that senses the activities of surrounding organisms and humans and collects that information.

[0100] "Biological activity information" refers to data on the behavior and movement patterns of wild animals and plants, which is useful for monitoring and conservation activities.

[0101] "Human activity information" refers to data about human movement and behavior, and is used in particular to detect suspicious activity and illegal intrusion.

[0102] An "artificial intelligence processor" is a computing infrastructure used to analyze collected data and run machine learning models that recognize specific patterns.

[0103] An "anomaly detection process" is a process that identifies unusual activity from analyzed information and notifies users of this activity as a warning or notification.

[0104] "Communication means" refers to the technical means for transmitting generated information to the user's terminal, enabling real-time notification.

[0105] The "evaluation process configuration" is the process of receiving feedback from users and retraining the system to improve the accuracy of the model.

[0106] To implement this invention, a system combining an information acquisition device, an artificial intelligence processor, an anomaly detection process, communication means, and an evaluation processing configuration is required. The operation of this system will be described in detail below.

[0107] The server receives biological and human activity information transmitted from the information acquisition device in compressed data format and performs the process of decompressing it. This information acquisition device includes devices with compression capabilities, specifically various sensors and camera modules used for data collection. The received data is then analyzed by an artificial intelligence processor. This analysis process includes the ability to identify the species and behavioral tendencies of organisms using trained models. The analysis is performed using machine learning frameworks such as TensorFlow and PyTorch.

[0108] The server further identifies biological and human activity that deviates from normal patterns through an anomaly detection process. For example, it can detect unnecessary human intrusions in protected areas or unusual animal movements. This generates timely notifications, which are then pushed to user terminals via communication channels. Real-time notification technologies such as Firebase Cloud Messaging are used here.

[0109] Users receive anomaly information displayed on their terminals and take prompt action on-site. During this process, user feedback is transmitted to the server through an evaluation processing configuration, and the system's model learning is updated. This feedback improves the accuracy of anomaly detection.

[0110] For example, if movement of an animal species not typically found in a wildlife sanctuary is detected, the system immediately notifies the user with the message: "Notable animal activity has been detected. Location: X coordinate, Time: 12:34. Please investigate further." This prompt allows the user to quickly understand the situation and take the necessary action.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The terminal collects biological and human activity information using information acquisition devices. This includes data collection using sensors and cameras, and the collected data is compressed using a compression algorithm. The input is raw data from the field, and the output is compressed data.

[0114] Step 2:

[0115] The server receives compressed data and performs a decompression process. This decompression process restores the original raw data. The input is compressed data, and the output is the decompressed raw data.

[0116] Step 3:

[0117] The server passes the decompressed data to an artificial intelligence processor for analysis. This analysis identifies the species and behavioral tendencies of organisms. The input is the decompressed data, and the output is identified pattern information. A machine learning framework (e.g., TensorFlow) is used for the analysis.

[0118] Step 4:

[0119] The server passes the analyzed pattern information to the anomaly detection process to identify unusual activity. This process detects anomalies by comparing them to a set standard. The input is the identified pattern information, and the output is the detected anomaly information.

[0120] Step 5:

[0121] The server generates an alarm in real time using communication methods based on detected anomaly information and notifies the user's terminal. The input is the anomaly information, and the output is the notification message to the user. Specifically, push notifications are sent using Firebase Cloud Messaging.

[0122] Step 6:

[0123] Users check notifications displayed on their devices and take prompt action on-site. User feedback is sent to the server via the device. Input is the user's response status, and output is updated feedback information.

[0124] Step 7:

[0125] The server passes the received feedback information to the evaluation processing configuration and performs model retraining. This allows the system to continuously improve its accuracy. The input is the feedback information, and the output is the updated model parameters.

[0126] 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.

[0127] This invention aims to improve anomaly detection and response by combining a conventional system that collects and analyzes animal activity data and human activity data with an emotion engine that recognizes the user's emotions. This system has the following configuration.

[0128] First, a terminal is used to collect animal activity data and human activity data from sensors and cameras installed within the wildlife sanctuary. The collected data is compressed and sent to a server. The server receives the data and analyzes it using an artificial intelligence module. This analysis identifies animal species and behavioral patterns and determines whether or not there are any abnormalities.

[0129] When an anomaly is detected, the server generates an alarm and notifies the user via the communication module. A sentiment engine is added at this point to acquire real-time sentiment data from the user. The sentiment engine evaluates the user's emotional state based on factors such as their voice tone and entered text information.

[0130] User emotion data is used to adjust the priority of alerts. For example, if a user is experiencing stress or anxiety, the alert priority is increased, prompting a quicker response. Furthermore, user emotion feedback is collected through a feedback processing unit and incorporated into the retraining process of the artificial intelligence model, improving the overall accuracy and responsiveness of the system.

[0131] For example, if an animal that is normally inactive at night suddenly starts moving, the server detects this as an anomaly and issues an alarm. The user receives the notification and begins on-site investigation. Simultaneously, the emotion engine monitors the user's emotional state, and if it determines that the user is experiencing high stress, the system adjusts to provide further support. This allows the user to deal with the anomaly more effectively.

[0132] This invention aims to improve the safety of animal sanctuaries and achieve efficient, human-centered anomaly response, providing a new monitoring system that integrates emotion and technology.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The device collects real-time animal and human activity data from sensors and cameras placed within the wildlife sanctuary. This data will include video, audio, and location information. The device temporarily caches this data and prepares to send it to the server when communication is possible.

[0136] Step 2:

[0137] The device compresses the cached data and sends it to the server at regular intervals or according to the amount of data. Once the data transfer is complete, the device moves on to the next data collection cycle.

[0138] Step 3:

[0139] The server decompresses the data received from the terminal and performs analysis using an artificial intelligence module. Here, a pre-trained model is used to identify animal species, behavioral patterns, and human activities. Based on the analysis results, the server determines whether there is any unusual behavior.

[0140] Step 4:

[0141] If an anomaly is identified through analysis, the server uses an anomaly detection module to perform a more detailed check. This identifies the type, location, and time of the anomaly, and generates relevant alarms.

[0142] Step 5:

[0143] The server uses an emotion engine to assess the user's emotional state and adjust the priority of alert notifications accordingly. For example, if the user is feeling stressed, alert notifications will be emphasized to encourage a quicker response.

[0144] Step 6:

[0145] The user receives an alarm notification and begins a rapid response to the scene. After the necessary actions have been taken, the user inputs their emotions and the situation as feedback into the system. This feedback is used to verify the system's response.

[0146] Step 7:

[0147] After receiving user feedback, the server analyzes it through a feedback processing unit and uses it as training data for the artificial intelligence module. This process improves the accuracy of anomaly detection and optimizes the alarm system. The server continuously improves future anomaly detection performance by updating the model with the new training data.

[0148] (Example 2)

[0149] 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 will be referred to as the "terminal."

[0150] Conventional anomaly detection systems collect and analyze biological and human activity information, but they fail to take into account the emotional state of users, resulting in insufficient prioritization of alarms. Furthermore, inadequate model learning updates based on feedback hindered improvements in accuracy and responsiveness.

[0151] 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.

[0152] In this invention, the server includes means for collecting biological activity information and human activity information from a data provision device, an emotion evaluation element for acquiring user emotion information using an emotion engine and adjusting the priority of alarms, and a feedback processing device for receiving feedback from the user and updating the learning of an artificial intelligence model. This enables flexible adjustment of alarm priorities based on the user's emotional state when anomaly is detected, and improves system accuracy through feedback.

[0153] A "data provision device" is a device for acquiring biological activity information and human activity information and transmitting it to a system.

[0154] "Biological activity information" refers to information about the behavior and state of living organisms such as animals and plants.

[0155] "Human activity information" refers to information about human behavior and conditions.

[0156] "Artificial intelligence components" refer to machine learning models and algorithms used to analyze information on the activities of living organisms and humans and to identify specific patterns.

[0157] An "anomaly detection module" is an element used to identify abnormal activity or behavior from analyzed information.

[0158] A "communication device" is a device used to transmit and notify information from a system to a user.

[0159] An "emotion engine" is software or a module that acquires a user's emotional information and evaluates their emotional state.

[0160] "Emotional evaluation elements" are components used to adjust the priority of alarms based on the user's emotional information.

[0161] A "feedback processing device" is a device that collects feedback from users and updates the learning of an artificial intelligence model based on that feedback.

[0162] This invention is a system that collects and analyzes biological and human activity information, and uses an emotion engine to optimize anomaly detection and response in a human-centered manner. The following hardware and software are used to implement the system.

[0163] The terminal functions as a data provider, acquiring information on biological and human activity from various sensors and cameras within the protected area. Sensors detect movement, temperature, and sound, while cameras collect video data. This data is compressed by the terminal and transmitted to the server via an efficient communication protocol.

[0164] Upon receiving data, the server uses artificial intelligence components to perform analysis. Based on the identified data, an anomaly detection module identifies unusual activity. For example, if an animal that is normally inactive at night exhibits unexpected movement, the server immediately records it as an anomaly. Any anomalies detected through the analysis are notified to the user via a communication device, and an alarm is issued.

[0165] When a user receives an alert, the emotion engine acquires the user's emotional information in real time. Through voice tone analysis and evaluation of text information, it understands the user's emotional state. The emotion evaluation element uses this information to adjust the alert priority. If the system determines that the user is experiencing high stress, it increases the priority and prompts a quicker response.

[0166] Furthermore, users can provide feedback. This feedback is aggregated by a feedback processing unit and incorporated into the retraining of the generated AI model, thereby improving the system's accuracy and adaptability. This type of adaptive feedback mechanism serves as the cornerstone of continuous system improvement.

[0167] As a concrete example, imagine an animal that is normally diurnal becomes active during the night. The server immediately detects this anomaly and sends a prompt message to the user stating, "An anomaly has been detected. Please check the situation." As the user checks the situation, the emotion engine evaluates the user's feelings in real time, and the system adjusts to provide further support as needed. This process allows the user to respond to the anomaly more effectively.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The terminal collects biological and human activity information from data provision devices. Sensors detect movement, temperature, and sound, while cameras capture video information. Input is raw data from sensors and cameras, and output is the collected unprocessed data. This information is stored for subsequent analysis.

[0171] Step 2:

[0172] The terminal compresses the collected data and sends it to the server. A data compression algorithm is used to reduce the size of the information and optimize bandwidth during communication. The input is raw data, and the output is a compressed data file. The compressed data is sent to the server via the HTTPS protocol.

[0173] Step 3:

[0174] The server receives the compressed data and decompresses it. The decompressed data is then input into the artificial intelligence components to begin analysis. In this step, the data is made accessible again and ready for analysis. The input is compressed data, and the output is analyzable data.

[0175] Step 4:

[0176] The server processes the decompressed data through artificial intelligence components to identify animal species and behavioral patterns. A generative AI model is used to extract and classify features from the data. The input is analyzable data, and the output is the identified species and behavioral patterns. This step performs pattern recognition and classification operations.

[0177] Step 5:

[0178] The server uses the identified data to activate an anomaly detection module and identify abnormal activity or behavior. It compares this to pre-configured criteria, and if an anomaly is detected, it generates an alarm. The input is the identified pattern, and the output is the anomaly detection result. When an anomaly is detected, the alarm management process is triggered.

[0179] Step 6:

[0180] The server notifies the user of the generated alarm via a communication device. It sends a prompt message to the user's terminal to draw their attention. The input is the anomaly detection result, and the output is the alarm notification. For example, the prompt message "An anomaly has been detected. Please check the situation." is sent.

[0181] Step 7:

[0182] When a user receives an alarm and conducts on-site verification, the server activates the emotion engine to retrieve the user's emotional information. It analyzes voice tone and text input to evaluate the emotional state. Input consists of voice and text data, and output is the evaluated emotional state.

[0183] Step 8:

[0184] The server adjusts alarm priorities using acquired emotional information. If a high stress level is detected, the priority is increased, and the response is accelerated. The input is the evaluated emotional state, and the output is the adjusted alarm priority.

[0185] Step 9:

[0186] The server receives feedback from the user and retrains the generated AI model via a feedback processing unit. The feedback data is analyzed to update the model, improving the system's accuracy and adaptability. The input is the feedback data, and the output is the updated model. This process continuously improves the system's adaptability.

[0187] (Application Example 2)

[0188] 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".

[0189] Conventional monitoring systems have a fixed priority for alarms after anomaly detection, making it difficult to respond quickly and appropriately while considering the user's emotional state. This can increase the burden on users and potentially decrease accuracy and efficiency.

[0190] 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.

[0191] In this invention, the server includes means for collecting animal activity data and human activity data from a data acquisition device, an artificial intelligence module for analyzing the collected data to identify animal species and behavioral patterns, and an emotion analysis module for evaluating the user's emotional state and adjusting the priority of alarms. This makes it possible to adjust the priority of alarms according to the user's emotional state.

[0192] A "data acquisition device" is a device that is set up to collect animal activity data and human activity data.

[0193] An "artificial intelligence module" is a software component that analyzes collected data to identify animal species and behavioral patterns.

[0194] An "anomaly detection module" is a program used to identify abnormal activity or animal behavior from analyzed data.

[0195] A "communication module" is a device or software that has the function of notifying users of information necessary for monitoring activities based on detected anomalies.

[0196] The "emotion analysis module" is a module used to evaluate the user's emotional state and adjust the priority of alarms based on the information obtained.

[0197] A "feedback processing unit" is a device or software component that receives feedback from users and updates the learning of an artificial intelligence model based on that information.

[0198] "Data transfer means" refers to a device or system that has the function of compressing and efficiently transferring collected data.

[0199] A "reference comparison module" is software used to compare and evaluate abnormal activity against pre-defined criteria.

[0200] This invention constructs a security system that collects and analyzes animal activity data and human activity data using data acquisition devices, communication terminals, and servers, and notifies users of any anomalies.

[0201] The server receives compressed animal and human activity data collected via data acquisition devices. Efficient data transfer methods are used for compression. The received data is analyzed by an artificial intelligence module to identify animal species and behavioral patterns. An anomaly detection module uses this analyzed data to identify abnormal activity and animal behavior, and based on this, a communication module generates an alarm.

[0202] Furthermore, an emotion analysis module evaluates the user's emotional state and adjusts the alarm priority based on the obtained emotional information, including voice tone and text information. If the user's emotional state is determined to be anxiety or stress, the alarm priority is set higher, enabling a quicker response.

[0203] Users receive alert notifications via their smartphones or other devices and take the necessary actions. During this process, the user's emotional feedback is collected by a feedback processing unit and used to retrain the AI ​​model. Specifically, for example, if an animal that normally does not move suddenly becomes active in an animal sanctuary at night, this is detected as an anomaly, and the user is notified. At that time, emotional analysis is used to increase the urgency of the alert, enabling a more accurate response.

[0204] An example of a prompt message might be: "Security cameras have detected unusual activity around your residence. How would you like the alert to be adjusted considering the user's current emotional state?"

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The terminal collects animal activity data and human activity data via a data acquisition device. The input is raw data from sensors and cameras, which is then compressed for efficient transmission to the server. The output is the compressed data.

[0208] Step 2:

[0209] The server decompresses the compressed data received from the terminal and analyzes the data using an artificial intelligence module. The input is compressed data, which is then decompressed and analyzed by AI to identify the animal species and behavioral patterns. The output is information on the animal species and behavioral patterns.

[0210] Step 3:

[0211] The server processes the analyzed behavioral pattern data with an anomaly detection module to identify abnormal activity or animal behavior. The input is behavioral pattern data, and data calculations are performed to detect anomalies by comparing it with past normal data. The output is a flag indicating the presence or absence of an anomaly.

[0212] Step 4:

[0213] When an anomaly is detected, the server uses a communication module to generate an alarm and send a notification to the user. The input is the anomaly detection result, and the alarm is generated by setting the notification content as appropriate. The output is the generated alarm message.

[0214] Step 5:

[0215] The server uses an emotion analysis module to collect user emotion data and adjusts alarm priorities based on that information. Inputs include the user's voice tone and text data, and an emotion recognition algorithm evaluates their emotional state. The output is the adjusted alarm priority.

[0216] Step 6:

[0217] Users receive alerts tailored to their emotional state via their devices or smartphones and take necessary actions. The input is a pre-configured alert message, which is output as a display on the device screen.

[0218] Step 7:

[0219] The server collects user feedback in a feedback processing unit and uses it to retrain the model. The input is user feedback data, which is used to update the artificial intelligence model and improve the system's accuracy. The output is the updated model parameters.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention relates to a system that supports the monitoring of large-scale wildlife protection areas by collecting and analyzing animal activity data and human activity data in real time and detecting anomalies. This system consists of devices that perform the following operations.

[0237] First, a terminal is used to collect animal activity data and human activity data from local sensors and cameras as a data acquisition device. This data is collected in real time and transmitted to a server in a compressed format.

[0238] The server decompresses the received data and analyzes it using an artificial intelligence module. This module includes a pre-trained model to identify animal species and behavioral patterns. If the server detects unusual animal behavior or anomalies in human activity data, it immediately identifies the anomaly using an anomaly detection module.

[0239] When an anomaly is detected, the server generates an alarm and notifies the user using the communication module. This notification includes detailed information such as the nature of the anomaly, its location, and the time it occurred, allowing the user to take prompt action.

[0240] Furthermore, users can input their on-site observations into the system as feedback. The server receives this feedback through a feedback processing unit, retrains the model, and improves the accuracy of anomaly detection.

[0241] For example, if an animal is detected moving to a location where it doesn't normally appear at night, the server will determine that its behavior is abnormal and issue an alarm. The same applies when suspicious human activity is detected in areas of a protected zone where there is normally no human activity. This enables a swift and efficient response, contributing to the suppression of poaching and illegal activities.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The device collects animal and human activity data in real time from sensors and cameras installed within the wildlife sanctuary. This includes audio, video, and location information. The device temporarily stores this data locally.

[0245] Step 2:

[0246] The terminal compresses the collected data and sends it to the server based on a predetermined time interval or trigger event. Compression improves the efficiency of data transfer.

[0247] Step 3:

[0248] The server receives data from the terminal and performs decompression. The data is then input into an artificial intelligence module to identify the animal species and behavioral patterns. The AI ​​module performs this analysis using a pre-trained model.

[0249] Step 4:

[0250] The server evaluates the analyzed data using an anomaly detection module. This module compares the data to normal data to determine if there is any abnormal animal behavior or human activity.

[0251] Step 5:

[0252] The server generates an alarm when an anomaly is detected. The alarm includes the type, location, time, and possible cause of the anomaly.

[0253] Step 6:

[0254] The server notifies the user of an alarm via a communication module. This notification is sent via email, SMS, or a dedicated app. The user can then take action upon receiving this notification.

[0255] Step 7:

[0256] Users can check the situation on-site and input feedback into the system. This feedback includes information about the validity of the alarm and the actual situation.

[0257] Step 8:

[0258] The server receives feedback from users and performs analysis in the feedback processing unit. Based on this information, the artificial intelligence model is updated to further improve the accuracy of anomaly detection.

[0259] (Example 1)

[0260] 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."

[0261] Conventional monitoring systems for biological and human activities have problems with efficient real-time data collection and analysis across a wide range of data, making rapid detection and response to anomalies difficult. Furthermore, the lack of mechanisms to effectively utilize user feedback and continuously improve analytical accuracy sometimes results in insufficient system accuracy and reliability.

[0262] 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.

[0263] In this invention, the server includes means for collecting biological activity information and human activity information from a data collection device, knowledge processing module means for analyzing the collected information to identify the species and behavioral patterns of organisms, and an anomaly detection unit means for identifying abnormal activity or abnormal biological behavior from the analyzed information. This makes it possible to monitor a wide range of activities in real time and to quickly detect and respond to anomalies. Furthermore, since the accuracy of the entire system can be improved by utilizing evaluation information from users, long-term reliability is improved.

[0264] A "data collection device" refers to devices such as sensors and cameras used to collect information on biological and human activities in the field.

[0265] "Biological activity information" refers to information about the behavior and migration patterns of organisms, especially wild animals, in a specific region.

[0266] "Human activity information" refers to data on human movement and behavior, particularly information used to monitor human activity in natural environments and protected areas.

[0267] A "knowledge processing module" is a software configuration equipped with artificial intelligence technology used to analyze collected information and identify species and their behavioral patterns.

[0268] An "anomaly detection unit" is a device or software that has the function of identifying unusual activity or biological behavior from analyzed information.

[0269] A "transmission unit" is a communication device that notifies users of alarms generated based on detected anomalies, along with necessary information.

[0270] An "evaluation processing configuration" is a configuration that receives feedback information from users, updates the knowledge base based on this information, and has functions to improve the overall analysis accuracy of the system.

[0271] The "information transmission function" is a function that efficiently compresses collected information and transmits it via a communication network.

[0272] A "reference comparison configuration" is a configuration that has the function of comparing acquired data with pre-set reference values ​​or conditions when detecting abnormal activity.

[0273] The embodiments for carrying out this invention are shown below.

[0274] First, the terminal functions as a data collection device, utilizing sensors (e.g., infrared sensors) and high-resolution cameras installed on-site to collect information on biological and human activity. This information is aggregated in real time on the terminal and compressed for efficient data transfer. For example, the H.264 codec is commonly used for video compression.

[0275] Next, the terminal sends the compressed information to the server. The server receives it and first decompresses the information to make it analyzable. At this stage, the decompression technique to be used is selected according to the compression format of the received data.

[0276] Next, the server analyzes the information using a knowledge processing module. This module includes a generative AI model built using deep learning frameworks such as TensorFlow and PyTorch, and is pre-trained to identify species and behavioral patterns of organisms. Based on the analysis results, the server uses an anomaly detection unit to identify unusual activities and behaviors. In this process, a reference comparison configuration is used to compare the observed behavior with a set baseline value.

[0277] If an anomaly is detected, the server generates an alarm via a transmission unit and notifies the user. This notification includes information such as the type of anomaly, its location, and the time it occurred. Based on this information, the user can take prompt action.

[0278] Furthermore, users can feed back their on-site observation results into the system as evaluation information. The server receives this feedback through the evaluation processing configuration and updates its knowledge base to improve the accuracy of anomaly detection.

[0279] As a concrete example, a possible prompt message might be, "Analyze the behavior of animals detected off animal trails at night." This invention enables efficient monitoring of a wide range of biological and human activities, allowing for rapid detection and response to anomalies, and is expected to deter illegal activities in protected areas.

[0280] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0281] Step 1:

[0282] The terminal, as a data collection device, collects biological activity information and human activity information from infrared sensors and high-resolution cameras installed on-site. In this collection stage, the input is the raw data obtained from the sensors and cameras, and the output is the information that consolidates them in a unified manner. As a specific operation, a program executed at regular intervals acquires the scan results from each device and accumulates the data.

[0283] Step 2:

[0284] The terminal compresses the data in order to efficiently transmit the collected information to the server. The input is the set of raw data, and the output is the compressed data generated using a compression algorithm (e.g., H.264 codec). The compressed data is then transferred to the server via the network. As a specific operation, a compression processor on the terminal side operates to generate a compressed file.

[0285] Step 3:

[0286] The server receives the compressed data sent from the terminal and starts the decompression process. The input is the compressed data, and the output is the data in the original format that can be analyzed. For decompression, an algorithm in the opposite direction to compression is executed. As a specific operation, the decompression software installed on the server reads and expands the data stream.

[0287] Step 4:

[0288] The server analyzes the decompressed data using a knowledge processing module. The input is the decompressed biological activity information and human activity information, and the output is the information on the identified biological species and behavior patterns. For this analysis, a generative AI model is used, and a model pre-trained using, for example, TensorFlow operates. As a specific operation, the model component scans the data and extracts abnormal patterns and features.

[0289] Step 5:

[0290] If an anomaly is detected based on the analysis results, the server uses an anomaly detection unit to identify the anomaly. The input is the analysis results, and the output is identified information such as the type and location of the anomaly. A baseline comparison configuration is used at this stage and compared with normal operating data. Specifically, the anomaly detection algorithm retrieves baseline values ​​from the database and performs a comparative analysis.

[0291] Step 6:

[0292] If an anomaly is detected, the server generates an alarm through a transmission unit and notifies the user. The input is information from the anomaly detection unit, and the output is the alarm message sent to the user. Transmission is done via email or a dedicated application over the internet. Specifically, the notification software creates a message containing detailed information, including the time and location of the incident, and adds it to the transmission queue.

[0293] Step 7:

[0294] Users can provide feedback to the server based on on-site observations. The input is user feedback, and the output is an updated knowledge base reflecting that feedback. The server uses an evaluation processing configuration to incorporate new information into the system. Specifically, the feedback interface receives the information and automatically updates the knowledge base.

[0295] (Application Example 1)

[0296] 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."

[0297] There is a need for a system that can accurately monitor wildlife and human activity in large protected areas in real time and respond immediately if anomalies are detected. This system is expected to strengthen the suppression of poaching and illegal activities, as well as wildlife protection.

[0298] 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.

[0299] In this invention, the server includes means for collecting biological activity information and human activity information from a data acquisition device; artificial intelligence processor means for analyzing the collected information to identify the species and behavioral tendencies of organisms; anomaly detection process means for identifying abnormal activity or abnormal biological behavior from the analyzed information; and means for transmitting notifications in real time to user terminals to support rapid response at the site. This enables instantaneous detection of anomalies, rapid response, and increased efficiency of protection activities.

[0300] An "information acquisition device" is a hardware or software component that senses the activities of surrounding organisms and humans and collects that information.

[0301] "Biological activity information" refers to data on the behavior and movement patterns of wild animals and plants, which is useful for monitoring and conservation activities.

[0302] "Human activity information" refers to data about human movement and behavior, and is used in particular to detect suspicious activity and illegal intrusion.

[0303] An "artificial intelligence processor" is a computing infrastructure used to analyze collected data and run machine learning models that recognize specific patterns.

[0304] An "anomaly detection process" is a process that identifies unusual activity from analyzed information and notifies users of this activity as a warning or notification.

[0305] "Communication means" refers to the technical means for transmitting generated information to the user's terminal, enabling real-time notification.

[0306] The "evaluation process configuration" is a process that receives feedback provided by users and retrains the system to improve the accuracy of the model.

[0307] To implement this invention, a system that combines an information acquisition device, an artificial intelligence processor, an anomaly detection process, communication means, and an evaluation process configuration is required. The operation of this system will be described in detail below.

[0308] The server receives the biological activity information and human activity information transmitted from the information acquisition device in a compressed data format and executes a process of decompressing it. This information acquisition device includes devices with a compression function. Specifically, various sensors and camera modules are used for data collection. The received data is then analyzed by the artificial intelligence processor. This analysis process includes a function of identifying the species and behavior tendencies of organisms using a pre-trained model. The analysis is performed using a machine learning framework such as TensorFlow or PyTorch.

[0309] The server further identifies activities of organisms and humans that deviate from normal patterns through an anomaly detection process. For example, it detects unnecessary human intrusion in a protected area or abnormal movement of organisms. Thereby, notifications are generated in a timely manner and pushed to the user terminal through the communication means. Here, real-time notification technologies such as Firebase Cloud Messaging are used.

[0310] The user receives the anomaly information displayed on the user terminal and makes a prompt response on-site. At this time, the feedback from the user is transmitted to the server through the evaluation process configuration, and the model learning of the system is updated. This feedback improves the accuracy of anomaly detection.

[0311] For example, if movement of an animal species not typically found in a wildlife sanctuary is detected, the system immediately notifies the user with the message: "Notable animal activity has been detected. Location: X coordinate, Time: 12:34. Please investigate further." This prompt allows the user to quickly understand the situation and take the necessary action.

[0312] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0313] Step 1:

[0314] The terminal collects biological and human activity information using information acquisition devices. This includes data collection using sensors and cameras, and the collected data is compressed using a compression algorithm. The input is raw data from the field, and the output is compressed data.

[0315] Step 2:

[0316] The server receives compressed data and performs a decompression process. This decompression process restores the original raw data. The input is compressed data, and the output is the decompressed raw data.

[0317] Step 3:

[0318] The server passes the decompressed data to an artificial intelligence processor for analysis. This analysis identifies the species and behavioral tendencies of organisms. The input is the decompressed data, and the output is identified pattern information. A machine learning framework (e.g., TensorFlow) is used for the analysis.

[0319] Step 4:

[0320] The server passes the analyzed pattern information to the anomaly detection process to identify unusual activity. This process detects anomalies by comparing them to a set standard. The input is the identified pattern information, and the output is the detected anomaly information.

[0321] Step 5:

[0322] The server generates an alarm in real time using communication methods based on detected anomaly information and notifies the user's terminal. The input is the anomaly information, and the output is the notification message to the user. Specifically, push notifications are sent using Firebase Cloud Messaging.

[0323] Step 6:

[0324] Users check notifications displayed on their devices and take prompt action on-site. User feedback is sent to the server via the device. Input is the user's response status, and output is updated feedback information.

[0325] Step 7:

[0326] The server passes the received feedback information to the evaluation processing configuration and performs model retraining. This allows the system to continuously improve its accuracy. The input is the feedback information, and the output is the updated model parameters.

[0327] 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.

[0328] This invention aims to improve anomaly detection and response by combining a conventional system that collects and analyzes animal activity data and human activity data with an emotion engine that recognizes the user's emotions. This system has the following configuration.

[0329] First, a terminal is used to collect animal activity data and human activity data from sensors and cameras installed within the wildlife sanctuary. The collected data is compressed and sent to a server. The server receives the data and analyzes it using an artificial intelligence module. This analysis identifies animal species and behavioral patterns and determines whether or not there are any abnormalities.

[0330] When an anomaly is detected, the server generates an alarm and notifies the user via the communication module. A sentiment engine is added at this point to acquire real-time sentiment data from the user. The sentiment engine evaluates the user's emotional state based on factors such as their voice tone and entered text information.

[0331] User emotion data is used to adjust the priority of alerts. For example, if a user is experiencing stress or anxiety, the alert priority is increased, prompting a quicker response. Furthermore, user emotion feedback is collected through a feedback processing unit and incorporated into the retraining process of the artificial intelligence model, improving the overall accuracy and responsiveness of the system.

[0332] For example, if an animal that is normally inactive at night suddenly starts moving, the server detects this as an anomaly and issues an alarm. The user receives the notification and begins on-site investigation. Simultaneously, the emotion engine monitors the user's emotional state, and if it determines that the user is experiencing high stress, the system adjusts to provide further support. This allows the user to deal with the anomaly more effectively.

[0333] This invention aims to improve the safety of animal sanctuaries and achieve efficient, human-centered anomaly response, providing a new monitoring system that integrates emotion and technology.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] The device collects real-time animal and human activity data from sensors and cameras placed within the wildlife sanctuary. This data will include video, audio, and location information. The device temporarily caches this data and prepares to send it to the server when communication is possible.

[0337] Step 2:

[0338] The device compresses the cached data and sends it to the server at regular intervals or according to the amount of data. Once the data transfer is complete, the device moves on to the next data collection cycle.

[0339] Step 3:

[0340] The server decompresses the data received from the terminal and performs analysis using an artificial intelligence module. Here, a pre-trained model is used to identify animal species, behavioral patterns, and human activities. Based on the analysis results, the server determines whether there is any unusual behavior.

[0341] Step 4:

[0342] If an anomaly is identified through analysis, the server uses an anomaly detection module to perform a more detailed check. This identifies the type, location, and time of the anomaly, and generates relevant alarms.

[0343] Step 5:

[0344] The server uses an emotion engine to assess the user's emotional state and adjust the priority of alert notifications accordingly. For example, if the user is feeling stressed, alert notifications will be emphasized to encourage a quicker response.

[0345] Step 6:

[0346] The user receives an alarm notification and begins a rapid response to the scene. After the necessary actions have been taken, the user inputs their emotions and the situation as feedback into the system. This feedback is used to verify the system's response.

[0347] Step 7:

[0348] After receiving user feedback, the server analyzes it through a feedback processing unit and uses it as training data for the artificial intelligence module. This process improves the accuracy of anomaly detection and optimizes the alarm system. The server continuously improves future anomaly detection performance by updating the model with the new training data.

[0349] (Example 2)

[0350] 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".

[0351] Conventional anomaly detection systems collect and analyze biological and human activity information, but they fail to take into account the emotional state of users, resulting in insufficient prioritization of alarms. Furthermore, inadequate model learning updates based on feedback hindered improvements in accuracy and responsiveness.

[0352] 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.

[0353] In this invention, the server includes means for collecting biological activity information and human activity information from a data provision device, an emotion evaluation element for acquiring user emotion information using an emotion engine and adjusting the priority of alarms, and a feedback processing device for receiving feedback from the user and updating the learning of an artificial intelligence model. This enables flexible adjustment of alarm priorities based on the user's emotional state when anomaly is detected, and improves system accuracy through feedback.

[0354] A "data provision device" is a device for acquiring biological activity information and human activity information and transmitting it to a system.

[0355] "Biological activity information" refers to information about the behavior and state of living organisms such as animals and plants.

[0356] "Human activity information" refers to information about human behavior and conditions.

[0357] "Artificial intelligence components" refer to machine learning models and algorithms used to analyze information on the activities of living organisms and humans and to identify specific patterns.

[0358] An "anomaly detection module" is an element used to identify abnormal activity or behavior from analyzed information.

[0359] A "communication device" is a device used to transmit and notify information from a system to a user.

[0360] An "emotion engine" is software or a module that acquires a user's emotional information and evaluates their emotional state.

[0361] "Emotional evaluation elements" are components used to adjust the priority of alarms based on the user's emotional information.

[0362] A "feedback processing device" is a device that collects feedback from users and updates the learning of an artificial intelligence model based on that feedback.

[0363] This invention is a system that collects and analyzes biological and human activity information, and uses an emotion engine to optimize anomaly detection and response in a human-centered manner. The following hardware and software are used to implement the system.

[0364] The terminal functions as a data provider, acquiring information on biological and human activity from various sensors and cameras within the protected area. Sensors detect movement, temperature, and sound, while cameras collect video data. This data is compressed by the terminal and transmitted to the server via an efficient communication protocol.

[0365] Upon receiving data, the server uses artificial intelligence components to perform analysis. Based on the identified data, an anomaly detection module identifies unusual activity. For example, if an animal that is normally inactive at night exhibits unexpected movement, the server immediately records it as an anomaly. Any anomalies detected through the analysis are notified to the user via a communication device, and an alarm is issued.

[0366] When a user receives an alert, the emotion engine acquires the user's emotional information in real time. Through voice tone analysis and evaluation of text information, it understands the user's emotional state. The emotion evaluation element uses this information to adjust the alert priority. If the system determines that the user is experiencing high stress, it increases the priority and prompts a quicker response.

[0367] Furthermore, users can provide feedback. This feedback is aggregated by a feedback processing unit and incorporated into the retraining of the generated AI model, thereby improving the system's accuracy and adaptability. This type of adaptive feedback mechanism serves as the cornerstone of continuous system improvement.

[0368] As a concrete example, imagine an animal that is normally diurnal becomes active during the night. The server immediately detects this anomaly and sends a prompt message to the user stating, "An anomaly has been detected. Please check the situation." As the user checks the situation, the emotion engine evaluates the user's feelings in real time, and the system adjusts to provide further support as needed. This process allows the user to respond to the anomaly more effectively.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The terminal collects biological and human activity information from data provision devices. Sensors detect movement, temperature, and sound, while cameras capture video information. Input is raw data from sensors and cameras, and output is the collected unprocessed data. This information is stored for subsequent analysis.

[0372] Step 2:

[0373] The terminal compresses the collected data and sends it to the server. A data compression algorithm is used to reduce the size of the information and optimize bandwidth during communication. The input is raw data, and the output is a compressed data file. The compressed data is sent to the server via the HTTPS protocol.

[0374] Step 3:

[0375] The server receives the compressed data and decompresses it. The decompressed data is then input into the artificial intelligence components to begin analysis. In this step, the data is made accessible again and ready for analysis. The input is compressed data, and the output is analyzable data.

[0376] Step 4:

[0377] The server processes the decompressed data through artificial intelligence components to identify animal species and behavioral patterns. A generative AI model is used to extract and classify features from the data. The input is analyzable data, and the output is the identified species and behavioral patterns. This step performs pattern recognition and classification operations.

[0378] Step 5:

[0379] The server uses the identified data to activate an anomaly detection module and identify abnormal activity or behavior. It compares this to pre-configured criteria, and if an anomaly is detected, it generates an alarm. The input is the identified pattern, and the output is the anomaly detection result. When an anomaly is detected, the alarm management process is triggered.

[0380] Step 6:

[0381] The server notifies the user of the generated alarm via a communication device. It sends a prompt message to the user's terminal to draw their attention. The input is the anomaly detection result, and the output is the alarm notification. For example, the prompt message "An anomaly has been detected. Please check the situation." is sent.

[0382] Step 7:

[0383] When a user receives an alarm and conducts on-site verification, the server activates the emotion engine to retrieve the user's emotional information. It analyzes voice tone and text input to evaluate the emotional state. Input consists of voice and text data, and output is the evaluated emotional state.

[0384] Step 8:

[0385] The server adjusts alarm priorities using acquired emotional information. If a high stress level is detected, the priority is increased, and the response is accelerated. The input is the evaluated emotional state, and the output is the adjusted alarm priority.

[0386] Step 9:

[0387] The server receives feedback from the user and retrains the generated AI model via a feedback processing unit. The feedback data is analyzed to update the model, improving the system's accuracy and adaptability. The input is the feedback data, and the output is the updated model. This process continuously improves the system's adaptability.

[0388] (Application Example 2)

[0389] 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."

[0390] Conventional monitoring systems have a fixed priority for alarms after anomaly detection, making it difficult to respond quickly and appropriately while considering the user's emotional state. This can increase the burden on users and potentially decrease accuracy and efficiency.

[0391] 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.

[0392] In this invention, the server includes means for collecting animal activity data and human activity data from a data acquisition device, an artificial intelligence module for analyzing the collected data to identify animal species and behavioral patterns, and an emotion analysis module for evaluating the user's emotional state and adjusting the priority of alarms. This makes it possible to adjust the priority of alarms according to the user's emotional state.

[0393] A "data acquisition device" is a device that is set up to collect animal activity data and human activity data.

[0394] An "artificial intelligence module" is a software component that analyzes collected data to identify animal species and behavioral patterns.

[0395] An "anomaly detection module" is a program used to identify abnormal activity or animal behavior from analyzed data.

[0396] A "communication module" is a device or software that has the function of notifying users of information necessary for monitoring activities based on detected anomalies.

[0397] The "emotion analysis module" is a module used to evaluate the user's emotional state and adjust the priority of alarms based on the information obtained.

[0398] A "feedback processing unit" is a device or software component that receives feedback from users and updates the learning of an artificial intelligence model based on that information.

[0399] "Data transfer means" refers to a device or system that has the function of compressing and efficiently transferring collected data.

[0400] A "reference comparison module" is software used to compare and evaluate abnormal activity against pre-defined criteria.

[0401] This invention constructs a security system that collects and analyzes animal activity data and human activity data using data acquisition devices, communication terminals, and servers, and notifies users of any anomalies.

[0402] The server receives compressed animal and human activity data collected via data acquisition devices. Efficient data transfer methods are used for compression. The received data is analyzed by an artificial intelligence module to identify animal species and behavioral patterns. An anomaly detection module uses this analyzed data to identify abnormal activity and animal behavior, and based on this, a communication module generates an alarm.

[0403] Furthermore, an emotion analysis module evaluates the user's emotional state and adjusts the alarm priority based on the obtained emotional information, including voice tone and text information. If the user's emotional state is determined to be anxiety or stress, the alarm priority is set higher, enabling a quicker response.

[0404] Users receive alert notifications via their smartphones or other devices and take the necessary actions. During this process, the user's emotional feedback is collected by a feedback processing unit and used to retrain the AI ​​model. Specifically, for example, if an animal that normally does not move suddenly becomes active in an animal sanctuary at night, this is detected as an anomaly, and the user is notified. At that time, emotional analysis is used to increase the urgency of the alert, enabling a more accurate response.

[0405] An example of a prompt message might be: "Security cameras have detected unusual activity around your residence. How would you like the alert to be adjusted considering the user's current emotional state?"

[0406] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0407] Step 1:

[0408] The terminal collects animal activity data and human activity data via a data acquisition device. The input is raw data from sensors and cameras, which is then compressed for efficient transmission to the server. The output is the compressed data.

[0409] Step 2:

[0410] The server decompresses the compressed data received from the terminal and analyzes the data using an artificial intelligence module. The input is compressed data, which is then decompressed and analyzed by AI to identify the animal species and behavioral patterns. The output is information on the animal species and behavioral patterns.

[0411] Step 3:

[0412] The server processes the analyzed behavioral pattern data with an anomaly detection module to identify abnormal activity or animal behavior. The input is behavioral pattern data, and data calculations are performed to detect anomalies by comparing it with past normal data. The output is a flag indicating the presence or absence of an anomaly.

[0413] Step 4:

[0414] When an anomaly is detected, the server uses a communication module to generate an alarm and send a notification to the user. The input is the anomaly detection result, and the alarm is generated by setting the notification content as appropriate. The output is the generated alarm message.

[0415] Step 5:

[0416] The server uses an emotion analysis module to collect user emotion data and adjusts alarm priorities based on that information. Inputs include the user's voice tone and text data, and an emotion recognition algorithm evaluates their emotional state. The output is the adjusted alarm priority.

[0417] Step 6:

[0418] Users receive alerts tailored to their emotional state via their devices or smartphones and take necessary actions. The input is a pre-configured alert message, which is output as a display on the device screen.

[0419] Step 7:

[0420] The server collects user feedback in a feedback processing unit and uses it to retrain the model. The input is user feedback data, which is used to update the artificial intelligence model and improve the system's accuracy. The output is the updated model parameters.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] [Third Embodiment]

[0425] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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".

[0437] This invention relates to a system that supports the monitoring of large-scale wildlife protection areas by collecting and analyzing animal activity data and human activity data in real time and detecting anomalies. This system consists of devices that perform the following operations.

[0438] First, a terminal is used to collect animal activity data and human activity data from local sensors and cameras as a data acquisition device. This data is collected in real time and transmitted to a server in a compressed format.

[0439] The server decompresses the received data and analyzes it using an artificial intelligence module. This module includes a pre-trained model to identify animal species and behavioral patterns. If the server detects unusual animal behavior or anomalies in human activity data, it immediately identifies the anomaly using an anomaly detection module.

[0440] When an anomaly is detected, the server generates an alarm and notifies the user using the communication module. This notification includes detailed information such as the nature of the anomaly, its location, and the time it occurred, allowing the user to take prompt action.

[0441] Furthermore, users can input their on-site observations into the system as feedback. The server receives this feedback through a feedback processing unit, retrains the model, and improves the accuracy of anomaly detection.

[0442] For example, if an animal is detected moving to a location where it doesn't normally appear at night, the server will determine that its behavior is abnormal and issue an alarm. The same applies when suspicious human activity is detected in areas of a protected zone where there is normally no human activity. This enables a swift and efficient response, contributing to the suppression of poaching and illegal activities.

[0443] The following describes the processing flow.

[0444] Step 1:

[0445] The device collects animal and human activity data in real time from sensors and cameras installed within the wildlife sanctuary. This includes audio, video, and location information. The device temporarily stores this data locally.

[0446] Step 2:

[0447] The terminal compresses the collected data and sends it to the server based on a predetermined time interval or trigger event. Compression improves the efficiency of data transfer.

[0448] Step 3:

[0449] The server receives data from the terminal and performs decompression. The data is then input into an artificial intelligence module to identify the animal species and behavioral patterns. The AI ​​module performs this analysis using a pre-trained model.

[0450] Step 4:

[0451] The server evaluates the analyzed data using an anomaly detection module. This module compares the data to normal data to determine if there is any abnormal animal behavior or human activity.

[0452] Step 5:

[0453] The server generates an alarm when an anomaly is detected. The alarm includes the type, location, time, and possible cause of the anomaly.

[0454] Step 6:

[0455] The server notifies the user of an alarm via a communication module. This notification is sent via email, SMS, or a dedicated app. The user can then take action upon receiving this notification.

[0456] Step 7:

[0457] Users can check the situation on-site and input feedback into the system. This feedback includes information about the validity of the alarm and the actual situation.

[0458] Step 8:

[0459] The server receives feedback from users and performs analysis in the feedback processing unit. Based on this information, the artificial intelligence model is updated to further improve the accuracy of anomaly detection.

[0460] (Example 1)

[0461] 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."

[0462] Conventional monitoring systems for biological and human activities have problems with efficient real-time data collection and analysis across a wide range of data, making rapid detection and response to anomalies difficult. Furthermore, the lack of mechanisms to effectively utilize user feedback and continuously improve analytical accuracy sometimes results in insufficient system accuracy and reliability.

[0463] 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.

[0464] In this invention, the server includes means for collecting biological activity information and human activity information from a data collection device, knowledge processing module means for analyzing the collected information to identify the species and behavioral patterns of organisms, and an anomaly detection unit means for identifying abnormal activity or abnormal biological behavior from the analyzed information. This makes it possible to monitor a wide range of activities in real time and to quickly detect and respond to anomalies. Furthermore, since the accuracy of the entire system can be improved by utilizing evaluation information from users, long-term reliability is improved.

[0465] A "data collection device" refers to devices such as sensors and cameras used to collect information on biological and human activities in the field.

[0466] "Biological activity information" refers to information about the behavior and migration patterns of organisms, especially wild animals, in a specific region.

[0467] "Human activity information" refers to data on human movement and behavior, particularly information used to monitor human activity in natural environments and protected areas.

[0468] A "knowledge processing module" is a software configuration equipped with artificial intelligence technology used to analyze collected information and identify species and their behavioral patterns.

[0469] An "anomaly detection unit" is a device or software that has the function of identifying unusual activity or biological behavior from analyzed information.

[0470] A "transmission unit" is a communication device that notifies users of alarms generated based on detected anomalies, along with necessary information.

[0471] An "evaluation processing configuration" is a configuration that receives feedback information from users, updates the knowledge base based on this information, and has functions to improve the overall analysis accuracy of the system.

[0472] The "information transmission function" is a function that efficiently compresses collected information and transmits it via a communication network.

[0473] A "reference comparison configuration" is a configuration that has the function of comparing acquired data with pre-set reference values ​​or conditions when detecting abnormal activity.

[0474] The embodiments for carrying out this invention are shown below.

[0475] First, the terminal functions as a data collection device, utilizing sensors (e.g., infrared sensors) and high-resolution cameras installed on-site to collect information on biological and human activity. This information is aggregated in real time on the terminal and compressed for efficient data transfer. For example, the H.264 codec is commonly used for video compression.

[0476] Next, the terminal sends the compressed information to the server. The server receives it and first decompresses the information to make it analyzable. At this stage, the decompression technique to be used is selected according to the compression format of the received data.

[0477] Next, the server analyzes the information using a knowledge processing module. This module includes a generative AI model built using deep learning frameworks such as TensorFlow and PyTorch, and is pre-trained to identify species and behavioral patterns of organisms. Based on the analysis results, the server uses an anomaly detection unit to identify unusual activities and behaviors. In this process, a reference comparison configuration is used to compare the observed behavior with a set baseline value.

[0478] If an anomaly is detected, the server generates an alarm via a transmission unit and notifies the user. This notification includes information such as the type of anomaly, its location, and the time it occurred. Based on this information, the user can take prompt action.

[0479] Furthermore, users can feed back their on-site observation results into the system as evaluation information. The server receives this feedback through the evaluation processing configuration and updates its knowledge base to improve the accuracy of anomaly detection.

[0480] As a concrete example, a possible prompt message might be, "Analyze the behavior of animals detected off animal trails at night." This invention enables efficient monitoring of a wide range of biological and human activities, allowing for rapid detection and response to anomalies, and is expected to deter illegal activities in protected areas.

[0481] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0482] Step 1:

[0483] The terminal collects information on biological and human activity from infrared sensors and high-resolution cameras installed on-site as data acquisition devices. In this collection stage, the input is raw data obtained from sensors and cameras, and the output is information compiled from that data in a unified manner. Specifically, a program that runs at regular intervals acquires scan results from each device and stores the data.

[0484] Step 2:

[0485] The terminal compresses the collected data to efficiently transmit it to the server. The input is a collection of raw data, and the output is compressed data generated using a compression algorithm (e.g., H.264 codec). The compressed data is then transferred to the server over the network. Specifically, a compression processor operates on the terminal side to generate a compressed file.

[0486] Step 3:

[0487] The server receives compressed data sent from the terminal and starts the decompression process. The input is compressed data, and the output is the original data in a parseable format. Decompression uses an algorithm that is the reverse of the compression algorithm. Specifically, decompression software installed on the server reads the data stream and decompresses it.

[0488] Step 4:

[0489] The server uses a knowledge processing module to analyze the decompressed data. The input is decompressed biological activity information and human activity information, and the output is information on the identified species and behavioral patterns of organisms. A generative AI model is used for this analysis, for example, a model pre-trained using TensorFlow. Specifically, the model component scans the data and extracts anomalous patterns and features.

[0490] Step 5:

[0491] If an anomaly is detected based on the analysis results, the server uses an anomaly detection unit to identify the anomaly. The input is the analysis results, and the output is identified information such as the type and location of the anomaly. A baseline comparison configuration is used at this stage and compared with normal operating data. Specifically, the anomaly detection algorithm retrieves baseline values ​​from the database and performs a comparative analysis.

[0492] Step 6:

[0493] If an anomaly is detected, the server generates an alarm through a transmission unit and notifies the user. The input is information from the anomaly detection unit, and the output is the alarm message sent to the user. Transmission is done via email or a dedicated application over the internet. Specifically, the notification software creates a message containing detailed information, including the time and location of the incident, and adds it to the transmission queue.

[0494] Step 7:

[0495] Users can provide feedback to the server based on on-site observations. The input is user feedback, and the output is an updated knowledge base reflecting that feedback. The server uses an evaluation processing configuration to incorporate new information into the system. Specifically, the feedback interface receives the information and automatically updates the knowledge base.

[0496] (Application Example 1)

[0497] 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."

[0498] There is a need for a system that can accurately monitor wildlife and human activity in large protected areas in real time and respond immediately if anomalies are detected. This system is expected to strengthen the suppression of poaching and illegal activities, as well as wildlife protection.

[0499] 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.

[0500] In this invention, the server includes means for collecting biological activity information and human activity information from a data acquisition device; artificial intelligence processor means for analyzing the collected information to identify the species and behavioral tendencies of organisms; anomaly detection process means for identifying abnormal activity or abnormal biological behavior from the analyzed information; and means for transmitting notifications in real time to user terminals to support rapid response at the site. This enables instantaneous detection of anomalies, rapid response, and increased efficiency of protection activities.

[0501] An "information acquisition device" is a hardware or software component that senses the activities of surrounding organisms and humans and collects that information.

[0502] "Biological activity information" refers to data on the behavior and movement patterns of wild animals and plants, which is useful for monitoring and conservation activities.

[0503] "Human activity information" refers to data about human movement and behavior, and is used in particular to detect suspicious activity and illegal intrusion.

[0504] An "artificial intelligence processor" is a computing infrastructure used to analyze collected data and run machine learning models that recognize specific patterns.

[0505] An "anomaly detection process" is a process that identifies unusual activity from analyzed information and notifies users of this activity as a warning or notification.

[0506] "Communication means" refers to the technical means for transmitting generated information to the user's terminal, enabling real-time notification.

[0507] The "evaluation process configuration" is the process of receiving feedback from users and retraining the system to improve the accuracy of the model.

[0508] To implement this invention, a system combining an information acquisition device, an artificial intelligence processor, an anomaly detection process, communication means, and an evaluation processing configuration is required. The operation of this system will be described in detail below.

[0509] The server receives biological and human activity information transmitted from the information acquisition device in compressed data format and performs the process of decompressing it. This information acquisition device includes devices with compression capabilities, specifically various sensors and camera modules used for data collection. The received data is then analyzed by an artificial intelligence processor. This analysis process includes the ability to identify the species and behavioral tendencies of organisms using trained models. The analysis is performed using machine learning frameworks such as TensorFlow and PyTorch.

[0510] The server further identifies biological and human activity that deviates from normal patterns through an anomaly detection process. For example, it can detect unnecessary human intrusions in protected areas or unusual animal movements. This generates timely notifications, which are then pushed to user terminals via communication channels. Real-time notification technologies such as Firebase Cloud Messaging are used here.

[0511] Users receive anomaly information displayed on their terminals and take prompt action on-site. During this process, user feedback is transmitted to the server through an evaluation processing configuration, and the system's model learning is updated. This feedback improves the accuracy of anomaly detection.

[0512] For example, if movement of an animal species not typically found in a wildlife sanctuary is detected, the system immediately notifies the user with the message: "Notable animal activity has been detected. Location: X coordinate, Time: 12:34. Please investigate further." This prompt allows the user to quickly understand the situation and take the necessary action.

[0513] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0514] Step 1:

[0515] The terminal collects biological and human activity information using information acquisition devices. This includes data collection using sensors and cameras, and the collected data is compressed using a compression algorithm. The input is raw data from the field, and the output is compressed data.

[0516] Step 2:

[0517] The server receives compressed data and performs a decompression process. This decompression process restores the original raw data. The input is compressed data, and the output is the decompressed raw data.

[0518] Step 3:

[0519] The server passes the decompressed data to an artificial intelligence processor for analysis. This analysis identifies the species and behavioral tendencies of organisms. The input is the decompressed data, and the output is identified pattern information. A machine learning framework (e.g., TensorFlow) is used for the analysis.

[0520] Step 4:

[0521] The server passes the analyzed pattern information to the anomaly detection process to identify unusual activity. This process detects anomalies by comparing them to a set standard. The input is the identified pattern information, and the output is the detected anomaly information.

[0522] Step 5:

[0523] The server generates an alarm in real time using communication methods based on detected anomaly information and notifies the user's terminal. The input is the anomaly information, and the output is the notification message to the user. Specifically, push notifications are sent using Firebase Cloud Messaging.

[0524] Step 6:

[0525] Users check notifications displayed on their devices and take prompt action on-site. User feedback is sent to the server via the device. Input is the user's response status, and output is updated feedback information.

[0526] Step 7:

[0527] The server passes the received feedback information to the evaluation processing configuration and performs model retraining. This allows the system to continuously improve its accuracy. The input is the feedback information, and the output is the updated model parameters.

[0528] 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.

[0529] This invention aims to improve anomaly detection and response by combining a conventional system that collects and analyzes animal activity data and human activity data with an emotion engine that recognizes the user's emotions. This system has the following configuration.

[0530] First, a terminal is used to collect animal activity data and human activity data from sensors and cameras installed within the wildlife sanctuary. The collected data is compressed and sent to a server. The server receives the data and analyzes it using an artificial intelligence module. This analysis identifies animal species and behavioral patterns and determines whether or not there are any abnormalities.

[0531] When an anomaly is detected, the server generates an alarm and notifies the user via the communication module. A sentiment engine is added at this point to acquire real-time sentiment data from the user. The sentiment engine evaluates the user's emotional state based on factors such as their voice tone and entered text information.

[0532] User emotion data is used to adjust the priority of alerts. For example, if a user is experiencing stress or anxiety, the alert priority is increased, prompting a quicker response. Furthermore, user emotion feedback is collected through a feedback processing unit and incorporated into the retraining process of the artificial intelligence model, improving the overall accuracy and responsiveness of the system.

[0533] For example, if an animal that is normally inactive at night suddenly starts moving, the server detects this as an anomaly and issues an alarm. The user receives the notification and begins on-site investigation. Simultaneously, the emotion engine monitors the user's emotional state, and if it determines that the user is experiencing high stress, the system adjusts to provide further support. This allows the user to deal with the anomaly more effectively.

[0534] This invention aims to improve the safety of animal sanctuaries and achieve efficient, human-centered anomaly response, providing a new monitoring system that integrates emotion and technology.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The device collects real-time animal and human activity data from sensors and cameras placed within the wildlife sanctuary. This data will include video, audio, and location information. The device temporarily caches this data and prepares to send it to the server when communication is possible.

[0538] Step 2:

[0539] The device compresses the cached data and sends it to the server at regular intervals or according to the amount of data. Once the data transfer is complete, the device moves on to the next data collection cycle.

[0540] Step 3:

[0541] The server decompresses the data received from the terminal and performs analysis using an artificial intelligence module. Here, a pre-trained model is used to identify animal species, behavioral patterns, and human activities. Based on the analysis results, the server determines whether there is any unusual behavior.

[0542] Step 4:

[0543] If an anomaly is identified through analysis, the server uses an anomaly detection module to perform a more detailed check. This identifies the type, location, and time of the anomaly, and generates relevant alarms.

[0544] Step 5:

[0545] The server uses an emotion engine to assess the user's emotional state and adjust the priority of alert notifications accordingly. For example, if the user is feeling stressed, alert notifications will be emphasized to encourage a quicker response.

[0546] Step 6:

[0547] The user receives an alarm notification and begins a rapid response to the scene. After the necessary actions have been taken, the user inputs their emotions and the situation as feedback into the system. This feedback is used to verify the system's response.

[0548] Step 7:

[0549] After receiving user feedback, the server analyzes it through a feedback processing unit and uses it as training data for the artificial intelligence module. This process improves the accuracy of anomaly detection and optimizes the alarm system. The server continuously improves future anomaly detection performance by updating the model with the new training data.

[0550] (Example 2)

[0551] 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."

[0552] Conventional anomaly detection systems collect and analyze biological and human activity information, but they fail to take into account the emotional state of users, resulting in insufficient prioritization of alarms. Furthermore, inadequate model learning updates based on feedback hindered improvements in accuracy and responsiveness.

[0553] 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.

[0554] In this invention, the server includes means for collecting biological activity information and human activity information from a data provision device, an emotion evaluation element for acquiring user emotion information using an emotion engine and adjusting the priority of alarms, and a feedback processing device for receiving feedback from the user and updating the learning of an artificial intelligence model. This enables flexible adjustment of alarm priorities based on the user's emotional state when anomaly is detected, and improves system accuracy through feedback.

[0555] A "data provision device" is a device for acquiring biological activity information and human activity information and transmitting it to a system.

[0556] "Biological activity information" refers to information about the behavior and state of living organisms such as animals and plants.

[0557] "Human activity information" refers to information about human behavior and conditions.

[0558] "Artificial intelligence components" refer to machine learning models and algorithms used to analyze information on the activities of living organisms and humans and to identify specific patterns.

[0559] An "anomaly detection module" is an element used to identify abnormal activity or behavior from analyzed information.

[0560] A "communication device" is a device used to transmit and notify information from a system to a user.

[0561] An "emotion engine" is software or a module that acquires a user's emotional information and evaluates their emotional state.

[0562] "Emotional evaluation elements" are components used to adjust the priority of alarms based on the user's emotional information.

[0563] A "feedback processing device" is a device that collects feedback from users and updates the learning of an artificial intelligence model based on that feedback.

[0564] This invention is a system that collects and analyzes biological and human activity information, and uses an emotion engine to optimize anomaly detection and response in a human-centered manner. The following hardware and software are used to implement the system.

[0565] The terminal functions as a data provider, acquiring information on biological and human activity from various sensors and cameras within the protected area. Sensors detect movement, temperature, and sound, while cameras collect video data. This data is compressed by the terminal and transmitted to the server via an efficient communication protocol.

[0566] Upon receiving data, the server uses artificial intelligence components to perform analysis. Based on the identified data, an anomaly detection module identifies unusual activity. For example, if an animal that is normally inactive at night exhibits unexpected movement, the server immediately records it as an anomaly. Any anomalies detected through the analysis are notified to the user via a communication device, and an alarm is issued.

[0567] When a user receives an alert, the emotion engine acquires the user's emotional information in real time. Through voice tone analysis and evaluation of text information, it understands the user's emotional state. The emotion evaluation element uses this information to adjust the alert priority. If the system determines that the user is experiencing high stress, it increases the priority and prompts a quicker response.

[0568] Furthermore, users can provide feedback. This feedback is aggregated by a feedback processing unit and incorporated into the retraining of the generated AI model, thereby improving the system's accuracy and adaptability. This type of adaptive feedback mechanism serves as the cornerstone of continuous system improvement.

[0569] As a concrete example, imagine an animal that is normally diurnal becomes active during the night. The server immediately detects this anomaly and sends a prompt message to the user stating, "An anomaly has been detected. Please check the situation." As the user checks the situation, the emotion engine evaluates the user's feelings in real time, and the system adjusts to provide further support as needed. This process allows the user to respond to the anomaly more effectively.

[0570] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0571] Step 1:

[0572] The terminal collects biological and human activity information from data provision devices. Sensors detect movement, temperature, and sound, while cameras capture video information. Input is raw data from sensors and cameras, and output is the collected unprocessed data. This information is stored for subsequent analysis.

[0573] Step 2:

[0574] The terminal compresses the collected data and sends it to the server. A data compression algorithm is used to reduce the size of the information and optimize bandwidth during communication. The input is raw data, and the output is a compressed data file. The compressed data is sent to the server via the HTTPS protocol.

[0575] Step 3:

[0576] The server receives the compressed data and decompresses it. The decompressed data is then input into the artificial intelligence components to begin analysis. In this step, the data is made accessible again and ready for analysis. The input is compressed data, and the output is analyzable data.

[0577] Step 4:

[0578] The server processes the decompressed data through artificial intelligence components to identify animal species and behavioral patterns. A generative AI model is used to extract and classify features from the data. The input is analyzable data, and the output is the identified species and behavioral patterns. This step performs pattern recognition and classification operations.

[0579] Step 5:

[0580] The server uses the identified data to activate an anomaly detection module and identify abnormal activity or behavior. It compares this to pre-configured criteria, and if an anomaly is detected, it generates an alarm. The input is the identified pattern, and the output is the anomaly detection result. When an anomaly is detected, the alarm management process is triggered.

[0581] Step 6:

[0582] The server notifies the user of the generated alarm via a communication device. It sends a prompt message to the user's terminal to draw their attention. The input is the anomaly detection result, and the output is the alarm notification. For example, the prompt message "An anomaly has been detected. Please check the situation." is sent.

[0583] Step 7:

[0584] When a user receives an alarm and conducts on-site verification, the server activates the emotion engine to retrieve the user's emotional information. It analyzes voice tone and text input to evaluate the emotional state. Input consists of voice and text data, and output is the evaluated emotional state.

[0585] Step 8:

[0586] The server adjusts alarm priorities using acquired emotional information. If a high stress level is detected, the priority is increased, and the response is accelerated. The input is the evaluated emotional state, and the output is the adjusted alarm priority.

[0587] Step 9:

[0588] The server receives feedback from the user and retrains the generated AI model via a feedback processing unit. The feedback data is analyzed to update the model, improving the system's accuracy and adaptability. The input is the feedback data, and the output is the updated model. This process continuously improves the system's adaptability.

[0589] (Application Example 2)

[0590] 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."

[0591] Conventional monitoring systems have a fixed priority for alarms after anomaly detection, making it difficult to respond quickly and appropriately while considering the user's emotional state. This can increase the burden on users and potentially decrease accuracy and efficiency.

[0592] 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.

[0593] In this invention, the server includes means for collecting animal activity data and human activity data from a data acquisition device, an artificial intelligence module for analyzing the collected data to identify animal species and behavioral patterns, and an emotion analysis module for evaluating the user's emotional state and adjusting the priority of alarms. This makes it possible to adjust the priority of alarms according to the user's emotional state.

[0594] A "data acquisition device" is a device that is set up to collect animal activity data and human activity data.

[0595] An "artificial intelligence module" is a software component that analyzes collected data to identify animal species and behavioral patterns.

[0596] An "anomaly detection module" is a program used to identify abnormal activity or animal behavior from analyzed data.

[0597] A "communication module" is a device or software that has the function of notifying users of information necessary for monitoring activities based on detected anomalies.

[0598] The "emotion analysis module" is a module used to evaluate the user's emotional state and adjust the priority of alarms based on the information obtained.

[0599] A "feedback processing unit" is a device or software component that receives feedback from users and updates the learning of an artificial intelligence model based on that information.

[0600] "Data transfer means" refers to a device or system that has the function of compressing and efficiently transferring collected data.

[0601] A "reference comparison module" is software used to compare and evaluate abnormal activity against pre-defined criteria.

[0602] This invention constructs a security system that collects and analyzes animal activity data and human activity data using data acquisition devices, communication terminals, and servers, and notifies users of any anomalies.

[0603] The server receives compressed animal and human activity data collected via data acquisition devices. Efficient data transfer methods are used for compression. The received data is analyzed by an artificial intelligence module to identify animal species and behavioral patterns. An anomaly detection module uses this analyzed data to identify abnormal activity and animal behavior, and based on this, a communication module generates an alarm.

[0604] Furthermore, an emotion analysis module evaluates the user's emotional state and adjusts the alarm priority based on the obtained emotional information, including voice tone and text information. If the user's emotional state is determined to be anxiety or stress, the alarm priority is set higher, enabling a quicker response.

[0605] Users receive alert notifications via their smartphones or other devices and take the necessary actions. During this process, the user's emotional feedback is collected by a feedback processing unit and used to retrain the AI ​​model. Specifically, for example, if an animal that normally does not move suddenly becomes active in an animal sanctuary at night, this is detected as an anomaly, and the user is notified. At that time, emotional analysis is used to increase the urgency of the alert, enabling a more accurate response.

[0606] An example of a prompt message might be: "Security cameras have detected unusual activity around your residence. How would you like the alert to be adjusted considering the user's current emotional state?"

[0607] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0608] Step 1:

[0609] The terminal collects animal activity data and human activity data via a data acquisition device. The input is raw data from sensors and cameras, which is then compressed for efficient transmission to the server. The output is the compressed data.

[0610] Step 2:

[0611] The server decompresses the compressed data received from the terminal and analyzes the data using an artificial intelligence module. The input is compressed data, which is then decompressed and analyzed by AI to identify the animal species and behavioral patterns. The output is information on the animal species and behavioral patterns.

[0612] Step 3:

[0613] The server processes the analyzed behavioral pattern data with an anomaly detection module to identify abnormal activity or animal behavior. The input is behavioral pattern data, and data calculations are performed to detect anomalies by comparing it with past normal data. The output is a flag indicating the presence or absence of an anomaly.

[0614] Step 4:

[0615] When an anomaly is detected, the server uses a communication module to generate an alarm and send a notification to the user. The input is the anomaly detection result, and the alarm is generated by setting the notification content as appropriate. The output is the generated alarm message.

[0616] Step 5:

[0617] The server uses an emotion analysis module to collect user emotion data and adjusts alarm priorities based on that information. Inputs include the user's voice tone and text data, and an emotion recognition algorithm evaluates their emotional state. The output is the adjusted alarm priority.

[0618] Step 6:

[0619] Users receive alerts tailored to their emotional state via their devices or smartphones and take necessary actions. The input is a pre-configured alert message, which is output as a display on the device screen.

[0620] Step 7:

[0621] The server collects user feedback in a feedback processing unit and uses it to retrain the model. The input is user feedback data, which is used to update the artificial intelligence model and improve the system's accuracy. The output is the updated model parameters.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] [Fourth Embodiment]

[0626] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0627] 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.

[0628] 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).

[0629] 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.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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".

[0639] This invention relates to a system that supports the monitoring of large-scale wildlife protection areas by collecting and analyzing animal activity data and human activity data in real time and detecting anomalies. This system consists of devices that perform the following operations.

[0640] First, a terminal is used to collect animal activity data and human activity data from local sensors and cameras as a data acquisition device. This data is collected in real time and transmitted to a server in a compressed format.

[0641] The server decompresses the received data and analyzes it using an artificial intelligence module. This module includes a pre-trained model to identify animal species and behavioral patterns. If the server detects unusual animal behavior or anomalies in human activity data, it immediately identifies the anomaly using an anomaly detection module.

[0642] When an anomaly is detected, the server generates an alarm and notifies the user using the communication module. This notification includes detailed information such as the nature of the anomaly, its location, and the time it occurred, allowing the user to take prompt action.

[0643] Furthermore, users can input their on-site observations into the system as feedback. The server receives this feedback through a feedback processing unit, retrains the model, and improves the accuracy of anomaly detection.

[0644] For example, if an animal is detected moving to a location where it doesn't normally appear at night, the server will determine that its behavior is abnormal and issue an alarm. The same applies when suspicious human activity is detected in areas of a protected zone where there is normally no human activity. This enables a swift and efficient response, contributing to the suppression of poaching and illegal activities.

[0645] The following describes the processing flow.

[0646] Step 1:

[0647] The device collects animal and human activity data in real time from sensors and cameras installed within the wildlife sanctuary. This includes audio, video, and location information. The device temporarily stores this data locally.

[0648] Step 2:

[0649] The terminal compresses the collected data and sends it to the server based on a predetermined time interval or trigger event. Compression improves the efficiency of data transfer.

[0650] Step 3:

[0651] The server receives data from the terminal and performs decompression. The data is then input into an artificial intelligence module to identify the animal species and behavioral patterns. The AI ​​module performs this analysis using a pre-trained model.

[0652] Step 4:

[0653] The server evaluates the analyzed data using an anomaly detection module. This module compares the data to normal data to determine if there is any abnormal animal behavior or human activity.

[0654] Step 5:

[0655] The server generates an alarm when an anomaly is detected. The alarm includes the type, location, time, and possible cause of the anomaly.

[0656] Step 6:

[0657] The server notifies the user of an alarm via a communication module. This notification is sent via email, SMS, or a dedicated app. The user can then take action upon receiving this notification.

[0658] Step 7:

[0659] Users can check the situation on-site and input feedback into the system. This feedback includes information about the validity of the alarm and the actual situation.

[0660] Step 8:

[0661] The server receives feedback from users and performs analysis in the feedback processing unit. Based on this information, the artificial intelligence model is updated to further improve the accuracy of anomaly detection.

[0662] (Example 1)

[0663] 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".

[0664] Conventional monitoring systems for biological and human activities have problems with efficient real-time data collection and analysis across a wide range of data, making rapid detection and response to anomalies difficult. Furthermore, the lack of mechanisms to effectively utilize user feedback and continuously improve analytical accuracy sometimes results in insufficient system accuracy and reliability.

[0665] 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.

[0666] In this invention, the server includes means for collecting biological activity information and human activity information from a data collection device, knowledge processing module means for analyzing the collected information to identify the species and behavioral patterns of organisms, and an anomaly detection unit means for identifying abnormal activity or abnormal biological behavior from the analyzed information. This makes it possible to monitor a wide range of activities in real time and to quickly detect and respond to anomalies. Furthermore, since the accuracy of the entire system can be improved by utilizing evaluation information from users, long-term reliability is improved.

[0667] A "data collection device" refers to devices such as sensors and cameras used to collect information on biological and human activities in the field.

[0668] "Biological activity information" refers to information about the behavior and migration patterns of organisms, especially wild animals, in a specific region.

[0669] "Human activity information" refers to data on human movement and behavior, particularly information used to monitor human activity in natural environments and protected areas.

[0670] A "knowledge processing module" is a software configuration equipped with artificial intelligence technology used to analyze collected information and identify species and their behavioral patterns.

[0671] An "anomaly detection unit" is a device or software that has the function of identifying unusual activity or biological behavior from analyzed information.

[0672] A "transmission unit" is a communication device that notifies users of alarms generated based on detected anomalies, along with necessary information.

[0673] An "evaluation processing configuration" is a configuration that receives feedback information from users, updates the knowledge base based on this information, and has functions to improve the overall analysis accuracy of the system.

[0674] The "information transmission function" is a function that efficiently compresses collected information and transmits it via a communication network.

[0675] A "reference comparison configuration" is a configuration that has the function of comparing acquired data with pre-set reference values ​​or conditions when detecting abnormal activity.

[0676] The embodiments for carrying out this invention are shown below.

[0677] First, the terminal functions as a data collection device, utilizing sensors (e.g., infrared sensors) and high-resolution cameras installed on-site to collect information on biological and human activity. This information is aggregated in real time on the terminal and compressed for efficient data transfer. For example, the H.264 codec is commonly used for video compression.

[0678] Next, the terminal sends the compressed information to the server. The server receives it and first decompresses the information to make it analyzable. At this stage, the decompression technique to be used is selected according to the compression format of the received data.

[0679] Next, the server analyzes the information using a knowledge processing module. This module includes a generative AI model built using deep learning frameworks such as TensorFlow and PyTorch, and is pre-trained to identify species and behavioral patterns of organisms. Based on the analysis results, the server uses an anomaly detection unit to identify unusual activities and behaviors. In this process, a reference comparison configuration is used to compare the observed behavior with a set baseline value.

[0680] If an anomaly is detected, the server generates an alarm via a transmission unit and notifies the user. This notification includes information such as the type of anomaly, its location, and the time it occurred. Based on this information, the user can take prompt action.

[0681] Furthermore, users can feed back their on-site observation results into the system as evaluation information. The server receives this feedback through the evaluation processing configuration and updates its knowledge base to improve the accuracy of anomaly detection.

[0682] As a concrete example, a possible prompt message might be, "Analyze the behavior of animals detected off animal trails at night." This invention enables efficient monitoring of a wide range of biological and human activities, allowing for rapid detection and response to anomalies, and is expected to deter illegal activities in protected areas.

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The terminal collects information on biological and human activity from infrared sensors and high-resolution cameras installed on-site as data acquisition devices. In this collection stage, the input is raw data obtained from sensors and cameras, and the output is information compiled from that data in a unified manner. Specifically, a program that runs at regular intervals acquires scan results from each device and stores the data.

[0686] Step 2:

[0687] The terminal compresses the collected data to efficiently transmit it to the server. The input is a collection of raw data, and the output is compressed data generated using a compression algorithm (e.g., H.264 codec). The compressed data is then transferred to the server over the network. Specifically, a compression processor operates on the terminal side to generate a compressed file.

[0688] Step 3:

[0689] The server receives compressed data sent from the terminal and starts the decompression process. The input is compressed data, and the output is the original data in a parseable format. Decompression uses an algorithm that is the reverse of the compression algorithm. Specifically, decompression software installed on the server reads the data stream and decompresses it.

[0690] Step 4:

[0691] The server uses a knowledge processing module to analyze the decompressed data. The input is decompressed biological activity information and human activity information, and the output is information on the identified species and behavioral patterns of organisms. A generative AI model is used for this analysis, for example, a model pre-trained using TensorFlow. Specifically, the model component scans the data and extracts anomalous patterns and features.

[0692] Step 5:

[0693] If an anomaly is detected based on the analysis results, the server uses an anomaly detection unit to identify the anomaly. The input is the analysis results, and the output is identified information such as the type and location of the anomaly. A baseline comparison configuration is used at this stage and compared with normal operating data. Specifically, the anomaly detection algorithm retrieves baseline values ​​from the database and performs a comparative analysis.

[0694] Step 6:

[0695] If an anomaly is detected, the server generates an alarm through a transmission unit and notifies the user. The input is information from the anomaly detection unit, and the output is the alarm message sent to the user. Transmission is done via email or a dedicated application over the internet. Specifically, the notification software creates a message containing detailed information, including the time and location of the incident, and adds it to the transmission queue.

[0696] Step 7:

[0697] Users can provide feedback to the server based on on-site observations. The input is user feedback, and the output is an updated knowledge base reflecting that feedback. The server uses an evaluation processing configuration to incorporate new information into the system. Specifically, the feedback interface receives the information and automatically updates the knowledge base.

[0698] (Application Example 1)

[0699] 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".

[0700] There is a need for a system that can accurately monitor wildlife and human activity in large protected areas in real time and respond immediately if anomalies are detected. This system is expected to strengthen the suppression of poaching and illegal activities, as well as wildlife protection.

[0701] 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.

[0702] In this invention, the server includes means for collecting biological activity information and human activity information from a data acquisition device; artificial intelligence processor means for analyzing the collected information to identify the species and behavioral tendencies of organisms; anomaly detection process means for identifying abnormal activity or abnormal biological behavior from the analyzed information; and means for transmitting notifications in real time to user terminals to support rapid response at the site. This enables instantaneous detection of anomalies, rapid response, and increased efficiency of protection activities.

[0703] An "information acquisition device" is a hardware or software component that senses the activities of surrounding organisms and humans and collects that information.

[0704] "Biological activity information" refers to data on the behavior and movement patterns of wild animals and plants, which is useful for monitoring and conservation activities.

[0705] "Human activity information" refers to data about human movement and behavior, and is used in particular to detect suspicious activity and illegal intrusion.

[0706] An "artificial intelligence processor" is a computing infrastructure used to analyze collected data and run machine learning models that recognize specific patterns.

[0707] An "anomaly detection process" is a process that identifies unusual activity from analyzed information and notifies users of this activity as a warning or notification.

[0708] "Communication means" refers to the technical means for transmitting generated information to the user's terminal, enabling real-time notification.

[0709] The "evaluation process configuration" is the process of receiving feedback from users and retraining the system to improve the accuracy of the model.

[0710] To implement this invention, a system combining an information acquisition device, an artificial intelligence processor, an anomaly detection process, communication means, and an evaluation processing configuration is required. The operation of this system will be described in detail below.

[0711] The server receives biological and human activity information transmitted from the information acquisition device in compressed data format and performs the process of decompressing it. This information acquisition device includes devices with compression capabilities, specifically various sensors and camera modules used for data collection. The received data is then analyzed by an artificial intelligence processor. This analysis process includes the ability to identify the species and behavioral tendencies of organisms using trained models. The analysis is performed using machine learning frameworks such as TensorFlow and PyTorch.

[0712] The server further identifies biological and human activity that deviates from normal patterns through an anomaly detection process. For example, it can detect unnecessary human intrusions in protected areas or unusual animal movements. This generates timely notifications, which are then pushed to user terminals via communication channels. Real-time notification technologies such as Firebase Cloud Messaging are used here.

[0713] Users receive anomaly information displayed on their terminals and take prompt action on-site. During this process, user feedback is transmitted to the server through an evaluation processing configuration, and the system's model learning is updated. This feedback improves the accuracy of anomaly detection.

[0714] For example, if movement of an animal species not typically found in a wildlife sanctuary is detected, the system immediately notifies the user with the message: "Notable animal activity has been detected. Location: X coordinate, Time: 12:34. Please investigate further." This prompt allows the user to quickly understand the situation and take the necessary action.

[0715] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0716] Step 1:

[0717] The terminal collects biological and human activity information using information acquisition devices. This includes data collection using sensors and cameras, and the collected data is compressed using a compression algorithm. The input is raw data from the field, and the output is compressed data.

[0718] Step 2:

[0719] The server receives compressed data and performs a decompression process. This decompression process restores the original raw data. The input is compressed data, and the output is the decompressed raw data.

[0720] Step 3:

[0721] The server passes the decompressed data to an artificial intelligence processor for analysis. This analysis identifies the species and behavioral tendencies of organisms. The input is the decompressed data, and the output is identified pattern information. A machine learning framework (e.g., TensorFlow) is used for the analysis.

[0722] Step 4:

[0723] The server passes the analyzed pattern information to the anomaly detection process to identify unusual activity. This process detects anomalies by comparing them to a set standard. The input is the identified pattern information, and the output is the detected anomaly information.

[0724] Step 5:

[0725] The server generates an alarm in real time using communication methods based on detected anomaly information and notifies the user's terminal. The input is the anomaly information, and the output is the notification message to the user. Specifically, push notifications are sent using Firebase Cloud Messaging.

[0726] Step 6:

[0727] Users check notifications displayed on their devices and take prompt action on-site. User feedback is sent to the server via the device. Input is the user's response status, and output is updated feedback information.

[0728] Step 7:

[0729] The server passes the received feedback information to the evaluation processing configuration and performs model retraining. This allows the system to continuously improve its accuracy. The input is the feedback information, and the output is the updated model parameters.

[0730] 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.

[0731] This invention aims to improve anomaly detection and response by combining a conventional system that collects and analyzes animal activity data and human activity data with an emotion engine that recognizes the user's emotions. This system has the following configuration.

[0732] First, a terminal is used to collect animal activity data and human activity data from sensors and cameras installed within the wildlife sanctuary. The collected data is compressed and sent to a server. The server receives the data and analyzes it using an artificial intelligence module. This analysis identifies animal species and behavioral patterns and determines whether or not there are any abnormalities.

[0733] When an anomaly is detected, the server generates an alarm and notifies the user via the communication module. A sentiment engine is added at this point to acquire real-time sentiment data from the user. The sentiment engine evaluates the user's emotional state based on factors such as their voice tone and entered text information.

[0734] User emotion data is used to adjust the priority of alerts. For example, if a user is experiencing stress or anxiety, the alert priority is increased, prompting a quicker response. Furthermore, user emotion feedback is collected through a feedback processing unit and incorporated into the retraining process of the artificial intelligence model, improving the overall accuracy and responsiveness of the system.

[0735] For example, if an animal that is normally inactive at night suddenly starts moving, the server detects this as an anomaly and issues an alarm. The user receives the notification and begins on-site investigation. Simultaneously, the emotion engine monitors the user's emotional state, and if it determines that the user is experiencing high stress, the system adjusts to provide further support. This allows the user to deal with the anomaly more effectively.

[0736] This invention aims to improve the safety of animal sanctuaries and achieve efficient, human-centered anomaly response, providing a new monitoring system that integrates emotion and technology.

[0737] The following describes the processing flow.

[0738] Step 1:

[0739] The device collects real-time animal and human activity data from sensors and cameras placed within the wildlife sanctuary. This data will include video, audio, and location information. The device temporarily caches this data and prepares to send it to the server when communication is possible.

[0740] Step 2:

[0741] The device compresses the cached data and sends it to the server at regular intervals or according to the amount of data. Once the data transfer is complete, the device moves on to the next data collection cycle.

[0742] Step 3:

[0743] The server decompresses the data received from the terminal and performs analysis using an artificial intelligence module. Here, a pre-trained model is used to identify animal species, behavioral patterns, and human activities. Based on the analysis results, the server determines whether there is any unusual behavior.

[0744] Step 4:

[0745] If an anomaly is identified through analysis, the server uses an anomaly detection module to perform a more detailed check. This identifies the type, location, and time of the anomaly, and generates relevant alarms.

[0746] Step 5:

[0747] The server uses an emotion engine to assess the user's emotional state and adjust the priority of alert notifications accordingly. For example, if the user is feeling stressed, alert notifications will be emphasized to encourage a quicker response.

[0748] Step 6:

[0749] The user receives an alarm notification and begins a rapid response to the scene. After the necessary actions have been taken, the user inputs their emotions and the situation as feedback into the system. This feedback is used to verify the system's response.

[0750] Step 7:

[0751] After receiving user feedback, the server analyzes it through a feedback processing unit and uses it as training data for the artificial intelligence module. This process improves the accuracy of anomaly detection and optimizes the alarm system. The server continuously improves future anomaly detection performance by updating the model with the new training data.

[0752] (Example 2)

[0753] 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".

[0754] Conventional anomaly detection systems collect and analyze biological and human activity information, but they fail to take into account the emotional state of users, resulting in insufficient prioritization of alarms. Furthermore, inadequate model learning updates based on feedback hindered improvements in accuracy and responsiveness.

[0755] 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.

[0756] In this invention, the server includes means for collecting biological activity information and human activity information from a data provision device, an emotion evaluation element for acquiring user emotion information using an emotion engine and adjusting the priority of alarms, and a feedback processing device for receiving feedback from the user and updating the learning of an artificial intelligence model. This enables flexible adjustment of alarm priorities based on the user's emotional state when anomaly is detected, and improves system accuracy through feedback.

[0757] A "data provision device" is a device for acquiring biological activity information and human activity information and transmitting it to a system.

[0758] "Biological activity information" refers to information about the behavior and state of living organisms such as animals and plants.

[0759] "Human activity information" refers to information about human behavior and conditions.

[0760] "Artificial intelligence components" refer to machine learning models and algorithms used to analyze information on the activities of living organisms and humans and to identify specific patterns.

[0761] An "anomaly detection module" is an element used to identify abnormal activity or behavior from analyzed information.

[0762] A "communication device" is a device used to transmit and notify information from a system to a user.

[0763] An "emotion engine" is software or a module that acquires a user's emotional information and evaluates their emotional state.

[0764] "Emotional evaluation elements" are components used to adjust the priority of alarms based on the user's emotional information.

[0765] A "feedback processing device" is a device that collects feedback from users and updates the learning of an artificial intelligence model based on that feedback.

[0766] This invention is a system that collects and analyzes biological and human activity information, and uses an emotion engine to optimize anomaly detection and response in a human-centered manner. The following hardware and software are used to implement the system.

[0767] The terminal functions as a data provider, acquiring information on biological and human activity from various sensors and cameras within the protected area. Sensors detect movement, temperature, and sound, while cameras collect video data. This data is compressed by the terminal and transmitted to the server via an efficient communication protocol.

[0768] Upon receiving data, the server uses artificial intelligence components to perform analysis. Based on the identified data, an anomaly detection module identifies unusual activity. For example, if an animal that is normally inactive at night exhibits unexpected movement, the server immediately records it as an anomaly. Any anomalies detected through the analysis are notified to the user via a communication device, and an alarm is issued.

[0769] When a user receives an alert, the emotion engine acquires the user's emotional information in real time. Through voice tone analysis and evaluation of text information, it understands the user's emotional state. The emotion evaluation element uses this information to adjust the alert priority. If the system determines that the user is experiencing high stress, it increases the priority and prompts a quicker response.

[0770] Furthermore, users can provide feedback. This feedback is aggregated by a feedback processing unit and incorporated into the retraining of the generated AI model, thereby improving the system's accuracy and adaptability. This type of adaptive feedback mechanism serves as the cornerstone of continuous system improvement.

[0771] As a concrete example, imagine an animal that is normally diurnal becomes active during the night. The server immediately detects this anomaly and sends a prompt message to the user stating, "An anomaly has been detected. Please check the situation." As the user checks the situation, the emotion engine evaluates the user's feelings in real time, and the system adjusts to provide further support as needed. This process allows the user to respond to the anomaly more effectively.

[0772] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0773] Step 1:

[0774] The terminal collects biological and human activity information from data provision devices. Sensors detect movement, temperature, and sound, while cameras capture video information. Input is raw data from sensors and cameras, and output is the collected unprocessed data. This information is stored for subsequent analysis.

[0775] Step 2:

[0776] The terminal compresses the collected data and sends it to the server. A data compression algorithm is used to reduce the size of the information and optimize bandwidth during communication. The input is raw data, and the output is a compressed data file. The compressed data is sent to the server via the HTTPS protocol.

[0777] Step 3:

[0778] The server receives the compressed data and decompresses it. The decompressed data is then input into the artificial intelligence components to begin analysis. In this step, the data is made accessible again and ready for analysis. The input is compressed data, and the output is analyzable data.

[0779] Step 4:

[0780] The server processes the decompressed data through artificial intelligence components to identify animal species and behavioral patterns. A generative AI model is used to extract and classify features from the data. The input is analyzable data, and the output is the identified species and behavioral patterns. This step performs pattern recognition and classification operations.

[0781] Step 5:

[0782] The server uses the identified data to activate an anomaly detection module and identify abnormal activity or behavior. It compares this to pre-configured criteria, and if an anomaly is detected, it generates an alarm. The input is the identified pattern, and the output is the anomaly detection result. When an anomaly is detected, the alarm management process is triggered.

[0783] Step 6:

[0784] The server notifies the user of the generated alarm via a communication device. It sends a prompt message to the user's terminal to draw their attention. The input is the anomaly detection result, and the output is the alarm notification. For example, the prompt message "An anomaly has been detected. Please check the situation." is sent.

[0785] Step 7:

[0786] When a user receives an alarm and conducts on-site verification, the server activates the emotion engine to retrieve the user's emotional information. It analyzes voice tone and text input to evaluate the emotional state. Input consists of voice and text data, and output is the evaluated emotional state.

[0787] Step 8:

[0788] The server adjusts alarm priorities using acquired emotional information. If a high stress level is detected, the priority is increased, and the response is accelerated. The input is the evaluated emotional state, and the output is the adjusted alarm priority.

[0789] Step 9:

[0790] The server receives feedback from the user and retrains the generated AI model via a feedback processing unit. The feedback data is analyzed to update the model, improving the system's accuracy and adaptability. The input is the feedback data, and the output is the updated model. This process continuously improves the system's adaptability.

[0791] (Application Example 2)

[0792] 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".

[0793] Conventional monitoring systems have a fixed priority for alarms after anomaly detection, making it difficult to respond quickly and appropriately while considering the user's emotional state. This can increase the burden on users and potentially decrease accuracy and efficiency.

[0794] 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.

[0795] In this invention, the server includes means for collecting animal activity data and human activity data from a data acquisition device, an artificial intelligence module for analyzing the collected data to identify animal species and behavioral patterns, and an emotion analysis module for evaluating the user's emotional state and adjusting the priority of alarms. This makes it possible to adjust the priority of alarms according to the user's emotional state.

[0796] A "data acquisition device" is a device that is set up to collect animal activity data and human activity data.

[0797] An "artificial intelligence module" is a software component that analyzes collected data to identify animal species and behavioral patterns.

[0798] An "anomaly detection module" is a program used to identify abnormal activity or animal behavior from analyzed data.

[0799] A "communication module" is a device or software that has the function of notifying users of information necessary for monitoring activities based on detected anomalies.

[0800] The "emotion analysis module" is a module used to evaluate the user's emotional state and adjust the priority of alarms based on the information obtained.

[0801] A "feedback processing unit" is a device or software component that receives feedback from users and updates the learning of an artificial intelligence model based on that information.

[0802] "Data transfer means" refers to a device or system that has the function of compressing and efficiently transferring collected data.

[0803] A "reference comparison module" is software used to compare and evaluate abnormal activity against pre-defined criteria.

[0804] This invention constructs a security system that collects and analyzes animal activity data and human activity data using data acquisition devices, communication terminals, and servers, and notifies users of any anomalies.

[0805] The server receives compressed animal and human activity data collected via data acquisition devices. Efficient data transfer methods are used for compression. The received data is analyzed by an artificial intelligence module to identify animal species and behavioral patterns. An anomaly detection module uses this analyzed data to identify abnormal activity and animal behavior, and based on this, a communication module generates an alarm.

[0806] Furthermore, an emotion analysis module evaluates the user's emotional state and adjusts the alarm priority based on the obtained emotional information, including voice tone and text information. If the user's emotional state is determined to be anxiety or stress, the alarm priority is set higher, enabling a quicker response.

[0807] Users receive alert notifications via their smartphones or other devices and take the necessary actions. During this process, the user's emotional feedback is collected by a feedback processing unit and used to retrain the AI ​​model. Specifically, for example, if an animal that normally does not move suddenly becomes active in an animal sanctuary at night, this is detected as an anomaly, and the user is notified. At that time, emotional analysis is used to increase the urgency of the alert, enabling a more accurate response.

[0808] An example of a prompt message might be: "Security cameras have detected unusual activity around your residence. How would you like the alert to be adjusted considering the user's current emotional state?"

[0809] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0810] Step 1:

[0811] The terminal collects animal activity data and human activity data via a data acquisition device. The input is raw data from sensors and cameras, which is then compressed for efficient transmission to the server. The output is the compressed data.

[0812] Step 2:

[0813] The server decompresses the compressed data received from the terminal and analyzes the data using an artificial intelligence module. The input is compressed data, which is then decompressed and analyzed by AI to identify the animal species and behavioral patterns. The output is information on the animal species and behavioral patterns.

[0814] Step 3:

[0815] The server processes the analyzed behavioral pattern data with an anomaly detection module to identify abnormal activity or animal behavior. The input is behavioral pattern data, and data calculations are performed to detect anomalies by comparing it with past normal data. The output is a flag indicating the presence or absence of an anomaly.

[0816] Step 4:

[0817] When an anomaly is detected, the server uses a communication module to generate an alarm and send a notification to the user. The input is the anomaly detection result, and the alarm is generated by setting the notification content as appropriate. The output is the generated alarm message.

[0818] Step 5:

[0819] The server uses an emotion analysis module to collect user emotion data and adjusts alarm priorities based on that information. Inputs include the user's voice tone and text data, and an emotion recognition algorithm evaluates their emotional state. The output is the adjusted alarm priority.

[0820] Step 6:

[0821] Users receive alerts tailored to their emotional state via their devices or smartphones and take necessary actions. The input is a pre-configured alert message, which is output as a display on the device screen.

[0822] Step 7:

[0823] The server collects user feedback in a feedback processing unit and uses it to retrain the model. The input is user feedback data, which is used to update the artificial intelligence model and improve the system's accuracy. The output is the updated model parameters.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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."

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0845] The following is further disclosed regarding the embodiments described above.

[0846] (Claim 1)

[0847] A means for collecting animal activity data and human activity data from a data acquisition device,

[0848] An artificial intelligence module means for analyzing collected data to identify animal species and behavioral patterns,

[0849] An anomaly detection module means for identifying abnormal activity or abnormal animal behavior from analyzed data,

[0850] A communication module means for generating an alarm based on detected anomalies and notifying the user of information necessary for monitoring activities,

[0851] A feedback processing unit means for receiving user feedback and updating model learning,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, further comprising data transfer means for compressing and transferring collected data.

[0855] (Claim 3)

[0856] The system according to claim 1, comprising a reference comparison module for comparing abnormal activity with a pre-set standard.

[0857] "Example 1"

[0858] (Claim 1)

[0859] A means for collecting biological activity information and human activity information from a data collection device,

[0860] A knowledge processing module means for analyzing collected information to identify the species and behavioral patterns of organisms,

[0861] An anomaly detection unit means for identifying abnormal activity or abnormal biological behavior from analyzed information,

[0862] A communication unit means for generating an alarm based on detected anomalies and notifying users of information necessary for monitoring activities,

[0863] A means for configuring evaluation processing to receive evaluation information from users and update the knowledge base,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, further comprising an information transmission function for compressing and transmitting collected information.

[0867] (Claim 3)

[0868] The system according to claim 1, comprising a criteria comparison configuration for comparing abnormal activity with a pre-set criterion.

[0869] "Application Example 1"

[0870] (Claim 1)

[0871] A means for collecting biological activity information and human activity information from an information acquisition device,

[0872] An artificial intelligence processor means for analyzing collected information to identify the species and behavioral tendencies of organisms,

[0873] An anomaly detection process means for identifying abnormal activity or abnormal biological behavior from analyzed information,

[0874] A communication means for generating notifications based on detected anomalies and notifying users of information necessary for monitoring activities,

[0875] A means for configuring an evaluation process to receive evaluations from users and update model learning,

[0876] A means of sending notifications to user terminals in real time to support a rapid response on-site,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, further comprising information transfer means for compressing collected information and transmitting it to a server.

[0880] (Claim 3)

[0881] The system according to claim 1, comprising a reference configuration for comparing with a pre-set standard in detecting abnormal activity.

[0882] "Example 2 of combining an emotion engine"

[0883] (Claim 1)

[0884] A means for collecting biological activity information and human activity information from a data provisioning device,

[0885] An artificial intelligence component means for analyzing collected information to identify the species and behavioral patterns of organisms,

[0886] An anomaly detection module means for identifying abnormal activity or abnormal biological behavior from analyzed information,

[0887] A communication device means for generating an alarm based on detected anomalies and notifying users of information necessary for management activities,

[0888] An emotion engine acquires user emotion information, and an emotion evaluation element means for adjusting the priority of alarms,

[0889] A feedback processing device for receiving user feedback and updating the learning of an artificial intelligence model,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, further comprising data transmission means for compressing and transferring collected information.

[0893] (Claim 3)

[0894] The system according to claim 1, comprising a reference comparison configuration for comparing abnormal activity with a pre-set standard.

[0895] "Application example 2 when combining with an emotional engine"

[0896] (Claim 1)

[0897] A means for collecting animal activity data and human activity data from a data acquisition device,

[0898] An artificial intelligence module means for analyzing collected data to identify animal species and behavioral patterns,

[0899] An anomaly detection module means for identifying abnormal activity or abnormal animal behavior from analyzed data,

[0900] A communication module means for generating an alarm based on detected anomalies and notifying the user of information necessary for monitoring activities,

[0901] An emotion analysis module means for evaluating the user's emotional state and adjusting the priority of alarms,

[0902] A feedback processing unit means for receiving user feedback and updating model learning,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, further comprising data transfer means for compressing and transferring collected data.

[0906] (Claim 3)

[0907] The system according to claim 1, comprising a reference comparison module for comparing abnormal activity with a pre-set standard. [Explanation of symbols]

[0908] 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 for collecting animal activity data and human activity data from a data acquisition device, An artificial intelligence module means for analyzing collected data to identify animal species and behavioral patterns, An anomaly detection module means for identifying abnormal activity or abnormal animal behavior from analyzed data, A communication module means for generating an alarm based on detected anomalies and notifying the user of information necessary for monitoring activities, A feedback processing unit means for receiving user feedback and updating model learning, A system that includes this.

2. The system according to claim 1, further comprising data transfer means for compressing and transferring collected data.

3. The system according to claim 1, further comprising a reference comparison module for comparing abnormal activity with a pre-set standard in the detection of abnormal activity.

Images