System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring biological data of livestock; means for storing the biological data in a database; means for analyzing the biological data and detecting an abnormality; means for outputting an abnormality detection result; means for notifying a manager of the output result; and means for receiving and evaluating feedback from the manager.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern livestock farming, there is a lack of means to monitor the health and behavior of livestock in real time, making it difficult to provide prompt and accurate care. This raises concerns that livestock health risks will increase and production efficiency will decline. Another issue is that it takes a great deal of time and effort for managers to monitor the condition of livestock and take appropriate measures, placing a heavy burden on management work. [Means for solving the problem]

[0005] The present invention provides a system that includes means for acquiring livestock biometric data, means for storing the acquired data, means for analyzing the data and detecting abnormalities, means for outputting the abnormality detection results, and means for notifying the manager of the output results. The system also includes means for receiving and evaluating feedback from the manager, enabling efficient and effective livestock management. Furthermore, the system also includes means for proposing livestock care methods based on the abnormality detection results, means for evaluating the effectiveness of the proposals in real time, and means for adding the results to a recommendation database, enabling continuous learning and improvement to improve the accuracy and efficiency of livestock health management.

[0006] "Biometric data" refers to measurement data related to the health and behavior of livestock, such as body temperature, heart rate, and activity level.

[0007] A "database" is an information storage system for managing biological data obtained from livestock.

[0008] "Anomaly detection" is the process of finding unusual values ​​or patterns in biometric data based on machine learning algorithms and statistical analysis.

[0009] "Output results" refers to the analysis results obtained by the anomaly detection process, specifically information about anomalies and risks.

[0010] "Notifications" are messages or warnings sent to notify administrators of output results, including smartphone apps, SMS, and email.

[0011] "Manager" refers to the livestock breeder or farmer responsible for the health and care of livestock.

[0012] "Feedback" refers to information provided by administrators to the system, including data on the care methods implemented and their results.

[0013] "Care methods" are specific actions or measures taken by managers to improve the health and welfare of livestock, including, for example, cooling and feeding methods.

[0014] The "recommendation database" is an information management system that uses data accumulated by the system to suggest future care methods and improvement measures. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is a system for efficiently managing the health and behavior of livestock. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, and a system that processes notifications and feedback to managers.

[0037] System configuration

[0038] 1. Terminal

[0039] The terminal is a sensor attached to the livestock, which periodically collects biological data such as body temperature, heart rate, and amount of exercise. The collected data is temporarily stored in the terminal's internal storage.

[0040] 2. Server

[0041] The server receives the biometric data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as if the animal's body temperature is too high or its heart rate is abnormally high.

[0042] 3. Users

[0043] Users are livestock breeders and farmers. When the server detects an abnormality, it sends a notification message to the user. The notification includes the type of abnormality and recommended care methods. The user receives the notification and can take action promptly.

[0044] Program processing flow (explained in natural language)

[0045] Data Acquisition Phase

[0046] The device periodically collects data such as the animal's body temperature, heart rate, and activity level. For example, it measures body temperature every minute.

[0047] The acquired data is temporarily stored in the device's internal storage.

[0048] Data Transfer Phase

[0049] Periodically, for example, every hour, the device sends the collected data to the server via wireless communication (Wi-Fi, Bluetooth, etc.).

[0050] Data analysis phase

[0051] The server stores the received data in a database and analyzes it in real time using machine learning algorithms to detect abnormalities, such as body temperature exceeding the normal range.

[0052] Notification Phase

[0053] Based on the anomaly detection results, the server generates a message such as "Livestock B's body temperature is high. Please take cooling measures."

[0054] The server will then send this notification message to the user via their smartphone app, SMS, email, etc.

[0055] Feedback Phase

[0056] Users receive notifications, go to the scene to check the condition of the livestock, and implement appropriate care measures (e.g., cooling measures).

[0057] The care method performed and the results are entered into a dedicated app, and feedback is sent to the server.

[0058] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. This updated data is then reflected in future care recommendations.

[0059] Specific examples

[0060] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[0061] 2. Every hour, the device sends the collected data to the server.

[0062] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[0063] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[0064] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[0065] 6. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[0066] 7. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[0067] 8. The server analyzes the cooling treatment data and learns new care methods.

[0068] The implementation of this system will significantly improve the efficiency of livestock health management. It will also enable real-time abnormality detection and rapid response, which is expected to reduce livestock health risks and improve production efficiency.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] The device measures the livestock's biological data, such as body temperature, heart rate, and activity, every minute, and the data is temporarily stored in the internal storage.

[0072] Step 2:

[0073] Every fixed time (for example, every hour), the terminal sends the collected data to the server via wireless communication.

[0074] Step 3:

[0075] The server stores the received data in a database, with each data point being given a timestamp and the livestock's individual identification information.

[0076] Step 4:

[0077] The server analyzes the data in the database using machine learning algorithms, such as comparing body temperature values ​​with normal ranges to detect abnormalities.

[0078] Step 5:

[0079] If the server detects an anomaly, it generates an output result including the type of anomaly, details of the data that became abnormal, and recommended care methods as an anomaly detection result.

[0080] Step 6:

[0081] The server generates a notification message based on the anomaly detection result, which includes the livestock ID, details of the anomaly, and the required action.

[0082] Step 7:

[0083] The server sends a notification message to the user via the user's smartphone app, SMS, email, etc.

[0084] Step 8:

[0085] Users receive notifications and can check the condition of livestock on-site, for example, by taking cooling measures if the animals have a high body temperature.

[0086] Step 9:

[0087] The user inputs the care method and results into a dedicated app and sends the data to a server. Feedback data includes changes in body temperature and specific measures taken.

[0088] Step 10:

[0089] The server analyzes the received feedback data and evaluates the effectiveness of the care method. The evaluation results are added to a recommendation database and used to suggest future care methods.

[0090] Step 11:

[0091] Based on the updated recommendation database, the server will be prepared to suggest more appropriate care methods when abnormalities are detected in the future.

[0092] This program automates and streamlines livestock health management, enabling real-time abnormality detection and rapid response.

[0093] Example 1

[0094] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0095] Conventional livestock health management systems have problems in that they do not collect biological data or detect abnormalities in real time, and managers are not notified promptly when abnormalities are discovered. Furthermore, feedback and suggestions for care methods after abnormalities are detected are not provided efficiently, making it difficult to reduce livestock health risks. Furthermore, feedback from managers is not reflected in the system, meaning it cannot be used to suggest future care methods, resulting in ineffective use of data.

[0096] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0097] In this invention, the server includes means for acquiring livestock biometric data, means for storing the biometric data in internal storage at regular intervals and periodically transmitting it to the server, means for storing the biometric data in a database and analyzing it in real time using a machine learning algorithm to detect abnormalities, means for generating a notification message based on the abnormality detection result and notifying the manager, and means for receiving feedback from the manager and evaluating its effectiveness. This reduces livestock health risks, enables rapid response, and realizes improvements in care methods through feedback.

[0098] "Means for acquiring biological data of livestock" refers to devices that periodically acquire data such as body temperature, heart rate, and amount of exercise using sensors attached to livestock.

[0099] "Means for storing the biometric data in internal storage at regular intervals and periodically transmitting it to a server" refers to a device or function that temporarily stores the acquired biometric data in a storage medium and transfers the data to a server at regular time intervals.

[0100] "Means for storing the biometric data in a database, analyzing it in real time using a machine learning algorithm, and detecting abnormalities" refers to a device or function that records the received biometric data in a database, analyzes the data in real time using a machine learning model, and identifies abnormalities that deviate from the reference values.

[0101] "Means for generating a notification message based on the anomaly detection result and notifying the administrator" refers to a device or function that creates an appropriate warning message when an anomaly is detected and provides the information to the administrator via SMS, email, etc.

[0102] The "means for receiving feedback from the administrator and evaluating its effectiveness" refers to a device or function that collects information provided by the administrator and analyzes and evaluates the effectiveness of that information.

[0103] The "means for proposing a care method for livestock based on the abnormality detection result" is a device or function that provides an appropriate countermeasure for the detected abnormality.

[0104] "Means for evaluating the effectiveness of the proposed care method in real time and adding the results to the recommendation database" refers to a device or function that instantly analyzes the effectiveness of the proposed care method and adds the results to a database to be used for the next recommendation.

[0105] The present invention is a system for efficiently managing the health and behavior of livestock. This system includes sensors (terminals) for acquiring livestock biometric data, a server for storing and analyzing the data, and a system for notifying and providing feedback to managers.

[0106] System configuration

[0107] 1. Terminal

[0108] The terminals are sensors attached to livestock, which periodically collect biological data such as body temperature, heart rate, and activity level. The sensors used include body temperature sensors and heart rate sensors.

[0109] The acquired data is temporarily stored in the device's internal storage, specifically, using a storage device such as a microSD card or internal flash memory.

[0110] 2. Server

[0111] The server receives the biometric data sent from the terminal and stores it in a database.

[0112] The server uses machine learning algorithms to analyze data in real time and detect anomalies, using software such as MySQL or PostgreSQL as databases and Scikit-learn or TensorFlow as machine learning libraries.

[0113] If an anomaly is detected, the server generates an appropriate notification message and notifies the administrator via an SMS gateway service (e.g., Twilio) or an email service (e.g., SendGrid).

[0114] 3. Users

[0115] Users are livestock farmers and breeders. They receive notifications from the server, check the condition of their livestock on-site, and provide appropriate care.

[0116] The care method and results are entered into a dedicated app, which is provided as a smartphone app and sends the data via the internet to the server.

[0117] Specific examples

[0118] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[0119] 2. Every hour, the device sends the collected data to the server.

[0120] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[0121] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[0122] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[0123] 6. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[0124] 7. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[0125] 8. The server analyzes the cooling treatment data and learns new care methods.

[0126] Example prompts for generative AI models

[0127] "I would like to develop a system that measures the body temperature, heart rate, and amount of movement of livestock, and notifies the user if an abnormality is detected. Please tell me which technology I should use for the specific algorithm and notification method."

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] The device acquires biometric data such as body temperature, heart rate, and activity level of livestock. For example, a body temperature sensor measures body temperature every minute, and a heart rate sensor monitors heart rate in real time. This data is temporarily stored in the device's internal storage. The input is the livestock's biometric data, and the output is the measurement data stored in the device's internal storage device.

[0131] Step 2:

[0132] The device periodically transmits collected data to the server. For example, every hour, the data is transferred to the server using Wi-Fi or Bluetooth. The input is the measurement data stored in the internal storage, and the output is the data transmitted to the server. This includes the waiting process until communication is established.

[0133] Step 3:

[0134] The server stores the received data in a database. Database systems used include MySQL and PostgreSQL, for example. The input is the measurement data sent from the device, and the output is the biometric data stored in the database. This also involves converting the data format and eliminating invalid data.

[0135] Step 4:

[0136] The server uses machine learning algorithms to analyze the received biometric data in real time and detect abnormalities. The machine learning models used are, for example, Scikit-learn or TensorFlow. The input is the measurement data stored in the database, and the output is the results of anomaly detection. Specifically, anomalies are identified when body temperature exceeds 38.5°C or when the heart rate exceeds 100 beats per minute.

[0137] Step 5:

[0138] The server generates a notification message based on the anomaly detection result. For example, it generates a message such as "Livestock B has a high body temperature. Please take cooling measures." The input is the anomaly detection result, and the output is the generated notification message. A template-based approach is used to generate the message.

[0139] Step 6:

[0140] The server sends a notification message to the user, using an SMS gateway service (e.g., Twilio) or an email service (e.g., SendGrid) based on the user's notification preferences. The input is the generated notification message, and the output is the notification sent to the user.

[0141] Step 7:

[0142] The user receives the notification and takes appropriate action. For example, the user checks the notification, rechecks the animal's temperature on-site, and then uses a cooler to cool it down. The input is the notification sent, and the output is the action taken.

[0143] Step 8:

[0144] The user enters the care method and its results into a dedicated app and sends feedback to the server. The user logs into the dedicated app, enters the care method and results performed in the input form, and presses the send button to send the data to the server. The input is the care method performed and the results, and the output is the feedback sent to the server.

[0145] Step 9:

[0146] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. The feedback is analyzed using a machine learning algorithm to evaluate the effectiveness of new care methods. The input is user feedback, and the output is an updated recommendation database.

[0147] (Application example 1)

[0148] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0149] Modern factories operate many robots and machines, but it is difficult to efficiently manage their health and take appropriate action before an abnormality occurs. Furthermore, if an abnormality in a machine or robot is left unattended, there is a higher risk of reduced production efficiency and serious breakdowns. To solve these problems, a system is needed that can monitor the health of robots and machines in real time and respond quickly when an abnormality is detected.

[0150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0151] In this invention, the server includes a means for acquiring motion data of an object, a means for storing the motion data in a database, and a means for analyzing the motion data and detecting abnormalities, thereby making it possible to monitor the health status of a robot or machine in real time and to respond quickly when an abnormality is detected.

[0152] "Objects" refer to robots and machines operating within the factory.

[0153] "Operational data" refers to data relating to the operating conditions of an object, such as its temperature, vibration, and operation patterns.

[0154] "Database" refers to an information system for storing and managing operational data.

[0155] "Analysis" refers to the process of evaluating acquired operational data to determine if there are any anomalies.

[0156] "Anomaly detection" refers to the discovery of values ​​or patterns in operational data that deviate from normal ranges.

[0157] "Output" refers to generating anomaly detection results as a report or notification message and conveying them to an administrator.

[0158] "Administrator" refers to the person in charge of operating and maintaining robots and machinery within the factory.

[0159] "Notification" refers to the act of sending the abnormality detection results to the administrator's smartphone, computer, etc.

[0160] "Feedback" refers to the data returned to the system regarding the measures taken by the administrator in response to an abnormality and the results of those measures.

[0161] "Care method" refers to the recommended repair and maintenance method for the object when an abnormality is detected.

[0162] A "recommendation database" refers to a database that accumulates effective care methods and suggests them the next time an abnormality is detected.

[0163] This invention is a system for efficiently managing the health status of robots and machines in a factory. This system includes sensors for acquiring operational data of objects, a server for storing and analyzing the data, and a system for notifying and providing feedback to an administrator. The implementation method of the system will be described in detail below.

[0164] System configuration

[0165] 1. Sensor (terminal)

[0166] The terminal is a sensor attached to a robot or machine in a factory. This periodically collects operational data such as the temperature, vibration, and movement patterns of the object. The collected data is temporarily stored in the terminal's internal storage.

[0167] 2. Server

[0168] The server receives the operational data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as when the robot's temperature is too high or when vibrations are abnormally strong.

[0169] 3. Administrator

[0170] The administrator is the person in charge of operating and maintaining the factory. When the server detects an abnormality, it sends a notification message to the administrator. The notification includes the type of abnormality and recommended care methods. The administrator receives the notification and can take action promptly.

[0171] Program processing flow

[0172] Data Acquisition Phase

[0173] The sensor (terminal) periodically collects data such as the temperature, vibration, and movement patterns of the robot or machine. For example, it measures the temperature every minute.

[0174] The acquired data is temporarily stored in the device's internal storage.

[0175] Data Transfer Phase

[0176] The sensor (terminal) periodically sends the collected data to the server, for example, every hour. The data is sent via wireless communication (Wi-Fi, Bluetooth, etc.).

[0177] Data analysis phase

[0178] The server stores the received data in a database and analyzes it in real time using machine learning algorithms to detect anomalies, such as when temperatures exceed normal limits.

[0179] Notification Phase

[0180] Based on the abnormality detection results, the server generates a message such as "Robot 1's temperature is too high. Please cool it down."

[0181] The server sends this notification message to the administrator, who is notified via their smartphone app, SMS, email, etc.

[0182] Feedback Phase

[0183] Administrators receive notifications, check the status of the robots and machines on-site, and implement appropriate care measures (e.g., cooling measures).

[0184] The care method performed and the results are entered into a dedicated app, and feedback is sent to the server.

[0185] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. This updated data is then reflected in future care recommendations.

[0186] Specific examples

[0187] 1. The sensor (terminal) measures the temperature of Robot 1 every minute and saves the data in its internal storage.

[0188] 2. Every hour, the sensor (terminal) sends the collected data to the server.

[0189] 3. The server stores the data in a database and uses machine learning algorithms to detect temperature anomalies.

[0190] 4. The server detects that Robot 1's temperature is 31.0 degrees, which is high, and determines that there is a high risk of overheating.

[0191] 5. The server sends a notification to the administrator saying, "Robot 1's temperature is too high. Please cool it down."

[0192] 6. The administrator checks the notification and takes measures to cool Robot 1 (e.g., activates the cooling system).

[0193] 7. The administrator enters the results of the cooling measures into a dedicated app and sends them back to the server.

[0194] 8. The server analyzes cooling data and learns new maintenance methods.

[0195] Example prompt sentence:

[0196] "My robot is experiencing high temperatures and vibrations. What steps should I take to manage this situation?"

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] Data Acquisition Phase

[0200] The terminal periodically acquires operational data such as the temperature, vibration, and movement patterns of the robot or machine. For example, it measures the temperature every minute. The terminal temporarily stores the acquired data in its internal storage. The input of this process is the current status information of the object, and the output is the acquired operational data.

[0201] Step 2:

[0202] Data Transfer Phase

[0203] The device periodically (for example, every hour) transmits the collected operation data to the server. The data is transmitted via wireless communication (Wi-Fi, Bluetooth, etc.). The input of this process is the operation data stored on the device, and the output is the operation data transmitted to the server.

[0204] Step 3:

[0205] Data storage phase

[0206] The server stores the received operation data in a database. Specifically, it converts the received data into an appropriate format and records it in the database. The input of this process is the operation data sent from the terminal, and the output is the data stored in the database.

[0207] Step 4:

[0208] Data analysis phase

[0209] The server uses machine learning algorithms to analyze the operational data stored in the database in real time. For example, it detects abnormalities when the temperature exceeds the normal range or when vibrations are abnormally large. The input to this process is the operational data obtained from the database, and the output is the anomaly detection result.

[0210] Step 5:

[0211] Notification Phase

[0212] Based on the anomaly detection result, the server generates a message such as "Robot 1's temperature is too high. Please cool it down." The generated message is sent to the administrator. The input of this process is the anomaly detection result, and the output is the notification message sent to the administrator.

[0213] Step 6:

[0214] Care Delivery Phase

[0215] The administrator receives the notification, checks the status of the robot or machine on-site, and implements appropriate maintenance measures, such as turning on the cooling system. The input to this process is the notification message from the server, and the output is the result of the implemented maintenance measures.

[0216] Step 7:

[0217] Feedback Phase

[0218] The administrator enters the care methods and results into a dedicated app and sends feedback to the server. The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. The input to this process is the feedback information from the administrator, and the output is an updated recommendation database.

[0219] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0220] This invention combines a system for efficiently managing the health and behavior of livestock with a function for recognizing the emotions of managers. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, and an emotion engine that recognizes the emotions of managers, in addition to processing notifications and feedback to managers.

[0221] System configuration

[0222] 1. Terminal

[0223] The terminal is a sensor attached to the livestock, which periodically collects biological data such as body temperature, heart rate, and amount of exercise. The collected data is temporarily stored in the terminal's internal storage.

[0224] 2. Server

[0225] The server receives the biometric data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as if the animal's body temperature is too high or its heart rate is abnormally high.

[0226] 3. Users

[0227] Users are livestock breeders and farmers. When the server detects an abnormality, it sends a notification message to the user. The notification includes the type of abnormality and recommended care methods. The user receives the notification and can take action promptly.

[0228] 4. Emotion Engine

[0229] The emotion engine is a module for recognizing the user's emotions, and identifies the user's emotional state by analyzing voice data and facial expression data acquired from the camera and microphone.

[0230] Program processing flow (explained in natural language)

[0231] Data Acquisition Phase

[0232] The device periodically collects data such as the animal's body temperature, heart rate, and activity level. For example, it measures body temperature every minute.

[0233] The acquired data is temporarily stored in the device's internal storage.

[0234] Data Transfer Phase

[0235] Periodically, for example, every hour, the terminal transmits the collected data to the server via wireless communication.

[0236] Data analysis phase

[0237] The server stores the received data in a database and analyzes it in real time using machine learning algorithms, for example, comparing body temperature values ​​with the normal range to detect abnormalities.

[0238] Emotion Recognition Phase

[0239] The emotion engine analyzes the user's voice and facial expression data to determine their current emotional state. For example, it analyzes images taken with a camera to determine whether the user is feeling stressed.

[0240] Notification Phase

[0241] Based on the anomaly detection results, the server generates a message such as "Livestock B's body temperature is high. Please take cooling measures."

[0242] The server will then send this notification message to the user via their smartphone app, SMS, email, etc.

[0243] Emotional Adaptation Phase

[0244] The emotion engine recognizes the user's emotions and adapts the notification content and care suggestions based on that emotion. For example, if the user is feeling stressed, the notification message will be more concise and easy to understand.

[0245] Feedback Phase

[0246] Users receive notifications, go to the scene to check the condition of the livestock, and implement appropriate care measures (e.g., cooling measures).

[0247] The care methods and results are entered into a dedicated app, and feedback is sent to the server, including changes in body temperature and specific measures taken.

[0248] Feedback Analysis Phase

[0249] The server analyzes the received feedback data and evaluates the effectiveness of the care method. The evaluation results are added to a recommendation database and used to suggest future care methods.

[0250] The emotion engine also receives feedback data and reflects the emotion-adapted feedback data in the recommendation database.

[0251] Specific examples

[0252] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[0253] 2. Every hour, the device sends the collected data to the server.

[0254] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[0255] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[0256] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[0257] 6. The emotion engine recognizes that the user is feeling stressed through facial recognition and voice analysis.

[0258] 7. The server tailors notification messages to be concise and clear.

[0259] 8. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[0260] 9. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[0261] 10. The server analyzes the cooling data and learns new care methods.

[0262] 11. The emotion engine also analyzes user feedback and reflects it in improving the entire system.

[0263] This system not only significantly improves the efficiency of livestock health management, but also makes it possible to propose care methods that take into account the emotions of managers, which is expected to reduce user stress and help create a better livestock farming environment.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] The device measures the livestock's biological data, such as body temperature, heart rate, and activity, every minute, and the measured data is temporarily stored in the device's internal storage.

[0267] Step 2:

[0268] Every fixed time (for example, every hour), the terminal sends the collected data to the server using wireless communication (Wi-Fi, Bluetooth, etc.).

[0269] Step 3:

[0270] The server stores the received biometric data in a database, and when stored, each data item is given a timestamp and the livestock's individual identification information.

[0271] Step 4:

[0272] The server uses machine learning algorithms to analyze the data in the database in real time and detect abnormalities, such as when a person's body temperature exceeds the normal range.

[0273] Step 5:

[0274] The emotion engine analyzes the user's voice data and facial expression data to identify their current emotional state, for example by analyzing images and audio captured by the user's smartphone camera.

[0275] Step 6:

[0276] The server generates an output result including the type of anomaly, details of the anomaly data, and recommended care methods as anomaly detection results.

[0277] Step 7:

[0278] An emotion engine optimizes notification content based on the user's emotional state. For example, if the user is stressed, the message will be formatted succinctly and clearly.

[0279] Step 8:

[0280] The server generates an optimized notification message and sends it to the user via a smartphone app, SMS, email, etc.

[0281] Step 9:

[0282] Users can receive notifications and check the condition of livestock on-site, for example, by taking measures to cool down livestock with high body temperatures.

[0283] Step 10:

[0284] The user enters the care method and results into a dedicated app, and feedback data, including changes in body temperature and specific measures taken, is sent to a server.

[0285] Step 11:

[0286] The server analyzes the received feedback data, evaluates the effectiveness of the care method, and adds the evaluation results to the recommendation database.

[0287] Step 12:

[0288] The emotion engine also analyzes emotional feedback from users to improve notifications and care suggestions, and this data is reflected in the recommendation database.

[0289] Step 13:

[0290] Based on the updated recommendation database, the server will be prepared to suggest more appropriate care methods the next time an abnormality is detected.

[0291] This process flow allows for efficient and effective livestock health management and provides support that takes into account the emotions of managers, thereby reducing livestock health risks and easing the burden on managers.

[0292] Example 2

[0293] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0294] While conventional livestock management systems can acquire livestock biometric data and detect abnormalities, they lack the ability to recognize the emotions of managers and lack the means to reduce manager stress and burden. As a result, managers can sometimes become overly stressed, making it difficult to implement appropriate care methods. Another issue is that feedback is not fully utilized, preventing improvements to care methods.

[0295] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing biometric data of livestock in a database, a means for analyzing the biometric data and detecting abnormalities, and a means for recognizing the emotions of the manager from voice data and facial expression data. This makes it possible to provide appropriate notification content according to the manager's emotional state and to quickly and effectively suggest livestock care methods based on the abnormality detection results. In addition, by analyzing feedback from the manager and reflecting it in the next proposal, it is possible to continuously improve the care methods.

[0296] "Livestock" is a general term for animals kept in captivity, and refers primarily to animals used in agriculture and animal husbandry.

[0297] "Biometric data" refers to information related to the vital activities of livestock, such as body temperature, heart rate, and amount of movement.

[0298] A "database" refers to a system for efficiently managing, searching, and storing large amounts of data.

[0299] "Analysis" refers to the method of processing acquired data to find specific patterns or anomalies.

[0300] "Abnormal" refers to a value or condition that deviates from the normal range, indicating that something unusual has happened to the health of livestock.

[0301] "Voice data" refers to data that records information about the voice of the administrator.

[0302] "Facial expression data" refers to information obtained from the facial expression of an administrator and is used to determine the administrator's emotional state.

[0303] "Emotion recognition" refers to technology that identifies the current emotional state of a manager based on voice and facial expression data.

[0304] "Notification" refers to a message sent to notify an administrator when an abnormality is detected.

[0305] "Feedback" refers to the administrator returning information to the system about the care methods implemented and their results.

[0306] "Care methods" refer to the specific countermeasures and treatments implemented for livestock in which abnormalities are detected.

[0307] A "recommendation database" refers to a database that will be used for future proposals based on analysis results and feedback information.

[0308] This invention combines a system for efficiently managing the health and behavior of livestock with a function for recognizing the emotions of managers. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, a system that processes notifications and feedback to managers, and an emotion engine that recognizes the emotions of managers.

[0309] Specific system configuration

[0310] Terminal

[0311] The terminals are sensors attached to livestock and collect biometric data such as body temperature, heart rate, and exercise volume.

[0312] The acquired data is temporarily stored in the device's internal storage.

[0313] Examples:

[0314] The body temperature of livestock A is measured every minute and the data is stored in the internal storage.

[0315] server

[0316] The server receives the data sent from the terminal and stores it in a database.

[0317] The server uses machine learning algorithms to analyze the received data in real time and detect anomalies.

[0318] Examples:

[0319] The server stores the body temperature data of livestock A in a database and uses a machine learning algorithm to detect abnormalities in body temperature.

[0320] User

[0321] Users are livestock breeders and farmers.

[0322] If the server detects an anomaly, a notification message is sent to the user.

[0323] Examples:

[0324] A notification is sent to the user saying, "Livestock A has a high body temperature. Please take cooling measures."

[0325] Emotion Engine

[0326] The emotion engine identifies the user's emotional state by analyzing voice data and facial expression data.

[0327] Data is collected using a camera and microphone to recognize emotional states.

[0328] Examples:

[0329] The emotion engine analyzes the user's camera image and determines that the user is feeling stressed.

[0330] Detailed example of system operation

[0331] The device measures the body temperature of Livestock A every minute and stores the data in its internal storage. Every hour, the device sends the collected data to a server. The server stores the data in a database and uses a machine learning algorithm to detect abnormalities in body temperature. The server detects that Livestock A's body temperature is high at 39.0°C and determines that there is a high risk of heatstroke. The server sends a notification to the user stating, "Livestock A's body temperature is high. Please take cooling measures."

[0332] The emotion engine recognizes that the user is feeling stressed through facial recognition and voice analysis. The server adjusts the notification message to be concise and clear, stating, "Temperature is high. Cooling is required." The user confirms the notification and takes measures to cool down Livestock A. For example, they may use a cooling fan. The user enters the results of the cooling measures into a dedicated app and sends them back to the server. The server analyzes the cooling measures data and learns new care methods. The emotion engine also analyzes user feedback data and reflects it in improvements to the system as a whole.

[0333] This system not only significantly improves the efficiency of livestock health management, but also makes it possible to propose care methods that take into account the emotions of the manager, which is expected to reduce user stress and create a better livestock farming environment.

[0334] Prompt Sentence Examples

[0335] Please propose an AI solution that adds a function to the system to periodically collect biological data such as body temperature, heart rate, and amount of exercise of livestock, and notify if an abnormality is detected. Also, please incorporate a function to recognize the emotions of managers and design it to reduce stress by adjusting the content of notifications.

[0336] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0337] Step 1: Start acquiring data

[0338] The device collects biometric data such as body temperature, heart rate, and activity level from sensors attached to the livestock every minute.

[0339] Input: Livestock body temperature, heart rate, and activity

[0340] Data processing: The sensor operates to acquire and store biometric data, and the acquired data is temporarily stored in the internal storage.

[0341] Output: Biometric data stored in storage

[0342] Specific operation: Data is obtained showing that livestock A's body temperature is 37.5 degrees and its heart rate is 80 bpm.

[0343] Step 2: Data verification

[0344] The device performs a simple check to ensure the acquired biometric data is accurate and free of any abnormalities.

[0345] Input: Captured biometric data

[0346] Data processing: Noise filtering and data shaping.

[0347] Output: Clean data after filtering

[0348] Specific operation: If the acquired data contains noise, the noise is removed.

[0349] Step 3: Prepare for data transfer

[0350] Every hour, the device compiles the stored data and prepares it for transmission.

[0351] Input: Filtered biometric data

[0352] Data processing: Batch processing is used to combine one hour's worth of data into a single transmission packet.

[0353] Output: Outgoing packets

[0354] Specific operation: Compress one hour's worth of data and prepare it for transfer.

[0355] Step 4: Send data

[0356] The terminal transmits the collected data to the server via wireless communication.

[0357] Input: Outgoing packets

[0358] Data processing: Sending data via wireless communication using a data transmission protocol.

[0359] Output: Data sent to the server

[0360] Specific operation: Transfer data to the server using Bluetooth or Wi-Fi.

[0361] Step 5: Receiving Data

[0362] The server receives the data sent from the terminal.

[0363] Input: Data sent

[0364] Data processing: Decodes the received data and converts it into a format suitable for storing in the database.

[0365] Output: Data stored in a database

[0366] Specific operation: The server receives the data and stores it in the database as "body temperature data of livestock A."

[0367] Step 6: Data analysis

[0368] The server analyzes the stored data in real time using machine learning algorithms to detect anomalies.

[0369] Input: Biometric data stored in a database

[0370] Data processing: Using machine learning models, we run anomaly detection algorithms.

[0371] Output: Anomaly detection results

[0372] Specific behavior: Generates an alert if the body temperature exceeds 39.0 degrees.

[0373] Step 7: Acquire voice and facial expression data

[0374] The emotion engine acquires voice data and facial expression data from the administrator (user) via a camera or microphone.

[0375] Input: Camera image and audio recording

[0376] Data processing: Analyzes voice data and extracts facial expression data from images.

[0377] Output: Administrator's emotional state data

[0378] What it does: It records what the user says in front of the camera and analyzes the images to determine their emotional state.

[0379] Step 8: Emotion Recognition Analysis

[0380] The emotion engine analyzes the captured voice and facial expression data to identify the user's current emotional state.

[0381] Input: Administrator emotional state data

[0382] Data processing: Integrate audio and image data and classify emotional states using emotion recognition models.

[0383] Output: Emotion recognition result

[0384] Specific operation: Based on microphone recordings and camera images, it determines whether the user is in a "stressed state."

[0385] Step 9: Generate notification message

[0386] Based on the anomaly detection results and emotion recognition results, the server generates a notification message such as, "Livestock B's body temperature is high. Please take cooling measures."

[0387] Input: Anomaly detection results and emotion recognition results

[0388] Data processing: Generate notification messages and customize them according to the emotional state.

[0389] Output: Information message

[0390] Specific action: The notification content will be concise, such as "High body temperature. Cool down immediately."

[0391] Step 10: Send notification

[0392] The server generates a notification message and sends it to the user.

[0393] Input: Notification message

[0394] Data processing: Send notifications to the user's device using messaging protocols.

[0395] Output: The notification message displayed on the user's device

[0396] Specific behavior: Sends notifications to the user's smartphone via SMS or email.

[0397] Step 11: Adjust notification content

[0398] An emotion engine adapts notification content to be more concise and understandable based on the user's emotional state.

[0399] Input: Emotion recognition results

[0400] Data processing: Adjust the notification wording to simplify it and reduce stress.

[0401] Output: The adjusted notification message

[0402] Specific action: Change "The livestock has a high body temperature. Please take measures to cool them down." to "High body temperature. Rapid cooling."

[0403] Step 12: Care Delivery

[0404] The user checks the notification and checks the condition of the livestock on-site, and if necessary, takes cooling measures such as using a cooling fan.

[0405] Input: Notification message and field data

[0406] Data processing: After checking the condition, select and implement appropriate measures.

[0407] Output: Care implementation results

[0408] Specific action: Cools livestock using a cooling fan until their body temperature drops to 38.0°C.

[0409] Step 13: Enter feedback

[0410] The user enters the care method and results into a dedicated app and sends them as feedback to the server.

[0411] Input: Care implementation results

[0412] Data processing: The feedback data is formatted and sent to the server.

[0413] Output: Feedback data sent to the server

[0414] Specific operations: Enter changes in body temperature after cooling measures have been implemented into the app.

[0415] Step 14: Feedback analysis

[0416] The server analyzes the received feedback data and evaluates the effectiveness of the care method.

[0417] Input: Feedback data

[0418] Data processing: Evaluate the effectiveness of care methods through data analysis.

[0419] Output: Evaluation result

[0420] Specific actions: Based on the results of the cooling measures, we recommend the same method next time.

[0421] Step 15: Reflecting Emotional Feedback

[0422] The emotion engine also receives user feedback data and reflects it in improving the overall system.

[0423] Input: Feedback data and emotion recognition results

[0424] Data processing: Analyze the feedback data and reflect it in the next notification method.

[0425] Output: Improved system profile

[0426] Specific actions: Learn specific notification methods to reduce stress and reflect them in the next notification method.

[0427] (Application example 2)

[0428] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0429] In modern factories, it is important to constantly monitor the health of equipment and detect abnormalities early. However, conventional systems have difficulty taking into account the emotions and stress levels of managers. This can hinder a prompt and effective response after an abnormality is detected. Another problem is that inaccurate notifications increase the burden on managers. Therefore, the objective of this invention is to not only monitor equipment and detect abnormalities, but also recognize the emotions of managers and adjust the content of notifications according to their emotions, thereby making it easier to respond after an abnormality is discovered.

[0430] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0431] In this invention, the server includes means for acquiring biological data of livestock, means for saving the data in a database, means for analyzing the data and detecting abnormalities, means for outputting abnormality detection results, means for notifying a manager of the output results, means for receiving and evaluating feedback from the manager, means for recognizing the manager's emotions, and means for adjusting notification content based on the manager's emotions. This makes it possible to detect equipment abnormalities early, provide appropriate notifications and propose care methods according to the manager's emotional state, and achieve rapid and effective response.

[0432] "Livestock biological data" refers to physiological information such as livestock body temperature, heart rate, and amount of exercise.

[0433] A "database" is an information management system for organizing and storing acquired data.

[0434] "Analysis" is the process of calculation and evaluation using acquired data to detect anomalies or find specific patterns or trends.

[0435] "Abnormality detection results" refer to unusual conditions or problems that are discovered through analysis.

[0436] "Notification" is a means of informing an administrator of abnormality detection results and other important information.

[0437] "Feedback" refers to returning information to the system about the actions taken by the administrator and their results.

[0438] "Administrator emotion recognition" is a technology that identifies the emotional state of an administrator from their facial expressions and voice.

[0439] "Adjusting notification content" refers to changing the content and expression of notifications depending on the administrator's emotional state.

[0440] "Proposing care methods" refers to proposing to the manager the measures and procedures that should be implemented when an abnormality is found.

[0441] The embodiment of the present invention requires a specific configuration and operation of a system for monitoring the health status of factory equipment. The system is composed of the following main components:

[0442] Device:

[0443] The terminals are sensors placed on each piece of equipment in the factory, and periodically collect data on the equipment's temperature, vibration, operating status, etc. The data collected from the sensors is temporarily stored in the terminal's internal storage. This terminal includes hardware such as high-precision sensors, and communicates data with the server using a wireless communication module.

[0444] server:

[0445] The server receives the biometric data sent from the device and stores it in a database. The server is equipped with a machine learning algorithm that analyzes the data in real time and detects anomalies. Machine learning libraries such as TensorFlow and Keras are used for anomaly detection. If an anomaly is detected, the server outputs it and notifies the administrator.

[0446] User:

[0447] The user is the factory manager. When the server detects an abnormality, it sends a notification message to the user. This notification is sent via a smartphone app or smart glasses. The notification includes the type of abnormality and how to deal with it. Feedback from the user is also important, and the actions taken and their results are sent back to the server via a dedicated app.

[0448] Emotion Engine:

[0449] The emotion engine is a module for recognizing the emotions of administrators. It analyzes the administrator's facial expressions and voice data to identify their emotional state. For example, the emotion engine uses facial recognition technology from OpenCV and emotion recognition models from TensorFlow / Keras. Based on the recognized emotions, the content of notifications is adjusted and appropriate countermeasures are proposed according to the administrator's condition.

[0450] Natural language description of program processing:

[0451] 1. Data Acquisition Phase:

[0452] The device periodically collects data such as temperature and vibration of factory equipment and stores it in its internal storage.

[0453] 2. Data transfer phase:

[0454] The terminal transmits the collected data to the server, for example, every hour, using wireless communication.

[0455] 3. Data analysis phase:

[0456] The server analyzes the data stored in the database and detects outliers using machine learning algorithms.

[0457] 4. Emotion Recognition Phase:

[0458] Using a camera on a smartphone or smart glasses, the manager's facial expressions are captured and input into an emotion recognition model to identify their emotional state.

[0459] 5. Notification Phase:

[0460] The server generates notification messages based on the anomaly detection results and sends them to administrators, whose notifications are tailored according to the administrator's emotional state.

[0461] For example, if the temperature of a factory machine suddenly rises, the system will detect the abnormality and send a notification to the manager saying, "The temperature of the equipment is high. Please take measures to cool it down immediately." If the emotion engine recognizes that the manager is feeling stressed, it will simplify the notification to say, "An equipment abnormality has occurred. Please cool it down." After the manager takes measures, they enter their feedback into a dedicated app and send it to the server. The server will analyze this feedback and use it to make future suggestions.

[0462] Example prompts to input to the generative AI model:

[0463] "Please support the design and implementation of a smartphone app that monitors the health of factory equipment, detects abnormalities, and adjusts notification content based on the manager's emotions."

[0464] This configuration makes it possible to detect abnormalities in factory equipment and to respond quickly and appropriately according to the feelings of the manager.

[0465] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0466] Step 1:

[0467] The device periodically collects data such as temperature, vibration, and operating status using sensors installed in the factory equipment, and this data is temporarily stored in the device's internal storage.

[0468] Input: Various sensor data from factory equipment (temperature, vibration, operating status)

[0469] Output: Local storage of acquired sensor data

[0470] Specific operation: High-precision sensors measure the equipment status and store the data in the terminal memory. For example, temperature data is acquired every minute and recorded in storage.

[0471] Step 2:

[0472] The terminal transmits the collected data every hour to the server via wireless communication.

[0473] Input: Sensor data stored on the device

[0474] Output: Sensor data sent to the server

[0475] Specific operation: Using the wireless communication module, the device uploads data to the server in bulk once per hour, using communication methods such as Bluetooth and Wi-Fi.

[0476] Step 3:

[0477] The server stores the received data in a database and uses machine learning algorithms to analyze the data in real time and detect anomalies.

[0478] Input: Sensor data sent to the server

[0479] Output: Anomaly detection results

[0480] How it works: Using machine learning libraries such as TensorFlow and Keras, it constantly analyzes the acquired data and detects abnormalities when temperature or vibrations fall within an abnormal range. For example, it determines that an abnormality exists when the temperature exceeds 80°C.

[0481] Step 4:

[0482] The server generates a notification message based on the anomaly detection results and sends it to the administrator's smartphone app or smart glasses.

[0483] Input: Anomaly detection results

[0484] Output: Notification message to administrator

[0485] Specific behavior: The server generates an appropriate notification based on the type of abnormality and sends it to the administrator's device, for example, a message saying "The temperature of the equipment is high. Please take measures to cool it down."

[0486] Step 5:

[0487] The emotion engine uses the camera on the administrator's smartphone or smart glasses to capture and analyze the administrator's facial expressions and voice data to understand their emotional state.

[0488] Input: Administrator's facial expression data, voice data

[0489] Output: Emotional state of the administrator

[0490] How it works: Facial recognition technology using OpenCV and emotion recognition models using TensorFlow / Keras identify emotions from the manager's facial expressions and voice. For example, it determines whether the manager is feeling stressed.

[0491] Step 6:

[0492] Once the administrator's emotional state is determined, the server tailors the notification content based on the administrator's emotional state and, if necessary, streamlines the process.

[0493] Input: Administrator's emotional state

[0494] Output: The adjusted notification message

[0495] Specific behavior: If the emotional state indicates stress, simplify the notification message. For example, omit detailed explanations and send a simple message such as "Equipment abnormality. Please cool down."

[0496] Step 7:

[0497] The user receives a notification, takes appropriate measures, and feeds the results back to the server via a dedicated app.

[0498] Input: Administrator response result

[0499] Output: Feedback data

[0500] Specific operation: The administrator implements cooling measures and inputs the results (e.g., whether the temperature has dropped) into a dedicated app. The feedback data is sent to the server.

[0501] Step 8:

[0502] The server analyzes the feedback data, evaluates the effectiveness of the care methods, and updates the recommendation database.

[0503] Input: Feedback data

[0504] Output: Updated recommendation database

[0505] Specific operation: The server analyzes the feedback data and evaluates the effectiveness of the proposed care method. The evaluation results are added to the recommendation database to be used for future recommendations.

[0506] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0507] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0508] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0509] [Second embodiment]

[0510] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0511] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0512] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0513] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0514] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0515] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0516] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0517] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0518] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0519] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0520] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0521] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0522] The present invention is a system for efficiently managing the health and behavior of livestock. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, and a system that processes notifications and feedback to managers.

[0523] System configuration

[0524] 1. Terminal

[0525] The terminal is a sensor attached to the livestock, which periodically collects biological data such as body temperature, heart rate, and amount of exercise. The collected data is temporarily stored in the terminal's internal storage.

[0526] 2. Server

[0527] The server receives the biometric data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as if the animal's body temperature is too high or its heart rate is abnormally high.

[0528] 3. Users

[0529] Users are livestock breeders and farmers. When the server detects an abnormality, it sends a notification message to the user. The notification includes the type of abnormality and recommended care methods. The user receives the notification and can take action promptly.

[0530] Program processing flow (explained in natural language)

[0531] Data Acquisition Phase

[0532] The device periodically collects data such as the animal's body temperature, heart rate, and activity level. For example, it measures body temperature every minute.

[0533] The acquired data is temporarily stored in the device's internal storage.

[0534] Data Transfer Phase

[0535] Periodically, for example, every hour, the device sends the collected data to the server via wireless communication (Wi-Fi, Bluetooth, etc.).

[0536] Data analysis phase

[0537] The server stores the received data in a database and analyzes it in real time using machine learning algorithms to detect abnormalities, such as body temperature exceeding the normal range.

[0538] Notification Phase

[0539] Based on the anomaly detection results, the server generates a message such as "Livestock B's body temperature is high. Please take cooling measures."

[0540] The server will then send this notification message to the user via their smartphone app, SMS, email, etc.

[0541] Feedback Phase

[0542] Users receive notifications, go to the scene to check the condition of the livestock, and implement appropriate care measures (e.g., cooling measures).

[0543] The care method performed and the results are entered into a dedicated app, and feedback is sent to the server.

[0544] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. This updated data is then reflected in future care recommendations.

[0545] Specific examples

[0546] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[0547] 2. Every hour, the device sends the collected data to the server.

[0548] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[0549] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[0550] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[0551] 6. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[0552] 7. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[0553] 8. The server analyzes the cooling treatment data and learns new care methods.

[0554] The implementation of this system will significantly improve the efficiency of livestock health management. It will also enable real-time abnormality detection and rapid response, which is expected to reduce livestock health risks and improve production efficiency.

[0555] The processing flow will be explained below.

[0556] Step 1:

[0557] The device measures the livestock's biological data, such as body temperature, heart rate, and activity, every minute, and the data is temporarily stored in the internal storage.

[0558] Step 2:

[0559] Every fixed time (for example, every hour), the terminal sends the collected data to the server via wireless communication.

[0560] Step 3:

[0561] The server stores the received data in a database, with each data point being given a timestamp and the livestock's individual identification information.

[0562] Step 4:

[0563] The server analyzes the data in the database using machine learning algorithms, such as comparing body temperature values ​​with normal ranges to detect abnormalities.

[0564] Step 5:

[0565] If the server detects an anomaly, it generates an output result including the type of anomaly, details of the data that became abnormal, and recommended care methods as an anomaly detection result.

[0566] Step 6:

[0567] The server generates a notification message based on the anomaly detection result, which includes the livestock ID, details of the anomaly, and the required action.

[0568] Step 7:

[0569] The server sends a notification message to the user via the user's smartphone app, SMS, email, etc.

[0570] Step 8:

[0571] Users receive notifications and can check the condition of livestock on-site, for example, by taking cooling measures if the animals have a high body temperature.

[0572] Step 9:

[0573] The user inputs the care method and results into a dedicated app and sends the data to a server. Feedback data includes changes in body temperature and specific measures taken.

[0574] Step 10:

[0575] The server analyzes the received feedback data and evaluates the effectiveness of the care method. The evaluation results are added to a recommendation database and used to suggest future care methods.

[0576] Step 11:

[0577] Based on the updated recommendation database, the server will be prepared to suggest more appropriate care methods when abnormalities are detected in the future.

[0578] This program automates and streamlines livestock health management, enabling real-time abnormality detection and rapid response.

[0579] Example 1

[0580] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0581] Conventional livestock health management systems have problems in that they do not collect biological data or detect abnormalities in real time, and managers are not notified promptly when abnormalities are discovered. Furthermore, feedback and suggestions for care methods after abnormalities are detected are not provided efficiently, making it difficult to reduce livestock health risks. Furthermore, feedback from managers is not reflected in the system, meaning it cannot be used to suggest future care methods, resulting in ineffective use of data.

[0582] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0583] In this invention, the server includes means for acquiring livestock biometric data, means for storing the biometric data in internal storage at regular intervals and periodically transmitting it to the server, means for storing the biometric data in a database and analyzing it in real time using a machine learning algorithm to detect abnormalities, means for generating a notification message based on the abnormality detection result and notifying the manager, and means for receiving feedback from the manager and evaluating its effectiveness. This reduces livestock health risks, enables rapid response, and realizes improvements in care methods through feedback.

[0584] "Means for acquiring biological data of livestock" refers to devices that periodically acquire data such as body temperature, heart rate, and amount of exercise using sensors attached to livestock.

[0585] "Means for storing the biometric data in internal storage at regular intervals and periodically transmitting it to a server" refers to a device or function that temporarily stores the acquired biometric data in a storage medium and transfers the data to a server at regular time intervals.

[0586] "Means for storing the biometric data in a database, analyzing it in real time using a machine learning algorithm, and detecting abnormalities" refers to a device or function that records the received biometric data in a database, analyzes the data in real time using a machine learning model, and identifies abnormalities that deviate from the reference values.

[0587] "Means for generating a notification message based on the anomaly detection result and notifying the administrator" refers to a device or function that creates an appropriate warning message when an anomaly is detected and provides the information to the administrator via SMS, email, etc.

[0588] The "means for receiving feedback from the administrator and evaluating its effectiveness" refers to a device or function that collects information provided by the administrator and analyzes and evaluates the effectiveness of that information.

[0589] The "means for proposing a care method for livestock based on the abnormality detection result" is a device or function that provides an appropriate countermeasure for the detected abnormality.

[0590] "Means for evaluating the effectiveness of the proposed care method in real time and adding the results to the recommendation database" refers to a device or function that instantly analyzes the effectiveness of the proposed care method and adds the results to a database to be used for the next recommendation.

[0591] The present invention is a system for efficiently managing the health and behavior of livestock. This system includes sensors (terminals) for acquiring livestock biometric data, a server for storing and analyzing the data, and a system for notifying and providing feedback to managers.

[0592] System configuration

[0593] 1. Terminal

[0594] The terminals are sensors attached to livestock, which periodically collect biological data such as body temperature, heart rate, and activity level. The sensors used include body temperature sensors and heart rate sensors.

[0595] The acquired data is temporarily stored in the device's internal storage, specifically, using a storage device such as a microSD card or internal flash memory.

[0596] 2. Server

[0597] The server receives the biometric data sent from the terminal and stores it in a database.

[0598] The server uses machine learning algorithms to analyze data in real time and detect anomalies, using software such as MySQL or PostgreSQL as databases and Scikit-learn or TensorFlow as machine learning libraries.

[0599] If an anomaly is detected, the server generates an appropriate notification message and notifies the administrator via an SMS gateway service (e.g., Twilio) or an email service (e.g., SendGrid).

[0600] 3. Users

[0601] Users are livestock farmers and breeders. They receive notifications from the server, check the condition of their livestock on-site, and provide appropriate care.

[0602] The care method and results are entered into a dedicated app, which is provided as a smartphone app and sends the data via the internet to the server.

[0603] Specific examples

[0604] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[0605] 2. Every hour, the device sends the collected data to the server.

[0606] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[0607] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[0608] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[0609] 6. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[0610] 7. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[0611] 8. The server analyzes the cooling treatment data and learns new care methods.

[0612] Example prompts for generative AI models

[0613] "I would like to develop a system that measures the body temperature, heart rate, and amount of movement of livestock, and notifies the user if an abnormality is detected. Please tell me which technology I should use for the specific algorithm and notification method."

[0614] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0615] Step 1:

[0616] The device acquires biometric data such as body temperature, heart rate, and activity level of livestock. For example, a body temperature sensor measures body temperature every minute, and a heart rate sensor monitors heart rate in real time. This data is temporarily stored in the device's internal storage. The input is the livestock's biometric data, and the output is the measurement data stored in the device's internal storage device.

[0617] Step 2:

[0618] The device periodically transmits collected data to the server. For example, every hour, the data is transferred to the server using Wi-Fi or Bluetooth. The input is the measurement data stored in the internal storage, and the output is the data transmitted to the server. This includes the waiting process until communication is established.

[0619] Step 3:

[0620] The server stores the received data in a database. Database systems used include MySQL and PostgreSQL, for example. The input is the measurement data sent from the device, and the output is the biometric data stored in the database. This also involves converting the data format and eliminating invalid data.

[0621] Step 4:

[0622] The server uses machine learning algorithms to analyze the received biometric data in real time and detect abnormalities. The machine learning models used are, for example, Scikit-learn or TensorFlow. The input is the measurement data stored in the database, and the output is the results of anomaly detection. Specifically, anomalies are identified when body temperature exceeds 38.5°C or when the heart rate exceeds 100 beats per minute.

[0623] Step 5:

[0624] The server generates a notification message based on the anomaly detection result. For example, it generates a message such as "Livestock B has a high body temperature. Please take cooling measures." The input is the anomaly detection result, and the output is the generated notification message. A template-based approach is used to generate the message.

[0625] Step 6:

[0626] The server sends a notification message to the user, using an SMS gateway service (e.g., Twilio) or an email service (e.g., SendGrid) based on the user's notification preferences. The input is the generated notification message, and the output is the notification sent to the user.

[0627] Step 7:

[0628] The user receives the notification and takes appropriate action. For example, the user checks the notification, rechecks the animal's temperature on-site, and then uses a cooler to cool it down. The input is the notification sent, and the output is the action taken.

[0629] Step 8:

[0630] The user enters the care method and its results into a dedicated app and sends feedback to the server. The user logs into the dedicated app, enters the care method and results performed in the input form, and presses the send button to send the data to the server. The input is the care method performed and the results, and the output is the feedback sent to the server.

[0631] Step 9:

[0632] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. The feedback is analyzed using a machine learning algorithm to evaluate the effectiveness of new care methods. The input is user feedback, and the output is an updated recommendation database.

[0633] (Application example 1)

[0634] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0635] Modern factories operate many robots and machines, but it is difficult to efficiently manage their health and take appropriate action before an abnormality occurs. Furthermore, if an abnormality in a machine or robot is left unattended, there is a higher risk of reduced production efficiency and serious breakdowns. To solve these problems, a system is needed that can monitor the health of robots and machines in real time and respond quickly when an abnormality is detected.

[0636] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0637] In this invention, the server includes a means for acquiring motion data of an object, a means for storing the motion data in a database, and a means for analyzing the motion data and detecting abnormalities, thereby making it possible to monitor the health status of a robot or machine in real time and to respond quickly when an abnormality is detected.

[0638] "Objects" refer to robots and machines operating within the factory.

[0639] "Operational data" refers to data relating to the operating conditions of an object, such as its temperature, vibration, and operation patterns.

[0640] "Database" refers to an information system for storing and managing operational data.

[0641] "Analysis" refers to the process of evaluating acquired operational data to determine if there are any anomalies.

[0642] "Anomaly detection" refers to the discovery of values ​​or patterns in operational data that deviate from normal ranges.

[0643] "Output" refers to generating anomaly detection results as a report or notification message and conveying them to an administrator.

[0644] "Administrator" refers to the person in charge of operating and maintaining robots and machinery within the factory.

[0645] "Notification" refers to the act of sending the abnormality detection results to the administrator's smartphone, computer, etc.

[0646] "Feedback" refers to the data returned to the system regarding the measures taken by the administrator in response to an abnormality and the results of those measures.

[0647] "Care method" refers to the recommended repair and maintenance method for the object when an abnormality is detected.

[0648] A "recommendation database" refers to a database that accumulates effective care methods and suggests them the next time an abnormality is detected.

[0649] This invention is a system for efficiently managing the health status of robots and machines in a factory. This system includes sensors for acquiring operational data of objects, a server for storing and analyzing the data, and a system for notifying and providing feedback to an administrator. The implementation method of the system will be described in detail below.

[0650] System configuration

[0651] 1. Sensor (terminal)

[0652] The terminal is a sensor attached to a robot or machine in a factory. This periodically collects operational data such as the temperature, vibration, and movement patterns of the object. The collected data is temporarily stored in the terminal's internal storage.

[0653] 2. Server

[0654] The server receives the operational data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as when the robot's temperature is too high or when vibrations are abnormally strong.

[0655] 3. Administrator

[0656] The administrator is the person in charge of operating and maintaining the factory. When the server detects an abnormality, it sends a notification message to the administrator. The notification includes the type of abnormality and recommended care methods. The administrator receives the notification and can take action promptly.

[0657] Program processing flow

[0658] Data Acquisition Phase

[0659] The sensor (terminal) periodically collects data such as the temperature, vibration, and movement patterns of the robot or machine. For example, it measures the temperature every minute.

[0660] The acquired data is temporarily stored in the device's internal storage.

[0661] Data Transfer Phase

[0662] The sensor (terminal) periodically sends the collected data to the server, for example, every hour. The data is sent via wireless communication (Wi-Fi, Bluetooth, etc.).

[0663] Data analysis phase

[0664] The server stores the received data in a database and analyzes it in real time using machine learning algorithms to detect anomalies, such as when temperatures exceed normal limits.

[0665] Notification Phase

[0666] Based on the abnormality detection results, the server generates a message such as "Robot 1's temperature is too high. Please cool it down."

[0667] The server sends this notification message to the administrator, who is notified via their smartphone app, SMS, email, etc.

[0668] Feedback Phase

[0669] Administrators receive notifications, check the status of the robots and machines on-site, and implement appropriate care measures (e.g., cooling measures).

[0670] The care method performed and the results are entered into a dedicated app, and feedback is sent to the server.

[0671] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. This updated data is then reflected in future care recommendations.

[0672] Specific examples

[0673] 1. The sensor (terminal) measures the temperature of Robot 1 every minute and saves the data in its internal storage.

[0674] 2. Every hour, the sensor (terminal) sends the collected data to the server.

[0675] 3. The server stores the data in a database and uses machine learning algorithms to detect temperature anomalies.

[0676] 4. The server detects that Robot 1's temperature is 31.0 degrees, which is high, and determines that there is a high risk of overheating.

[0677] 5. The server sends a notification to the administrator saying, "Robot 1's temperature is too high. Please cool it down."

[0678] 6. The administrator checks the notification and takes measures to cool Robot 1 (e.g., activates the cooling system).

[0679] 7. The administrator enters the results of the cooling measures into a dedicated app and sends them back to the server.

[0680] 8. The server analyzes cooling data and learns new maintenance methods.

[0681] Example prompt sentence:

[0682] "My robot is experiencing high temperatures and vibrations. What steps should I take to manage this situation?"

[0683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0684] Step 1:

[0685] Data Acquisition Phase

[0686] The terminal periodically acquires operational data such as the temperature, vibration, and movement patterns of the robot or machine. For example, it measures the temperature every minute. The terminal temporarily stores the acquired data in its internal storage. The input of this process is the current status information of the object, and the output is the acquired operational data.

[0687] Step 2:

[0688] Data Transfer Phase

[0689] The device periodically (for example, every hour) transmits the collected operation data to the server. The data is transmitted via wireless communication (Wi-Fi, Bluetooth, etc.). The input of this process is the operation data stored on the device, and the output is the operation data transmitted to the server.

[0690] Step 3:

[0691] Data storage phase

[0692] The server stores the received operation data in a database. Specifically, it converts the received data into an appropriate format and records it in the database. The input of this process is the operation data sent from the terminal, and the output is the data stored in the database.

[0693] Step 4:

[0694] Data analysis phase

[0695] The server uses machine learning algorithms to analyze the operational data stored in the database in real time. For example, it detects abnormalities when the temperature exceeds the normal range or when vibrations are abnormally large. The input to this process is the operational data obtained from the database, and the output is the anomaly detection result.

[0696] Step 5:

[0697] Notification Phase

[0698] Based on the anomaly detection result, the server generates a message such as "Robot 1's temperature is too high. Please cool it down." The generated message is sent to the administrator. The input of this process is the anomaly detection result, and the output is the notification message sent to the administrator.

[0699] Step 6:

[0700] Care Delivery Phase

[0701] The administrator receives the notification, checks the status of the robot or machine on-site, and implements appropriate maintenance measures, such as turning on the cooling system. The input to this process is the notification message from the server, and the output is the result of the implemented maintenance measures.

[0702] Step 7:

[0703] Feedback Phase

[0704] The administrator enters the care methods and results into a dedicated app and sends feedback to the server. The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. The input to this process is the feedback information from the administrator, and the output is an updated recommendation database.

[0705] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0706] This invention combines a system for efficiently managing the health and behavior of livestock with a function for recognizing the emotions of managers. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, and an emotion engine that recognizes the emotions of managers, in addition to processing notifications and feedback to managers.

[0707] System configuration

[0708] 1. Terminal

[0709] The terminal is a sensor attached to the livestock, which periodically collects biological data such as body temperature, heart rate, and amount of exercise. The collected data is temporarily stored in the terminal's internal storage.

[0710] 2. Server

[0711] The server receives the biometric data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as if the animal's body temperature is too high or its heart rate is abnormally high.

[0712] 3. Users

[0713] Users are livestock breeders and farmers. When the server detects an abnormality, it sends a notification message to the user. The notification includes the type of abnormality and recommended care methods. The user receives the notification and can take action promptly.

[0714] 4. Emotion Engine

[0715] The emotion engine is a module for recognizing the user's emotions, and identifies the user's emotional state by analyzing voice data and facial expression data acquired from the camera and microphone.

[0716] Program processing flow (explained in natural language)

[0717] Data Acquisition Phase

[0718] The device periodically collects data such as the animal's body temperature, heart rate, and activity level. For example, it measures body temperature every minute.

[0719] The acquired data is temporarily stored in the device's internal storage.

[0720] Data Transfer Phase

[0721] Periodically, for example, every hour, the terminal transmits the collected data to the server via wireless communication.

[0722] Data analysis phase

[0723] The server stores the received data in a database and analyzes it in real time using machine learning algorithms, for example, comparing body temperature values ​​with the normal range to detect abnormalities.

[0724] Emotion Recognition Phase

[0725] The emotion engine analyzes the user's voice and facial expression data to determine their current emotional state. For example, it analyzes images taken with a camera to determine whether the user is feeling stressed.

[0726] Notification Phase

[0727] Based on the anomaly detection results, the server generates a message such as "Livestock B's body temperature is high. Please take cooling measures."

[0728] The server will then send this notification message to the user via their smartphone app, SMS, email, etc.

[0729] Emotional Adaptation Phase

[0730] The emotion engine recognizes the user's emotions and adapts the notification content and care suggestions based on that emotion. For example, if the user is feeling stressed, the notification message will be more concise and easy to understand.

[0731] Feedback Phase

[0732] Users receive notifications, go to the scene to check the condition of the livestock, and implement appropriate care measures (e.g., cooling measures).

[0733] The care methods and results are entered into a dedicated app, and feedback is sent to the server, including changes in body temperature and specific measures taken.

[0734] Feedback Analysis Phase

[0735] The server analyzes the received feedback data and evaluates the effectiveness of the care method. The evaluation results are added to a recommendation database and used to suggest future care methods.

[0736] The emotion engine also receives feedback data and reflects the emotion-adapted feedback data in the recommendation database.

[0737] Specific examples

[0738] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[0739] 2. Every hour, the device sends the collected data to the server.

[0740] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[0741] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[0742] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[0743] 6. The emotion engine recognizes that the user is feeling stressed through facial recognition and voice analysis.

[0744] 7. The server tailors notification messages to be concise and clear.

[0745] 8. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[0746] 9. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[0747] 10. The server analyzes the cooling data and learns new care methods.

[0748] 11. The emotion engine also analyzes user feedback and reflects it in improving the entire system.

[0749] This system not only significantly improves the efficiency of livestock health management, but also makes it possible to propose care methods that take into account the emotions of managers, which is expected to reduce user stress and help create a better livestock farming environment.

[0750] The processing flow will be explained below.

[0751] Step 1:

[0752] The device measures the livestock's biological data, such as body temperature, heart rate, and activity, every minute, and the measured data is temporarily stored in the device's internal storage.

[0753] Step 2:

[0754] Every fixed time (for example, every hour), the terminal sends the collected data to the server using wireless communication (Wi-Fi, Bluetooth, etc.).

[0755] Step 3:

[0756] The server stores the received biometric data in a database, and when stored, each data item is given a timestamp and the livestock's individual identification information.

[0757] Step 4:

[0758] The server uses machine learning algorithms to analyze the data in the database in real time and detect abnormalities, such as when a person's body temperature exceeds the normal range.

[0759] Step 5:

[0760] The emotion engine analyzes the user's voice data and facial expression data to identify their current emotional state, for example by analyzing images and audio captured by the user's smartphone camera.

[0761] Step 6:

[0762] The server generates an output result including the type of anomaly, details of the anomaly data, and recommended care methods as anomaly detection results.

[0763] Step 7:

[0764] An emotion engine optimizes notification content based on the user's emotional state. For example, if the user is stressed, the message will be formatted succinctly and clearly.

[0765] Step 8:

[0766] The server generates an optimized notification message and sends it to the user via a smartphone app, SMS, email, etc.

[0767] Step 9:

[0768] Users can receive notifications and check the condition of livestock on-site, for example, by taking measures to cool down livestock with high body temperatures.

[0769] Step 10:

[0770] The user enters the care method and results into a dedicated app, and feedback data, including changes in body temperature and specific measures taken, is sent to a server.

[0771] Step 11:

[0772] The server analyzes the received feedback data, evaluates the effectiveness of the care method, and adds the evaluation results to the recommendation database.

[0773] Step 12:

[0774] The emotion engine also analyzes emotional feedback from users to improve notifications and care suggestions, and this data is reflected in the recommendation database.

[0775] Step 13:

[0776] Based on the updated recommendation database, the server will be prepared to suggest more appropriate care methods the next time an abnormality is detected.

[0777] This process flow allows for efficient and effective livestock health management and provides support that takes into account the emotions of managers, thereby reducing livestock health risks and easing the burden on managers.

[0778] Example 2

[0779] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0780] While conventional livestock management systems can acquire livestock biometric data and detect abnormalities, they lack the ability to recognize the emotions of managers and lack the means to reduce manager stress and burden. As a result, managers can sometimes become overly stressed, making it difficult to implement appropriate care methods. Another issue is that feedback is not fully utilized, preventing improvements to care methods.

[0781] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing biometric data of livestock in a database, a means for analyzing the biometric data and detecting abnormalities, and a means for recognizing the emotions of the manager from voice data and facial expression data. This makes it possible to provide appropriate notification content according to the manager's emotional state and to quickly and effectively suggest livestock care methods based on the abnormality detection results. In addition, by analyzing feedback from the manager and reflecting it in the next proposal, it is possible to continuously improve the care methods.

[0782] "Livestock" is a general term for animals kept in captivity, and refers primarily to animals used in agriculture and animal husbandry.

[0783] "Biometric data" refers to information related to the vital activities of livestock, such as body temperature, heart rate, and amount of movement.

[0784] A "database" refers to a system for efficiently managing, searching, and storing large amounts of data.

[0785] "Analysis" refers to the method of processing acquired data to find specific patterns or anomalies.

[0786] "Abnormal" refers to a value or condition that deviates from the normal range, indicating that something unusual has happened to the health of livestock.

[0787] "Voice data" refers to data that records information about the voice of the administrator.

[0788] "Facial expression data" refers to information obtained from the facial expression of an administrator and is used to determine the administrator's emotional state.

[0789] "Emotion recognition" refers to technology that identifies the current emotional state of a manager based on voice and facial expression data.

[0790] "Notification" refers to a message sent to notify an administrator when an abnormality is detected.

[0791] "Feedback" refers to the administrator returning information to the system about the care methods implemented and their results.

[0792] "Care methods" refer to the specific countermeasures and treatments implemented for livestock in which abnormalities are detected.

[0793] A "recommendation database" refers to a database that will be used for future proposals based on analysis results and feedback information.

[0794] This invention combines a system for efficiently managing the health and behavior of livestock with a function for recognizing the emotions of managers. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, a system that processes notifications and feedback to managers, and an emotion engine that recognizes the emotions of managers.

[0795] Specific system configuration

[0796] Terminal

[0797] The terminals are sensors attached to livestock and collect biometric data such as body temperature, heart rate, and exercise volume.

[0798] The acquired data is temporarily stored in the device's internal storage.

[0799] Examples:

[0800] The body temperature of livestock A is measured every minute and the data is stored in the internal storage.

[0801] server

[0802] The server receives the data sent from the terminal and stores it in a database.

[0803] The server uses machine learning algorithms to analyze the received data in real time and detect anomalies.

[0804] Examples:

[0805] The server stores the body temperature data of livestock A in a database and uses a machine learning algorithm to detect abnormalities in body temperature.

[0806] User

[0807] Users are livestock breeders and farmers.

[0808] If the server detects an anomaly, a notification message is sent to the user.

[0809] Examples:

[0810] A notification is sent to the user saying, "Livestock A has a high body temperature. Please take cooling measures."

[0811] Emotion Engine

[0812] The emotion engine identifies the user's emotional state by analyzing voice data and facial expression data.

[0813] Data is collected using a camera and microphone to recognize emotional states.

[0814] Examples:

[0815] The emotion engine analyzes the user's camera image and determines that the user is feeling stressed.

[0816] Detailed example of system operation

[0817] The device measures the body temperature of Livestock A every minute and stores the data in its internal storage. Every hour, the device sends the collected data to a server. The server stores the data in a database and uses a machine learning algorithm to detect abnormalities in body temperature. The server detects that Livestock A's body temperature is high at 39.0°C and determines that there is a high risk of heatstroke. The server sends a notification to the user stating, "Livestock A's body temperature is high. Please take cooling measures."

[0818] The emotion engine recognizes that the user is feeling stressed through facial recognition and voice analysis. The server adjusts the notification message to be concise and clear, stating, "Temperature is high. Cooling is required." The user confirms the notification and takes measures to cool down Livestock A. For example, they may use a cooling fan. The user enters the results of the cooling measures into a dedicated app and sends them back to the server. The server analyzes the cooling measures data and learns new care methods. The emotion engine also analyzes user feedback data and reflects it in improvements to the system as a whole.

[0819] This system not only significantly improves the efficiency of livestock health management, but also makes it possible to propose care methods that take into account the emotions of the manager, which is expected to reduce user stress and create a better livestock farming environment.

[0820] Prompt Sentence Examples

[0821] Please propose an AI solution that adds a function to the system to periodically collect biological data such as body temperature, heart rate, and amount of exercise of livestock, and notify if an abnormality is detected. Also, please incorporate a function to recognize the emotions of managers and design it to reduce stress by adjusting the content of notifications.

[0822] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0823] Step 1: Start acquiring data

[0824] The device collects biometric data such as body temperature, heart rate, and activity level from sensors attached to the livestock every minute.

[0825] Input: Livestock body temperature, heart rate, and activity

[0826] Data processing: The sensor operates to acquire and store biometric data, and the acquired data is temporarily stored in the internal storage.

[0827] Output: Biometric data stored in storage

[0828] Specific operation: Data is obtained showing that livestock A's body temperature is 37.5 degrees and its heart rate is 80 bpm.

[0829] Step 2: Data verification

[0830] The device performs a simple check to ensure the acquired biometric data is accurate and free of any abnormalities.

[0831] Input: Captured biometric data

[0832] Data processing: Noise filtering and data shaping.

[0833] Output: Clean data after filtering

[0834] Specific operation: If the acquired data contains noise, the noise is removed.

[0835] Step 3: Prepare for data transfer

[0836] Every hour, the device compiles the stored data and prepares it for transmission.

[0837] Input: Filtered biometric data

[0838] Data processing: Batch processing is used to combine one hour's worth of data into a single transmission packet.

[0839] Output: Outgoing packets

[0840] Specific operation: Compress one hour's worth of data and prepare it for transfer.

[0841] Step 4: Send data

[0842] The terminal transmits the collected data to the server via wireless communication.

[0843] Input: Outgoing packets

[0844] Data processing: Sending data via wireless communication using a data transmission protocol.

[0845] Output: Data sent to the server

[0846] Specific operation: Transfer data to the server using Bluetooth or Wi-Fi.

[0847] Step 5: Receiving Data

[0848] The server receives the data sent from the terminal.

[0849] Input: Data sent

[0850] Data processing: Decodes the received data and converts it into a format suitable for storing in the database.

[0851] Output: Data stored in a database

[0852] Specific operation: The server receives the data and stores it in the database as "body temperature data of livestock A."

[0853] Step 6: Data analysis

[0854] The server analyzes the stored data in real time using machine learning algorithms to detect anomalies.

[0855] Input: Biometric data stored in a database

[0856] Data processing: Using machine learning models, we run anomaly detection algorithms.

[0857] Output: Anomaly detection results

[0858] Specific behavior: Generates an alert if the body temperature exceeds 39.0 degrees.

[0859] Step 7: Acquire voice and facial expression data

[0860] The emotion engine acquires voice data and facial expression data from the administrator (user) via a camera or microphone.

[0861] Input: Camera image and audio recording

[0862] Data processing: Analyzes voice data and extracts facial expression data from images.

[0863] Output: Administrator's emotional state data

[0864] What it does: It records what the user says in front of the camera and analyzes the images to determine their emotional state.

[0865] Step 8: Emotion Recognition Analysis

[0866] The emotion engine analyzes the captured voice and facial expression data to identify the user's current emotional state.

[0867] Input: Administrator emotional state data

[0868] Data processing: Integrate audio and image data and classify emotional states using emotion recognition models.

[0869] Output: Emotion recognition result

[0870] Specific operation: Based on microphone recordings and camera images, it determines whether the user is in a "stressed state."

[0871] Step 9: Generate notification message

[0872] Based on the anomaly detection results and emotion recognition results, the server generates a notification message such as, "Livestock B's body temperature is high. Please take cooling measures."

[0873] Input: Anomaly detection results and emotion recognition results

[0874] Data processing: Generate notification messages and customize them according to the emotional state.

[0875] Output: Information message

[0876] Specific action: The notification content will be concise, such as "High body temperature. Cool down immediately."

[0877] Step 10: Send notification

[0878] The server generates a notification message and sends it to the user.

[0879] Input: Notification message

[0880] Data processing: Send notifications to the user's device using messaging protocols.

[0881] Output: The notification message displayed on the user's device

[0882] Specific behavior: Sends notifications to the user's smartphone via SMS or email.

[0883] Step 11: Adjust notification content

[0884] An emotion engine adapts notification content to be more concise and understandable based on the user's emotional state.

[0885] Input: Emotion recognition results

[0886] Data processing: Adjust the notification wording to simplify it and reduce stress.

[0887] Output: The adjusted notification message

[0888] Specific action: Change "The livestock has a high body temperature. Please take measures to cool them down." to "High body temperature. Rapid cooling."

[0889] Step 12: Care Delivery

[0890] The user checks the notification and checks the condition of the livestock on-site, and if necessary, takes cooling measures such as using a cooling fan.

[0891] Input: Notification message and field data

[0892] Data processing: After checking the condition, select and implement appropriate measures.

[0893] Output: Care implementation results

[0894] Specific action: Cools livestock using a cooling fan until their body temperature drops to 38.0°C.

[0895] Step 13: Enter feedback

[0896] The user enters the care method and results into a dedicated app and sends them as feedback to the server.

[0897] Input: Care implementation results

[0898] Data processing: The feedback data is formatted and sent to the server.

[0899] Output: Feedback data sent to the server

[0900] Specific operations: Enter changes in body temperature after cooling measures have been implemented into the app.

[0901] Step 14: Feedback analysis

[0902] The server analyzes the received feedback data and evaluates the effectiveness of the care method.

[0903] Input: Feedback data

[0904] Data processing: Evaluate the effectiveness of care methods through data analysis.

[0905] Output: Evaluation result

[0906] Specific actions: Based on the results of the cooling measures, we recommend the same method next time.

[0907] Step 15: Reflecting Emotional Feedback

[0908] The emotion engine also receives user feedback data and reflects it in improving the overall system.

[0909] Input: Feedback data and emotion recognition results

[0910] Data processing: Analyze the feedback data and reflect it in the next notification method.

[0911] Output: Improved system profile

[0912] Specific actions: Learn specific notification methods to reduce stress and reflect them in the next notification method.

[0913] (Application example 2)

[0914] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0915] In modern factories, it is important to constantly monitor the health of equipment and detect abnormalities early. However, conventional systems have difficulty taking into account the emotions and stress levels of managers. This can hinder a prompt and effective response after an abnormality is detected. Another problem is that inaccurate notifications increase the burden on managers. Therefore, the objective of this invention is to not only monitor equipment and detect abnormalities, but also recognize the emotions of managers and adjust the content of notifications according to their emotions, thereby making it easier to respond after an abnormality is discovered.

[0916] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0917] In this invention, the server includes means for acquiring biological data of livestock, means for saving the data in a database, means for analyzing the data and detecting abnormalities, means for outputting abnormality detection results, means for notifying a manager of the output results, means for receiving and evaluating feedback from the manager, means for recognizing the manager's emotions, and means for adjusting notification content based on the manager's emotions. This makes it possible to detect equipment abnormalities early, provide appropriate notifications and propose care methods according to the manager's emotional state, and achieve rapid and effective response.

[0918] "Livestock biological data" refers to physiological information such as livestock body temperature, heart rate, and amount of exercise.

[0919] A "database" is an information management system for organizing and storing acquired data.

[0920] "Analysis" is the process of calculation and evaluation using acquired data to detect anomalies or find specific patterns or trends.

[0921] "Abnormality detection results" refer to unusual conditions or problems that are discovered through analysis.

[0922] "Notification" is a means of informing an administrator of abnormality detection results and other important information.

[0923] "Feedback" refers to returning information to the system about the actions taken by the administrator and their results.

[0924] "Administrator emotion recognition" is a technology that identifies the emotional state of an administrator from their facial expressions and voice.

[0925] "Adjusting notification content" refers to changing the content and expression of notifications depending on the administrator's emotional state.

[0926] "Proposing care methods" refers to proposing to the manager the measures and procedures that should be implemented when an abnormality is found.

[0927] The embodiment of the present invention requires a specific configuration and operation of a system for monitoring the health status of factory equipment. The system is composed of the following main components:

[0928] Device:

[0929] The terminals are sensors placed on each piece of equipment in the factory, and periodically collect data on the equipment's temperature, vibration, operating status, etc. The data collected from the sensors is temporarily stored in the terminal's internal storage. This terminal includes hardware such as high-precision sensors, and communicates data with the server using a wireless communication module.

[0930] server:

[0931] The server receives the biometric data sent from the device and stores it in a database. The server is equipped with a machine learning algorithm that analyzes the data in real time and detects anomalies. Machine learning libraries such as TensorFlow and Keras are used for anomaly detection. If an anomaly is detected, the server outputs it and notifies the administrator.

[0932] User:

[0933] The user is the factory manager. When the server detects an abnormality, it sends a notification message to the user. This notification is sent via a smartphone app or smart glasses. The notification includes the type of abnormality and how to deal with it. Feedback from the user is also important, and the actions taken and their results are sent back to the server via a dedicated app.

[0934] Emotion Engine:

[0935] The emotion engine is a module for recognizing the emotions of administrators. It analyzes the administrator's facial expressions and voice data to identify their emotional state. For example, the emotion engine uses facial recognition technology from OpenCV and emotion recognition models from TensorFlow / Keras. Based on the recognized emotions, the content of notifications is adjusted and appropriate countermeasures are proposed according to the administrator's condition.

[0936] Natural language description of program processing:

[0937] 1. Data Acquisition Phase:

[0938] The device periodically collects data such as temperature and vibration of factory equipment and stores it in its internal storage.

[0939] 2. Data transfer phase:

[0940] The terminal transmits the collected data to the server, for example, every hour, using wireless communication.

[0941] 3. Data analysis phase:

[0942] The server analyzes the data stored in the database and detects outliers using machine learning algorithms.

[0943] 4. Emotion Recognition Phase:

[0944] Using a camera on a smartphone or smart glasses, the manager's facial expressions are captured and input into an emotion recognition model to identify their emotional state.

[0945] 5. Notification Phase:

[0946] The server generates notification messages based on the anomaly detection results and sends them to administrators, whose notifications are tailored according to the administrator's emotional state.

[0947] For example, if the temperature of a factory machine suddenly rises, the system will detect the abnormality and send a notification to the manager saying, "The temperature of the equipment is high. Please take measures to cool it down immediately." If the emotion engine recognizes that the manager is feeling stressed, it will simplify the notification to say, "An equipment abnormality has occurred. Please cool it down." After the manager takes measures, they enter their feedback into a dedicated app and send it to the server. The server will analyze this feedback and use it to make future suggestions.

[0948] Example prompts to input to the generative AI model:

[0949] "Please support the design and implementation of a smartphone app that monitors the health of factory equipment, detects abnormalities, and adjusts notification content based on the manager's emotions."

[0950] This configuration makes it possible to detect abnormalities in factory equipment and to respond quickly and appropriately according to the feelings of the manager.

[0951] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0952] Step 1:

[0953] The device periodically collects data such as temperature, vibration, and operating status using sensors installed in the factory equipment, and this data is temporarily stored in the device's internal storage.

[0954] Input: Various sensor data from factory equipment (temperature, vibration, operating status)

[0955] Output: Local storage of acquired sensor data

[0956] Specific operation: High-precision sensors measure the equipment status and store the data in the terminal memory. For example, temperature data is acquired every minute and recorded in storage.

[0957] Step 2:

[0958] The terminal transmits the collected data every hour to the server via wireless communication.

[0959] Input: Sensor data stored on the device

[0960] Output: Sensor data sent to the server

[0961] Specific operation: Using the wireless communication module, the device uploads data to the server in bulk once per hour, using communication methods such as Bluetooth and Wi-Fi.

[0962] Step 3:

[0963] The server stores the received data in a database and uses machine learning algorithms to analyze the data in real time and detect anomalies.

[0964] Input: Sensor data sent to the server

[0965] Output: Anomaly detection results

[0966] How it works: Using machine learning libraries such as TensorFlow and Keras, it constantly analyzes the acquired data and detects abnormalities when temperature or vibrations fall within an abnormal range. For example, it determines that an abnormality exists when the temperature exceeds 80°C.

[0967] Step 4:

[0968] The server generates a notification message based on the anomaly detection results and sends it to the administrator's smartphone app or smart glasses.

[0969] Input: Anomaly detection results

[0970] Output: Notification message to administrator

[0971] Specific behavior: The server generates an appropriate notification based on the type of abnormality and sends it to the administrator's device, for example, a message saying "The temperature of the equipment is high. Please take measures to cool it down."

[0972] Step 5:

[0973] The emotion engine uses the camera on the administrator's smartphone or smart glasses to capture and analyze the administrator's facial expressions and voice data to understand their emotional state.

[0974] Input: Administrator's facial expression data, voice data

[0975] Output: Emotional state of the administrator

[0976] How it works: Facial recognition technology using OpenCV and emotion recognition models using TensorFlow / Keras identify emotions from the manager's facial expressions and voice. For example, it determines whether the manager is feeling stressed.

[0977] Step 6:

[0978] Once the administrator's emotional state is determined, the server tailors the notification content based on the administrator's emotional state and, if necessary, streamlines the process.

[0979] Input: Administrator's emotional state

[0980] Output: The adjusted notification message

[0981] Specific behavior: If the emotional state indicates stress, simplify the notification message. For example, omit detailed explanations and send a simple message such as "Equipment abnormality. Please cool down."

[0982] Step 7:

[0983] The user receives a notification, takes appropriate measures, and feeds the results back to the server via a dedicated app.

[0984] Input: Administrator response result

[0985] Output: Feedback data

[0986] Specific operation: The administrator implements cooling measures and inputs the results (e.g., whether the temperature has dropped) into a dedicated app. The feedback data is sent to the server.

[0987] Step 8:

[0988] The server analyzes the feedback data, evaluates the effectiveness of the care methods, and updates the recommendation database.

[0989] Input: Feedback data

[0990] Output: Updated recommendation database

[0991] Specific operation: The server analyzes the feedback data and evaluates the effectiveness of the proposed care method. The evaluation results are added to the recommendation database to be used for future recommendations.

[0992] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0993] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0994] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0995] [Third embodiment]

[0996] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0997] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0998] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0999] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1000] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1001] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1002] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1003] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1004] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1005] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1006] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1007] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1008] The present invention is a system for efficiently managing the health and behavior of livestock. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, and a system that processes notifications and feedback to managers.

[1009] System configuration

[1010] 1. Terminal

[1011] The terminal is a sensor attached to the livestock, which periodically collects biological data such as body temperature, heart rate, and amount of exercise. The collected data is temporarily stored in the terminal's internal storage.

[1012] 2. Server

[1013] The server receives the biometric data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as if the animal's body temperature is too high or its heart rate is abnormally high.

[1014] 3. Users

[1015] Users are livestock breeders and farmers. When the server detects an abnormality, it sends a notification message to the user. The notification includes the type of abnormality and recommended care methods. The user receives the notification and can take action promptly.

[1016] Program processing flow (explained in natural language)

[1017] Data Acquisition Phase

[1018] The device periodically collects data such as the animal's body temperature, heart rate, and activity level. For example, it measures body temperature every minute.

[1019] The acquired data is temporarily stored in the device's internal storage.

[1020] Data Transfer Phase

[1021] Periodically, for example, every hour, the device sends the collected data to the server via wireless communication (Wi-Fi, Bluetooth, etc.).

[1022] Data analysis phase

[1023] The server stores the received data in a database and analyzes it in real time using machine learning algorithms to detect abnormalities, such as body temperature exceeding the normal range.

[1024] Notification Phase

[1025] Based on the anomaly detection results, the server generates a message such as "Livestock B's body temperature is high. Please take cooling measures."

[1026] The server will then send this notification message to the user via their smartphone app, SMS, email, etc.

[1027] Feedback Phase

[1028] Users receive notifications, go to the scene to check the condition of the livestock, and implement appropriate care measures (e.g., cooling measures).

[1029] The care method performed and the results are entered into a dedicated app, and feedback is sent to the server.

[1030] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. This updated data is then reflected in future care recommendations.

[1031] Specific examples

[1032] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[1033] 2. Every hour, the device sends the collected data to the server.

[1034] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[1035] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[1036] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[1037] 6. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[1038] 7. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[1039] 8. The server analyzes the cooling treatment data and learns new care methods.

[1040] The implementation of this system will significantly improve the efficiency of livestock health management. It will also enable real-time abnormality detection and rapid response, which is expected to reduce livestock health risks and improve production efficiency.

[1041] The processing flow will be explained below.

[1042] Step 1:

[1043] The device measures the livestock's biological data, such as body temperature, heart rate, and activity, every minute, and the data is temporarily stored in the internal storage.

[1044] Step 2:

[1045] Every fixed time (for example, every hour), the terminal sends the collected data to the server via wireless communication.

[1046] Step 3:

[1047] The server stores the received data in a database, with each data point being given a timestamp and the livestock's individual identification information.

[1048] Step 4:

[1049] The server analyzes the data in the database using machine learning algorithms, such as comparing body temperature values ​​with normal ranges to detect abnormalities.

[1050] Step 5:

[1051] If the server detects an anomaly, it generates an output result including the type of anomaly, details of the data that became abnormal, and recommended care methods as an anomaly detection result.

[1052] Step 6:

[1053] The server generates a notification message based on the anomaly detection result, which includes the livestock ID, details of the anomaly, and the required action.

[1054] Step 7:

[1055] The server sends a notification message to the user via the user's smartphone app, SMS, email, etc.

[1056] Step 8:

[1057] Users receive notifications and can check the condition of livestock on-site, for example, by taking cooling measures if the animals have a high body temperature.

[1058] Step 9:

[1059] The user inputs the care method and results into a dedicated app and sends the data to a server. Feedback data includes changes in body temperature and specific measures taken.

[1060] Step 10:

[1061] The server analyzes the received feedback data and evaluates the effectiveness of the care method. The evaluation results are added to a recommendation database and used to suggest future care methods.

[1062] Step 11:

[1063] Based on the updated recommendation database, the server will be prepared to suggest more appropriate care methods when abnormalities are detected in the future.

[1064] This program automates and streamlines livestock health management, enabling real-time abnormality detection and rapid response.

[1065] Example 1

[1066] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1067] Conventional livestock health management systems have problems in that they do not collect biological data or detect abnormalities in real time, and managers are not notified promptly when abnormalities are discovered. Furthermore, feedback and suggestions for care methods after abnormalities are detected are not provided efficiently, making it difficult to reduce livestock health risks. Furthermore, feedback from managers is not reflected in the system, meaning it cannot be used to suggest future care methods, resulting in ineffective use of data.

[1068] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1069] In this invention, the server includes means for acquiring livestock biometric data, means for storing the biometric data in internal storage at regular intervals and periodically transmitting it to the server, means for storing the biometric data in a database and analyzing it in real time using a machine learning algorithm to detect abnormalities, means for generating a notification message based on the abnormality detection result and notifying the manager, and means for receiving feedback from the manager and evaluating its effectiveness. This reduces livestock health risks, enables rapid response, and realizes improvements in care methods through feedback.

[1070] "Means for acquiring biological data of livestock" refers to devices that periodically acquire data such as body temperature, heart rate, and amount of exercise using sensors attached to livestock.

[1071] "Means for storing the biometric data in internal storage at regular intervals and periodically transmitting it to a server" refers to a device or function that temporarily stores the acquired biometric data in a storage medium and transfers the data to a server at regular time intervals.

[1072] "Means for storing the biometric data in a database, analyzing it in real time using a machine learning algorithm, and detecting abnormalities" refers to a device or function that records the received biometric data in a database, analyzes the data in real time using a machine learning model, and identifies abnormalities that deviate from the reference values.

[1073] "Means for generating a notification message based on the anomaly detection result and notifying the administrator" refers to a device or function that creates an appropriate warning message when an anomaly is detected and provides the information to the administrator via SMS, email, etc.

[1074] The "means for receiving feedback from the administrator and evaluating its effectiveness" refers to a device or function that collects information provided by the administrator and analyzes and evaluates the effectiveness of that information.

[1075] The "means for proposing a care method for livestock based on the abnormality detection result" is a device or function that provides an appropriate countermeasure for the detected abnormality.

[1076] "Means for evaluating the effectiveness of the proposed care method in real time and adding the results to the recommendation database" refers to a device or function that instantly analyzes the effectiveness of the proposed care method and adds the results to a database to be used for the next recommendation.

[1077] The present invention is a system for efficiently managing the health and behavior of livestock. This system includes sensors (terminals) for acquiring livestock biometric data, a server for storing and analyzing the data, and a system for notifying and providing feedback to managers.

[1078] System configuration

[1079] 1. Terminal

[1080] The terminals are sensors attached to livestock, which periodically collect biological data such as body temperature, heart rate, and activity level. The sensors used include body temperature sensors and heart rate sensors.

[1081] The acquired data is temporarily stored in the device's internal storage, specifically, using a storage device such as a microSD card or internal flash memory.

[1082] 2. Server

[1083] The server receives the biometric data sent from the terminal and stores it in a database.

[1084] The server uses machine learning algorithms to analyze data in real time and detect anomalies, using software such as MySQL or PostgreSQL as databases and Scikit-learn or TensorFlow as machine learning libraries.

[1085] If an anomaly is detected, the server generates an appropriate notification message and notifies the administrator via an SMS gateway service (e.g., Twilio) or an email service (e.g., SendGrid).

[1086] 3. Users

[1087] Users are livestock farmers and breeders. They receive notifications from the server, check the condition of their livestock on-site, and provide appropriate care.

[1088] The care method and results are entered into a dedicated app, which is provided as a smartphone app and sends the data via the internet to the server.

[1089] Specific examples

[1090] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[1091] 2. Every hour, the device sends the collected data to the server.

[1092] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[1093] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[1094] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[1095] 6. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[1096] 7. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[1097] 8. The server analyzes the cooling treatment data and learns new care methods.

[1098] Example prompts for generative AI models

[1099] "I would like to develop a system that measures the body temperature, heart rate, and amount of movement of livestock, and notifies the user if an abnormality is detected. Please tell me which technology I should use for the specific algorithm and notification method."

[1100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1101] Step 1:

[1102] The device acquires biometric data such as body temperature, heart rate, and activity level of livestock. For example, a body temperature sensor measures body temperature every minute, and a heart rate sensor monitors heart rate in real time. This data is temporarily stored in the device's internal storage. The input is the livestock's biometric data, and the output is the measurement data stored in the device's internal storage device.

[1103] Step 2:

[1104] The device periodically transmits collected data to the server. For example, every hour, the data is transferred to the server using Wi-Fi or Bluetooth. The input is the measurement data stored in the internal storage, and the output is the data transmitted to the server. This includes the waiting process until communication is established.

[1105] Step 3:

[1106] The server stores the received data in a database. Database systems used include MySQL and PostgreSQL, for example. The input is the measurement data sent from the device, and the output is the biometric data stored in the database. This also involves converting the data format and eliminating invalid data.

[1107] Step 4:

[1108] The server uses machine learning algorithms to analyze the received biometric data in real time and detect abnormalities. The machine learning models used are, for example, Scikit-learn or TensorFlow. The input is the measurement data stored in the database, and the output is the results of anomaly detection. Specifically, anomalies are identified when body temperature exceeds 38.5°C or when the heart rate exceeds 100 beats per minute.

[1109] Step 5:

[1110] The server generates a notification message based on the anomaly detection result. For example, it generates a message such as "Livestock B has a high body temperature. Please take cooling measures." The input is the anomaly detection result, and the output is the generated notification message. A template-based approach is used to generate the message.

[1111] Step 6:

[1112] The server sends a notification message to the user, using an SMS gateway service (e.g., Twilio) or an email service (e.g., SendGrid) based on the user's notification preferences. The input is the generated notification message, and the output is the notification sent to the user.

[1113] Step 7:

[1114] The user receives the notification and takes appropriate action. For example, the user checks the notification, rechecks the animal's temperature on-site, and then uses a cooler to cool it down. The input is the notification sent, and the output is the action taken.

[1115] Step 8:

[1116] The user enters the care method and its results into a dedicated app and sends feedback to the server. The user logs into the dedicated app, enters the care method and results performed in the input form, and presses the send button to send the data to the server. The input is the care method performed and the results, and the output is the feedback sent to the server.

[1117] Step 9:

[1118] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. The feedback is analyzed using a machine learning algorithm to evaluate the effectiveness of new care methods. The input is user feedback, and the output is an updated recommendation database.

[1119] (Application example 1)

[1120] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1121] Modern factories operate many robots and machines, but it is difficult to efficiently manage their health and take appropriate action before an abnormality occurs. Furthermore, if an abnormality in a machine or robot is left unattended, there is a higher risk of reduced production efficiency and serious breakdowns. To solve these problems, a system is needed that can monitor the health of robots and machines in real time and respond quickly when an abnormality is detected.

[1122] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1123] In this invention, the server includes a means for acquiring motion data of an object, a means for storing the motion data in a database, and a means for analyzing the motion data and detecting abnormalities, thereby making it possible to monitor the health status of a robot or machine in real time and to respond quickly when an abnormality is detected.

[1124] "Objects" refer to robots and machines operating within the factory.

[1125] "Operational data" refers to data relating to the operating conditions of an object, such as its temperature, vibration, and operation patterns.

[1126] "Database" refers to an information system for storing and managing operational data.

[1127] "Analysis" refers to the process of evaluating acquired operational data to determine if there are any anomalies.

[1128] "Anomaly detection" refers to the discovery of values ​​or patterns in operational data that deviate from normal ranges.

[1129] "Output" refers to generating anomaly detection results as a report or notification message and conveying them to an administrator.

[1130] "Administrator" refers to the person in charge of operating and maintaining robots and machinery within the factory.

[1131] "Notification" refers to the act of sending the abnormality detection results to the administrator's smartphone, computer, etc.

[1132] "Feedback" refers to the data returned to the system regarding the measures taken by the administrator in response to an abnormality and the results of those measures.

[1133] "Care method" refers to the recommended repair and maintenance method for the object when an abnormality is detected.

[1134] A "recommendation database" refers to a database that accumulates effective care methods and suggests them the next time an abnormality is detected.

[1135] This invention is a system for efficiently managing the health status of robots and machines in a factory. This system includes sensors for acquiring operational data of objects, a server for storing and analyzing the data, and a system for notifying and providing feedback to an administrator. The implementation method of the system will be described in detail below.

[1136] System configuration

[1137] 1. Sensor (terminal)

[1138] The terminal is a sensor attached to a robot or machine in a factory. This periodically collects operational data such as the temperature, vibration, and movement patterns of the object. The collected data is temporarily stored in the terminal's internal storage.

[1139] 2. Server

[1140] The server receives the operational data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as when the robot's temperature is too high or when vibrations are abnormally strong.

[1141] 3. Administrator

[1142] The administrator is the person in charge of operating and maintaining the factory. When the server detects an abnormality, it sends a notification message to the administrator. The notification includes the type of abnormality and recommended care methods. The administrator receives the notification and can take action promptly.

[1143] Program processing flow

[1144] Data Acquisition Phase

[1145] The sensor (terminal) periodically collects data such as the temperature, vibration, and movement patterns of the robot or machine. For example, it measures the temperature every minute.

[1146] The acquired data is temporarily stored in the device's internal storage.

[1147] Data Transfer Phase

[1148] The sensor (terminal) periodically sends the collected data to the server, for example, every hour. The data is sent via wireless communication (Wi-Fi, Bluetooth, etc.).

[1149] Data analysis phase

[1150] The server stores the received data in a database and analyzes it in real time using machine learning algorithms to detect anomalies, such as when temperatures exceed normal limits.

[1151] Notification Phase

[1152] Based on the abnormality detection results, the server generates a message such as "Robot 1's temperature is too high. Please cool it down."

[1153] The server sends this notification message to the administrator, who is notified via their smartphone app, SMS, email, etc.

[1154] Feedback Phase

[1155] Administrators receive notifications, check the status of the robots and machines on-site, and implement appropriate care measures (e.g., cooling measures).

[1156] The care method performed and the results are entered into a dedicated app, and feedback is sent to the server.

[1157] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. This updated data is then reflected in future care recommendations.

[1158] Specific examples

[1159] 1. The sensor (terminal) measures the temperature of Robot 1 every minute and saves the data in its internal storage.

[1160] 2. Every hour, the sensor (terminal) sends the collected data to the server.

[1161] 3. The server stores the data in a database and uses machine learning algorithms to detect temperature anomalies.

[1162] 4. The server detects that Robot 1's temperature is 31.0 degrees, which is high, and determines that there is a high risk of overheating.

[1163] 5. The server sends a notification to the administrator saying, "Robot 1's temperature is too high. Please cool it down."

[1164] 6. The administrator checks the notification and takes measures to cool Robot 1 (e.g., activates the cooling system).

[1165] 7. The administrator enters the results of the cooling measures into a dedicated app and sends them back to the server.

[1166] 8. The server analyzes cooling data and learns new maintenance methods.

[1167] Example prompt sentence:

[1168] "My robot is experiencing high temperatures and vibrations. What steps should I take to manage this situation?"

[1169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1170] Step 1:

[1171] Data Acquisition Phase

[1172] The terminal periodically acquires operational data such as the temperature, vibration, and movement patterns of the robot or machine. For example, it measures the temperature every minute. The terminal temporarily stores the acquired data in its internal storage. The input of this process is the current status information of the object, and the output is the acquired operational data.

[1173] Step 2:

[1174] Data Transfer Phase

[1175] The device periodically (for example, every hour) transmits the collected operation data to the server. The data is transmitted via wireless communication (Wi-Fi, Bluetooth, etc.). The input of this process is the operation data stored on the device, and the output is the operation data transmitted to the server.

[1176] Step 3:

[1177] Data storage phase

[1178] The server stores the received operation data in a database. Specifically, it converts the received data into an appropriate format and records it in the database. The input of this process is the operation data sent from the terminal, and the output is the data stored in the database.

[1179] Step 4:

[1180] Data analysis phase

[1181] The server uses machine learning algorithms to analyze the operational data stored in the database in real time. For example, it detects abnormalities when the temperature exceeds the normal range or when vibrations are abnormally large. The input to this process is the operational data obtained from the database, and the output is the anomaly detection result.

[1182] Step 5:

[1183] Notification Phase

[1184] Based on the anomaly detection result, the server generates a message such as "Robot 1's temperature is too high. Please cool it down." The generated message is sent to the administrator. The input of this process is the anomaly detection result, and the output is the notification message sent to the administrator.

[1185] Step 6:

[1186] Care Delivery Phase

[1187] The administrator receives the notification, checks the status of the robot or machine on-site, and implements appropriate maintenance measures, such as turning on the cooling system. The input to this process is the notification message from the server, and the output is the result of the implemented maintenance measures.

[1188] Step 7:

[1189] Feedback Phase

[1190] The administrator enters the care methods and results into a dedicated app and sends feedback to the server. The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. The input to this process is the feedback information from the administrator, and the output is an updated recommendation database.

[1191] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1192] This invention combines a system for efficiently managing the health and behavior of livestock with a function for recognizing the emotions of managers. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, and an emotion engine that recognizes the emotions of managers, in addition to processing notifications and feedback to managers.

[1193] System configuration

[1194] 1. Terminal

[1195] The terminal is a sensor attached to the livestock, which periodically collects biological data such as body temperature, heart rate, and amount of exercise. The collected data is temporarily stored in the terminal's internal storage.

[1196] 2. Server

[1197] The server receives the biometric data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as if the animal's body temperature is too high or its heart rate is abnormally high.

[1198] 3. Users

[1199] Users are livestock breeders and farmers. When the server detects an abnormality, it sends a notification message to the user. The notification includes the type of abnormality and recommended care methods. The user receives the notification and can take action promptly.

[1200] 4. Emotion Engine

[1201] The emotion engine is a module for recognizing the user's emotions, and identifies the user's emotional state by analyzing voice data and facial expression data acquired from the camera and microphone.

[1202] Program processing flow (explained in natural language)

[1203] Data Acquisition Phase

[1204] The device periodically collects data such as the animal's body temperature, heart rate, and activity level. For example, it measures body temperature every minute.

[1205] The acquired data is temporarily stored in the device's internal storage.

[1206] Data Transfer Phase

[1207] Periodically, for example, every hour, the terminal transmits the collected data to the server via wireless communication.

[1208] Data analysis phase

[1209] The server stores the received data in a database and analyzes it in real time using machine learning algorithms, for example, comparing body temperature values ​​with the normal range to detect abnormalities.

[1210] Emotion Recognition Phase

[1211] The emotion engine analyzes the user's voice and facial expression data to determine their current emotional state. For example, it analyzes images taken with a camera to determine whether the user is feeling stressed.

[1212] Notification Phase

[1213] Based on the anomaly detection results, the server generates a message such as "Livestock B's body temperature is high. Please take cooling measures."

[1214] The server will then send this notification message to the user via their smartphone app, SMS, email, etc.

[1215] Emotional Adaptation Phase

[1216] The emotion engine recognizes the user's emotions and adapts the notification content and care suggestions based on that emotion. For example, if the user is feeling stressed, the notification message will be more concise and easy to understand.

[1217] Feedback Phase

[1218] Users receive notifications, go to the scene to check the condition of the livestock, and implement appropriate care measures (e.g., cooling measures).

[1219] The care methods and results are entered into a dedicated app, and feedback is sent to the server, including changes in body temperature and specific measures taken.

[1220] Feedback Analysis Phase

[1221] The server analyzes the received feedback data and evaluates the effectiveness of the care method. The evaluation results are added to a recommendation database and used to suggest future care methods.

[1222] The emotion engine also receives feedback data and reflects the emotion-adapted feedback data in the recommendation database.

[1223] Specific examples

[1224] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[1225] 2. Every hour, the device sends the collected data to the server.

[1226] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[1227] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[1228] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[1229] 6. The emotion engine recognizes that the user is feeling stressed through facial recognition and voice analysis.

[1230] 7. The server tailors notification messages to be concise and clear.

[1231] 8. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[1232] 9. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[1233] 10. The server analyzes the cooling data and learns new care methods.

[1234] 11. The emotion engine also analyzes user feedback and reflects it in improving the entire system.

[1235] This system not only significantly improves the efficiency of livestock health management, but also makes it possible to propose care methods that take into account the emotions of managers, which is expected to reduce user stress and help create a better livestock farming environment.

[1236] The processing flow will be explained below.

[1237] Step 1:

[1238] The device measures the livestock's biological data, such as body temperature, heart rate, and activity, every minute, and the measured data is temporarily stored in the device's internal storage.

[1239] Step 2:

[1240] Every fixed time (for example, every hour), the terminal sends the collected data to the server using wireless communication (Wi-Fi, Bluetooth, etc.).

[1241] Step 3:

[1242] The server stores the received biometric data in a database, and when stored, each data item is given a timestamp and the livestock's individual identification information.

[1243] Step 4:

[1244] The server uses machine learning algorithms to analyze the data in the database in real time and detect abnormalities, such as when a person's body temperature exceeds the normal range.

[1245] Step 5:

[1246] The emotion engine analyzes the user's voice data and facial expression data to identify their current emotional state, for example by analyzing images and audio captured by the user's smartphone camera.

[1247] Step 6:

[1248] The server generates an output result including the type of anomaly, details of the anomaly data, and recommended care methods as anomaly detection results.

[1249] Step 7:

[1250] An emotion engine optimizes notification content based on the user's emotional state. For example, if the user is stressed, the message will be formatted succinctly and clearly.

[1251] Step 8:

[1252] The server generates an optimized notification message and sends it to the user via a smartphone app, SMS, email, etc.

[1253] Step 9:

[1254] Users can receive notifications and check the condition of livestock on-site, for example, by taking measures to cool down livestock with high body temperatures.

[1255] Step 10:

[1256] The user enters the care method and results into a dedicated app, and feedback data, including changes in body temperature and specific measures taken, is sent to a server.

[1257] Step 11:

[1258] The server analyzes the received feedback data, evaluates the effectiveness of the care method, and adds the evaluation results to the recommendation database.

[1259] Step 12:

[1260] The emotion engine also analyzes emotional feedback from users to improve notifications and care suggestions, and this data is reflected in the recommendation database.

[1261] Step 13:

[1262] Based on the updated recommendation database, the server will be prepared to suggest more appropriate care methods the next time an abnormality is detected.

[1263] This process flow allows for efficient and effective livestock health management and provides support that takes into account the emotions of managers, thereby reducing livestock health risks and easing the burden on managers.

[1264] Example 2

[1265] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1266] While conventional livestock management systems can acquire livestock biometric data and detect abnormalities, they lack the ability to recognize the emotions of managers and lack the means to reduce manager stress and burden. As a result, managers can sometimes become overly stressed, making it difficult to implement appropriate care methods. Another issue is that feedback is not fully utilized, preventing improvements to care methods.

[1267] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing biometric data of livestock in a database, a means for analyzing the biometric data and detecting abnormalities, and a means for recognizing the emotions of the manager from voice data and facial expression data. This makes it possible to provide appropriate notification content according to the manager's emotional state and to quickly and effectively suggest livestock care methods based on the abnormality detection results. In addition, by analyzing feedback from the manager and reflecting it in the next proposal, it is possible to continuously improve the care methods.

[1268] "Livestock" is a general term for animals kept in captivity, and refers primarily to animals used in agriculture and animal husbandry.

[1269] "Biometric data" refers to information related to the vital activities of livestock, such as body temperature, heart rate, and amount of movement.

[1270] A "database" refers to a system for efficiently managing, searching, and storing large amounts of data.

[1271] "Analysis" refers to the method of processing acquired data to find specific patterns or anomalies.

[1272] "Abnormal" refers to a value or condition that deviates from the normal range, indicating that something unusual has happened to the health of livestock.

[1273] "Voice data" refers to data that records information about the voice of the administrator.

[1274] "Facial expression data" refers to information obtained from the facial expression of an administrator and is used to determine the administrator's emotional state.

[1275] "Emotion recognition" refers to technology that identifies the current emotional state of a manager based on voice and facial expression data.

[1276] "Notification" refers to a message sent to notify an administrator when an abnormality is detected.

[1277] "Feedback" refers to the administrator returning information to the system about the care methods implemented and their results.

[1278] "Care methods" refer to the specific countermeasures and treatments implemented for livestock in which abnormalities are detected.

[1279] A "recommendation database" refers to a database that will be used for future proposals based on analysis results and feedback information.

[1280] This invention combines a system for efficiently managing the health and behavior of livestock with a function for recognizing the emotions of managers. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, a system that processes notifications and feedback to managers, and an emotion engine that recognizes the emotions of managers.

[1281] Specific system configuration

[1282] Terminal

[1283] The terminals are sensors attached to livestock and collect biometric data such as body temperature, heart rate, and exercise volume.

[1284] The acquired data is temporarily stored in the device's internal storage.

[1285] Examples:

[1286] The body temperature of livestock A is measured every minute and the data is stored in the internal storage.

[1287] server

[1288] The server receives the data sent from the terminal and stores it in a database.

[1289] The server uses machine learning algorithms to analyze the received data in real time and detect anomalies.

[1290] Examples:

[1291] The server stores the body temperature data of livestock A in a database and uses a machine learning algorithm to detect abnormalities in body temperature.

[1292] User

[1293] Users are livestock breeders and farmers.

[1294] If the server detects an anomaly, a notification message is sent to the user.

[1295] Examples:

[1296] A notification is sent to the user saying, "Livestock A has a high body temperature. Please take cooling measures."

[1297] Emotion Engine

[1298] The emotion engine identifies the user's emotional state by analyzing voice data and facial expression data.

[1299] Data is collected using a camera and microphone to recognize emotional states.

[1300] Examples:

[1301] The emotion engine analyzes the user's camera image and determines that the user is feeling stressed.

[1302] Detailed example of system operation

[1303] The device measures the body temperature of Livestock A every minute and stores the data in its internal storage. Every hour, the device sends the collected data to a server. The server stores the data in a database and uses a machine learning algorithm to detect abnormalities in body temperature. The server detects that Livestock A's body temperature is high at 39.0°C and determines that there is a high risk of heatstroke. The server sends a notification to the user stating, "Livestock A's body temperature is high. Please take cooling measures."

[1304] The emotion engine recognizes that the user is feeling stressed through facial recognition and voice analysis. The server adjusts the notification message to be concise and clear, stating, "Temperature is high. Cooling is required." The user confirms the notification and takes measures to cool down Livestock A. For example, they may use a cooling fan. The user enters the results of the cooling measures into a dedicated app and sends them back to the server. The server analyzes the cooling measures data and learns new care methods. The emotion engine also analyzes user feedback data and reflects it in improvements to the system as a whole.

[1305] This system not only significantly improves the efficiency of livestock health management, but also makes it possible to propose care methods that take into account the emotions of the manager, which is expected to reduce user stress and create a better livestock farming environment.

[1306] Prompt Sentence Examples

[1307] Please propose an AI solution that adds a function to the system to periodically collect biological data such as body temperature, heart rate, and amount of exercise of livestock, and notify if an abnormality is detected. Also, please incorporate a function to recognize the emotions of managers and design it to reduce stress by adjusting the content of notifications.

[1308] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1309] Step 1: Start acquiring data

[1310] The device collects biometric data such as body temperature, heart rate, and activity level from sensors attached to the livestock every minute.

[1311] Input: Livestock body temperature, heart rate, and activity

[1312] Data processing: The sensor operates to acquire and store biometric data, and the acquired data is temporarily stored in the internal storage.

[1313] Output: Biometric data stored in storage

[1314] Specific operation: Data is obtained showing that livestock A's body temperature is 37.5 degrees and its heart rate is 80 bpm.

[1315] Step 2: Data verification

[1316] The device performs a simple check to ensure the acquired biometric data is accurate and free of any abnormalities.

[1317] Input: Captured biometric data

[1318] Data processing: Noise filtering and data shaping.

[1319] Output: Clean data after filtering

[1320] Specific operation: If the acquired data contains noise, the noise is removed.

[1321] Step 3: Prepare for data transfer

[1322] Every hour, the device compiles the stored data and prepares it for transmission.

[1323] Input: Filtered biometric data

[1324] Data processing: Batch processing is used to combine one hour's worth of data into a single transmission packet.

[1325] Output: Outgoing packets

[1326] Specific operation: Compress one hour's worth of data and prepare it for transfer.

[1327] Step 4: Send data

[1328] The terminal transmits the collected data to the server via wireless communication.

[1329] Input: Outgoing packets

[1330] Data processing: Sending data via wireless communication using a data transmission protocol.

[1331] Output: Data sent to the server

[1332] Specific operation: Transfer data to the server using Bluetooth or Wi-Fi.

[1333] Step 5: Receiving Data

[1334] The server receives the data sent from the terminal.

[1335] Input: Data sent

[1336] Data processing: Decodes the received data and converts it into a format suitable for storing in the database.

[1337] Output: Data stored in a database

[1338] Specific operation: The server receives the data and stores it in the database as "body temperature data of livestock A."

[1339] Step 6: Data analysis

[1340] The server analyzes the stored data in real time using machine learning algorithms to detect anomalies.

[1341] Input: Biometric data stored in a database

[1342] Data processing: Using machine learning models, we run anomaly detection algorithms.

[1343] Output: Anomaly detection results

[1344] Specific behavior: Generates an alert if the body temperature exceeds 39.0 degrees.

[1345] Step 7: Acquire voice and facial expression data

[1346] The emotion engine acquires voice data and facial expression data from the administrator (user) via a camera or microphone.

[1347] Input: Camera image and audio recording

[1348] Data processing: Analyzes voice data and extracts facial expression data from images.

[1349] Output: Administrator's emotional state data

[1350] What it does: It records what the user says in front of the camera and analyzes the images to determine their emotional state.

[1351] Step 8: Emotion Recognition Analysis

[1352] The emotion engine analyzes the captured voice and facial expression data to identify the user's current emotional state.

[1353] Input: Administrator emotional state data

[1354] Data processing: Integrate audio and image data and classify emotional states using emotion recognition models.

[1355] Output: Emotion recognition result

[1356] Specific operation: Based on microphone recordings and camera images, it determines whether the user is in a "stressed state."

[1357] Step 9: Generate notification message

[1358] Based on the anomaly detection results and emotion recognition results, the server generates a notification message such as, "Livestock B's body temperature is high. Please take cooling measures."

[1359] Input: Anomaly detection results and emotion recognition results

[1360] Data processing: Generate notification messages and customize them according to the emotional state.

[1361] Output: Information message

[1362] Specific action: The notification content will be concise, such as "High body temperature. Cool down immediately."

[1363] Step 10: Send notification

[1364] The server generates a notification message and sends it to the user.

[1365] Input: Notification message

[1366] Data processing: Send notifications to the user's device using messaging protocols.

[1367] Output: The notification message displayed on the user's device

[1368] Specific behavior: Sends notifications to the user's smartphone via SMS or email.

[1369] Step 11: Adjust notification content

[1370] An emotion engine adapts notification content to be more concise and understandable based on the user's emotional state.

[1371] Input: Emotion recognition results

[1372] Data processing: Adjust the notification wording to simplify it and reduce stress.

[1373] Output: The adjusted notification message

[1374] Specific action: Change "The livestock has a high body temperature. Please take measures to cool them down." to "High body temperature. Rapid cooling."

[1375] Step 12: Care Delivery

[1376] The user checks the notification and checks the condition of the livestock on-site, and if necessary, takes cooling measures such as using a cooling fan.

[1377] Input: Notification message and field data

[1378] Data processing: After checking the condition, select and implement appropriate measures.

[1379] Output: Care implementation results

[1380] Specific action: Cools livestock using a cooling fan until their body temperature drops to 38.0°C.

[1381] Step 13: Enter feedback

[1382] The user enters the care method and results into a dedicated app and sends them as feedback to the server.

[1383] Input: Care implementation results

[1384] Data processing: The feedback data is formatted and sent to the server.

[1385] Output: Feedback data sent to the server

[1386] Specific operations: Enter changes in body temperature after cooling measures have been implemented into the app.

[1387] Step 14: Feedback analysis

[1388] The server analyzes the received feedback data and evaluates the effectiveness of the care method.

[1389] Input: Feedback data

[1390] Data processing: Evaluate the effectiveness of care methods through data analysis.

[1391] Output: Evaluation result

[1392] Specific actions: Based on the results of the cooling measures, we recommend the same method next time.

[1393] Step 15: Reflecting Emotional Feedback

[1394] The emotion engine also receives user feedback data and reflects it in improving the overall system.

[1395] Input: Feedback data and emotion recognition results

[1396] Data processing: Analyze the feedback data and reflect it in the next notification method.

[1397] Output: Improved system profile

[1398] Specific actions: Learn specific notification methods to reduce stress and reflect them in the next notification method.

[1399] (Application example 2)

[1400] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1401] In modern factories, it is important to constantly monitor the health of equipment and detect abnormalities early. However, conventional systems have difficulty taking into account the emotions and stress levels of managers. This can hinder a prompt and effective response after an abnormality is detected. Another problem is that inaccurate notifications increase the burden on managers. Therefore, the objective of this invention is to not only monitor equipment and detect abnormalities, but also recognize the emotions of managers and adjust the content of notifications according to their emotions, thereby making it easier to respond after an abnormality is discovered.

[1402] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1403] In this invention, the server includes means for acquiring biological data of livestock, means for saving the data in a database, means for analyzing the data and detecting abnormalities, means for outputting abnormality detection results, means for notifying a manager of the output results, means for receiving and evaluating feedback from the manager, means for recognizing the manager's emotions, and means for adjusting notification content based on the manager's emotions. This makes it possible to detect equipment abnormalities early, provide appropriate notifications and propose care methods according to the manager's emotional state, and achieve rapid and effective response.

[1404] "Livestock biological data" refers to physiological information such as livestock body temperature, heart rate, and amount of exercise.

[1405] A "database" is an information management system for organizing and storing acquired data.

[1406] "Analysis" is the process of calculation and evaluation using acquired data to detect anomalies or find specific patterns or trends.

[1407] "Abnormality detection results" refer to unusual conditions or problems that are discovered through analysis.

[1408] "Notification" is a means of informing an administrator of abnormality detection results and other important information.

[1409] "Feedback" refers to returning information to the system about the actions taken by the administrator and their results.

[1410] "Administrator emotion recognition" is a technology that identifies the emotional state of an administrator from their facial expressions and voice.

[1411] "Adjusting notification content" refers to changing the content and expression of notifications depending on the administrator's emotional state.

[1412] "Proposing care methods" refers to proposing to the manager the measures and procedures that should be implemented when an abnormality is found.

[1413] The embodiment of the present invention requires a specific configuration and operation of a system for monitoring the health status of factory equipment. The system is composed of the following main components:

[1414] Device:

[1415] The terminals are sensors placed on each piece of equipment in the factory, and periodically collect data on the equipment's temperature, vibration, operating status, etc. The data collected from the sensors is temporarily stored in the terminal's internal storage. This terminal includes hardware such as high-precision sensors, and communicates data with the server using a wireless communication module.

[1416] server:

[1417] The server receives the biometric data sent from the device and stores it in a database. The server is equipped with a machine learning algorithm that analyzes the data in real time and detects anomalies. Machine learning libraries such as TensorFlow and Keras are used for anomaly detection. If an anomaly is detected, the server outputs it and notifies the administrator.

[1418] User:

[1419] The user is the factory manager. When the server detects an abnormality, it sends a notification message to the user. This notification is sent via a smartphone app or smart glasses. The notification includes the type of abnormality and how to deal with it. Feedback from the user is also important, and the actions taken and their results are sent back to the server via a dedicated app.

[1420] Emotion Engine:

[1421] The emotion engine is a module for recognizing the emotions of administrators. It analyzes the administrator's facial expressions and voice data to identify their emotional state. For example, the emotion engine uses facial recognition technology from OpenCV and emotion recognition models from TensorFlow / Keras. Based on the recognized emotions, the content of notifications is adjusted and appropriate countermeasures are proposed according to the administrator's condition.

[1422] Natural language description of program processing:

[1423] 1. Data Acquisition Phase:

[1424] The device periodically collects data such as temperature and vibration of factory equipment and stores it in its internal storage.

[1425] 2. Data transfer phase:

[1426] The terminal transmits the collected data to the server, for example, every hour, using wireless communication.

[1427] 3. Data analysis phase:

[1428] The server analyzes the data stored in the database and detects outliers using machine learning algorithms.

[1429] 4. Emotion Recognition Phase:

[1430] Using a camera on a smartphone or smart glasses, the manager's facial expressions are captured and input into an emotion recognition model to identify their emotional state.

[1431] 5. Notification Phase:

[1432] The server generates notification messages based on the anomaly detection results and sends them to administrators, whose notifications are tailored according to the administrator's emotional state.

[1433] For example, if the temperature of a factory machine suddenly rises, the system will detect the abnormality and send a notification to the manager saying, "The temperature of the equipment is high. Please take measures to cool it down immediately." If the emotion engine recognizes that the manager is feeling stressed, it will simplify the notification to say, "An equipment abnormality has occurred. Please cool it down." After the manager takes measures, they enter their feedback into a dedicated app and send it to the server. The server will analyze this feedback and use it to make future suggestions.

[1434] Example prompts to input to the generative AI model:

[1435] "Please support the design and implementation of a smartphone app that monitors the health of factory equipment, detects abnormalities, and adjusts notification content based on the manager's emotions."

[1436] This configuration makes it possible to detect abnormalities in factory equipment and to respond quickly and appropriately according to the feelings of the manager.

[1437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1438] Step 1:

[1439] The device periodically collects data such as temperature, vibration, and operating status using sensors installed in the factory equipment, and this data is temporarily stored in the device's internal storage.

[1440] Input: Various sensor data from factory equipment (temperature, vibration, operating status)

[1441] Output: Local storage of acquired sensor data

[1442] Specific operation: High-precision sensors measure the equipment status and store the data in the terminal memory. For example, temperature data is acquired every minute and recorded in storage.

[1443] Step 2:

[1444] The terminal transmits the collected data every hour to the server via wireless communication.

[1445] Input: Sensor data stored on the device

[1446] Output: Sensor data sent to the server

[1447] Specific operation: Using the wireless communication module, the device uploads data to the server in bulk once per hour, using communication methods such as Bluetooth and Wi-Fi.

[1448] Step 3:

[1449] The server stores the received data in a database and uses machine learning algorithms to analyze the data in real time and detect anomalies.

[1450] Input: Sensor data sent to the server

[1451] Output: Anomaly detection results

[1452] How it works: Using machine learning libraries such as TensorFlow and Keras, it constantly analyzes the acquired data and detects abnormalities when temperature or vibrations fall within an abnormal range. For example, it determines that an abnormality exists when the temperature exceeds 80°C.

[1453] Step 4:

[1454] The server generates a notification message based on the anomaly detection results and sends it to the administrator's smartphone app or smart glasses.

[1455] Input: Anomaly detection results

[1456] Output: Notification message to administrator

[1457] Specific behavior: The server generates an appropriate notification based on the type of abnormality and sends it to the administrator's device, for example, a message saying "The temperature of the equipment is high. Please take measures to cool it down."

[1458] Step 5:

[1459] The emotion engine uses the camera on the administrator's smartphone or smart glasses to capture and analyze the administrator's facial expressions and voice data to understand their emotional state.

[1460] Input: Administrator's facial expression data, voice data

[1461] Output: Emotional state of the administrator

[1462] How it works: Facial recognition technology using OpenCV and emotion recognition models using TensorFlow / Keras identify emotions from the manager's facial expressions and voice. For example, it determines whether the manager is feeling stressed.

[1463] Step 6:

[1464] Once the administrator's emotional state is determined, the server tailors the notification content based on the administrator's emotional state and, if necessary, streamlines the process.

[1465] Input: Administrator's emotional state

[1466] Output: The adjusted notification message

[1467] Specific behavior: If the emotional state indicates stress, simplify the notification message. For example, omit detailed explanations and send a simple message such as "Equipment abnormality. Please cool down."

[1468] Step 7:

[1469] The user receives a notification, takes appropriate measures, and feeds the results back to the server via a dedicated app.

[1470] Input: Administrator response result

[1471] Output: Feedback data

[1472] Specific operation: The administrator implements cooling measures and inputs the results (e.g., whether the temperature has dropped) into a dedicated app. The feedback data is sent to the server.

[1473] Step 8:

[1474] The server analyzes the feedback data, evaluates the effectiveness of the care methods, and updates the recommendation database.

[1475] Input: Feedback data

[1476] Output: Updated recommendation database

[1477] Specific operation: The server analyzes the feedback data and evaluates the effectiveness of the proposed care method. The evaluation results are added to the recommendation database to be used for future recommendations.

[1478] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1479] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1480] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1481] [Fourth embodiment]

[1482] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1483] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1484] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1485] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1486] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1487] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1488] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1489] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1490] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1491] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1492] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1493] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1494] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1495] The present invention is a system for efficiently managing the health and behavior of livestock. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, and a system that processes notifications and feedback to managers.

[1496] System configuration

[1497] 1. Terminal

[1498] The terminal is a sensor attached to the livestock, which periodically collects biological data such as body temperature, heart rate, and amount of exercise. The collected data is temporarily stored in the terminal's internal storage.

[1499] 2. Server

[1500] The server receives the biometric data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as if the animal's body temperature is too high or its heart rate is abnormally high.

[1501] 3. Users

[1502] Users are livestock breeders and farmers. When the server detects an abnormality, it sends a notification message to the user. The notification includes the type of abnormality and recommended care methods. The user receives the notification and can take action promptly.

[1503] Program processing flow (explained in natural language)

[1504] Data Acquisition Phase

[1505] The device periodically collects data such as the animal's body temperature, heart rate, and activity level. For example, it measures body temperature every minute.

[1506] The acquired data is temporarily stored in the device's internal storage.

[1507] Data Transfer Phase

[1508] Periodically, for example, every hour, the device sends the collected data to the server via wireless communication (Wi-Fi, Bluetooth, etc.).

[1509] Data analysis phase

[1510] The server stores the received data in a database and analyzes it in real time using machine learning algorithms to detect abnormalities, such as body temperature exceeding the normal range.

[1511] Notification Phase

[1512] Based on the anomaly detection results, the server generates a message such as "Livestock B's body temperature is high. Please take cooling measures."

[1513] The server will then send this notification message to the user via their smartphone app, SMS, email, etc.

[1514] Feedback Phase

[1515] Users receive notifications, go to the scene to check the condition of the livestock, and implement appropriate care measures (e.g., cooling measures).

[1516] The care method performed and the results are entered into a dedicated app, and feedback is sent to the server.

[1517] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. This updated data is then reflected in future care recommendations.

[1518] Specific examples

[1519] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[1520] 2. Every hour, the device sends the collected data to the server.

[1521] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[1522] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[1523] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[1524] 6. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[1525] 7. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[1526] 8. The server analyzes the cooling treatment data and learns new care methods.

[1527] The implementation of this system will significantly improve the efficiency of livestock health management. It will also enable real-time abnormality detection and rapid response, which is expected to reduce livestock health risks and improve production efficiency.

[1528] The processing flow will be explained below.

[1529] Step 1:

[1530] The device measures the livestock's biological data, such as body temperature, heart rate, and activity, every minute, and the data is temporarily stored in the internal storage.

[1531] Step 2:

[1532] Every fixed time (for example, every hour), the terminal sends the collected data to the server via wireless communication.

[1533] Step 3:

[1534] The server stores the received data in a database, with each data point being given a timestamp and the livestock's individual identification information.

[1535] Step 4:

[1536] The server analyzes the data in the database using machine learning algorithms, such as comparing body temperature values ​​with normal ranges to detect abnormalities.

[1537] Step 5:

[1538] If the server detects an anomaly, it generates an output result including the type of anomaly, details of the data that became abnormal, and recommended care methods as an anomaly detection result.

[1539] Step 6:

[1540] The server generates a notification message based on the anomaly detection result, which includes the livestock ID, details of the anomaly, and the required action.

[1541] Step 7:

[1542] The server sends a notification message to the user via the user's smartphone app, SMS, email, etc.

[1543] Step 8:

[1544] Users receive notifications and can check the condition of livestock on-site, for example, by taking cooling measures if the animals have a high body temperature.

[1545] Step 9:

[1546] The user inputs the care method and results into a dedicated app and sends the data to a server. Feedback data includes changes in body temperature and specific measures taken.

[1547] Step 10:

[1548] The server analyzes the received feedback data and evaluates the effectiveness of the care method. The evaluation results are added to a recommendation database and used to suggest future care methods.

[1549] Step 11:

[1550] Based on the updated recommendation database, the server will be prepared to suggest more appropriate care methods when abnormalities are detected in the future.

[1551] This program automates and streamlines livestock health management, enabling real-time abnormality detection and rapid response.

[1552] Example 1

[1553] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1554] Conventional livestock health management systems have problems in that they do not collect biological data or detect abnormalities in real time, and managers are not notified promptly when abnormalities are discovered. Furthermore, feedback and suggestions for care methods after abnormalities are detected are not provided efficiently, making it difficult to reduce livestock health risks. Furthermore, feedback from managers is not reflected in the system, meaning it cannot be used to suggest future care methods, resulting in ineffective use of data.

[1555] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1556] In this invention, the server includes means for acquiring livestock biometric data, means for storing the biometric data in internal storage at regular intervals and periodically transmitting it to the server, means for storing the biometric data in a database and analyzing it in real time using a machine learning algorithm to detect abnormalities, means for generating a notification message based on the abnormality detection result and notifying the manager, and means for receiving feedback from the manager and evaluating its effectiveness. This reduces livestock health risks, enables rapid response, and realizes improvements in care methods through feedback.

[1557] "Means for acquiring biological data of livestock" refers to devices that periodically acquire data such as body temperature, heart rate, and amount of exercise using sensors attached to livestock.

[1558] "Means for storing the biometric data in internal storage at regular intervals and periodically transmitting it to a server" refers to a device or function that temporarily stores the acquired biometric data in a storage medium and transfers the data to a server at regular time intervals.

[1559] "Means for storing the biometric data in a database, analyzing it in real time using a machine learning algorithm, and detecting abnormalities" refers to a device or function that records the received biometric data in a database, analyzes the data in real time using a machine learning model, and identifies abnormalities that deviate from the reference values.

[1560] "Means for generating a notification message based on the anomaly detection result and notifying the administrator" refers to a device or function that creates an appropriate warning message when an anomaly is detected and provides the information to the administrator via SMS, email, etc.

[1561] The "means for receiving feedback from the administrator and evaluating its effectiveness" refers to a device or function that collects information provided by the administrator and analyzes and evaluates the effectiveness of that information.

[1562] The "means for proposing a care method for livestock based on the abnormality detection result" is a device or function that provides an appropriate countermeasure for the detected abnormality.

[1563] "Means for evaluating the effectiveness of the proposed care method in real time and adding the results to the recommendation database" refers to a device or function that instantly analyzes the effectiveness of the proposed care method and adds the results to a database to be used for the next recommendation.

[1564] The present invention is a system for efficiently managing the health and behavior of livestock. This system includes sensors (terminals) for acquiring livestock biometric data, a server for storing and analyzing the data, and a system for notifying and providing feedback to managers.

[1565] System configuration

[1566] 1. Terminal

[1567] The terminals are sensors attached to livestock, which periodically collect biological data such as body temperature, heart rate, and activity level. The sensors used include body temperature sensors and heart rate sensors.

[1568] The acquired data is temporarily stored in the device's internal storage, specifically, using a storage device such as a microSD card or internal flash memory.

[1569] 2. Server

[1570] The server receives the biometric data sent from the terminal and stores it in a database.

[1571] The server uses machine learning algorithms to analyze data in real time and detect anomalies, using software such as MySQL or PostgreSQL as databases and Scikit-learn or TensorFlow as machine learning libraries.

[1572] If an anomaly is detected, the server generates an appropriate notification message and notifies the administrator via an SMS gateway service (e.g., Twilio) or an email service (e.g., SendGrid).

[1573] 3. Users

[1574] Users are livestock farmers and breeders. They receive notifications from the server, check the condition of their livestock on-site, and provide appropriate care.

[1575] The care method and results are entered into a dedicated app, which is provided as a smartphone app and sends the data via the internet to the server.

[1576] Specific examples

[1577] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[1578] 2. Every hour, the device sends the collected data to the server.

[1579] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[1580] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[1581] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[1582] 6. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[1583] 7. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[1584] 8. The server analyzes the cooling treatment data and learns new care methods.

[1585] Example prompts for generative AI models

[1586] "I would like to develop a system that measures the body temperature, heart rate, and amount of movement of livestock, and notifies the user if an abnormality is detected. Please tell me which technology I should use for the specific algorithm and notification method."

[1587] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1588] Step 1:

[1589] The device acquires biometric data such as body temperature, heart rate, and activity level of livestock. For example, a body temperature sensor measures body temperature every minute, and a heart rate sensor monitors heart rate in real time. This data is temporarily stored in the device's internal storage. The input is the livestock's biometric data, and the output is the measurement data stored in the device's internal storage device.

[1590] Step 2:

[1591] The device periodically transmits collected data to the server. For example, every hour, the data is transferred to the server using Wi-Fi or Bluetooth. The input is the measurement data stored in the internal storage, and the output is the data transmitted to the server. This includes the waiting process until communication is established.

[1592] Step 3:

[1593] The server stores the received data in a database. Database systems used include MySQL and PostgreSQL, for example. The input is the measurement data sent from the device, and the output is the biometric data stored in the database. This also involves converting the data format and eliminating invalid data.

[1594] Step 4:

[1595] The server uses machine learning algorithms to analyze the received biometric data in real time and detect abnormalities. The machine learning models used are, for example, Scikit-learn or TensorFlow. The input is the measurement data stored in the database, and the output is the results of anomaly detection. Specifically, anomalies are identified when body temperature exceeds 38.5°C or when the heart rate exceeds 100 beats per minute.

[1596] Step 5:

[1597] The server generates a notification message based on the anomaly detection result. For example, it generates a message such as "Livestock B has a high body temperature. Please take cooling measures." The input is the anomaly detection result, and the output is the generated notification message. A template-based approach is used to generate the message.

[1598] Step 6:

[1599] The server sends a notification message to the user, using an SMS gateway service (e.g., Twilio) or an email service (e.g., SendGrid) based on the user's notification preferences. The input is the generated notification message, and the output is the notification sent to the user.

[1600] Step 7:

[1601] The user receives the notification and takes appropriate action. For example, the user checks the notification, rechecks the animal's temperature on-site, and then uses a cooler to cool it down. The input is the notification sent, and the output is the action taken.

[1602] Step 8:

[1603] The user enters the care method and its results into a dedicated app and sends feedback to the server. The user logs into the dedicated app, enters the care method and results performed in the input form, and presses the send button to send the data to the server. The input is the care method performed and the results, and the output is the feedback sent to the server.

[1604] Step 9:

[1605] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. The feedback is analyzed using a machine learning algorithm to evaluate the effectiveness of new care methods. The input is user feedback, and the output is an updated recommendation database.

[1606] (Application example 1)

[1607] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1608] Modern factories operate many robots and machines, but it is difficult to efficiently manage their health and take appropriate action before an abnormality occurs. Furthermore, if an abnormality in a machine or robot is left unattended, there is a higher risk of reduced production efficiency and serious breakdowns. To solve these problems, a system is needed that can monitor the health of robots and machines in real time and respond quickly when an abnormality is detected.

[1609] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1610] In this invention, the server includes a means for acquiring motion data of an object, a means for storing the motion data in a database, and a means for analyzing the motion data and detecting abnormalities, thereby making it possible to monitor the health status of a robot or machine in real time and to respond quickly when an abnormality is detected.

[1611] "Objects" refer to robots and machines operating within the factory.

[1612] "Operational data" refers to data relating to the operating conditions of an object, such as its temperature, vibration, and operation patterns.

[1613] "Database" refers to an information system for storing and managing operational data.

[1614] "Analysis" refers to the process of evaluating acquired operational data to determine if there are any anomalies.

[1615] "Anomaly detection" refers to the discovery of values ​​or patterns in operational data that deviate from normal ranges.

[1616] "Output" refers to generating anomaly detection results as a report or notification message and conveying them to an administrator.

[1617] "Administrator" refers to the person in charge of operating and maintaining robots and machinery within the factory.

[1618] "Notification" refers to the act of sending the abnormality detection results to the administrator's smartphone, computer, etc.

[1619] "Feedback" refers to the data returned to the system regarding the measures taken by the administrator in response to an abnormality and the results of those measures.

[1620] "Care method" refers to the recommended repair and maintenance method for the object when an abnormality is detected.

[1621] A "recommendation database" refers to a database that accumulates effective care methods and suggests them the next time an abnormality is detected.

[1622] This invention is a system for efficiently managing the health status of robots and machines in a factory. This system includes sensors for acquiring operational data of objects, a server for storing and analyzing the data, and a system for notifying and providing feedback to an administrator. The implementation method of the system will be described in detail below.

[1623] System configuration

[1624] 1. Sensor (terminal)

[1625] The terminal is a sensor attached to a robot or machine in a factory. This periodically collects operational data such as the temperature, vibration, and movement patterns of the object. The collected data is temporarily stored in the terminal's internal storage.

[1626] 2. Server

[1627] The server receives the operational data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as when the robot's temperature is too high or when vibrations are abnormally strong.

[1628] 3. Administrator

[1629] The administrator is the person in charge of operating and maintaining the factory. When the server detects an abnormality, it sends a notification message to the administrator. The notification includes the type of abnormality and recommended care methods. The administrator receives the notification and can take action promptly.

[1630] Program processing flow

[1631] Data Acquisition Phase

[1632] The sensor (terminal) periodically collects data such as the temperature, vibration, and movement patterns of the robot or machine. For example, it measures the temperature every minute.

[1633] The acquired data is temporarily stored in the device's internal storage.

[1634] Data Transfer Phase

[1635] The sensor (terminal) periodically sends the collected data to the server, for example, every hour. The data is sent via wireless communication (Wi-Fi, Bluetooth, etc.).

[1636] Data analysis phase

[1637] The server stores the received data in a database and analyzes it in real time using machine learning algorithms to detect anomalies, such as when temperatures exceed normal limits.

[1638] Notification Phase

[1639] Based on the abnormality detection results, the server generates a message such as "Robot 1's temperature is too high. Please cool it down."

[1640] The server sends this notification message to the administrator, who is notified via their smartphone app, SMS, email, etc.

[1641] Feedback Phase

[1642] Administrators receive notifications, check the status of the robots and machines on-site, and implement appropriate care measures (e.g., cooling measures).

[1643] The care method performed and the results are entered into a dedicated app, and feedback is sent to the server.

[1644] The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. This updated data is then reflected in future care recommendations.

[1645] Specific examples

[1646] 1. The sensor (terminal) measures the temperature of Robot 1 every minute and saves the data in its internal storage.

[1647] 2. Every hour, the sensor (terminal) sends the collected data to the server.

[1648] 3. The server stores the data in a database and uses machine learning algorithms to detect temperature anomalies.

[1649] 4. The server detects that Robot 1's temperature is 31.0 degrees, which is high, and determines that there is a high risk of overheating.

[1650] 5. The server sends a notification to the administrator saying, "Robot 1's temperature is too high. Please cool it down."

[1651] 6. The administrator checks the notification and takes measures to cool Robot 1 (e.g., activates the cooling system).

[1652] 7. The administrator enters the results of the cooling measures into a dedicated app and sends them back to the server.

[1653] 8. The server analyzes cooling data and learns new maintenance methods.

[1654] Example prompt sentence:

[1655] "My robot is experiencing high temperatures and vibrations. What steps should I take to manage this situation?"

[1656] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1657] Step 1:

[1658] Data Acquisition Phase

[1659] The terminal periodically acquires operational data such as the temperature, vibration, and movement patterns of the robot or machine. For example, it measures the temperature every minute. The terminal temporarily stores the acquired data in its internal storage. The input of this process is the current status information of the object, and the output is the acquired operational data.

[1660] Step 2:

[1661] Data Transfer Phase

[1662] The device periodically (for example, every hour) transmits the collected operation data to the server. The data is transmitted via wireless communication (Wi-Fi, Bluetooth, etc.). The input of this process is the operation data stored on the device, and the output is the operation data transmitted to the server.

[1663] Step 3:

[1664] Data storage phase

[1665] The server stores the received operation data in a database. Specifically, it converts the received data into an appropriate format and records it in the database. The input of this process is the operation data sent from the terminal, and the output is the data stored in the database.

[1666] Step 4:

[1667] Data analysis phase

[1668] The server uses machine learning algorithms to analyze the operational data stored in the database in real time. For example, it detects abnormalities when the temperature exceeds the normal range or when vibrations are abnormally large. The input to this process is the operational data obtained from the database, and the output is the anomaly detection result.

[1669] Step 5:

[1670] Notification Phase

[1671] Based on the anomaly detection result, the server generates a message such as "Robot 1's temperature is too high. Please cool it down." The generated message is sent to the administrator. The input of this process is the anomaly detection result, and the output is the notification message sent to the administrator.

[1672] Step 6:

[1673] Care Delivery Phase

[1674] The administrator receives the notification, checks the status of the robot or machine on-site, and implements appropriate maintenance measures, such as turning on the cooling system. The input to this process is the notification message from the server, and the output is the result of the implemented maintenance measures.

[1675] Step 7:

[1676] Feedback Phase

[1677] The administrator enters the care methods and results into a dedicated app and sends feedback to the server. The server receives the feedback, evaluates its effectiveness, and updates the recommendation database. The input to this process is the feedback information from the administrator, and the output is an updated recommendation database.

[1678] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1679] This invention combines a system for efficiently managing the health and behavior of livestock with a function for recognizing the emotions of managers. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, and an emotion engine that recognizes the emotions of managers, in addition to processing notifications and feedback to managers.

[1680] System configuration

[1681] 1. Terminal

[1682] The terminal is a sensor attached to the livestock, which periodically collects biological data such as body temperature, heart rate, and amount of exercise. The collected data is temporarily stored in the terminal's internal storage.

[1683] 2. Server

[1684] The server receives the biometric data sent from the device and stores it in a database. The server then uses machine learning algorithms to analyze the data in real time and detect abnormalities, such as if the animal's body temperature is too high or its heart rate is abnormally high.

[1685] 3. Users

[1686] Users are livestock breeders and farmers. When the server detects an abnormality, it sends a notification message to the user. The notification includes the type of abnormality and recommended care methods. The user receives the notification and can take action promptly.

[1687] 4. Emotion Engine

[1688] The emotion engine is a module for recognizing the user's emotions, and identifies the user's emotional state by analyzing voice data and facial expression data acquired from the camera and microphone.

[1689] Program processing flow (explained in natural language)

[1690] Data Acquisition Phase

[1691] The device periodically collects data such as the animal's body temperature, heart rate, and activity level. For example, it measures body temperature every minute.

[1692] The acquired data is temporarily stored in the device's internal storage.

[1693] Data Transfer Phase

[1694] Periodically, for example, every hour, the terminal transmits the collected data to the server via wireless communication.

[1695] Data analysis phase

[1696] The server stores the received data in a database and analyzes it in real time using machine learning algorithms, for example, comparing body temperature values ​​with the normal range to detect abnormalities.

[1697] Emotion Recognition Phase

[1698] The emotion engine analyzes the user's voice and facial expression data to determine their current emotional state. For example, it analyzes images taken with a camera to determine whether the user is feeling stressed.

[1699] Notification Phase

[1700] Based on the anomaly detection results, the server generates a message such as "Livestock B's body temperature is high. Please take cooling measures."

[1701] The server will then send this notification message to the user via their smartphone app, SMS, email, etc.

[1702] Emotional Adaptation Phase

[1703] The emotion engine recognizes the user's emotions and adapts the notification content and care suggestions based on that emotion. For example, if the user is feeling stressed, the notification message will be more concise and easy to understand.

[1704] Feedback Phase

[1705] Users receive notifications, go to the scene to check the condition of the livestock, and implement appropriate care measures (e.g., cooling measures).

[1706] The care methods and results are entered into a dedicated app, and feedback is sent to the server, including changes in body temperature and specific measures taken.

[1707] Feedback Analysis Phase

[1708] The server analyzes the received feedback data and evaluates the effectiveness of the care method. The evaluation results are added to a recommendation database and used to suggest future care methods.

[1709] The emotion engine also receives feedback data and reflects the emotion-adapted feedback data in the recommendation database.

[1710] Specific examples

[1711] 1. The device measures the body temperature of livestock A every minute and stores the data in its internal storage.

[1712] 2. Every hour, the device sends the collected data to the server.

[1713] 3. The server stores the data in a database and uses machine learning algorithms to detect abnormalities in body temperature.

[1714] 4. The server detects that Livestock A's body temperature is high at 39.0 degrees and determines that there is a high risk of heatstroke.

[1715] 5. The server sends a notification to the user saying, "Livestock A's body temperature is high. Please take cooling measures."

[1716] 6. The emotion engine recognizes that the user is feeling stressed through facial recognition and voice analysis.

[1717] 7. The server tailors notification messages to be concise and clear.

[1718] 8. The user confirms the notification and takes measures to cool down Livestock A, such as using a cooling fan.

[1719] 9. The user enters the results of the cooling measures into a dedicated app and sends them back to the server.

[1720] 10. The server analyzes the cooling data and learns new care methods.

[1721] 11. The emotion engine also analyzes user feedback and reflects it in improving the entire system.

[1722] This system not only significantly improves the efficiency of livestock health management, but also makes it possible to propose care methods that take into account the emotions of managers, which is expected to reduce user stress and help create a better livestock farming environment.

[1723] The processing flow will be explained below.

[1724] Step 1:

[1725] The device measures the livestock's biological data, such as body temperature, heart rate, and activity, every minute, and the measured data is temporarily stored in the device's internal storage.

[1726] Step 2:

[1727] Every fixed time (for example, every hour), the terminal sends the collected data to the server using wireless communication (Wi-Fi, Bluetooth, etc.).

[1728] Step 3:

[1729] The server stores the received biometric data in a database, and when stored, each data item is given a timestamp and the livestock's individual identification information.

[1730] Step 4:

[1731] The server uses machine learning algorithms to analyze the data in the database in real time and detect abnormalities, such as when a person's body temperature exceeds the normal range.

[1732] Step 5:

[1733] The emotion engine analyzes the user's voice data and facial expression data to identify their current emotional state, for example by analyzing images and audio captured by the user's smartphone camera.

[1734] Step 6:

[1735] The server generates an output result including the type of anomaly, details of the anomaly data, and recommended care methods as anomaly detection results.

[1736] Step 7:

[1737] An emotion engine optimizes notification content based on the user's emotional state. For example, if the user is stressed, the message will be formatted succinctly and clearly.

[1738] Step 8:

[1739] The server generates an optimized notification message and sends it to the user via a smartphone app, SMS, email, etc.

[1740] Step 9:

[1741] Users can receive notifications and check the condition of livestock on-site, for example, by taking measures to cool down livestock with high body temperatures.

[1742] Step 10:

[1743] The user enters the care method and results into a dedicated app, and feedback data, including changes in body temperature and specific measures taken, is sent to a server.

[1744] Step 11:

[1745] The server analyzes the received feedback data, evaluates the effectiveness of the care method, and adds the evaluation results to the recommendation database.

[1746] Step 12:

[1747] The emotion engine also analyzes emotional feedback from users to improve notifications and care suggestions, and this data is reflected in the recommendation database.

[1748] Step 13:

[1749] Based on the updated recommendation database, the server will be prepared to suggest more appropriate care methods the next time an abnormality is detected.

[1750] This process flow allows for efficient and effective livestock health management and provides support that takes into account the emotions of managers, thereby reducing livestock health risks and easing the burden on managers.

[1751] Example 2

[1752] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1753] While conventional livestock management systems can acquire livestock biometric data and detect abnormalities, they lack the ability to recognize the emotions of managers and lack the means to reduce manager stress and burden. As a result, managers can sometimes become overly stressed, making it difficult to implement appropriate care methods. Another issue is that feedback is not fully utilized, preventing improvements to care methods.

[1754] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing biometric data of livestock in a database, a means for analyzing the biometric data and detecting abnormalities, and a means for recognizing the emotions of the manager from voice data and facial expression data. This makes it possible to provide appropriate notification content according to the manager's emotional state and to quickly and effectively suggest livestock care methods based on the abnormality detection results. In addition, by analyzing feedback from the manager and reflecting it in the next proposal, it is possible to continuously improve the care methods.

[1755] "Livestock" is a general term for animals kept in captivity, and refers primarily to animals used in agriculture and animal husbandry.

[1756] "Biometric data" refers to information related to the vital activities of livestock, such as body temperature, heart rate, and amount of movement.

[1757] A "database" refers to a system for efficiently managing, searching, and storing large amounts of data.

[1758] "Analysis" refers to the method of processing acquired data to find specific patterns or anomalies.

[1759] "Abnormal" refers to a value or condition that deviates from the normal range, indicating that something unusual has happened to the health of livestock.

[1760] "Voice data" refers to data that records information about the voice of the administrator.

[1761] "Facial expression data" refers to information obtained from the facial expression of an administrator and is used to determine the administrator's emotional state.

[1762] "Emotion recognition" refers to technology that identifies the current emotional state of a manager based on voice and facial expression data.

[1763] "Notification" refers to a message sent to notify an administrator when an abnormality is detected.

[1764] "Feedback" refers to the administrator returning information to the system about the care methods implemented and their results.

[1765] "Care methods" refer to the specific countermeasures and treatments implemented for livestock in which abnormalities are detected.

[1766] A "recommendation database" refers to a database that will be used for future proposals based on analysis results and feedback information.

[1767] This invention combines a system for efficiently managing the health and behavior of livestock with a function for recognizing the emotions of managers. The system includes sensors (terminals) that acquire biometric data from livestock, a server that stores and analyzes the data, a system that processes notifications and feedback to managers, and an emotion engine that recognizes the emotions of managers.

[1768] Specific system configuration

[1769] Terminal

[1770] The terminals are sensors attached to livestock and collect biometric data such as body temperature, heart rate, and exercise volume.

[1771] The acquired data is temporarily stored in the device's internal storage.

[1772] Examples:

[1773] The body temperature of livestock A is measured every minute and the data is stored in the internal storage.

[1774] server

[1775] The server receives the data sent from the terminal and stores it in a database.

[1776] The server uses machine learning algorithms to analyze the received data in real time and detect anomalies.

[1777] Examples:

[1778] The server stores the body temperature data of livestock A in a database and uses a machine learning algorithm to detect abnormalities in body temperature.

[1779] User

[1780] Users are livestock breeders and farmers.

[1781] If the server detects an anomaly, a notification message is sent to the user.

[1782] Examples:

[1783] A notification is sent to the user saying, "Livestock A has a high body temperature. Please take cooling measures."

[1784] Emotion Engine

[1785] The emotion engine identifies the user's emotional state by analyzing voice data and facial expression data.

[1786] Data is collected using a camera and microphone to recognize emotional states.

[1787] Examples:

[1788] The emotion engine analyzes the user's camera image and determines that the user is feeling stressed.

[1789] Detailed example of system operation

[1790] The device measures the body temperature of Livestock A every minute and stores the data in its internal storage. Every hour, the device sends the collected data to a server. The server stores the data in a database and uses a machine learning algorithm to detect abnormalities in body temperature. The server detects that Livestock A's body temperature is high at 39.0°C and determines that there is a high risk of heatstroke. The server sends a notification to the user stating, "Livestock A's body temperature is high. Please take cooling measures."

[1791] The emotion engine recognizes that the user is feeling stressed through facial recognition and voice analysis. The server adjusts the notification message to be concise and clear, stating, "Temperature is high. Cooling is required." The user confirms the notification and takes measures to cool down Livestock A. For example, they may use a cooling fan. The user enters the results of the cooling measures into a dedicated app and sends them back to the server. The server analyzes the cooling measures data and learns new care methods. The emotion engine also analyzes user feedback data and reflects it in improvements to the system as a whole.

[1792] This system not only significantly improves the efficiency of livestock health management, but also makes it possible to propose care methods that take into account the emotions of the manager, which is expected to reduce user stress and create a better livestock farming environment.

[1793] Prompt Sentence Examples

[1794] Please propose an AI solution that adds a function to the system to periodically collect biological data such as body temperature, heart rate, and amount of exercise of livestock, and notify if an abnormality is detected. Also, please incorporate a function to recognize the emotions of managers and design it to reduce stress by adjusting the content of notifications.

[1795] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1796] Step 1: Start acquiring data

[1797] The device collects biometric data such as body temperature, heart rate, and activity level from sensors attached to the livestock every minute.

[1798] Input: Livestock body temperature, heart rate, and activity

[1799] Data processing: The sensor operates to acquire and store biometric data, and the acquired data is temporarily stored in the internal storage.

[1800] Output: Biometric data stored in storage

[1801] Specific operation: Data is obtained showing that livestock A's body temperature is 37.5 degrees and its heart rate is 80 bpm.

[1802] Step 2: Data verification

[1803] The device performs a simple check to ensure the acquired biometric data is accurate and free of any abnormalities.

[1804] Input: Captured biometric data

[1805] Data processing: Noise filtering and data shaping.

[1806] Output: Clean data after filtering

[1807] Specific operation: If the acquired data contains noise, the noise is removed.

[1808] Step 3: Prepare for data transfer

[1809] Every hour, the device compiles the stored data and prepares it for transmission.

[1810] Input: Filtered biometric data

[1811] Data processing: Batch processing is used to combine one hour's worth of data into a single transmission packet.

[1812] Output: Outgoing packets

[1813] Specific operation: Compress one hour's worth of data and prepare it for transfer.

[1814] Step 4: Send data

[1815] The terminal transmits the collected data to the server via wireless communication.

[1816] Input: Outgoing packets

[1817] Data processing: Sending data via wireless communication using a data transmission protocol.

[1818] Output: Data sent to the server

[1819] Specific operation: Transfer data to the server using Bluetooth or Wi-Fi.

[1820] Step 5: Receiving Data

[1821] The server receives the data sent from the terminal.

[1822] Input: Data sent

[1823] Data processing: Decodes the received data and converts it into a format suitable for storing in the database.

[1824] Output: Data stored in a database

[1825] Specific operation: The server receives the data and stores it in the database as "body temperature data of livestock A."

[1826] Step 6: Data analysis

[1827] The server analyzes the stored data in real time using machine learning algorithms to detect anomalies.

[1828] Input: Biometric data stored in a database

[1829] Data processing: Using machine learning models, we run anomaly detection algorithms.

[1830] Output: Anomaly detection results

[1831] Specific behavior: Generates an alert if the body temperature exceeds 39.0 degrees.

[1832] Step 7: Acquire voice and facial expression data

[1833] The emotion engine acquires voice data and facial expression data from the administrator (user) via a camera or microphone.

[1834] Input: Camera image and audio recording

[1835] Data processing: Analyzes voice data and extracts facial expression data from images.

[1836] Output: Administrator's emotional state data

[1837] What it does: It records what the user says in front of the camera and analyzes the images to determine their emotional state.

[1838] Step 8: Emotion Recognition Analysis

[1839] The emotion engine analyzes the captured voice and facial expression data to identify the user's current emotional state.

[1840] Input: Administrator emotional state data

[1841] Data processing: Integrate audio and image data and classify emotional states using emotion recognition models.

[1842] Output: Emotion recognition result

[1843] Specific operation: Based on microphone recordings and camera images, it determines whether the user is in a "stressed state."

[1844] Step 9: Generate notification message

[1845] Based on the anomaly detection results and emotion recognition results, the server generates a notification message such as, "Livestock B's body temperature is high. Please take cooling measures."

[1846] Input: Anomaly detection results and emotion recognition results

[1847] Data processing: Generate notification messages and customize them according to the emotional state.

[1848] Output: Information message

[1849] Specific action: The notification content will be concise, such as "High body temperature. Cool down immediately."

[1850] Step 10: Send notification

[1851] The server generates a notification message and sends it to the user.

[1852] Input: Notification message

[1853] Data processing: Send notifications to the user's device using messaging protocols.

[1854] Output: The notification message displayed on the user's device

[1855] Specific behavior: Sends notifications to the user's smartphone via SMS or email.

[1856] Step 11: Adjust notification content

[1857] An emotion engine adapts notification content to be more concise and understandable based on the user's emotional state.

[1858] Input: Emotion recognition results

[1859] Data processing: Adjust the notification wording to simplify it and reduce stress.

[1860] Output: The adjusted notification message

[1861] Specific action: Change "The livestock has a high body temperature. Please take measures to cool them down." to "High body temperature. Rapid cooling."

[1862] Step 12: Care Delivery

[1863] The user checks the notification and checks the condition of the livestock on-site, and if necessary, takes cooling measures such as using a cooling fan.

[1864] Input: Notification message and field data

[1865] Data processing: After checking the condition, select and implement appropriate measures.

[1866] Output: Care implementation results

[1867] Specific action: Cools livestock using a cooling fan until their body temperature drops to 38.0°C.

[1868] Step 13: Enter feedback

[1869] The user enters the care method and results into a dedicated app and sends them as feedback to the server.

[1870] Input: Care implementation results

[1871] Data processing: The feedback data is formatted and sent to the server.

[1872] Output: Feedback data sent to the server

[1873] Specific operations: Enter changes in body temperature after cooling measures have been implemented into the app.

[1874] Step 14: Feedback analysis

[1875] The server analyzes the received feedback data and evaluates the effectiveness of the care method.

[1876] Input: Feedback data

[1877] Data processing: Evaluate the effectiveness of care methods through data analysis.

[1878] Output: Evaluation result

[1879] Specific actions: Based on the results of the cooling measures, we recommend the same method next time.

[1880] Step 15: Reflecting Emotional Feedback

[1881] The emotion engine also receives user feedback data and reflects it in improving the overall system.

[1882] Input: Feedback data and emotion recognition results

[1883] Data processing: Analyze the feedback data and reflect it in the next notification method.

[1884] Output: Improved system profile

[1885] Specific actions: Learn specific notification methods to reduce stress and reflect them in the next notification method.

[1886] (Application example 2)

[1887] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1888] In modern factories, it is important to constantly monitor the health of equipment and detect abnormalities early. However, conventional systems have difficulty taking into account the emotions and stress levels of managers. This can hinder a prompt and effective response after an abnormality is detected. Another problem is that inaccurate notifications increase the burden on managers. Therefore, the objective of this invention is to not only monitor equipment and detect abnormalities, but also recognize the emotions of managers and adjust the content of notifications according to their emotions, thereby making it easier to respond after an abnormality is discovered.

[1889] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1890] In this invention, the server includes means for acquiring biological data of livestock, means for saving the data in a database, means for analyzing the data and detecting abnormalities, means for outputting abnormality detection results, means for notifying a manager of the output results, means for receiving and evaluating feedback from the manager, means for recognizing the manager's emotions, and means for adjusting notification content based on the manager's emotions. This makes it possible to detect equipment abnormalities early, provide appropriate notifications and propose care methods according to the manager's emotional state, and achieve rapid and effective response.

[1891] "Livestock biological data" refers to physiological information such as livestock body temperature, heart rate, and amount of exercise.

[1892] A "database" is an information management system for organizing and storing acquired data.

[1893] "Analysis" is the process of calculation and evaluation using acquired data to detect anomalies or find specific patterns or trends.

[1894] "Abnormality detection results" refer to unusual conditions or problems that are discovered through analysis.

[1895] "Notification" is a means of informing an administrator of abnormality detection results and other important information.

[1896] "Feedback" refers to returning information to the system about the actions taken by the administrator and their results.

[1897] "Administrator emotion recognition" is a technology that identifies the emotional state of an administrator from their facial expressions and voice.

[1898] "Adjusting notification content" refers to changing the content and expression of notifications depending on the administrator's emotional state.

[1899] "Proposing care methods" refers to proposing to the manager the measures and procedures that should be implemented when an abnormality is found.

[1900] The embodiment of the present invention requires a specific configuration and operation of a system for monitoring the health status of factory equipment. The system is composed of the following main components:

[1901] Device:

[1902] The terminals are sensors placed on each piece of equipment in the factory, and periodically collect data on the equipment's temperature, vibration, operating status, etc. The data collected from the sensors is temporarily stored in the terminal's internal storage. This terminal includes hardware such as high-precision sensors, and communicates data with the server using a wireless communication module.

[1903] server:

[1904] The server receives the biometric data sent from the device and stores it in a database. The server is equipped with a machine learning algorithm that analyzes the data in real time and detects anomalies. Machine learning libraries such as TensorFlow and Keras are used for anomaly detection. If an anomaly is detected, the server outputs it and notifies the administrator.

[1905] User:

[1906] The user is the factory manager. When the server detects an abnormality, it sends a notification message to the user. This notification is sent via a smartphone app or smart glasses. The notification includes the type of abnormality and how to deal with it. Feedback from the user is also important, and the actions taken and their results are sent back to the server via a dedicated app.

[1907] Emotion Engine:

[1908] The emotion engine is a module for recognizing the emotions of administrators. It analyzes the administrator's facial expressions and voice data to identify their emotional state. For example, the emotion engine uses facial recognition technology from OpenCV and emotion recognition models from TensorFlow / Keras. Based on the recognized emotions, the content of notifications is adjusted and appropriate countermeasures are proposed according to the administrator's condition.

[1909] Natural language description of program processing:

[1910] 1. Data Acquisition Phase:

[1911] The device periodically collects data such as temperature and vibration of factory equipment and stores it in its internal storage.

[1912] 2. Data transfer phase:

[1913] The terminal transmits the collected data to the server, for example, every hour, using wireless communication.

[1914] 3. Data analysis phase:

[1915] The server analyzes the data stored in the database and detects outliers using machine learning algorithms.

[1916] 4. Emotion Recognition Phase:

[1917] Using a camera on a smartphone or smart glasses, the manager's facial expressions are captured and input into an emotion recognition model to identify their emotional state.

[1918] 5. Notification Phase:

[1919] The server generates notification messages based on the anomaly detection results and sends them to administrators, whose notifications are tailored according to the administrator's emotional state.

[1920] For example, if the temperature of a factory machine suddenly rises, the system will detect the abnormality and send a notification to the manager saying, "The temperature of the equipment is high. Please take measures to cool it down immediately." If the emotion engine recognizes that the manager is feeling stressed, it will simplify the notification to say, "An equipment abnormality has occurred. Please cool it down." After the manager takes measures, they enter their feedback into a dedicated app and send it to the server. The server will analyze this feedback and use it to make future suggestions.

[1921] Example prompts to input to the generative AI model:

[1922] "Please support the design and implementation of a smartphone app that monitors the health of factory equipment, detects abnormalities, and adjusts notification content based on the manager's emotions."

[1923] This configuration makes it possible to detect abnormalities in factory equipment and to respond quickly and appropriately according to the feelings of the manager.

[1924] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1925] Step 1:

[1926] The device periodically collects data such as temperature, vibration, and operating status using sensors installed in the factory equipment, and this data is temporarily stored in the device's internal storage.

[1927] Input: Various sensor data from factory equipment (temperature, vibration, operating status)

[1928] Output: Local storage of acquired sensor data

[1929] Specific operation: High-precision sensors measure the equipment status and store the data in the terminal memory. For example, temperature data is acquired every minute and recorded in storage.

[1930] Step 2:

[1931] The terminal transmits the collected data every hour to the server via wireless communication.

[1932] Input: Sensor data stored on the device

[1933] Output: Sensor data sent to the server

[1934] Specific operation: Using the wireless communication module, the device uploads data to the server in bulk once per hour, using communication methods such as Bluetooth and Wi-Fi.

[1935] Step 3:

[1936] The server stores the received data in a database and uses machine learning algorithms to analyze the data in real time and detect anomalies.

[1937] Input: Sensor data sent to the server

[1938] Output: Anomaly detection results

[1939] How it works: Using machine learning libraries such as TensorFlow and Keras, it constantly analyzes the acquired data and detects abnormalities when temperature or vibrations fall within an abnormal range. For example, it determines that an abnormality exists when the temperature exceeds 80°C.

[1940] Step 4:

[1941] The server generates a notification message based on the anomaly detection results and sends it to the administrator's smartphone app or smart glasses.

[1942] Input: Anomaly detection results

[1943] Output: Notification message to administrator

[1944] Specific behavior: The server generates an appropriate notification based on the type of abnormality and sends it to the administrator's device, for example, a message saying "The temperature of the equipment is high. Please take measures to cool it down."

[1945] Step 5:

[1946] The emotion engine uses the camera on the administrator's smartphone or smart glasses to capture and analyze the administrator's facial expressions and voice data to understand their emotional state.

[1947] Input: Administrator's facial expression data, voice data

[1948] Output: Emotional state of the administrator

[1949] How it works: Facial recognition technology using OpenCV and emotion recognition models using TensorFlow / Keras identify emotions from the manager's facial expressions and voice. For example, it determines whether the manager is feeling stressed.

[1950] Step 6:

[1951] Once the administrator's emotional state is determined, the server tailors the notification content based on the administrator's emotional state and, if necessary, streamlines the process.

[1952] Input: Administrator's emotional state

[1953] Output: The adjusted notification message

[1954] Specific behavior: If the emotional state indicates stress, simplify the notification message. For example, omit detailed explanations and send a simple message such as "Equipment abnormality. Please cool down."

[1955] Step 7:

[1956] The user receives a notification, takes appropriate measures, and feeds the results back to the server via a dedicated app.

[1957] Input: Administrator response result

[1958] Output: Feedback data

[1959] Specific operation: The administrator implements cooling measures and inputs the results (e.g., whether the temperature has dropped) into a dedicated app. The feedback data is sent to the server.

[1960] Step 8:

[1961] The server analyzes the feedback data, evaluates the effectiveness of the care methods, and updates the recommendation database.

[1962] Input: Feedback data

[1963] Output: Updated recommendation database

[1964] Specific operation: The server analyzes the feedback data and evaluates the effectiveness of the proposed care method. The evaluation results are added to the recommendation database to be used for future recommendations.

[1965] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1966] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1967] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1968] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1969] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1970] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1971] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1972] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1973] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1974] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1975] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1976] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1977] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1978] 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.

[1979] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1980] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1981] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1982] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1983] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1984] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1985] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1986] The following is further disclosed regarding the above embodiment.

[1987] (Claim 1)

[1988] a means for acquiring livestock biometric data;

[1989] means for storing the biometric data in a database;

[1990] means for analyzing the biological data and detecting abnormalities;

[1991] means for outputting an abnormality detection result;

[1992] means for notifying an administrator of the output result;

[1993] A system that includes a means of receiving and evaluating feedback from management.

[1994] (Claim 2)

[1995] The system of claim 1 , further comprising means for suggesting a care method for livestock based on the anomaly detection result.

[1996] (Claim 3)

[1997] 10. The system of claim 1, further comprising means for evaluating the effectiveness of the care suggestions in real time and adding the results to a recommendation database.

[1998] "Example 1"

[1999] (Claim 1)

[2000] a means for acquiring livestock biometric data;

[2001] means for storing the biometric data in an internal storage at regular intervals and periodically transmitting the biometric data to a server;

[2002] a means for storing the biological data in a database and analyzing the biological data in real time using a machine learning algorithm to detect abnormalities;

[2003] a means for generating a notification message based on the anomaly detection result and notifying the administrator;

[2004] A system that includes a means of receiving feedback from management and evaluating its effectiveness.

[2005] (Claim 2)

[2006] The system of claim 1 , further comprising means for suggesting a care method for livestock based on the anomaly detection result.

[2007] (Claim 3)

[2008] 10. The system of claim 1, further comprising means for evaluating the effectiveness of the care suggestions in real time and adding the results to a recommendation database.

[2009] "Application Example 1"

[2010] (Claim 1)

[2011] means for acquiring motion data of an object;

[2012] means for storing said operational data in a database;

[2013] means for analyzing the operational data and detecting an abnormality;

[2014] means for outputting an abnormality detection result;

[2015] means for notifying an administrator of the output result;

[2016] A system that includes a means of receiving and evaluating feedback from management.

[2017] (Claim 2)

[2018] The system according to claim 1 , further comprising: means for suggesting a care method for the object based on the abnormality detection result.

[2019] (Claim 3)

[2020] 10. The system of claim 1, further comprising means for evaluating the effectiveness of the care suggestions in real time and adding the results to a recommendation database.

[2021] "Example 2: Combining Emotion Engines"

[2022] (Claim 1)

[2023] a means for acquiring livestock biometric data;

[2024] means for storing the biometric data in a database;

[2025] means for analyzing the biological data and detecting abnormalities;

[2026] means for outputting an abnormality detection result;

[2027] means for notifying an administrator of the output result;

[2028] A means for recognizing the emotions of the administrator from voice data and facial expression data;

[2029] means for adapting notification content based on the emotional state of the administrator;

[2030] A system that includes a means of receiving and evaluating feedback from management.

[2031] (Claim 2)

[2032] The system according to claim 1, further comprising means for suggesting a care method for livestock based on the abnormality detection result.

[2033] (Claim 3)

[2034] 10. The system of claim 1, further comprising means for evaluating the effectiveness of the care suggestions in real time and adding the results to a recommendation database.

[2035] "Application example 2 when combining emotion engines"

[2036] (Claim 1)

[2037] a means for acquiring livestock biometric data;

[2038] means for storing the biometric data in a database;

[2039] means for analyzing the biological data and detecting abnormalities;

[2040] means for outputting an abnormality detection result;

[2041] means for notifying an administrator of the output result;

[2042] a means of receiving and evaluating feedback from management;

[2043] a means of recognizing the manager's emotions;

[2044] The system includes means for adjusting notification content based on the manager's emotions.

[2045] (Claim 2)

[2046] a means for proposing a care method for livestock based on the abnormality detection result;

[2047] 10. The system of claim 1, further comprising means for evaluating the effectiveness of the proposed care methods in real time and adding the results to the recommendation database.

[2048] (Claim 3)

[2049] 10. The system of claim 1, further comprising means for adjusting care suggestions based on manager sentiment and for making notifications concise and clear. [Explanation of symbols]

[2050] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for acquiring livestock biometric data; means for storing the biometric data in a database; means for analyzing the biological data and detecting abnormalities; means for outputting an abnormality detection result; means for notifying an administrator of the output result; A system that includes a means of receiving and evaluating feedback from management.

2. The system according to claim 1 , further comprising means for suggesting a care method for livestock based on the abnormality detection result.

3. The system of claim 1 , further comprising means for evaluating the effectiveness of the care suggestions in real time and adding the results to a recommendation database.

Images