System

Abstract

A system is provided.SOLUTION: A system comprising: means for photographing an approaching animal by a camera; means for transmitting an image to a server; means for identifying the animal in the image by the server; means for determining an image and a sound that the animal is weak at based on the identified animal; means for displaying the determined image on a display; and means for reproducing the determined sound from a speaker.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] Farmers' crops are often severely damaged by various pests. Traditional scarecrows and other physical protection measures are only effective temporarily and lack the flexibility to deal with different types of pests. Furthermore, implementing effective measures against a wide variety of pests is expensive. Therefore, new methods are needed to continuously and effectively protect crops from a wide range of pests. [Means for solving the problem]

[0005] The present invention provides a system that uses a camera to capture images of approaching animals and transmits the images to a server. The server then identifies the animal in the image and, based on the identified animal, determines images and sounds that the animal dislikes. These images are displayed on a display and sounds are played through a speaker to scare off pests and prevent them from invading crops. A pre-trained artificial intelligence model is used to identify animals, and the determined images and sounds are retrieved from a database pre-configured for each type of animal. This enables effective protection against a wide variety of pests, ensuring long-term and economical crop protection.

[0006] A "camera" is a device used to photograph approaching animals.

[0007] A "server" is a central computing device that receives and analyzes captured images.

[0008] "Image" refers to visual data of an animal captured by a camera.

[0009] "Animals" are living organisms that can cause damage to crops.

[0010] "Identification" is the process of determining the type of animal based on the transmitted image.

[0011] A "display" is a display device for displaying the determined image.

[0012] A "speaker" is an acoustic device for reproducing a determined sound.

[0013] An "artificial intelligence model" is a data analysis program that has been pre-trained to identify animal species.

[0014] The "database" is a collection of information that stores image and sound information that is preset in correspondence with the type of animal.

[0015] "Determining images and sounds" refers to the process of selecting images and sounds that an animal dislikes based on the identified animal. [Brief explanation of the drawings]

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

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

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

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

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

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

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0037] The present invention is a system in which a terminal installed in farmland uses a camera to capture images of approaching animals and transmits the images to a server. The server analyzes the transmitted images and identifies the type of animal. Next, based on the identified animal, it determines the images and sounds that the animal dislikes and transmits a response to the terminal. Based on the received response, the terminal displays the image on its display and plays the sound from its speaker. This system can effectively protect crops from a wide variety of pests.

[0038] Specific program processing explanation

[0039] Server Initialization

[0040] The server loads the artificial intelligence model and distributes it to the terminal.

[0041] When a user initially configures the system, the server loads the trained AI model (animal_recognition_model) and distributes it to all devices, enabling each device to recognize animals.

[0042] Animal recognition by device

[0043] The device uses a camera to capture images of the animals and send them to the server.

[0044] The device periodically captures images of its surroundings using a camera. For example, an image is taken once per second, and the captured images are sent to a server. This allows the server to perform real-time image analysis on devices installed in remote locations.

[0045] Server-based animal identification

[0046] The server analyzes the image and identifies the type of animal.

[0047] The server analyzes the received images using an artificial intelligence model to identify the type of animal depicted in the image.

[0048] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0049] Based on the identified animal, the server selects images and sounds that the animal fears from a database and sends this information to the device, causing the animal to feel fear.

[0050] Terminal display of responses

[0051] The terminal plays the images and sounds received from the server.

[0052] The device displays the image received from the server on the display and simultaneously plays sound from the speaker, effectively scaring away animals.

[0053] Specific examples

[0054] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0055] Device animal recognition:

[0056] The device captures an image of the rabbit with its camera and sends the image to the server.

[0057] Server-based animal identification:

[0058] The server analyzes the received image and identifies the animal as a rabbit.

[0059] Server response generation:

[0060] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0061] Terminal display of response:

[0062] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0063] This prevents rabbits from approaching crops, protecting them. This system can be remotely controlled and is effective against a wide range of pests, making it a highly effective agricultural protection tool.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] Server Initialization

[0067] The server loads the artificial intelligence model (animal_recognition_model) and distributes it to each device. This initial setup prepares the device to recognize animals.

[0068] Step 2:

[0069] Animal detection by device

[0070] The device uses a camera to periodically capture images of its surroundings, for example, once per second, to monitor for approaching animals.

[0071] Step 3:

[0072] Sending images by device

[0073] The captured image is immediately uploaded to the server, allowing the server to perform image analysis in real time.

[0074] Step 4:

[0075] Server-based animal identification

[0076] The server then uses an artificial intelligence model to analyze the received images and identify the type of animal that is present in the image, which then identifies which animal is approaching.

[0077] Step 5:

[0078] Server decides what to do

[0079] Based on the identified animal type, the server determines the images and sounds that the animal dislikes, which information is obtained from a pre-defined database.

[0080] Step 6:

[0081] Server Response Generation

[0082] The server generates response data containing images and sounds that the animal dislikes, and sends it to the device. This data is then formatted in a format that the device can accept.

[0083] Step 7:

[0084] Displaying images by device

[0085] The device displays the image received from the server on its display, creating a visual threat to the animals.

[0086] Step 8:

[0087] Playing sounds through the device

[0088] The device receives the sound from the server and plays it back through the speaker, creating an auditory threat to the animals.

[0089] Step 9:

[0090] Observing pest behavior

[0091] Users can view logs on their devices and on the server to see which animals responded and how they reacted, allowing them to assess the effectiveness of the system and make adjustments as needed.

[0092] Example 1

[0093] 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."

[0094] There is a need for an effective method to repel animals that damage crops in agricultural fields. Conventional methods have difficulty in quickly taking different countermeasures depending on the type of animal, and there is a lack of systems that allow remote control. This has led to the problem of not being able to prevent animal damage in a timely manner.

[0095] 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.

[0096] In this invention, the server includes means for taking pictures of approaching animals with a camera, means for transmitting the images to the server, means for identifying the animals in the images by the server, means for determining images and sounds that the animals dislike based on the identified animals, means for displaying the determined images on a display, and means for playing the determined sounds from a speaker. This makes it possible to identify animals in real time and instantly scare them away using appropriate images and sounds.

[0097] A "camera" is a device that captures images of the surroundings and outputs them as image data.

[0098] A "server" is a computer system that receives requests from client terminals via a network and processes them.

[0099] An "image" is a digital representation of visual information captured by a camera.

[0100] "Animals" refers to a group of living organisms that have a specific behavior, and in the present invention refers to organisms that may cause damage to agricultural land.

[0101] An "artificial intelligence model" is a set of pre-trained algorithms used to analyze input data and make decisions.

[0102] A "terminal" is an electronic device that can be connected to a network and communicates with a server.

[0103] A "display" is an output device for displaying images and videos.

[0104] A "speaker" is an output device for reproducing voice or sound.

[0105] A "database" is a collection of data and a system that enables efficient search and retrieval of data.

[0106] "Recognition" is the process of identifying a specific object from input image data.

[0107] The present invention is a system that uses a terminal installed in farmland to detect the approach of animals and respond appropriately. This system is realized by combining a camera, a server, a display, a speaker, and an artificial intelligence model.

[0108] First, when the user initially configures the system, the server loads a trained artificial intelligence model (animal_recognition_model) and distributes it to each device. This model is a group of algorithms for identifying animal species, and through training it is possible to achieve highly accurate identification.

[0109] The device is then installed in the field and periodically captures images of the surrounding area with its camera. This image data is then sent to the server at intervals of, for example, once per second. The transmission protocol is HTTP POST, and the image data is sent in binary format.

[0110] The server then calls an AI model running on a Python script to analyze the received image. The AI ​​model analyzes the image provided as input and identifies the type of animal depicted in the image. The identification result is expressed as a probability, and is returned in the form of, for example, "80% probability that it is a rabbit."

[0111] Based on the identified animal, the server selects images and sounds that the animal dislikes from a database containing pre-defined image and sound pairs for each animal type. Once the appropriate images and sounds are selected, they are sent to the device.

[0112] The device displays the received image on the screen and plays a sound from the speaker at the same time, which scares the animals and makes them leave the field, preventing them from damaging crops.

[0113] As a concrete example of this system, consider the case where a device installed in a farm recognizes a rabbit using a camera. In this case, the device captures an image of the rabbit with its camera and sends it to the server. The server analyzes the received image and identifies it as a rabbit. The server then selects an image of an eagle, which rabbits are afraid of, and the sound of a dog barking, and sends these to the device. The device displays the received image of the eagle on its display and plays the sound of a dog barking from its speaker, thereby scaring away the rabbit.

[0114] An example prompt might be, "Please explain how to identify the type of animal recognized by a camera-equipped device installed in farmland, determine the image and sound to scare the animal away, and send them to the device."

[0115] As a result, this system can be remotely controlled and is a highly effective means of protecting farmland against a wide range of pests.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1:

[0118] The server loads the artificial intelligence model and distributes it to the terminal.

[0119] Input: The user clicks the "Initial Settings" button on the system administration screen.

[0120] How it works: The server loads a trained artificial intelligence model for animal recognition (animal_recognition_model) into memory, then distributes this model to each device in the form of a firmware update.

[0121] Output: The animal_recognition_model is installed on each device.

[0122] Step 2:

[0123] The device uses a camera to capture images of the animals and send them to the server.

[0124] Input: A still image taken by the camera.

[0125] How it works: The device's camera captures an image of its surroundings once every second. The image data is sent to the server using HTTP POST. This image data is sent in binary format.

[0126] Output: Image data sent to the server.

[0127] Step 3:

[0128] The server analyzes the image and identifies the type of animal.

[0129] Input: Image data sent from the device.

[0130] How it works: The server calls an AI model running on a Python script and provides image data as input. The AI ​​model analyzes the image and identifies the type of animal in it. The identification result is expressed as a probability, such as "80% chance that it's a rabbit."

[0131] Output: Identified animal species and their probabilities.

[0132] Step 4:

[0133] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0134] Input: Animal species and their probabilities obtained from the AI ​​model.

[0135] How it works: Based on the identified animal type, the server selects images and sounds that the animal dislikes from a database. After selecting the appropriate images and sounds, it sends this information to the device.

[0136] Output: Image and sound data sent to the device.

[0137] Step 5:

[0138] The terminal plays the images and sounds received from the server.

[0139] Input: Image and sound data sent from the server.

[0140] Operation: The device first displays an image on the display using the received image data, and simultaneously plays sound data from the speaker using the audio library.

[0141] Output: The image shown on the display and the sound played through the speakers.

[0142] These are the specific processing steps of the program for this system, which enables real-time detection of animals damaging crops in farmland and immediate response.

[0143] (Application example 1)

[0144] 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."

[0145] Problems such as the introduction of foreign objects and unauthorized intrusions into factory production lines have a significant impact on safety and efficiency. Conventional methods require manual detection and removal of foreign objects, which requires significant time and manpower and increases the risk of errors. Furthermore, systems for quickly taking appropriate action are lacking, making real-time monitoring and response difficult. Therefore, the present invention aims to solve these problems and improve the efficiency and safety of factory operations.

[0146] 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.

[0147] In this invention, the server includes means for capturing an image of an approaching object with a camera, means for transmitting the image to the server, means for identifying the object in the image by the server, means for determining an image and sound that the object is sensitive to based on the identified object, means for displaying the determined image on a display device, means for playing the determined sound from an audio device, and means for performing an action to remove the object when it enters a specific area, thereby enabling the efficiency and safety of factory work to be improved.

[0148] "Object" refers to any object that exists on a factory line or within a detection range and needs to be identified or removed.

[0149] A "camera" is a photographic device that captures images and videos and provides the data for subsequent processing.

[0150] A "server" is a central processing unit that analyzes and manages data and serves as the control center for the entire system.

[0151] The "means for transmitting images" is a combination of network equipment and software for transferring captured images to a server.

[0152] "Means for identification" refers to algorithms and software that identify objects in captured images and determine their type and condition.

[0153] A "generative AI model" is an artificial intelligence model that is trained in advance based on a large amount of data and is able to identify images and objects with high accuracy in real time.

[0154] A "display device" is a display for visualizing images or messages.

[0155] "Sound device" means a speaker for playing determined sounds and providing auditory alerts and effects.

[0156] "Means for performing an action to remove an object when it invades" refers to a physical driving device such as a robot arm or actuator for removing an object when it invades a specific area.

[0157] A system for implementing this invention is for effectively managing foreign matter contamination, unauthorized entry, etc. in a factory production line. This system includes a camera, a server, a display device, an audio device, and several software components.

[0158] First, a camera periodically captures images of the production line. The captured images are then transferred to a server using an image transmission method. When the server receives the images, it uses a generative AI model to identify objects in the images. This generative AI model has been trained in advance using a large amount of data, enabling highly accurate identification in real time.

[0159] Based on the identified object, the server determines from a database the image and sound that the object is sensitive to. The determined image is displayed on a display device, and the determined sound is played from an audio device. This improves the efficiency and safety of the production line.

[0160] Furthermore, if an object enters a specific area, the server executes an action to remove the object, using physical driving devices such as a robot arm or actuator.

[0161] As a concrete example, consider the case where garbage gets mixed into a beverage production line at a factory. A camera captures an image of the garbage and sends it to a server. The server uses a generative AI model to identify the garbage, determines an appropriate image and sound for that garbage, and displays and plays them on a display and audio device. Furthermore, if the garbage enters a specific area, a robotic arm removes the garbage.

[0162] An example prompt might look like this:

[0163] "How can I use a trained model to detect debris and foreign objects on a production line in real time?"

[0164] How can I send an HTTP request to retrieve image and audio data based on the classification results?

[0165] In this way, the present invention makes it possible to respond quickly and accurately in real time to the intrusion of foreign matter or unauthorized access into a factory production line, thereby improving production efficiency and ensuring safety.

[0166] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0167] Step 1:

[0168] A camera periodically captures images of the factory production line. The input is the image data captured by the camera lens, and the output is the captured image file.

[0169] Step 2:

[0170] The captured image data is transferred to a server using an image transmission means, where the input is the captured image file and the output is the image data sent to the server.

[0171] Step 3:

[0172] The server passes the received image data to the generative AI model to identify the object. The input is the image data, and the output is the type and location of the identified object. Specifically, the generative AI model analyzes the image data and performs data calculations to identify the object.

[0173] Step 4:

[0174] Based on the identification results, the server determines the image and sound corresponding to the object from the database. The input is the type and location information of the identified object, and the output is the URL of the image to display and the URL of the audio file to play. Specifically, the server executes a database query to retrieve the appropriate data.

[0175] Step 5:

[0176] The determined image is sent from the server to the display device and displayed on the display device. The input is the URL of the image, and the output is the displayed image. Specifically, the image data is rendered on the display device's screen.

[0177] Step 6:

[0178] The determined sound is sent from the server to the sound device and played from the sound device. The input is the URL of the audio file, and the output is the played sound. Specifically, the audio data is played on the sound device's speaker.

[0179] Step 7:

[0180] When an object enters a specific area, the server executes an action to remove the object. The input is the object's location information, and the output is a trigger for the removal action. Specifically, the robot arm operates to remove the object.

[0181] Step 8:

[0182] After the elimination action is completed, the server records the system status as a log and notifies the user. The input is the result of the elimination action, and the output is the log data and a user notification. Specifically, the server saves the log in a database and creates a notification message based on the generative AI model.

[0183] This series of processing steps efficiently enables real-time detection and removal of foreign objects on factory production lines.

[0184] 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.

[0185] The present invention combines a system in which a device installed in farmland uses a camera to capture approaching animals and transmits the images to a server, with an emotion engine that recognizes the user's emotions. The server analyzes the transmitted images and identifies the type of animal. Next, based on the identified animal, it determines the images and sounds that the animal dislikes and transmits a response to the device. Based on the received response, the device displays an image on the display and plays a sound from the speaker. This system can effectively protect crops from a wide variety of pests. The emotion engine also recognizes the user's emotions, allowing the server to adjust countermeasures against animals as necessary.

[0186] Specific program processing explanation

[0187] Server Initialization

[0188] The server loads the artificial intelligence model and distributes it to the terminal.

[0189] When a user initially configures the system, the server loads the trained AI model (animal_recognition_model) and emotion engine and distributes this model to all devices, so that each device is ready to identify animals and adjust its response based on the user's emotions.

[0190] Animal recognition by device

[0191] The device uses a camera to capture images of the animals and send them to the server.

[0192] The device periodically captures images of its surroundings using a camera. For example, an image is taken once per second, and the captured images are sent to a server. This allows the server to perform real-time image analysis on devices installed in remote locations.

[0193] Server-based animal identification

[0194] The server analyzes the image and identifies the type of animal.

[0195] The server analyzes the received images using an artificial intelligence model to identify the type of animal depicted in the image.

[0196] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0197] Based on the identified animal, the server selects images and sounds that the animal fears from a database and sends this information to the device, causing the animal to feel fear.

[0198] Terminal display of responses

[0199] The terminal plays the images and sounds received from the server.

[0200] The device displays the image received from the server on the display and simultaneously plays sound from the speaker, effectively scaring away animals.

[0201] Use of emotion engine by server

[0202] The server recognizes the user's emotions.

[0203] The emotion engine captures the user's facial expression data with a camera and analyzes their stress and satisfaction, thereby understanding the user's emotional state in real time.

[0204] The server adjusts the response based on the output of the emotion engine.

[0205] If the user's emotional state is inappropriate, the server runs an algorithm to optimize the animal's response, adjusting the images and sounds to make the animal feel more frightened, and then sends this adjusted information back to the device.

[0206] Specific examples

[0207] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0208] Device animal recognition:

[0209] The device captures an image of the rabbit with its camera and sends the image to the server.

[0210] Server-based animal identification:

[0211] The server analyzes the image and identifies the animal as a rabbit.

[0212] Server response generation:

[0213] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0214] Terminal display of response:

[0215] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0216] Server-based emotion recognition and modulation:

[0217] The server analyzes the user's emotional state with an emotion engine, and if the user is feeling stressed, determines more powerful images and sounds and retransmits them to the terminal.

[0218] In this way, the system of the present invention provides an efficient and effective response to pests, and can be optimized taking into account the emotional state of the user.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] Server Initialization

[0222] The server loads the artificial intelligence model (animal_recognition_model) and emotion engine and distributes them to each device. With this initial setup, each device is ready to identify animals and adjust its response based on the user's emotions.

[0223] Step 2:

[0224] Animal detection by device

[0225] The device uses a camera to periodically capture images of its surroundings, for example, once per second, to monitor for approaching animals.

[0226] Step 3:

[0227] Sending images by device

[0228] The captured image is immediately uploaded to the server, allowing the server to perform image analysis in real time.

[0229] Step 4:

[0230] Server-based animal identification

[0231] The server then uses an artificial intelligence model to analyze the received images and identify the type of animal that is present in the image, which then identifies which animal is approaching.

[0232] Step 5:

[0233] Server decides what to do

[0234] Based on the identified animal type, the server determines the images and sounds that the animal dislikes, which information is obtained from a pre-defined database.

[0235] Step 6:

[0236] Server Response Generation

[0237] The server generates response data containing images and sounds that the animal dislikes, and sends it to the device. This data is then formatted in a format that the device can accept.

[0238] Step 7:

[0239] Displaying images by device

[0240] The device displays the image received from the server on its display, creating a visual threat to the animals.

[0241] Step 8:

[0242] Playing sounds through the device

[0243] The device receives the sound from the server and plays it back through the speaker, creating an auditory threat to the animals.

[0244] Step 9:

[0245] Use of emotion engine by server

[0246] The server uses an emotion engine to analyze the user's facial expression data and detect the user's stress and satisfaction, thereby understanding the user's emotional state in real time.

[0247] Step 10:

[0248] Adjusting responses based on user emotions

[0249] The server readjusts its response to the animal based on the output of the emotion engine: if the user is stressed, it determines stronger images and sounds and retransmits them to the device.

[0250] Specific examples

[0251] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0252] Device animal recognition:

[0253] The device captures an image of the rabbit with its camera and sends the image to the server.

[0254] Server-based animal identification:

[0255] The server analyzes the image and identifies the animal as a rabbit.

[0256] Server response generation:

[0257] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0258] Terminal display of response:

[0259] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0260] Server-based emotion recognition and modulation:

[0261] The server analyzes the user's emotional state with an emotion engine, and if the user is feeling stressed, determines more powerful images and sounds and retransmits them to the terminal.

[0262] In this way, the system of the present invention provides an efficient and effective response to pests, and can be optimized taking into account the emotional state of the user.

[0263] Example 2

[0264] 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."

[0265] While conventional animal repellent systems have the ability to identify the type of animal and determine the appropriate countermeasure, they lack the ability to adjust the countermeasure based on the user's emotional state, which means that their long-term effectiveness cannot be guaranteed.In addition, they often only take a certain countermeasure against animals, which can become less effective depending on the animal's adaptability.

[0266] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0267] In this invention, the server includes means for capturing an image of an approaching animal with a camera, means for transmitting the image to the server, means for identifying the animal in the image by the server, means for determining images and sounds that the animal dislikes based on the identified animal, means for displaying the determined images on a display, means for playing the determined sounds from a speaker, means for recognizing the user's emotions, and means for adjusting countermeasures against the animal based on the user's emotional state, thereby making it possible to provide optimal countermeasures that take into account not only the animal but also the user's emotional state.

[0268] A "camera" is a device that captures visual information from its surroundings and records it as an image.

[0269] A "server" is a centralized computer system that processes and manages data over a network.

[0270] "Means for transmitting images" refers to communication techniques and devices for transferring captured image data to a server.

[0271] "Animal identification means" refers to the technology or algorithms used to analyze the received image data and identify the type of animal in the image.

[0272] "Means for determining images and sounds that an animal dislikes" refers to a method and apparatus that, based on an identified animal, selects images and sounds that the animal tends to avoid.

[0273] "Means for displaying" refers to devices and techniques for visually displaying the determined image.

[0274] "Means for playing from a speaker" refers to devices and techniques for playing the determined sound as audio.

[0275] "Means for recognizing user emotions" refers to technologies and algorithms for analyzing a user's facial expressions and voice data to identify their emotional state.

[0276] "Means for adjusting behavior toward animals" refers to means and techniques for dynamically changing behavior toward animals based on the emotional state of the user.

[0277] An "artificial intelligence model" is a computational model based on machine learning algorithms that are trained to perform specific tasks.

[0278] A "database" is a system for efficiently storing and retrieving structured data.

[0279] In this invention, a system is implemented that provides effective measures against a wide variety of harmful animals using terminals installed on farmland, a server, and an emotion engine for recognizing user emotions.

[0280] First, the device is installed in the field and uses a camera module to capture images of approaching animals. The images are temporarily stored on the device and then sent to a server via network communication. This communication mainly uses wireless networks such as Wi-Fi, 4G, and 5G.

[0281] The server analyzes the transmitted image using a trained AI model (animal_recognition_model). This AI model includes the characteristics of various animals and uses a specific algorithm to identify the type of animal in the image. Based on the identified animal, the server selects images and sounds that the animal dislikes from a database. This database contains pre-registered images and sounds that each type of animal dislikes.

[0282] The server then retransmits the selected image and sound data to the device, which displays the received images on its display and plays the sounds through its speaker, thus driving animals away from the field and protecting the crops.

[0283] Furthermore, the system incorporates an emotion engine. To recognize the user's emotional state, the emotion engine captures and analyzes the user's facial expression data using a camera. Based on the analysis results obtained from the emotion engine, the server adjusts the response to the animals as needed. For example, if the user is feeling anxious or stressed, the server selects more powerful images and sounds and retransmits them to the device.

[0284] As a concrete example, consider the case where a device installed in a field recognizes a rabbit using a camera. The device captures an image of the rabbit and sends it to a server. The server analyzes the received image and identifies the animal as a rabbit. The server then selects an image of an eagle and the sound of a dog barking, which rabbits are afraid of, and sends these to the device. The device then displays the received image of the eagle on its display and plays the sound of a dog barking through its speaker. This process can scare away rabbits from the field.

[0285] If the user expresses dissatisfaction with the system's operation, the emotion engine analyzes the facial expression data and sends the results to the server, which then selects more effective images and sounds and retransmits them to the device, thereby enhancing the animal-repelling effect.

[0286] Examples of prompts include:

[0287] "Please explain the process by which a device installed on farmland uses a camera to recognize rabbits and determine the image and sound to scare them away."

[0288] "Please explain how the server will change its response if the user expresses dissatisfaction with the system."

[0289] This system provides optimal animal repelling measures that take into account not only the animals but also the emotional state of the user.

[0290] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0291] Program processing flow

[0292] Step 1: Initial Setup

[0293] 1. Loading and distributing models by the server

[0294] Input: Trained AI model and emotion engine

[0295] Specific operation: The server loads the trained AI model (animal_recognition_model) and emotion engine and distributes them to all devices via the network. The distributed model is used by the device to identify animals.

[0296] Step 2: Prepare for Animal Recognition

[0297] 2. Device camera and communication settings

[0298] Input: Camera module and communication module

[0299] Specific operation: The device initializes the camera and sets up network communication with the server, so that the device is ready to capture image data and send it to the server.

[0300] Step 3: Capture an image of the animal

[0301] 3. Periodic image capture by the device

[0302] Input: Visual information of the surroundings acquired by the camera

[0303] Specific operation: The device captures an image of the surroundings using the camera once per second. For example, it calls the "capture_image()" function to obtain image data.

[0304] Output: Captured image data

[0305] 4. Sending images to the server

[0306] Input: Captured image data

[0307] Specific operation: The device uses the "send_image_to_server(image)" function to send the captured image data to the server.

[0308] Output: Image data sent to the server

[0309] Step 4: Identify the animal species

[0310] 5. Image analysis by the server

[0311] Input: Submitted image data and artificial intelligence model

[0312] Specific operation: The server uses the "analyze_image(image, animal_recognition_model)" function to analyze the image data with an artificial intelligence model to identify the type of animal in the image.

[0313] Output: Identified animal species

[0314] Step 5: Determine the images and sounds you find difficult

[0315] 6. Server Determination of Response Data

[0316] Input: Identified animal species

[0317] What happens: The server uses the "select_response_for_animal(animal_type)" function to select from the database the images and sounds that the animal dislikes. For example, for a rabbit, it selects the image of an eagle and the sound of a dog barking.

[0318] Output: Determined image and sound data

[0319] 7. Sending response data to the terminal

[0320] Input: Determined image and sound data

[0321] Specific operation: The server uses the "send_response_to_terminal(response_data)" function to send the selected image and sound to the terminal.

[0322] Output: Image and sound data sent to the device

[0323] Step 6: View the response

[0324] 8. Displaying images and playing sounds on the device

[0325] Input: Image and sound data sent to the device

[0326] Specific operation: The device displays an image on the display using the "display_image(image)" function and plays a sound from the speaker using the "play_sound(sound)" function, which has a deterrent effect on the animals.

[0327] Output: The displayed image and the played sound

[0328] Step 7: Use the Emotion Engine

[0329] 9. Emotion Analysis by Server

[0330] Input: User's facial expression data

[0331] Specific operation: The server uses the emotion engine to identify the user's emotional state by analyzing the user's facial expression data, for example, by using the "analyze_user_emotion(user_image)" function.

[0332] Output: Emotional state analysis result

[0333] 10. Adjusting your response based on emotions

[0334] Input: Emotional state analysis results

[0335] What it does: The server uses the "adjust_response_based_on_emotion(emotion_data)" function to adjust its response to the animal based on its emotional state: if the user is stressed, it will select stronger images and sounds and resend them to the device.

[0336] Output: Modified image and sound data

[0337] Through these steps, the system can effectively identify animals and coordinate response measures.

[0338] (Application example 2)

[0339] 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."

[0340] Conventional security systems are limited to detecting intruders and suspicious individuals, and offer limited options for specific countermeasures after detection. Furthermore, because they provide only uniform countermeasures without taking the user's emotional state into consideration, inappropriate responses can be taken, limiting security optimization. This makes it difficult to implement effective and flexible countermeasures. The present invention aims to solve these problems and provide a more effective and user-friendly security system.

[0341] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing an image of an approaching target with a camera, means for transmitting the image to the server, means for identifying the target in the image by the server, means for determining images and sounds that the target dislikes based on the identified target, means for displaying the determined images on a display, means for playing the determined sounds from a speaker, means for recognizing the user's emotion using an emotion engine, and means for adjusting countermeasures based on the recognized emotion. This makes it possible to effectively repel intruders in real time and optimize countermeasures in accordance with the user's emotional state.

[0342] A "camera" is a device for taking images or videos.

[0343] A "server" is a computer system that processes and stores data, and provides services in response to requests from clients.

[0344] An "image" is information about a still image that visually captures an object, landscape, etc.

[0345] "Subject" refers to any object or living thing within the camera's field of view that is the subject of surveillance or identification.

[0346] "Identification" is the process of identifying specific objects in an image and determining their type and characteristics.

[0347] "Images that a particular subject dislikes" refers to visual information that a particular subject does not want to see or that a particular subject psychologically dislikes.

[0348] "Sound" is an auditory stimulus that is transmitted as vibrations in the air, and when a particular object is disliked, it acts to make the animal flee from that object.

[0349] A "display" is a device that displays images or videos by electrical means.

[0350] A "speaker" is a device that converts electrical signals into audio and produces sound.

[0351] An "emotion engine" is a software or hardware system that analyzes a user's facial expressions and behavior and recognizes their emotional state.

[0352] A "user" is a person who uses, operates, or monitors the system.

[0353] "Recognition" refers to the process of understanding and identifying the situation and characteristics of an object from data acquired by cameras and sensors.

[0354] "Countermeasures" refer to specific actions or measures taken to deal with a specific event or situation.

[0355] "Adjustment" refers to the act of making changes or adjustments to achieve an appropriate state according to given conditions or circumstances.

[0356] A "system" is a collection of integrated devices and processes in which different elements work together to achieve a specific function.

[0357] This invention is a security system that includes a camera, a server, a display, a speaker, and an emotion engine. By linking these elements, it provides a system that detects intruders and suspicious individuals in real time and implements effective countermeasures. The system configuration and operation are detailed below.

[0358] The basic operation of the system is as follows: First, the camera periodically sends images it captures to the server, and the server identifies the object in the received image. A pre-trained artificial intelligence model is used to do this. This model identifies the type of object and, based on the results, determines the images and sounds that the object dislikes. The determined images are shown on the display and the sounds are played from the speaker. This effectively scares away objects (such as suspicious people or animals).

[0359] Next, we will explain the function of the emotion engine. The emotion engine recognizes and analyzes the user's emotions in real time from facial expression data captured by the camera. The server uses this emotion data to adjust countermeasures as appropriate. For example, if the user is feeling very stressed, the server can use more effective images and sounds to scare away the target. This function allows the system to adapt to the user's emotional state and provide the most appropriate countermeasures.

[0360] Here's a specific example: Suppose a camera installed in a residential garden detects an intruder. In this case, the camera captures an image of the intruder and sends it to a server. The server analyzes the received image and identifies the intruder as a human. The server then determines an alarm sound (e.g., a loud dog barking) and an image (e.g., an image of a surveillance camera or a warning sign) that the intruder will dislike, and sends them to the device. The device then plays the received alarm sound from its speaker and displays the image on its display, effectively scaring the intruder away.

[0361] Furthermore, when the emotion engine is used, if the user is in a situation where they are feeling extremely stressed, the emotion engine can detect this and send instructions to the server to select stronger warning sounds or images, resulting in stronger responses being taken and increasing the effectiveness of the system.

[0362] Examples of prompts include:

[0363] "Design a system that uses image data captured by a camera to identify a suspicious individual and determine the optimal audible warning or visual image to scare them away."

[0364] In this way, the system of the present invention can realize real-time monitoring and effective repelling, and further provide flexible countermeasures that adapt to the user's emotional state.

[0365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0366] Step 1:

[0367] The device periodically captures images of the surrounding area using a camera and sends the captured image data to a server. The input is the raw image data captured by the camera, and the output is the image data sent to the server. Specifically, the camera captures images at regular intervals and sends the image data to the server via the Internet. This allows the server to receive monitoring data in real time.

[0368] Step 2:

[0369] The server takes the received image data as input and uses a pre-trained generative AI model to identify the object in the image. Based on this identification result, it determines the next countermeasure. Specifically, the server analyzes the image using an image recognition algorithm (e.g., a deep learning model) and classifies the object as human, suspicious person, animal, etc. The output is the type of object identified.

[0370] Step 3:

[0371] Based on the type of identified object, the server retrieves from a database images and sounds that the object finds frightening and sends them to the device. The input here is the type of identified object, and the output is image and sound data that will induce fear in the object appropriately. Specifically, the server searches the database for corresponding sound and image files and sends this data to the device. At this time, the emotion engine analyzes the user's emotional state, and the selection of images and sounds may be adjusted based on this information.

[0372] Step 4:

[0373] The device receives image and sound data from the server as input, displays the image on the display, and plays the sound from the speaker. This has the effect of scaring away the target. Specifically, the device's display displays a frightening image, and the speaker plays a warning sound. The output is the displayed image and the played sound, with the ultimate goal being to make the target leave the area.

[0374] Step 5:

[0375] The server uses an emotion engine to monitor the user's emotional state in real time. The input is the user's facial expression data, and the output is the user's emotional state. Specifically, it analyzes the facial expression data captured by the user's camera and determines whether the user is feeling stressed or satisfied.

[0376] Step 6:

[0377] The server adjusts the response to the target as needed based on the user's emotional state. The adjusted response is sent back to the device and played. The input is the user's emotional state, and the output is adjusted image and sound data. Specifically, if the emotion engine determines that the user's stress level is high, it selects stronger warning sounds and images. This adjusted data is sent to the device and played.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] [Second embodiment]

[0382] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0383] 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.

[0384] 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).

[0385] 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.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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."

[0394] The present invention is a system in which a terminal installed in farmland uses a camera to capture images of approaching animals and transmits the images to a server. The server analyzes the transmitted images and identifies the type of animal. Next, based on the identified animal, it determines the images and sounds that the animal dislikes and transmits a response to the terminal. Based on the received response, the terminal displays the image on its display and plays the sound from its speaker. This system can effectively protect crops from a wide variety of pests.

[0395] Specific program processing explanation

[0396] Server Initialization

[0397] The server loads the artificial intelligence model and distributes it to the terminal.

[0398] When a user initially configures the system, the server loads the trained AI model (animal_recognition_model) and distributes it to all devices, enabling each device to recognize animals.

[0399] Animal recognition by device

[0400] The device uses a camera to capture images of the animals and send them to the server.

[0401] The device periodically captures images of its surroundings using a camera. For example, an image is taken once per second, and the captured images are sent to a server. This allows the server to perform real-time image analysis on devices installed in remote locations.

[0402] Server-based animal identification

[0403] The server analyzes the image and identifies the type of animal.

[0404] The server analyzes the received images using an artificial intelligence model to identify the type of animal depicted in the image.

[0405] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0406] Based on the identified animal, the server selects images and sounds that the animal fears from a database and sends this information to the device, causing the animal to feel fear.

[0407] Terminal display of responses

[0408] The terminal plays the images and sounds received from the server.

[0409] The device displays the image received from the server on the display and simultaneously plays sound from the speaker, effectively scaring away animals.

[0410] Specific examples

[0411] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0412] Device animal recognition:

[0413] The device captures an image of the rabbit with its camera and sends the image to the server.

[0414] Server-based animal identification:

[0415] The server analyzes the received image and identifies the animal as a rabbit.

[0416] Server response generation:

[0417] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0418] Terminal display of response:

[0419] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0420] This prevents rabbits from approaching crops, protecting them. This system can be remotely controlled and is effective against a wide range of pests, making it a highly effective agricultural protection tool.

[0421] The processing flow will be explained below.

[0422] Step 1:

[0423] Server Initialization

[0424] The server loads the artificial intelligence model (animal_recognition_model) and distributes it to each device. This initial setup prepares the device to recognize animals.

[0425] Step 2:

[0426] Animal detection by device

[0427] The device uses a camera to periodically capture images of its surroundings, for example, once per second, to monitor for approaching animals.

[0428] Step 3:

[0429] Sending images by device

[0430] The captured image is immediately uploaded to the server, allowing the server to perform image analysis in real time.

[0431] Step 4:

[0432] Server-based animal identification

[0433] The server then uses an artificial intelligence model to analyze the received images and identify the type of animal that is present in the image, which then identifies which animal is approaching.

[0434] Step 5:

[0435] Server decides what to do

[0436] Based on the identified animal type, the server determines the images and sounds that the animal dislikes, which information is obtained from a pre-defined database.

[0437] Step 6:

[0438] Server Response Generation

[0439] The server generates response data containing images and sounds that the animal dislikes, and sends it to the device. This data is then formatted in a format that the device can accept.

[0440] Step 7:

[0441] Displaying images by device

[0442] The device displays the image received from the server on its display, creating a visual threat to the animals.

[0443] Step 8:

[0444] Playing sounds through the device

[0445] The device receives the sound from the server and plays it back through the speaker, creating an auditory threat to the animals.

[0446] Step 9:

[0447] Observing pest behavior

[0448] Users can view logs on their devices and on the server to see which animals responded and how they reacted, allowing them to assess the effectiveness of the system and make adjustments as needed.

[0449] Example 1

[0450] 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."

[0451] There is a need for an effective method to repel animals that damage crops in agricultural fields. Conventional methods have difficulty in quickly taking different countermeasures depending on the type of animal, and there is a lack of systems that allow remote control. This has led to the problem of not being able to prevent animal damage in a timely manner.

[0452] 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.

[0453] In this invention, the server includes means for taking pictures of approaching animals with a camera, means for transmitting the images to the server, means for identifying the animals in the images by the server, means for determining images and sounds that the animals dislike based on the identified animals, means for displaying the determined images on a display, and means for playing the determined sounds from a speaker. This makes it possible to identify animals in real time and instantly scare them away using appropriate images and sounds.

[0454] A "camera" is a device that captures images of the surroundings and outputs them as image data.

[0455] A "server" is a computer system that receives requests from client terminals via a network and processes them.

[0456] An "image" is a digital representation of visual information captured by a camera.

[0457] "Animals" refers to a group of living organisms that have a specific behavior, and in the present invention refers to organisms that may cause damage to agricultural land.

[0458] An "artificial intelligence model" is a set of pre-trained algorithms used to analyze input data and make decisions.

[0459] A "terminal" is an electronic device that can be connected to a network and communicates with a server.

[0460] A "display" is an output device for displaying images and videos.

[0461] A "speaker" is an output device for reproducing voice or sound.

[0462] A "database" is a collection of data and a system that enables efficient search and retrieval of data.

[0463] "Recognition" is the process of identifying a specific object from input image data.

[0464] The present invention is a system that uses a terminal installed in farmland to detect the approach of animals and respond appropriately. This system is realized by combining a camera, a server, a display, a speaker, and an artificial intelligence model.

[0465] First, when the user initially configures the system, the server loads a trained artificial intelligence model (animal_recognition_model) and distributes it to each device. This model is a group of algorithms for identifying animal species, and through training it is possible to achieve highly accurate identification.

[0466] The device is then installed in the field and periodically captures images of the surrounding area with its camera. This image data is then sent to the server at intervals of, for example, once per second. The transmission protocol is HTTP POST, and the image data is sent in binary format.

[0467] The server then calls an AI model running on a Python script to analyze the received image. The AI ​​model analyzes the image provided as input and identifies the type of animal depicted in the image. The identification result is expressed as a probability, and is returned in the form of, for example, "80% probability that it is a rabbit."

[0468] Based on the identified animal, the server selects images and sounds that the animal dislikes from a database containing pre-defined image and sound pairs for each animal type. Once the appropriate images and sounds are selected, they are sent to the device.

[0469] The device displays the received image on the screen and plays a sound from the speaker at the same time, which scares the animals and makes them leave the field, preventing them from damaging crops.

[0470] As a concrete example of this system, consider the case where a device installed in a farm recognizes a rabbit using a camera. In this case, the device captures an image of the rabbit with its camera and sends it to the server. The server analyzes the received image and identifies it as a rabbit. The server then selects an image of an eagle, which rabbits are afraid of, and the sound of a dog barking, and sends these to the device. The device displays the received image of the eagle on its display and plays the sound of a dog barking from its speaker, thereby scaring away the rabbit.

[0471] An example prompt might be, "Please explain how to identify the type of animal recognized by a camera-equipped device installed in farmland, determine the image and sound to scare the animal away, and send them to the device."

[0472] As a result, this system can be remotely controlled and is a highly effective means of protecting farmland against a wide range of pests.

[0473] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0474] Step 1:

[0475] The server loads the artificial intelligence model and distributes it to the terminal.

[0476] Input: The user clicks the "Initial Settings" button on the system administration screen.

[0477] How it works: The server loads a trained artificial intelligence model for animal recognition (animal_recognition_model) into memory, then distributes this model to each device in the form of a firmware update.

[0478] Output: The animal_recognition_model is installed on each device.

[0479] Step 2:

[0480] The device uses a camera to capture images of the animals and send them to the server.

[0481] Input: A still image taken by the camera.

[0482] How it works: The device's camera captures an image of its surroundings once every second. The image data is sent to the server using HTTP POST. This image data is sent in binary format.

[0483] Output: Image data sent to the server.

[0484] Step 3:

[0485] The server analyzes the image and identifies the type of animal.

[0486] Input: Image data sent from the device.

[0487] How it works: The server calls an AI model running on a Python script and provides image data as input. The AI ​​model analyzes the image and identifies the type of animal in it. The identification result is expressed as a probability, such as "80% chance that it's a rabbit."

[0488] Output: Identified animal species and their probabilities.

[0489] Step 4:

[0490] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0491] Input: Animal species and their probabilities obtained from the AI ​​model.

[0492] How it works: Based on the identified animal type, the server selects images and sounds that the animal dislikes from a database. After selecting the appropriate images and sounds, it sends this information to the device.

[0493] Output: Image and sound data sent to the device.

[0494] Step 5:

[0495] The terminal plays the images and sounds received from the server.

[0496] Input: Image and sound data sent from the server.

[0497] Operation: The device first displays an image on the display using the received image data, and simultaneously plays sound data from the speaker using the audio library.

[0498] Output: The image shown on the display and the sound played through the speakers.

[0499] These are the specific processing steps of the program for this system, which enables real-time detection of animals damaging crops in farmland and immediate response.

[0500] (Application example 1)

[0501] 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."

[0502] Problems such as the introduction of foreign objects and unauthorized intrusions into factory production lines have a significant impact on safety and efficiency. Conventional methods require manual detection and removal of foreign objects, which requires significant time and manpower and increases the risk of errors. Furthermore, systems for quickly taking appropriate action are lacking, making real-time monitoring and response difficult. Therefore, the present invention aims to solve these problems and improve the efficiency and safety of factory operations.

[0503] 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.

[0504] In this invention, the server includes means for capturing an image of an approaching object with a camera, means for transmitting the image to the server, means for identifying the object in the image by the server, means for determining an image and sound that the object is sensitive to based on the identified object, means for displaying the determined image on a display device, means for playing the determined sound from an audio device, and means for performing an action to remove the object when it enters a specific area, thereby enabling the efficiency and safety of factory work to be improved.

[0505] "Object" refers to any object that exists on a factory line or within a detection range and needs to be identified or removed.

[0506] A "camera" is a photographic device that captures images and videos and provides the data for subsequent processing.

[0507] A "server" is a central processing unit that analyzes and manages data and serves as the control center for the entire system.

[0508] The "means for transmitting images" is a combination of network equipment and software for transferring captured images to a server.

[0509] "Means for identification" refers to algorithms and software that identify objects in captured images and determine their type and condition.

[0510] A "generative AI model" is an artificial intelligence model that is trained in advance based on a large amount of data and is able to identify images and objects with high accuracy in real time.

[0511] A "display device" is a display for visualizing images or messages.

[0512] "Sound device" means a speaker for playing determined sounds and providing auditory alerts and effects.

[0513] "Means for performing an action to remove an object when it invades" refers to a physical driving device such as a robot arm or actuator for removing an object when it invades a specific area.

[0514] A system for implementing this invention is for effectively managing foreign matter contamination, unauthorized entry, etc. in a factory production line. This system includes a camera, a server, a display device, an audio device, and several software components.

[0515] First, a camera periodically captures images of the production line. The captured images are then transferred to a server using an image transmission method. When the server receives the images, it uses a generative AI model to identify objects in the images. This generative AI model has been trained in advance using a large amount of data, enabling highly accurate identification in real time.

[0516] Based on the identified object, the server determines from a database the image and sound that the object is sensitive to. The determined image is displayed on a display device, and the determined sound is played from an audio device. This improves the efficiency and safety of the production line.

[0517] Furthermore, if an object enters a specific area, the server executes an action to remove the object, using physical driving devices such as a robot arm or actuator.

[0518] As a concrete example, consider the case where garbage gets mixed into a beverage production line at a factory. A camera captures an image of the garbage and sends it to a server. The server uses a generative AI model to identify the garbage, determines an appropriate image and sound for that garbage, and displays and plays them on a display and audio device. Furthermore, if the garbage enters a specific area, a robotic arm removes the garbage.

[0519] An example prompt might look like this:

[0520] "How can I use a trained model to detect debris and foreign objects on a production line in real time?"

[0521] How can I send an HTTP request to retrieve image and audio data based on the classification results?

[0522] In this way, the present invention makes it possible to respond quickly and accurately in real time to the intrusion of foreign matter or unauthorized access into a factory production line, thereby improving production efficiency and ensuring safety.

[0523] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0524] Step 1:

[0525] A camera periodically captures images of the factory production line. The input is the image data captured by the camera lens, and the output is the captured image file.

[0526] Step 2:

[0527] The captured image data is transferred to a server using an image transmission means, where the input is the captured image file and the output is the image data sent to the server.

[0528] Step 3:

[0529] The server passes the received image data to the generative AI model to identify the object. The input is the image data, and the output is the type and location of the identified object. Specifically, the generative AI model analyzes the image data and performs data calculations to identify the object.

[0530] Step 4:

[0531] Based on the identification results, the server determines the image and sound corresponding to the object from the database. The input is the type and location information of the identified object, and the output is the URL of the image to display and the URL of the audio file to play. Specifically, the server executes a database query to retrieve the appropriate data.

[0532] Step 5:

[0533] The determined image is sent from the server to the display device and displayed on the display device. The input is the URL of the image, and the output is the displayed image. Specifically, the image data is rendered on the display device's screen.

[0534] Step 6:

[0535] The determined sound is sent from the server to the sound device and played from the sound device. The input is the URL of the audio file, and the output is the played sound. Specifically, the audio data is played on the sound device's speaker.

[0536] Step 7:

[0537] When an object enters a specific area, the server executes an action to remove the object. The input is the object's location information, and the output is a trigger for the removal action. Specifically, the robot arm operates to remove the object.

[0538] Step 8:

[0539] After the elimination action is completed, the server records the system status as a log and notifies the user. The input is the result of the elimination action, and the output is the log data and a user notification. Specifically, the server saves the log in a database and creates a notification message based on the generative AI model.

[0540] This series of processing steps efficiently enables real-time detection and removal of foreign objects on factory production lines.

[0541] 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.

[0542] The present invention combines a system in which a device installed in farmland uses a camera to capture approaching animals and transmits the images to a server, with an emotion engine that recognizes the user's emotions. The server analyzes the transmitted images and identifies the type of animal. Next, based on the identified animal, it determines the images and sounds that the animal dislikes and transmits a response to the device. Based on the received response, the device displays an image on the display and plays a sound from the speaker. This system can effectively protect crops from a wide variety of pests. The emotion engine also recognizes the user's emotions, allowing the server to adjust countermeasures against animals as necessary.

[0543] Specific program processing explanation

[0544] Server Initialization

[0545] The server loads the artificial intelligence model and distributes it to the terminal.

[0546] When a user initially configures the system, the server loads the trained AI model (animal_recognition_model) and emotion engine and distributes this model to all devices, so that each device is ready to identify animals and adjust its response based on the user's emotions.

[0547] Animal recognition by device

[0548] The device uses a camera to capture images of the animals and send them to the server.

[0549] The device periodically captures images of its surroundings using a camera. For example, an image is taken once per second, and the captured images are sent to a server. This allows the server to perform real-time image analysis on devices installed in remote locations.

[0550] Server-based animal identification

[0551] The server analyzes the image and identifies the type of animal.

[0552] The server analyzes the received images using an artificial intelligence model to identify the type of animal depicted in the image.

[0553] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0554] Based on the identified animal, the server selects images and sounds that the animal fears from a database and sends this information to the device, causing the animal to feel fear.

[0555] Terminal display of responses

[0556] The terminal plays the images and sounds received from the server.

[0557] The device displays the image received from the server on the display and simultaneously plays sound from the speaker, effectively scaring away animals.

[0558] Use of emotion engine by server

[0559] The server recognizes the user's emotions.

[0560] The emotion engine captures the user's facial expression data with a camera and analyzes their stress and satisfaction, thereby understanding the user's emotional state in real time.

[0561] The server adjusts the response based on the output of the emotion engine.

[0562] If the user's emotional state is inappropriate, the server runs an algorithm to optimize the animal's response, adjusting the images and sounds to make the animal feel more frightened, and then sends this adjusted information back to the device.

[0563] Specific examples

[0564] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0565] Device animal recognition:

[0566] The device captures an image of the rabbit with its camera and sends the image to the server.

[0567] Server-based animal identification:

[0568] The server analyzes the image and identifies the animal as a rabbit.

[0569] Server response generation:

[0570] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0571] Terminal display of response:

[0572] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0573] Server-based emotion recognition and modulation:

[0574] The server analyzes the user's emotional state with an emotion engine, and if the user is feeling stressed, determines more powerful images and sounds and retransmits them to the terminal.

[0575] In this way, the system of the present invention provides an efficient and effective response to pests, and can be optimized taking into account the emotional state of the user.

[0576] The processing flow will be explained below.

[0577] Step 1:

[0578] Server Initialization

[0579] The server loads the artificial intelligence model (animal_recognition_model) and emotion engine and distributes them to each device. With this initial setup, each device is ready to identify animals and adjust its response based on the user's emotions.

[0580] Step 2:

[0581] Animal detection by device

[0582] The device uses a camera to periodically capture images of its surroundings, for example, once per second, to monitor for approaching animals.

[0583] Step 3:

[0584] Sending images by device

[0585] The captured image is immediately uploaded to the server, allowing the server to perform image analysis in real time.

[0586] Step 4:

[0587] Server-based animal identification

[0588] The server then uses an artificial intelligence model to analyze the received images and identify the type of animal that is present in the image, which then identifies which animal is approaching.

[0589] Step 5:

[0590] Server decides what to do

[0591] Based on the identified animal type, the server determines the images and sounds that the animal dislikes, which information is obtained from a pre-defined database.

[0592] Step 6:

[0593] Server Response Generation

[0594] The server generates response data containing images and sounds that the animal dislikes, and sends it to the device. This data is then formatted in a format that the device can accept.

[0595] Step 7:

[0596] Displaying images by device

[0597] The device displays the image received from the server on its display, creating a visual threat to the animals.

[0598] Step 8:

[0599] Playing sounds through the device

[0600] The device receives the sound from the server and plays it back through the speaker, creating an auditory threat to the animals.

[0601] Step 9:

[0602] Use of emotion engine by server

[0603] The server uses an emotion engine to analyze the user's facial expression data and detect the user's stress and satisfaction, thereby understanding the user's emotional state in real time.

[0604] Step 10:

[0605] Adjusting responses based on user emotions

[0606] The server readjusts its response to the animal based on the output of the emotion engine: if the user is stressed, it determines stronger images and sounds and retransmits them to the device.

[0607] Specific examples

[0608] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0609] Device animal recognition:

[0610] The device captures an image of the rabbit with its camera and sends the image to the server.

[0611] Server-based animal identification:

[0612] The server analyzes the image and identifies the animal as a rabbit.

[0613] Server response generation:

[0614] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0615] Terminal display of response:

[0616] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0617] Server-based emotion recognition and modulation:

[0618] The server analyzes the user's emotional state with an emotion engine, and if the user is feeling stressed, determines more powerful images and sounds and retransmits them to the terminal.

[0619] In this way, the system of the present invention provides an efficient and effective response to pests, and can be optimized taking into account the emotional state of the user.

[0620] Example 2

[0621] 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."

[0622] While conventional animal repellent systems have the ability to identify the type of animal and determine the appropriate countermeasure, they lack the ability to adjust the countermeasure based on the user's emotional state, which means that their long-term effectiveness cannot be guaranteed.In addition, they often only take a certain countermeasure against animals, which can become less effective depending on the animal's adaptability.

[0623] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0624] In this invention, the server includes means for capturing an image of an approaching animal with a camera, means for transmitting the image to the server, means for identifying the animal in the image by the server, means for determining images and sounds that the animal dislikes based on the identified animal, means for displaying the determined images on a display, means for playing the determined sounds from a speaker, means for recognizing the user's emotions, and means for adjusting countermeasures against the animal based on the user's emotional state, thereby making it possible to provide optimal countermeasures that take into account not only the animal but also the user's emotional state.

[0625] A "camera" is a device that captures visual information from its surroundings and records it as an image.

[0626] A "server" is a centralized computer system that processes and manages data over a network.

[0627] "Means for transmitting images" refers to communication techniques and devices for transferring captured image data to a server.

[0628] "Animal identification means" refers to the technology or algorithms used to analyze the received image data and identify the type of animal in the image.

[0629] "Means for determining images and sounds that an animal dislikes" refers to a method and apparatus that, based on an identified animal, selects images and sounds that the animal tends to avoid.

[0630] "Means for displaying" refers to devices and techniques for visually displaying the determined image.

[0631] "Means for playing from a speaker" refers to devices and techniques for playing the determined sound as audio.

[0632] "Means for recognizing user emotions" refers to technologies and algorithms for analyzing a user's facial expressions and voice data to identify their emotional state.

[0633] "Means for adjusting behavior toward animals" refers to means and techniques for dynamically changing behavior toward animals based on the emotional state of the user.

[0634] An "artificial intelligence model" is a computational model based on machine learning algorithms that are trained to perform specific tasks.

[0635] A "database" is a system for efficiently storing and retrieving structured data.

[0636] In this invention, a system is implemented that provides effective measures against a wide variety of harmful animals using terminals installed on farmland, a server, and an emotion engine for recognizing user emotions.

[0637] First, the device is installed in the field and uses a camera module to capture images of approaching animals. The images are temporarily stored on the device and then sent to a server via network communication. This communication mainly uses wireless networks such as Wi-Fi, 4G, and 5G.

[0638] The server analyzes the transmitted image using a trained AI model (animal_recognition_model). This AI model includes the characteristics of various animals and uses a specific algorithm to identify the type of animal in the image. Based on the identified animal, the server selects images and sounds that the animal dislikes from a database. This database contains pre-registered images and sounds that each type of animal dislikes.

[0639] The server then retransmits the selected image and sound data to the device, which displays the received images on its display and plays the sounds through its speaker, thus driving animals away from the field and protecting the crops.

[0640] Furthermore, the system incorporates an emotion engine. To recognize the user's emotional state, the emotion engine captures and analyzes the user's facial expression data using a camera. Based on the analysis results obtained from the emotion engine, the server adjusts the response to the animals as needed. For example, if the user is feeling anxious or stressed, the server selects more powerful images and sounds and retransmits them to the device.

[0641] As a concrete example, consider the case where a device installed in a field recognizes a rabbit using a camera. The device captures an image of the rabbit and sends it to a server. The server analyzes the received image and identifies the animal as a rabbit. The server then selects an image of an eagle and the sound of a dog barking, which rabbits are afraid of, and sends these to the device. The device then displays the received image of the eagle on its display and plays the sound of a dog barking through its speaker. This process can scare away rabbits from the field.

[0642] If the user expresses dissatisfaction with the system's operation, the emotion engine analyzes the facial expression data and sends the results to the server, which then selects more effective images and sounds and retransmits them to the device, thereby enhancing the animal-repelling effect.

[0643] Examples of prompts include:

[0644] "Please explain the process by which a device installed on farmland uses a camera to recognize rabbits and determine the image and sound to scare them away."

[0645] "Please explain how the server will change its response if the user expresses dissatisfaction with the system."

[0646] This system provides optimal animal repelling measures that take into account not only the animals but also the emotional state of the user.

[0647] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0648] Program processing flow

[0649] Step 1: Initial Setup

[0650] 1. Loading and distributing models by the server

[0651] Input: Trained AI model and emotion engine

[0652] Specific operation: The server loads the trained AI model (animal_recognition_model) and emotion engine and distributes them to all devices via the network. The distributed model is used by the device to identify animals.

[0653] Step 2: Prepare for Animal Recognition

[0654] 2. Device camera and communication settings

[0655] Input: Camera module and communication module

[0656] Specific operation: The device initializes the camera and sets up network communication with the server, so that the device is ready to capture image data and send it to the server.

[0657] Step 3: Capture an image of the animal

[0658] 3. Periodic image capture by the device

[0659] Input: Visual information of the surroundings acquired by the camera

[0660] Specific operation: The device captures an image of the surroundings using the camera once per second. For example, it calls the "capture_image()" function to obtain image data.

[0661] Output: Captured image data

[0662] 4. Sending images to the server

[0663] Input: Captured image data

[0664] Specific operation: The device uses the "send_image_to_server(image)" function to send the captured image data to the server.

[0665] Output: Image data sent to the server

[0666] Step 4: Identify the animal species

[0667] 5. Image analysis by the server

[0668] Input: Submitted image data and artificial intelligence model

[0669] Specific operation: The server uses the "analyze_image(image, animal_recognition_model)" function to analyze the image data with an artificial intelligence model to identify the type of animal in the image.

[0670] Output: Identified animal species

[0671] Step 5: Determine the images and sounds you find difficult

[0672] 6. Server Determination of Response Data

[0673] Input: Identified animal species

[0674] What happens: The server uses the "select_response_for_animal(animal_type)" function to select from the database the images and sounds that the animal dislikes. For example, for a rabbit, it selects the image of an eagle and the sound of a dog barking.

[0675] Output: Determined image and sound data

[0676] 7. Sending response data to the terminal

[0677] Input: Determined image and sound data

[0678] Specific operation: The server uses the "send_response_to_terminal(response_data)" function to send the selected image and sound to the terminal.

[0679] Output: Image and sound data sent to the device

[0680] Step 6: View the response

[0681] 8. Displaying images and playing sounds on the device

[0682] Input: Image and sound data sent to the device

[0683] Specific operation: The device displays an image on the display using the "display_image(image)" function and plays a sound from the speaker using the "play_sound(sound)" function, which has a deterrent effect on the animals.

[0684] Output: The displayed image and the played sound

[0685] Step 7: Use the Emotion Engine

[0686] 9. Emotion Analysis by Server

[0687] Input: User's facial expression data

[0688] Specific operation: The server uses the emotion engine to identify the user's emotional state by analyzing the user's facial expression data, for example, by using the "analyze_user_emotion(user_image)" function.

[0689] Output: Emotional state analysis result

[0690] 10. Adjusting your response based on emotions

[0691] Input: Emotional state analysis results

[0692] What it does: The server uses the "adjust_response_based_on_emotion(emotion_data)" function to adjust its response to the animal based on its emotional state: if the user is stressed, it will select stronger images and sounds and resend them to the device.

[0693] Output: Modified image and sound data

[0694] Through these steps, the system can effectively identify animals and coordinate response measures.

[0695] (Application example 2)

[0696] 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."

[0697] Conventional security systems are limited to detecting intruders and suspicious individuals, and offer limited options for specific countermeasures after detection. Furthermore, because they provide only uniform countermeasures without taking the user's emotional state into consideration, inappropriate responses can be taken, limiting security optimization. This makes it difficult to implement effective and flexible countermeasures. The present invention aims to solve these problems and provide a more effective and user-friendly security system.

[0698] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing an image of an approaching target with a camera, means for transmitting the image to the server, means for identifying the target in the image by the server, means for determining images and sounds that the target dislikes based on the identified target, means for displaying the determined images on a display, means for playing the determined sounds from a speaker, means for recognizing the user's emotion using an emotion engine, and means for adjusting countermeasures based on the recognized emotion. This makes it possible to effectively repel intruders in real time and optimize countermeasures in accordance with the user's emotional state.

[0699] A "camera" is a device for taking images or videos.

[0700] A "server" is a computer system that processes and stores data, and provides services in response to requests from clients.

[0701] An "image" is information about a still image that visually captures an object, landscape, etc.

[0702] "Subject" refers to any object or living thing within the camera's field of view that is the subject of surveillance or identification.

[0703] "Identification" is the process of identifying specific objects in an image and determining their type and characteristics.

[0704] "Images that a particular subject dislikes" refers to visual information that a particular subject does not want to see or that a particular subject psychologically dislikes.

[0705] "Sound" is an auditory stimulus that is transmitted as vibrations in the air, and when a particular object is disliked, it acts to make the animal flee from that object.

[0706] A "display" is a device that displays images or videos by electrical means.

[0707] A "speaker" is a device that converts electrical signals into audio and produces sound.

[0708] An "emotion engine" is a software or hardware system that analyzes a user's facial expressions and behavior and recognizes their emotional state.

[0709] A "user" is a person who uses, operates, or monitors the system.

[0710] "Recognition" refers to the process of understanding and identifying the situation and characteristics of an object from data acquired by cameras and sensors.

[0711] "Countermeasures" refer to specific actions or measures taken to deal with a specific event or situation.

[0712] "Adjustment" refers to the act of making changes or adjustments to achieve an appropriate state according to given conditions or circumstances.

[0713] A "system" is a collection of integrated devices and processes in which different elements work together to achieve a specific function.

[0714] This invention is a security system that includes a camera, a server, a display, a speaker, and an emotion engine. By linking these elements, it provides a system that detects intruders and suspicious individuals in real time and implements effective countermeasures. The system configuration and operation are detailed below.

[0715] The basic operation of the system is as follows: First, the camera periodically sends images it captures to the server, and the server identifies the object in the received image. A pre-trained artificial intelligence model is used to do this. This model identifies the type of object and, based on the results, determines the images and sounds that the object dislikes. The determined images are shown on the display and the sounds are played from the speaker. This effectively scares away objects (such as suspicious people or animals).

[0716] Next, we will explain the function of the emotion engine. The emotion engine recognizes and analyzes the user's emotions in real time from facial expression data captured by the camera. The server uses this emotion data to adjust countermeasures as appropriate. For example, if the user is feeling very stressed, the server can use more effective images and sounds to scare away the target. This function allows the system to adapt to the user's emotional state and provide the most appropriate countermeasures.

[0717] Here's a specific example: Suppose a camera installed in a residential garden detects an intruder. In this case, the camera captures an image of the intruder and sends it to a server. The server analyzes the received image and identifies the intruder as a human. The server then determines an alarm sound (e.g., a loud dog barking) and an image (e.g., an image of a surveillance camera or a warning sign) that the intruder will dislike, and sends them to the device. The device then plays the received alarm sound from its speaker and displays the image on its display, effectively scaring the intruder away.

[0718] Furthermore, when the emotion engine is used, if the user is in a situation where they are feeling extremely stressed, the emotion engine can detect this and send instructions to the server to select stronger warning sounds or images, resulting in stronger responses being taken and increasing the effectiveness of the system.

[0719] Examples of prompts include:

[0720] "Design a system that uses image data captured by a camera to identify a suspicious individual and determine the optimal audible warning or visual image to scare them away."

[0721] In this way, the system of the present invention can realize real-time monitoring and effective repelling, and further provide flexible countermeasures that adapt to the user's emotional state.

[0722] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0723] Step 1:

[0724] The device periodically captures images of the surrounding area using a camera and sends the captured image data to a server. The input is the raw image data captured by the camera, and the output is the image data sent to the server. Specifically, the camera captures images at regular intervals and sends the image data to the server via the Internet. This allows the server to receive monitoring data in real time.

[0725] Step 2:

[0726] The server takes the received image data as input and uses a pre-trained generative AI model to identify the object in the image. Based on this identification result, it determines the next countermeasure. Specifically, the server analyzes the image using an image recognition algorithm (e.g., a deep learning model) and classifies the object as human, suspicious person, animal, etc. The output is the type of object identified.

[0727] Step 3:

[0728] Based on the type of identified object, the server retrieves from a database images and sounds that the object finds frightening and sends them to the device. The input here is the type of identified object, and the output is image and sound data that will induce fear in the object appropriately. Specifically, the server searches the database for corresponding sound and image files and sends this data to the device. At this time, the emotion engine analyzes the user's emotional state, and the selection of images and sounds may be adjusted based on this information.

[0729] Step 4:

[0730] The device receives image and sound data from the server as input, displays the image on the display, and plays the sound from the speaker. This has the effect of scaring away the target. Specifically, the device's display displays a frightening image, and the speaker plays a warning sound. The output is the displayed image and the played sound, with the ultimate goal being to make the target leave the area.

[0731] Step 5:

[0732] The server uses an emotion engine to monitor the user's emotional state in real time. The input is the user's facial expression data, and the output is the user's emotional state. Specifically, it analyzes the facial expression data captured by the user's camera and determines whether the user is feeling stressed or satisfied.

[0733] Step 6:

[0734] The server adjusts the response to the target as needed based on the user's emotional state. The adjusted response is sent back to the device and played. The input is the user's emotional state, and the output is adjusted image and sound data. Specifically, if the emotion engine determines that the user's stress level is high, it selects stronger warning sounds and images. This adjusted data is sent to the device and played.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] [Third embodiment]

[0739] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0740] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0741] 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).

[0742] 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.

[0743] 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.

[0744] 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).

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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."

[0751] The present invention is a system in which a terminal installed in farmland uses a camera to capture images of approaching animals and transmits the images to a server. The server analyzes the transmitted images and identifies the type of animal. Next, based on the identified animal, it determines the images and sounds that the animal dislikes and transmits a response to the terminal. Based on the received response, the terminal displays the image on its display and plays the sound from its speaker. This system can effectively protect crops from a wide variety of pests.

[0752] Specific program processing explanation

[0753] Server Initialization

[0754] The server loads the artificial intelligence model and distributes it to the terminal.

[0755] When a user initially configures the system, the server loads the trained AI model (animal_recognition_model) and distributes it to all devices, enabling each device to recognize animals.

[0756] Animal recognition by device

[0757] The device uses a camera to capture images of the animals and send them to the server.

[0758] The device periodically captures images of its surroundings using a camera. For example, an image is taken once per second, and the captured images are sent to a server. This allows the server to perform real-time image analysis on devices installed in remote locations.

[0759] Server-based animal identification

[0760] The server analyzes the image and identifies the type of animal.

[0761] The server analyzes the received images using an artificial intelligence model to identify the type of animal depicted in the image.

[0762] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0763] Based on the identified animal, the server selects images and sounds that the animal fears from a database and sends this information to the device, causing the animal to feel fear.

[0764] Terminal display of responses

[0765] The terminal plays the images and sounds received from the server.

[0766] The device displays the image received from the server on the display and simultaneously plays sound from the speaker, effectively scaring away animals.

[0767] Specific examples

[0768] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0769] Device animal recognition:

[0770] The device captures an image of the rabbit with its camera and sends the image to the server.

[0771] Server-based animal identification:

[0772] The server analyzes the received image and identifies the animal as a rabbit.

[0773] Server response generation:

[0774] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0775] Terminal display of response:

[0776] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0777] This prevents rabbits from approaching crops, protecting them. This system can be remotely controlled and is effective against a wide range of pests, making it a highly effective agricultural protection tool.

[0778] The processing flow will be explained below.

[0779] Step 1:

[0780] Server Initialization

[0781] The server loads the artificial intelligence model (animal_recognition_model) and distributes it to each device. This initial setup prepares the device to recognize animals.

[0782] Step 2:

[0783] Animal detection by device

[0784] The device uses a camera to periodically capture images of its surroundings, for example, once per second, to monitor for approaching animals.

[0785] Step 3:

[0786] Sending images by device

[0787] The captured image is immediately uploaded to the server, allowing the server to perform image analysis in real time.

[0788] Step 4:

[0789] Server-based animal identification

[0790] The server then uses an artificial intelligence model to analyze the received images and identify the type of animal that is present in the image, which then identifies which animal is approaching.

[0791] Step 5:

[0792] Server decides what to do

[0793] Based on the identified animal type, the server determines the images and sounds that the animal dislikes, which information is obtained from a pre-defined database.

[0794] Step 6:

[0795] Server Response Generation

[0796] The server generates response data containing images and sounds that the animal dislikes, and sends it to the device. This data is then formatted in a format that the device can accept.

[0797] Step 7:

[0798] Displaying images by device

[0799] The device displays the image received from the server on its display, creating a visual threat to the animals.

[0800] Step 8:

[0801] Playing sounds through the device

[0802] The device receives the sound from the server and plays it back through the speaker, creating an auditory threat to the animals.

[0803] Step 9:

[0804] Observing pest behavior

[0805] Users can view logs on their devices and on the server to see which animals responded and how they reacted, allowing them to assess the effectiveness of the system and make adjustments as needed.

[0806] Example 1

[0807] 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."

[0808] There is a need for an effective method to repel animals that damage crops in agricultural fields. Conventional methods have difficulty in quickly taking different countermeasures depending on the type of animal, and there is a lack of systems that allow remote control. This has led to the problem of not being able to prevent animal damage in a timely manner.

[0809] 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.

[0810] In this invention, the server includes means for taking pictures of approaching animals with a camera, means for transmitting the images to the server, means for identifying the animals in the images by the server, means for determining images and sounds that the animals dislike based on the identified animals, means for displaying the determined images on a display, and means for playing the determined sounds from a speaker. This makes it possible to identify animals in real time and instantly scare them away using appropriate images and sounds.

[0811] A "camera" is a device that captures images of the surroundings and outputs them as image data.

[0812] A "server" is a computer system that receives requests from client terminals via a network and processes them.

[0813] An "image" is a digital representation of visual information captured by a camera.

[0814] "Animals" refers to a group of living organisms that have a specific behavior, and in the present invention refers to organisms that may cause damage to agricultural land.

[0815] An "artificial intelligence model" is a set of pre-trained algorithms used to analyze input data and make decisions.

[0816] A "terminal" is an electronic device that can be connected to a network and communicates with a server.

[0817] A "display" is an output device for displaying images and videos.

[0818] A "speaker" is an output device for reproducing voice or sound.

[0819] A "database" is a collection of data and a system that enables efficient search and retrieval of data.

[0820] "Recognition" is the process of identifying a specific object from input image data.

[0821] The present invention is a system that uses a terminal installed in farmland to detect the approach of animals and respond appropriately. This system is realized by combining a camera, a server, a display, a speaker, and an artificial intelligence model.

[0822] First, when the user initially configures the system, the server loads a trained artificial intelligence model (animal_recognition_model) and distributes it to each device. This model is a group of algorithms for identifying animal species, and through training it is possible to achieve highly accurate identification.

[0823] The device is then installed in the field and periodically captures images of the surrounding area with its camera. This image data is then sent to the server at intervals of, for example, once per second. The transmission protocol is HTTP POST, and the image data is sent in binary format.

[0824] The server then calls an AI model running on a Python script to analyze the received image. The AI ​​model analyzes the image provided as input and identifies the type of animal depicted in the image. The identification result is expressed as a probability, and is returned in the form of, for example, "80% probability that it is a rabbit."

[0825] Based on the identified animal, the server selects images and sounds that the animal dislikes from a database containing pre-defined image and sound pairs for each animal type. Once the appropriate images and sounds are selected, they are sent to the device.

[0826] The device displays the received image on the screen and plays a sound from the speaker at the same time, which scares the animals and makes them leave the field, preventing them from damaging crops.

[0827] As a concrete example of this system, consider the case where a device installed in a farm recognizes a rabbit using a camera. In this case, the device captures an image of the rabbit with its camera and sends it to the server. The server analyzes the received image and identifies it as a rabbit. The server then selects an image of an eagle, which rabbits are afraid of, and the sound of a dog barking, and sends these to the device. The device displays the received image of the eagle on its display and plays the sound of a dog barking from its speaker, thereby scaring away the rabbit.

[0828] An example prompt might be, "Please explain how to identify the type of animal recognized by a camera-equipped device installed in farmland, determine the image and sound to scare the animal away, and send them to the device."

[0829] As a result, this system can be remotely controlled and is a highly effective means of protecting farmland against a wide range of pests.

[0830] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0831] Step 1:

[0832] The server loads the artificial intelligence model and distributes it to the terminal.

[0833] Input: The user clicks the "Initial Settings" button on the system administration screen.

[0834] How it works: The server loads a trained artificial intelligence model for animal recognition (animal_recognition_model) into memory, then distributes this model to each device in the form of a firmware update.

[0835] Output: The animal_recognition_model is installed on each device.

[0836] Step 2:

[0837] The device uses a camera to capture images of the animals and send them to the server.

[0838] Input: A still image taken by the camera.

[0839] How it works: The device's camera captures an image of its surroundings once every second. The image data is sent to the server using HTTP POST. This image data is sent in binary format.

[0840] Output: Image data sent to the server.

[0841] Step 3:

[0842] The server analyzes the image and identifies the type of animal.

[0843] Input: Image data sent from the device.

[0844] How it works: The server calls an AI model running on a Python script and provides image data as input. The AI ​​model analyzes the image and identifies the type of animal in it. The identification result is expressed as a probability, such as "80% chance that it's a rabbit."

[0845] Output: Identified animal species and their probabilities.

[0846] Step 4:

[0847] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0848] Input: Animal species and their probabilities obtained from the AI ​​model.

[0849] How it works: Based on the identified animal type, the server selects images and sounds that the animal dislikes from a database. After selecting the appropriate images and sounds, it sends this information to the device.

[0850] Output: Image and sound data sent to the device.

[0851] Step 5:

[0852] The terminal plays the images and sounds received from the server.

[0853] Input: Image and sound data sent from the server.

[0854] Operation: The device first displays an image on the display using the received image data, and simultaneously plays sound data from the speaker using the audio library.

[0855] Output: The image shown on the display and the sound played through the speakers.

[0856] These are the specific processing steps of the program for this system, which enables real-time detection of animals damaging crops in farmland and immediate response.

[0857] (Application example 1)

[0858] 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."

[0859] Problems such as the introduction of foreign objects and unauthorized intrusions into factory production lines have a significant impact on safety and efficiency. Conventional methods require manual detection and removal of foreign objects, which requires significant time and manpower and increases the risk of errors. Furthermore, systems for quickly taking appropriate action are lacking, making real-time monitoring and response difficult. Therefore, the present invention aims to solve these problems and improve the efficiency and safety of factory operations.

[0860] 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.

[0861] In this invention, the server includes means for capturing an image of an approaching object with a camera, means for transmitting the image to the server, means for identifying the object in the image by the server, means for determining an image and sound that the object is sensitive to based on the identified object, means for displaying the determined image on a display device, means for playing the determined sound from an audio device, and means for performing an action to remove the object when it enters a specific area, thereby enabling the efficiency and safety of factory work to be improved.

[0862] "Object" refers to any object that exists on a factory line or within a detection range and needs to be identified or removed.

[0863] A "camera" is a photographic device that captures images and videos and provides the data for subsequent processing.

[0864] A "server" is a central processing unit that analyzes and manages data and serves as the control center for the entire system.

[0865] The "means for transmitting images" is a combination of network equipment and software for transferring captured images to a server.

[0866] "Means for identification" refers to algorithms and software that identify objects in captured images and determine their type and condition.

[0867] A "generative AI model" is an artificial intelligence model that is trained in advance based on a large amount of data and is able to identify images and objects with high accuracy in real time.

[0868] A "display device" is a display for visualizing images or messages.

[0869] "Sound device" means a speaker for playing determined sounds and providing auditory alerts and effects.

[0870] "Means for performing an action to remove an object when it invades" refers to a physical driving device such as a robot arm or actuator for removing an object when it invades a specific area.

[0871] A system for implementing this invention is for effectively managing foreign matter contamination, unauthorized entry, etc. in a factory production line. This system includes a camera, a server, a display device, an audio device, and several software components.

[0872] First, a camera periodically captures images of the production line. The captured images are then transferred to a server using an image transmission method. When the server receives the images, it uses a generative AI model to identify objects in the images. This generative AI model has been trained in advance using a large amount of data, enabling highly accurate identification in real time.

[0873] Based on the identified object, the server determines from a database the image and sound that the object is sensitive to. The determined image is displayed on a display device, and the determined sound is played from an audio device. This improves the efficiency and safety of the production line.

[0874] Furthermore, if an object enters a specific area, the server executes an action to remove the object, using physical driving devices such as a robot arm or actuator.

[0875] As a concrete example, consider the case where garbage gets mixed into a beverage production line at a factory. A camera captures an image of the garbage and sends it to a server. The server uses a generative AI model to identify the garbage, determines an appropriate image and sound for that garbage, and displays and plays them on a display and audio device. Furthermore, if the garbage enters a specific area, a robotic arm removes the garbage.

[0876] An example prompt might look like this:

[0877] "How can I use a trained model to detect debris and foreign objects on a production line in real time?"

[0878] How can I send an HTTP request to retrieve image and audio data based on the classification results?

[0879] In this way, the present invention makes it possible to respond quickly and accurately in real time to the intrusion of foreign matter or unauthorized access into a factory production line, thereby improving production efficiency and ensuring safety.

[0880] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0881] Step 1:

[0882] A camera periodically captures images of the factory production line. The input is the image data captured by the camera lens, and the output is the captured image file.

[0883] Step 2:

[0884] The captured image data is transferred to a server using an image transmission means, where the input is the captured image file and the output is the image data sent to the server.

[0885] Step 3:

[0886] The server passes the received image data to the generative AI model to identify the object. The input is the image data, and the output is the type and location of the identified object. Specifically, the generative AI model analyzes the image data and performs data calculations to identify the object.

[0887] Step 4:

[0888] Based on the identification results, the server determines the image and sound corresponding to the object from the database. The input is the type and location information of the identified object, and the output is the URL of the image to display and the URL of the audio file to play. Specifically, the server executes a database query to retrieve the appropriate data.

[0889] Step 5:

[0890] The determined image is sent from the server to the display device and displayed on the display device. The input is the URL of the image, and the output is the displayed image. Specifically, the image data is rendered on the display device's screen.

[0891] Step 6:

[0892] The determined sound is sent from the server to the sound device and played from the sound device. The input is the URL of the audio file, and the output is the played sound. Specifically, the audio data is played on the sound device's speaker.

[0893] Step 7:

[0894] When an object enters a specific area, the server executes an action to remove the object. The input is the object's location information, and the output is a trigger for the removal action. Specifically, the robot arm operates to remove the object.

[0895] Step 8:

[0896] After the elimination action is completed, the server records the system status as a log and notifies the user. The input is the result of the elimination action, and the output is the log data and a user notification. Specifically, the server saves the log in a database and creates a notification message based on the generative AI model.

[0897] This series of processing steps efficiently enables real-time detection and removal of foreign objects on factory production lines.

[0898] 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.

[0899] The present invention combines a system in which a device installed in farmland uses a camera to capture approaching animals and transmits the images to a server, with an emotion engine that recognizes the user's emotions. The server analyzes the transmitted images and identifies the type of animal. Next, based on the identified animal, it determines the images and sounds that the animal dislikes and transmits a response to the device. Based on the received response, the device displays an image on the display and plays a sound from the speaker. This system can effectively protect crops from a wide variety of pests. The emotion engine also recognizes the user's emotions, allowing the server to adjust countermeasures against animals as necessary.

[0900] Specific program processing explanation

[0901] Server Initialization

[0902] The server loads the artificial intelligence model and distributes it to the terminal.

[0903] When a user initially configures the system, the server loads the trained AI model (animal_recognition_model) and emotion engine and distributes this model to all devices, so that each device is ready to identify animals and adjust its response based on the user's emotions.

[0904] Animal recognition by device

[0905] The device uses a camera to capture images of the animals and send them to the server.

[0906] The device periodically captures images of its surroundings using a camera. For example, an image is taken once per second, and the captured images are sent to a server. This allows the server to perform real-time image analysis on devices installed in remote locations.

[0907] Server-based animal identification

[0908] The server analyzes the image and identifies the type of animal.

[0909] The server analyzes the received images using an artificial intelligence model to identify the type of animal depicted in the image.

[0910] The server determines the sound and image based on the identification result and transmits them to the terminal.

[0911] Based on the identified animal, the server selects images and sounds that the animal fears from a database and sends this information to the device, causing the animal to feel fear.

[0912] Terminal display of responses

[0913] The terminal plays the images and sounds received from the server.

[0914] The device displays the image received from the server on the display and simultaneously plays sound from the speaker, effectively scaring away animals.

[0915] Use of emotion engine by server

[0916] The server recognizes the user's emotions.

[0917] The emotion engine captures the user's facial expression data with a camera and analyzes their stress and satisfaction, thereby understanding the user's emotional state in real time.

[0918] The server adjusts the response based on the output of the emotion engine.

[0919] If the user's emotional state is inappropriate, the server runs an algorithm to optimize the animal's response, adjusting the images and sounds to make the animal feel more frightened, and then sends this adjusted information back to the device.

[0920] Specific examples

[0921] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0922] Device animal recognition:

[0923] The device captures an image of the rabbit with its camera and sends the image to the server.

[0924] Server-based animal identification:

[0925] The server analyzes the image and identifies the animal as a rabbit.

[0926] Server response generation:

[0927] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0928] Terminal display of response:

[0929] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0930] Server-based emotion recognition and modulation:

[0931] The server analyzes the user's emotional state with an emotion engine, and if the user is feeling stressed, determines more powerful images and sounds and retransmits them to the terminal.

[0932] In this way, the system of the present invention provides an efficient and effective response to pests, and can be optimized taking into account the emotional state of the user.

[0933] The processing flow will be explained below.

[0934] Step 1:

[0935] Server Initialization

[0936] The server loads the artificial intelligence model (animal_recognition_model) and emotion engine and distributes them to each device. With this initial setup, each device is ready to identify animals and adjust its response based on the user's emotions.

[0937] Step 2:

[0938] Animal detection by device

[0939] The device uses a camera to periodically capture images of its surroundings, for example, once per second, to monitor for approaching animals.

[0940] Step 3:

[0941] Sending images by device

[0942] The captured image is immediately uploaded to the server, allowing the server to perform image analysis in real time.

[0943] Step 4:

[0944] Server-based animal identification

[0945] The server then uses an artificial intelligence model to analyze the received images and identify the type of animal that is present in the image, which then identifies which animal is approaching.

[0946] Step 5:

[0947] Server decides what to do

[0948] Based on the identified animal type, the server determines the images and sounds that the animal dislikes, which information is obtained from a pre-defined database.

[0949] Step 6:

[0950] Server Response Generation

[0951] The server generates response data containing images and sounds that the animal dislikes, and sends it to the device. This data is then formatted in a format that the device can accept.

[0952] Step 7:

[0953] Displaying images by device

[0954] The device displays the image received from the server on its display, creating a visual threat to the animals.

[0955] Step 8:

[0956] Playing sounds through the device

[0957] The device receives the sound from the server and plays it back through the speaker, creating an auditory threat to the animals.

[0958] Step 9:

[0959] Use of emotion engine by server

[0960] The server uses an emotion engine to analyze the user's facial expression data and detect the user's stress and satisfaction, thereby understanding the user's emotional state in real time.

[0961] Step 10:

[0962] Adjusting responses based on user emotions

[0963] The server readjusts its response to the animal based on the output of the emotion engine: if the user is stressed, it determines stronger images and sounds and retransmits them to the device.

[0964] Specific examples

[0965] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[0966] Device animal recognition:

[0967] The device captures an image of the rabbit with its camera and sends the image to the server.

[0968] Server-based animal identification:

[0969] The server analyzes the image and identifies the animal as a rabbit.

[0970] Server response generation:

[0971] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[0972] Terminal display of response:

[0973] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[0974] Server-based emotion recognition and modulation:

[0975] The server analyzes the user's emotional state with an emotion engine, and if the user is feeling stressed, determines more powerful images and sounds and retransmits them to the terminal.

[0976] In this way, the system of the present invention provides an efficient and effective response to pests, and can be optimized taking into account the emotional state of the user.

[0977] Example 2

[0978] 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."

[0979] While conventional animal repellent systems have the ability to identify the type of animal and determine the appropriate countermeasure, they lack the ability to adjust the countermeasure based on the user's emotional state, which means that their long-term effectiveness cannot be guaranteed.In addition, they often only take a certain countermeasure against animals, which can become less effective depending on the animal's adaptability.

[0980] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0981] In this invention, the server includes means for capturing an image of an approaching animal with a camera, means for transmitting the image to the server, means for identifying the animal in the image by the server, means for determining images and sounds that the animal dislikes based on the identified animal, means for displaying the determined images on a display, means for playing the determined sounds from a speaker, means for recognizing the user's emotions, and means for adjusting countermeasures against the animal based on the user's emotional state, thereby making it possible to provide optimal countermeasures that take into account not only the animal but also the user's emotional state.

[0982] A "camera" is a device that captures visual information from its surroundings and records it as an image.

[0983] A "server" is a centralized computer system that processes and manages data over a network.

[0984] "Means for transmitting images" refers to communication techniques and devices for transferring captured image data to a server.

[0985] "Animal identification means" refers to the technology or algorithms used to analyze the received image data and identify the type of animal in the image.

[0986] "Means for determining images and sounds that an animal dislikes" refers to a method and apparatus that, based on an identified animal, selects images and sounds that the animal tends to avoid.

[0987] "Means for displaying" refers to devices and techniques for visually displaying the determined image.

[0988] "Means for playing from a speaker" refers to devices and techniques for playing the determined sound as audio.

[0989] "Means for recognizing user emotions" refers to technologies and algorithms for analyzing a user's facial expressions and voice data to identify their emotional state.

[0990] "Means for adjusting behavior toward animals" refers to means and techniques for dynamically changing behavior toward animals based on the emotional state of the user.

[0991] An "artificial intelligence model" is a computational model based on machine learning algorithms that are trained to perform specific tasks.

[0992] A "database" is a system for efficiently storing and retrieving structured data.

[0993] In this invention, a system is implemented that provides effective measures against a wide variety of harmful animals using terminals installed on farmland, a server, and an emotion engine for recognizing user emotions.

[0994] First, the device is installed in the field and uses a camera module to capture images of approaching animals. The images are temporarily stored on the device and then sent to a server via network communication. This communication mainly uses wireless networks such as Wi-Fi, 4G, and 5G.

[0995] The server analyzes the transmitted image using a trained AI model (animal_recognition_model). This AI model includes the characteristics of various animals and uses a specific algorithm to identify the type of animal in the image. Based on the identified animal, the server selects images and sounds that the animal dislikes from a database. This database contains pre-registered images and sounds that each type of animal dislikes.

[0996] The server then retransmits the selected image and sound data to the device, which displays the received images on its display and plays the sounds through its speaker, thus driving animals away from the field and protecting the crops.

[0997] Furthermore, the system incorporates an emotion engine. To recognize the user's emotional state, the emotion engine captures and analyzes the user's facial expression data using a camera. Based on the analysis results obtained from the emotion engine, the server adjusts the response to the animals as needed. For example, if the user is feeling anxious or stressed, the server selects more powerful images and sounds and retransmits them to the device.

[0998] As a concrete example, consider the case where a device installed in a field recognizes a rabbit using a camera. The device captures an image of the rabbit and sends it to a server. The server analyzes the received image and identifies the animal as a rabbit. The server then selects an image of an eagle and the sound of a dog barking, which rabbits are afraid of, and sends these to the device. The device then displays the received image of the eagle on its display and plays the sound of a dog barking through its speaker. This process can scare away rabbits from the field.

[0999] If the user expresses dissatisfaction with the system's operation, the emotion engine analyzes the facial expression data and sends the results to the server, which then selects more effective images and sounds and retransmits them to the device, thereby enhancing the animal-repelling effect.

[1000] Examples of prompts include:

[1001] "Please explain the process by which a device installed on farmland uses a camera to recognize rabbits and determine the image and sound to scare them away."

[1002] "Please explain how the server will change its response if the user expresses dissatisfaction with the system."

[1003] This system provides optimal animal repelling measures that take into account not only the animals but also the emotional state of the user.

[1004] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1005] Program processing flow

[1006] Step 1: Initial Setup

[1007] 1. Loading and distributing models by the server

[1008] Input: Trained AI model and emotion engine

[1009] Specific operation: The server loads the trained AI model (animal_recognition_model) and emotion engine and distributes them to all devices via the network. The distributed model is used by the device to identify animals.

[1010] Step 2: Prepare for Animal Recognition

[1011] 2. Device camera and communication settings

[1012] Input: Camera module and communication module

[1013] Specific operation: The device initializes the camera and sets up network communication with the server, so that the device is ready to capture image data and send it to the server.

[1014] Step 3: Capture an image of the animal

[1015] 3. Periodic image capture by the device

[1016] Input: Visual information of the surroundings acquired by the camera

[1017] Specific operation: The device captures an image of the surroundings using the camera once per second. For example, it calls the "capture_image()" function to obtain image data.

[1018] Output: Captured image data

[1019] 4. Sending images to the server

[1020] Input: Captured image data

[1021] Specific operation: The device uses the "send_image_to_server(image)" function to send the captured image data to the server.

[1022] Output: Image data sent to the server

[1023] Step 4: Identify the animal species

[1024] 5. Image analysis by the server

[1025] Input: Submitted image data and artificial intelligence model

[1026] Specific operation: The server uses the "analyze_image(image, animal_recognition_model)" function to analyze the image data with an artificial intelligence model to identify the type of animal in the image.

[1027] Output: Identified animal species

[1028] Step 5: Determine the images and sounds you find difficult

[1029] 6. Server Determination of Response Data

[1030] Input: Identified animal species

[1031] What happens: The server uses the "select_response_for_animal(animal_type)" function to select from the database the images and sounds that the animal dislikes. For example, for a rabbit, it selects the image of an eagle and the sound of a dog barking.

[1032] Output: Determined image and sound data

[1033] 7. Sending response data to the terminal

[1034] Input: Determined image and sound data

[1035] Specific operation: The server uses the "send_response_to_terminal(response_data)" function to send the selected image and sound to the terminal.

[1036] Output: Image and sound data sent to the device

[1037] Step 6: View the response

[1038] 8. Displaying images and playing sounds on the device

[1039] Input: Image and sound data sent to the device

[1040] Specific operation: The device displays an image on the display using the "display_image(image)" function and plays a sound from the speaker using the "play_sound(sound)" function, which has a deterrent effect on the animals.

[1041] Output: The displayed image and the played sound

[1042] Step 7: Use the Emotion Engine

[1043] 9. Emotion Analysis by Server

[1044] Input: User's facial expression data

[1045] Specific operation: The server uses the emotion engine to identify the user's emotional state by analyzing the user's facial expression data, for example, by using the "analyze_user_emotion(user_image)" function.

[1046] Output: Emotional state analysis result

[1047] 10. Adjusting your response based on emotions

[1048] Input: Emotional state analysis results

[1049] What it does: The server uses the "adjust_response_based_on_emotion(emotion_data)" function to adjust its response to the animal based on its emotional state: if the user is stressed, it will select stronger images and sounds and resend them to the device.

[1050] Output: Modified image and sound data

[1051] Through these steps, the system can effectively identify animals and coordinate response measures.

[1052] (Application example 2)

[1053] 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."

[1054] Conventional security systems are limited to detecting intruders and suspicious individuals, and offer limited options for specific countermeasures after detection. Furthermore, because they provide only uniform countermeasures without taking the user's emotional state into consideration, inappropriate responses can be taken, limiting security optimization. This makes it difficult to implement effective and flexible countermeasures. The present invention aims to solve these problems and provide a more effective and user-friendly security system.

[1055] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing an image of an approaching target with a camera, means for transmitting the image to the server, means for identifying the target in the image by the server, means for determining images and sounds that the target dislikes based on the identified target, means for displaying the determined images on a display, means for playing the determined sounds from a speaker, means for recognizing the user's emotion using an emotion engine, and means for adjusting countermeasures based on the recognized emotion. This makes it possible to effectively repel intruders in real time and optimize countermeasures in accordance with the user's emotional state.

[1056] A "camera" is a device for taking images or videos.

[1057] A "server" is a computer system that processes and stores data, and provides services in response to requests from clients.

[1058] An "image" is information about a still image that visually captures an object, landscape, etc.

[1059] "Subject" refers to any object or living thing within the camera's field of view that is the subject of surveillance or identification.

[1060] "Identification" is the process of identifying specific objects in an image and determining their type and characteristics.

[1061] "Images that a particular subject dislikes" refers to visual information that a particular subject does not want to see or that a particular subject psychologically dislikes.

[1062] "Sound" is an auditory stimulus that is transmitted as vibrations in the air, and when a particular object is disliked, it acts to make the animal flee from that object.

[1063] A "display" is a device that displays images or videos by electrical means.

[1064] A "speaker" is a device that converts electrical signals into audio and produces sound.

[1065] An "emotion engine" is a software or hardware system that analyzes a user's facial expressions and behavior and recognizes their emotional state.

[1066] A "user" is a person who uses, operates, or monitors the system.

[1067] "Recognition" refers to the process of understanding and identifying the situation and characteristics of an object from data acquired by cameras and sensors.

[1068] "Countermeasures" refer to specific actions or measures taken to deal with a specific event or situation.

[1069] "Adjustment" refers to the act of making changes or adjustments to achieve an appropriate state according to given conditions or circumstances.

[1070] A "system" is a collection of integrated devices and processes in which different elements work together to achieve a specific function.

[1071] This invention is a security system that includes a camera, a server, a display, a speaker, and an emotion engine. By linking these elements, it provides a system that detects intruders and suspicious individuals in real time and implements effective countermeasures. The system configuration and operation are detailed below.

[1072] The basic operation of the system is as follows: First, the camera periodically sends images it captures to the server, and the server identifies the object in the received image. A pre-trained artificial intelligence model is used to do this. This model identifies the type of object and, based on the results, determines the images and sounds that the object dislikes. The determined images are shown on the display and the sounds are played from the speaker. This effectively scares away objects (such as suspicious people or animals).

[1073] Next, we will explain the function of the emotion engine. The emotion engine recognizes and analyzes the user's emotions in real time from facial expression data captured by the camera. The server uses this emotion data to adjust countermeasures as appropriate. For example, if the user is feeling very stressed, the server can use more effective images and sounds to scare away the target. This function allows the system to adapt to the user's emotional state and provide the most appropriate countermeasures.

[1074] Here's a specific example: Suppose a camera installed in a residential garden detects an intruder. In this case, the camera captures an image of the intruder and sends it to a server. The server analyzes the received image and identifies the intruder as a human. The server then determines an alarm sound (e.g., a loud dog barking) and an image (e.g., an image of a surveillance camera or a warning sign) that the intruder will dislike, and sends them to the device. The device then plays the received alarm sound from its speaker and displays the image on its display, effectively scaring the intruder away.

[1075] Furthermore, when the emotion engine is used, if the user is in a situation where they are feeling extremely stressed, the emotion engine can detect this and send instructions to the server to select stronger warning sounds or images, resulting in stronger responses being taken and increasing the effectiveness of the system.

[1076] Examples of prompts include:

[1077] "Design a system that uses image data captured by a camera to identify a suspicious individual and determine the optimal audible warning or visual image to scare them away."

[1078] In this way, the system of the present invention can realize real-time monitoring and effective repelling, and further provide flexible countermeasures that adapt to the user's emotional state.

[1079] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1080] Step 1:

[1081] The device periodically captures images of the surrounding area using a camera and sends the captured image data to a server. The input is the raw image data captured by the camera, and the output is the image data sent to the server. Specifically, the camera captures images at regular intervals and sends the image data to the server via the Internet. This allows the server to receive monitoring data in real time.

[1082] Step 2:

[1083] The server takes the received image data as input and uses a pre-trained generative AI model to identify the object in the image. Based on this identification result, it determines the next countermeasure. Specifically, the server analyzes the image using an image recognition algorithm (e.g., a deep learning model) and classifies the object as human, suspicious person, animal, etc. The output is the type of object identified.

[1084] Step 3:

[1085] Based on the type of identified object, the server retrieves from a database images and sounds that the object finds frightening and sends them to the device. The input here is the type of identified object, and the output is image and sound data that will induce fear in the object appropriately. Specifically, the server searches the database for corresponding sound and image files and sends this data to the device. At this time, the emotion engine analyzes the user's emotional state, and the selection of images and sounds may be adjusted based on this information.

[1086] Step 4:

[1087] The device receives image and sound data from the server as input, displays the image on the display, and plays the sound from the speaker. This has the effect of scaring away the target. Specifically, the device's display displays a frightening image, and the speaker plays a warning sound. The output is the displayed image and the played sound, with the ultimate goal being to make the target leave the area.

[1088] Step 5:

[1089] The server uses an emotion engine to monitor the user's emotional state in real time. The input is the user's facial expression data, and the output is the user's emotional state. Specifically, it analyzes the facial expression data captured by the user's camera and determines whether the user is feeling stressed or satisfied.

[1090] Step 6:

[1091] The server adjusts the response to the target as needed based on the user's emotional state. The adjusted response is sent back to the device and played. The input is the user's emotional state, and the output is adjusted image and sound data. Specifically, if the emotion engine determines that the user's stress level is high, it selects stronger warning sounds and images. This adjusted data is sent to the device and played.

[1092] 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.

[1093] 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.

[1094] 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.

[1095] [Fourth embodiment]

[1096] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1097] 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.

[1098] 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).

[1099] 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.

[1100] 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.

[1101] 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).

[1102] 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.

[1103] 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.

[1104] 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.

[1105] 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.

[1106] 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.

[1107] 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.

[1108] 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."

[1109] The present invention is a system in which a terminal installed in farmland uses a camera to capture images of approaching animals and transmits the images to a server. The server analyzes the transmitted images and identifies the type of animal. Next, based on the identified animal, it determines the images and sounds that the animal dislikes and transmits a response to the terminal. Based on the received response, the terminal displays the image on its display and plays the sound from its speaker. This system can effectively protect crops from a wide variety of pests.

[1110] Specific program processing explanation

[1111] Server Initialization

[1112] The server loads the artificial intelligence model and distributes it to the terminal.

[1113] When a user initially configures the system, the server loads the trained AI model (animal_recognition_model) and distributes it to all devices, enabling each device to recognize animals.

[1114] Animal recognition by device

[1115] The device uses a camera to capture images of the animals and send them to the server.

[1116] The device periodically captures images of its surroundings using a camera. For example, an image is taken once per second, and the captured images are sent to a server. This allows the server to perform real-time image analysis on devices installed in remote locations.

[1117] Server-based animal identification

[1118] The server analyzes the image and identifies the type of animal.

[1119] The server analyzes the received images using an artificial intelligence model to identify the type of animal depicted in the image.

[1120] The server determines the sound and image based on the identification result and transmits them to the terminal.

[1121] Based on the identified animal, the server selects images and sounds that the animal fears from a database and sends this information to the device, causing the animal to feel fear.

[1122] Terminal display of responses

[1123] The terminal plays the images and sounds received from the server.

[1124] The device displays the image received from the server on the display and simultaneously plays sound from the speaker, effectively scaring away animals.

[1125] Specific examples

[1126] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[1127] Device animal recognition:

[1128] The device captures an image of the rabbit with its camera and sends the image to the server.

[1129] Server-based animal identification:

[1130] The server analyzes the received image and identifies the animal as a rabbit.

[1131] Server response generation:

[1132] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[1133] Terminal display of response:

[1134] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[1135] This prevents rabbits from approaching crops, protecting them. This system can be remotely controlled and is effective against a wide range of pests, making it a highly effective agricultural protection tool.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] Server Initialization

[1139] The server loads the artificial intelligence model (animal_recognition_model) and distributes it to each device. This initial setup prepares the device to recognize animals.

[1140] Step 2:

[1141] Animal detection by device

[1142] The device uses a camera to periodically capture images of its surroundings, for example, once per second, to monitor for approaching animals.

[1143] Step 3:

[1144] Sending images by device

[1145] The captured image is immediately uploaded to the server, allowing the server to perform image analysis in real time.

[1146] Step 4:

[1147] Server-based animal identification

[1148] The server then uses an artificial intelligence model to analyze the received images and identify the type of animal that is present in the image, which then identifies which animal is approaching.

[1149] Step 5:

[1150] Server decides what to do

[1151] Based on the identified animal type, the server determines the images and sounds that the animal dislikes, which information is obtained from a pre-defined database.

[1152] Step 6:

[1153] Server Response Generation

[1154] The server generates response data containing images and sounds that the animal dislikes, and sends it to the device. This data is then formatted in a format that the device can accept.

[1155] Step 7:

[1156] Displaying images by device

[1157] The device displays the image received from the server on its display, creating a visual threat to the animals.

[1158] Step 8:

[1159] Playing sounds through the device

[1160] The device receives the sound from the server and plays it back through the speaker, creating an auditory threat to the animals.

[1161] Step 9:

[1162] Observing pest behavior

[1163] Users can view logs on their devices and on the server to see which animals responded and how they reacted, allowing them to assess the effectiveness of the system and make adjustments as needed.

[1164] Example 1

[1165] 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."

[1166] There is a need for an effective method to repel animals that damage crops in agricultural fields. Conventional methods have difficulty in quickly taking different countermeasures depending on the type of animal, and there is a lack of systems that allow remote control. This has led to the problem of not being able to prevent animal damage in a timely manner.

[1167] 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.

[1168] In this invention, the server includes means for taking pictures of approaching animals with a camera, means for transmitting the images to the server, means for identifying the animals in the images by the server, means for determining images and sounds that the animals dislike based on the identified animals, means for displaying the determined images on a display, and means for playing the determined sounds from a speaker. This makes it possible to identify animals in real time and instantly scare them away using appropriate images and sounds.

[1169] A "camera" is a device that captures images of the surroundings and outputs them as image data.

[1170] A "server" is a computer system that receives requests from client terminals via a network and processes them.

[1171] An "image" is a digital representation of visual information captured by a camera.

[1172] "Animals" refers to a group of living organisms that have a specific behavior, and in the present invention refers to organisms that may cause damage to agricultural land.

[1173] An "artificial intelligence model" is a set of pre-trained algorithms used to analyze input data and make decisions.

[1174] A "terminal" is an electronic device that can be connected to a network and communicates with a server.

[1175] A "display" is an output device for displaying images and videos.

[1176] A "speaker" is an output device for reproducing voice or sound.

[1177] A "database" is a collection of data and a system that enables efficient search and retrieval of data.

[1178] "Recognition" is the process of identifying a specific object from input image data.

[1179] The present invention is a system that uses a terminal installed in farmland to detect the approach of animals and respond appropriately. This system is realized by combining a camera, a server, a display, a speaker, and an artificial intelligence model.

[1180] First, when the user initially configures the system, the server loads a trained artificial intelligence model (animal_recognition_model) and distributes it to each device. This model is a group of algorithms for identifying animal species, and through training it is possible to achieve highly accurate identification.

[1181] The device is then installed in the field and periodically captures images of the surrounding area with its camera. This image data is then sent to the server at intervals of, for example, once per second. The transmission protocol is HTTP POST, and the image data is sent in binary format.

[1182] The server then calls an AI model running on a Python script to analyze the received image. The AI ​​model analyzes the image provided as input and identifies the type of animal depicted in the image. The identification result is expressed as a probability, and is returned in the form of, for example, "80% probability that it is a rabbit."

[1183] Based on the identified animal, the server selects images and sounds that the animal dislikes from a database containing pre-defined image and sound pairs for each animal type. Once the appropriate images and sounds are selected, they are sent to the device.

[1184] The device displays the received image on the screen and plays a sound from the speaker at the same time, which scares the animals and makes them leave the field, preventing them from damaging crops.

[1185] As a concrete example of this system, consider the case where a device installed in a farm recognizes a rabbit using a camera. In this case, the device captures an image of the rabbit with its camera and sends it to the server. The server analyzes the received image and identifies it as a rabbit. The server then selects an image of an eagle, which rabbits are afraid of, and the sound of a dog barking, and sends these to the device. The device displays the received image of the eagle on its display and plays the sound of a dog barking from its speaker, thereby scaring away the rabbit.

[1186] An example prompt might be, "Please explain how to identify the type of animal recognized by a camera-equipped device installed in farmland, determine the image and sound to scare the animal away, and send them to the device."

[1187] As a result, this system can be remotely controlled and is a highly effective means of protecting farmland against a wide range of pests.

[1188] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1189] Step 1:

[1190] The server loads the artificial intelligence model and distributes it to the terminal.

[1191] Input: The user clicks the "Initial Settings" button on the system administration screen.

[1192] How it works: The server loads a trained artificial intelligence model for animal recognition (animal_recognition_model) into memory, then distributes this model to each device in the form of a firmware update.

[1193] Output: The animal_recognition_model is installed on each device.

[1194] Step 2:

[1195] The device uses a camera to capture images of the animals and send them to the server.

[1196] Input: A still image taken by the camera.

[1197] How it works: The device's camera captures an image of its surroundings once every second. The image data is sent to the server using HTTP POST. This image data is sent in binary format.

[1198] Output: Image data sent to the server.

[1199] Step 3:

[1200] The server analyzes the image and identifies the type of animal.

[1201] Input: Image data sent from the device.

[1202] How it works: The server calls an AI model running on a Python script and provides image data as input. The AI ​​model analyzes the image and identifies the type of animal in it. The identification result is expressed as a probability, such as "80% chance that it's a rabbit."

[1203] Output: Identified animal species and their probabilities.

[1204] Step 4:

[1205] The server determines the sound and image based on the identification result and transmits them to the terminal.

[1206] Input: Animal species and their probabilities obtained from the AI ​​model.

[1207] How it works: Based on the identified animal type, the server selects images and sounds that the animal dislikes from a database. After selecting the appropriate images and sounds, it sends this information to the device.

[1208] Output: Image and sound data sent to the device.

[1209] Step 5:

[1210] The terminal plays the images and sounds received from the server.

[1211] Input: Image and sound data sent from the server.

[1212] Operation: The device first displays an image on the display using the received image data, and simultaneously plays sound data from the speaker using the audio library.

[1213] Output: The image shown on the display and the sound played through the speakers.

[1214] These are the specific processing steps of the program for this system, which enables real-time detection of animals damaging crops in farmland and immediate response.

[1215] (Application example 1)

[1216] 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."

[1217] Problems such as the introduction of foreign objects and unauthorized intrusions into factory production lines have a significant impact on safety and efficiency. Conventional methods require manual detection and removal of foreign objects, which requires significant time and manpower and increases the risk of errors. Furthermore, systems for quickly taking appropriate action are lacking, making real-time monitoring and response difficult. Therefore, the present invention aims to solve these problems and improve the efficiency and safety of factory operations.

[1218] 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.

[1219] In this invention, the server includes means for capturing an image of an approaching object with a camera, means for transmitting the image to the server, means for identifying the object in the image by the server, means for determining an image and sound that the object is sensitive to based on the identified object, means for displaying the determined image on a display device, means for playing the determined sound from an audio device, and means for performing an action to remove the object when it enters a specific area, thereby enabling the efficiency and safety of factory work to be improved.

[1220] "Object" refers to any object that exists on a factory line or within a detection range and needs to be identified or removed.

[1221] A "camera" is a photographic device that captures images and videos and provides the data for subsequent processing.

[1222] A "server" is a central processing unit that analyzes and manages data and serves as the control center for the entire system.

[1223] The "means for transmitting images" is a combination of network equipment and software for transferring captured images to a server.

[1224] "Means for identification" refers to algorithms and software that identify objects in captured images and determine their type and condition.

[1225] A "generative AI model" is an artificial intelligence model that is trained in advance based on a large amount of data and is able to identify images and objects with high accuracy in real time.

[1226] A "display device" is a display for visualizing images or messages.

[1227] "Sound device" means a speaker for playing determined sounds and providing auditory alerts and effects.

[1228] "Means for performing an action to remove an object when it invades" refers to a physical driving device such as a robot arm or actuator for removing an object when it invades a specific area.

[1229] A system for implementing this invention is for effectively managing foreign matter contamination, unauthorized entry, etc. in a factory production line. This system includes a camera, a server, a display device, an audio device, and several software components.

[1230] First, a camera periodically captures images of the production line. The captured images are then transferred to a server using an image transmission method. When the server receives the images, it uses a generative AI model to identify objects in the images. This generative AI model has been trained in advance using a large amount of data, enabling highly accurate identification in real time.

[1231] Based on the identified object, the server determines from a database the image and sound that the object is sensitive to. The determined image is displayed on a display device, and the determined sound is played from an audio device. This improves the efficiency and safety of the production line.

[1232] Furthermore, if an object enters a specific area, the server executes an action to remove the object, using physical driving devices such as a robot arm or actuator.

[1233] As a concrete example, consider the case where garbage gets mixed into a beverage production line at a factory. A camera captures an image of the garbage and sends it to a server. The server uses a generative AI model to identify the garbage, determines an appropriate image and sound for that garbage, and displays and plays them on a display and audio device. Furthermore, if the garbage enters a specific area, a robotic arm removes the garbage.

[1234] An example prompt might look like this:

[1235] "How can I use a trained model to detect debris and foreign objects on a production line in real time?"

[1236] How can I send an HTTP request to retrieve image and audio data based on the classification results?

[1237] In this way, the present invention makes it possible to respond quickly and accurately in real time to the intrusion of foreign matter or unauthorized access into a factory production line, thereby improving production efficiency and ensuring safety.

[1238] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1239] Step 1:

[1240] A camera periodically captures images of the factory production line. The input is the image data captured by the camera lens, and the output is the captured image file.

[1241] Step 2:

[1242] The captured image data is transferred to a server using an image transmission means, where the input is the captured image file and the output is the image data sent to the server.

[1243] Step 3:

[1244] The server passes the received image data to the generative AI model to identify the object. The input is the image data, and the output is the type and location of the identified object. Specifically, the generative AI model analyzes the image data and performs data calculations to identify the object.

[1245] Step 4:

[1246] Based on the identification results, the server determines the image and sound corresponding to the object from the database. The input is the type and location information of the identified object, and the output is the URL of the image to display and the URL of the audio file to play. Specifically, the server executes a database query to retrieve the appropriate data.

[1247] Step 5:

[1248] The determined image is sent from the server to the display device and displayed on the display device. The input is the URL of the image, and the output is the displayed image. Specifically, the image data is rendered on the display device's screen.

[1249] Step 6:

[1250] The determined sound is sent from the server to the sound device and played from the sound device. The input is the URL of the audio file, and the output is the played sound. Specifically, the audio data is played on the sound device's speaker.

[1251] Step 7:

[1252] When an object enters a specific area, the server executes an action to remove the object. The input is the object's location information, and the output is a trigger for the removal action. Specifically, the robot arm operates to remove the object.

[1253] Step 8:

[1254] After the elimination action is completed, the server records the system status as a log and notifies the user. The input is the result of the elimination action, and the output is the log data and a user notification. Specifically, the server saves the log in a database and creates a notification message based on the generative AI model.

[1255] This series of processing steps efficiently enables real-time detection and removal of foreign objects on factory production lines.

[1256] 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.

[1257] The present invention combines a system in which a device installed in farmland uses a camera to capture approaching animals and transmits the images to a server, with an emotion engine that recognizes the user's emotions. The server analyzes the transmitted images and identifies the type of animal. Next, based on the identified animal, it determines the images and sounds that the animal dislikes and transmits a response to the device. Based on the received response, the device displays an image on the display and plays a sound from the speaker. This system can effectively protect crops from a wide variety of pests. The emotion engine also recognizes the user's emotions, allowing the server to adjust countermeasures against animals as necessary.

[1258] Specific program processing explanation

[1259] Server Initialization

[1260] The server loads the artificial intelligence model and distributes it to the terminal.

[1261] When a user initially configures the system, the server loads the trained AI model (animal_recognition_model) and emotion engine and distributes this model to all devices, so that each device is ready to identify animals and adjust its response based on the user's emotions.

[1262] Animal recognition by device

[1263] The device uses a camera to capture images of the animals and send them to the server.

[1264] The device periodically captures images of its surroundings using a camera. For example, an image is taken once per second, and the captured images are sent to a server. This allows the server to perform real-time image analysis on devices installed in remote locations.

[1265] Server-based animal identification

[1266] The server analyzes the image and identifies the type of animal.

[1267] The server analyzes the received images using an artificial intelligence model to identify the type of animal depicted in the image.

[1268] The server determines the sound and image based on the identification result and transmits them to the terminal.

[1269] Based on the identified animal, the server selects images and sounds that the animal fears from a database and sends this information to the device, causing the animal to feel fear.

[1270] Terminal display of responses

[1271] The terminal plays the images and sounds received from the server.

[1272] The device displays the image received from the server on the display and simultaneously plays sound from the speaker, effectively scaring away animals.

[1273] Use of emotion engine by server

[1274] The server recognizes the user's emotions.

[1275] The emotion engine captures the user's facial expression data with a camera and analyzes their stress and satisfaction, thereby understanding the user's emotional state in real time.

[1276] The server adjusts the response based on the output of the emotion engine.

[1277] If the user's emotional state is inappropriate, the server runs an algorithm to optimize the animal's response, adjusting the images and sounds to make the animal feel more frightened, and then sends this adjusted information back to the device.

[1278] Specific examples

[1279] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[1280] Device animal recognition:

[1281] The device captures an image of the rabbit with its camera and sends the image to the server.

[1282] Server-based animal identification:

[1283] The server analyzes the image and identifies the animal as a rabbit.

[1284] Server response generation:

[1285] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[1286] Terminal display of response:

[1287] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[1288] Server-based emotion recognition and modulation:

[1289] The server analyzes the user's emotional state with an emotion engine, and if the user is feeling stressed, determines more powerful images and sounds and retransmits them to the terminal.

[1290] In this way, the system of the present invention provides an efficient and effective response to pests, and can be optimized taking into account the emotional state of the user.

[1291] The processing flow will be explained below.

[1292] Step 1:

[1293] Server Initialization

[1294] The server loads the artificial intelligence model (animal_recognition_model) and emotion engine and distributes them to each device. With this initial setup, each device is ready to identify animals and adjust its response based on the user's emotions.

[1295] Step 2:

[1296] Animal detection by device

[1297] The device uses a camera to periodically capture images of its surroundings, for example, once per second, to monitor for approaching animals.

[1298] Step 3:

[1299] Sending images by device

[1300] The captured image is immediately uploaded to the server, allowing the server to perform image analysis in real time.

[1301] Step 4:

[1302] Server-based animal identification

[1303] The server then uses an artificial intelligence model to analyze the received images and identify the type of animal that is present in the image, which then identifies which animal is approaching.

[1304] Step 5:

[1305] Server decides what to do

[1306] Based on the identified animal type, the server determines the images and sounds that the animal dislikes, which information is obtained from a pre-defined database.

[1307] Step 6:

[1308] Server Response Generation

[1309] The server generates response data containing images and sounds that the animal dislikes, and sends it to the device. This data is then formatted in a format that the device can accept.

[1310] Step 7:

[1311] Displaying images by device

[1312] The device displays the image received from the server on its display, creating a visual threat to the animals.

[1313] Step 8:

[1314] Playing sounds through the device

[1315] The device receives the sound from the server and plays it back through the speaker, creating an auditory threat to the animals.

[1316] Step 9:

[1317] Use of emotion engine by server

[1318] The server uses an emotion engine to analyze the user's facial expression data and detect the user's stress and satisfaction, thereby understanding the user's emotional state in real time.

[1319] Step 10:

[1320] Adjusting responses based on user emotions

[1321] The server readjusts its response to the animal based on the output of the emotion engine: if the user is stressed, it determines stronger images and sounds and retransmits them to the device.

[1322] Specific examples

[1323] For example, consider the case where a device installed in a farmland recognizes a rabbit using a camera.

[1324] Device animal recognition:

[1325] The device captures an image of the rabbit with its camera and sends the image to the server.

[1326] Server-based animal identification:

[1327] The server analyzes the image and identifies the animal as a rabbit.

[1328] Server response generation:

[1329] The server determines the image (e.g., the figure of an eagle) and sound (e.g., the barking of a dog) that the rabbit dislikes and sends them to the terminal.

[1330] Terminal display of response:

[1331] The device displays the received image of an eagle on its display and plays the sound of a dog barking through its speaker.

[1332] Server-based emotion recognition and modulation:

[1333] The server analyzes the user's emotional state with an emotion engine, and if the user is feeling stressed, determines more powerful images and sounds and retransmits them to the terminal.

[1334] In this way, the system of the present invention provides an efficient and effective response to pests, and can be optimized taking into account the emotional state of the user.

[1335] Example 2

[1336] 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."

[1337] While conventional animal repellent systems have the ability to identify the type of animal and determine the appropriate countermeasure, they lack the ability to adjust the countermeasure based on the user's emotional state, which means that their long-term effectiveness cannot be guaranteed.In addition, they often only take a certain countermeasure against animals, which can become less effective depending on the animal's adaptability.

[1338] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1339] In this invention, the server includes means for capturing an image of an approaching animal with a camera, means for transmitting the image to the server, means for identifying the animal in the image by the server, means for determining images and sounds that the animal dislikes based on the identified animal, means for displaying the determined images on a display, means for playing the determined sounds from a speaker, means for recognizing the user's emotions, and means for adjusting countermeasures against the animal based on the user's emotional state, thereby making it possible to provide optimal countermeasures that take into account not only the animal but also the user's emotional state.

[1340] A "camera" is a device that captures visual information from its surroundings and records it as an image.

[1341] A "server" is a centralized computer system that processes and manages data over a network.

[1342] "Means for transmitting images" refers to communication techniques and devices for transferring captured image data to a server.

[1343] "Animal identification means" refers to the technology or algorithms used to analyze the received image data and identify the type of animal in the image.

[1344] "Means for determining images and sounds that an animal dislikes" refers to a method and apparatus that, based on an identified animal, selects images and sounds that the animal tends to avoid.

[1345] "Means for displaying" refers to devices and techniques for visually displaying the determined image.

[1346] "Means for playing from a speaker" refers to devices and techniques for playing the determined sound as audio.

[1347] "Means for recognizing user emotions" refers to technologies and algorithms for analyzing a user's facial expressions and voice data to identify their emotional state.

[1348] "Means for adjusting behavior toward animals" refers to means and techniques for dynamically changing behavior toward animals based on the emotional state of the user.

[1349] An "artificial intelligence model" is a computational model based on machine learning algorithms that are trained to perform specific tasks.

[1350] A "database" is a system for efficiently storing and retrieving structured data.

[1351] In this invention, a system is implemented that provides effective measures against a wide variety of harmful animals using terminals installed on farmland, a server, and an emotion engine for recognizing user emotions.

[1352] First, the device is installed in the field and uses a camera module to capture images of approaching animals. The images are temporarily stored on the device and then sent to a server via network communication. This communication mainly uses wireless networks such as Wi-Fi, 4G, and 5G.

[1353] The server analyzes the transmitted image using a trained AI model (animal_recognition_model). This AI model includes the characteristics of various animals and uses a specific algorithm to identify the type of animal in the image. Based on the identified animal, the server selects images and sounds that the animal dislikes from a database. This database contains pre-registered images and sounds that each type of animal dislikes.

[1354] The server then retransmits the selected image and sound data to the device, which displays the received images on its display and plays the sounds through its speaker, thus driving animals away from the field and protecting the crops.

[1355] Furthermore, the system incorporates an emotion engine. To recognize the user's emotional state, the emotion engine captures and analyzes the user's facial expression data using a camera. Based on the analysis results obtained from the emotion engine, the server adjusts the response to the animals as needed. For example, if the user is feeling anxious or stressed, the server selects more powerful images and sounds and retransmits them to the device.

[1356] As a concrete example, consider the case where a device installed in a field recognizes a rabbit using a camera. The device captures an image of the rabbit and sends it to a server. The server analyzes the received image and identifies the animal as a rabbit. The server then selects an image of an eagle and the sound of a dog barking, which rabbits are afraid of, and sends these to the device. The device then displays the received image of the eagle on its display and plays the sound of a dog barking through its speaker. This process can scare away rabbits from the field.

[1357] If the user expresses dissatisfaction with the system's operation, the emotion engine analyzes the facial expression data and sends the results to the server, which then selects more effective images and sounds and retransmits them to the device, thereby enhancing the animal-repelling effect.

[1358] Examples of prompts include:

[1359] "Please explain the process by which a device installed on farmland uses a camera to recognize rabbits and determine the image and sound to scare them away."

[1360] "Please explain how the server will change its response if the user expresses dissatisfaction with the system."

[1361] This system provides optimal animal repelling measures that take into account not only the animals but also the emotional state of the user.

[1362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1363] Program processing flow

[1364] Step 1: Initial Setup

[1365] 1. Loading and distributing models by the server

[1366] Input: Trained AI model and emotion engine

[1367] Specific operation: The server loads the trained AI model (animal_recognition_model) and emotion engine and distributes them to all devices via the network. The distributed model is used by the device to identify animals.

[1368] Step 2: Prepare for Animal Recognition

[1369] 2. Device camera and communication settings

[1370] Input: Camera module and communication module

[1371] Specific operation: The device initializes the camera and sets up network communication with the server, so that the device is ready to capture image data and send it to the server.

[1372] Step 3: Capture an image of the animal

[1373] 3. Periodic image capture by the device

[1374] Input: Visual information of the surroundings acquired by the camera

[1375] Specific operation: The device captures an image of the surroundings using the camera once per second. For example, it calls the "capture_image()" function to obtain image data.

[1376] Output: Captured image data

[1377] 4. Sending images to the server

[1378] Input: Captured image data

[1379] Specific operation: The device uses the "send_image_to_server(image)" function to send the captured image data to the server.

[1380] Output: Image data sent to the server

[1381] Step 4: Identify the animal species

[1382] 5. Image analysis by the server

[1383] Input: Submitted image data and artificial intelligence model

[1384] Specific operation: The server uses the "analyze_image(image, animal_recognition_model)" function to analyze the image data with an artificial intelligence model to identify the type of animal in the image.

[1385] Output: Identified animal species

[1386] Step 5: Determine the images and sounds you find difficult

[1387] 6. Server Determination of Response Data

[1388] Input: Identified animal species

[1389] What happens: The server uses the "select_response_for_animal(animal_type)" function to select from the database the images and sounds that the animal dislikes. For example, for a rabbit, it selects the image of an eagle and the sound of a dog barking.

[1390] Output: Determined image and sound data

[1391] 7. Sending response data to the terminal

[1392] Input: Determined image and sound data

[1393] Specific operation: The server uses the "send_response_to_terminal(response_data)" function to send the selected image and sound to the terminal.

[1394] Output: Image and sound data sent to the device

[1395] Step 6: View the response

[1396] 8. Displaying images and playing sounds on the device

[1397] Input: Image and sound data sent to the device

[1398] Specific operation: The device displays an image on the display using the "display_image(image)" function and plays a sound from the speaker using the "play_sound(sound)" function, which has a deterrent effect on the animals.

[1399] Output: The displayed image and the played sound

[1400] Step 7: Use the Emotion Engine

[1401] 9. Emotion Analysis by Server

[1402] Input: User's facial expression data

[1403] Specific operation: The server uses the emotion engine to identify the user's emotional state by analyzing the user's facial expression data, for example, by using the "analyze_user_emotion(user_image)" function.

[1404] Output: Emotional state analysis result

[1405] 10. Adjusting your response based on emotions

[1406] Input: Emotional state analysis results

[1407] What it does: The server uses the "adjust_response_based_on_emotion(emotion_data)" function to adjust its response to the animal based on its emotional state: if the user is stressed, it will select stronger images and sounds and resend them to the device.

[1408] Output: Modified image and sound data

[1409] Through these steps, the system can effectively identify animals and coordinate response measures.

[1410] (Application example 2)

[1411] 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."

[1412] Conventional security systems are limited to detecting intruders and suspicious individuals, and offer limited options for specific countermeasures after detection. Furthermore, because they provide only uniform countermeasures without taking the user's emotional state into consideration, inappropriate responses can be taken, limiting security optimization. This makes it difficult to implement effective and flexible countermeasures. The present invention aims to solve these problems and provide a more effective and user-friendly security system.

[1413] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing an image of an approaching target with a camera, means for transmitting the image to the server, means for identifying the target in the image by the server, means for determining images and sounds that the target dislikes based on the identified target, means for displaying the determined images on a display, means for playing the determined sounds from a speaker, means for recognizing the user's emotion using an emotion engine, and means for adjusting countermeasures based on the recognized emotion. This makes it possible to effectively repel intruders in real time and optimize countermeasures in accordance with the user's emotional state.

[1414] A "camera" is a device for taking images or videos.

[1415] A "server" is a computer system that processes and stores data, and provides services in response to requests from clients.

[1416] An "image" is information about a still image that visually captures an object, landscape, etc.

[1417] "Subject" refers to any object or living thing within the camera's field of view that is the subject of surveillance or identification.

[1418] "Identification" is the process of identifying specific objects in an image and determining their type and characteristics.

[1419] "Images that a particular subject dislikes" refers to visual information that a particular subject does not want to see or that a particular subject psychologically dislikes.

[1420] "Sound" is an auditory stimulus that is transmitted as vibrations in the air, and when a particular object is disliked, it acts to make the animal flee from that object.

[1421] A "display" is a device that displays images or videos by electrical means.

[1422] A "speaker" is a device that converts electrical signals into audio and produces sound.

[1423] An "emotion engine" is a software or hardware system that analyzes a user's facial expressions and behavior and recognizes their emotional state.

[1424] A "user" is a person who uses, operates, or monitors the system.

[1425] "Recognition" refers to the process of understanding and identifying the situation and characteristics of an object from data acquired by cameras and sensors.

[1426] "Countermeasures" refer to specific actions or measures taken to deal with a specific event or situation.

[1427] "Adjustment" refers to the act of making changes or adjustments to achieve an appropriate state according to given conditions or circumstances.

[1428] A "system" is a collection of integrated devices and processes in which different elements work together to achieve a specific function.

[1429] This invention is a security system that includes a camera, a server, a display, a speaker, and an emotion engine. By linking these elements, it provides a system that detects intruders and suspicious individuals in real time and implements effective countermeasures. The system configuration and operation are detailed below.

[1430] The basic operation of the system is as follows: First, the camera periodically sends images it captures to the server, and the server identifies the object in the received image. A pre-trained artificial intelligence model is used to do this. This model identifies the type of object and, based on the results, determines the images and sounds that the object dislikes. The determined images are shown on the display and the sounds are played from the speaker. This effectively scares away objects (such as suspicious people or animals).

[1431] Next, we will explain the function of the emotion engine. The emotion engine recognizes and analyzes the user's emotions in real time from facial expression data captured by the camera. The server uses this emotion data to adjust countermeasures as appropriate. For example, if the user is feeling very stressed, the server can use more effective images and sounds to scare away the target. This function allows the system to adapt to the user's emotional state and provide the most appropriate countermeasures.

[1432] Here's a specific example: Suppose a camera installed in a residential garden detects an intruder. In this case, the camera captures an image of the intruder and sends it to a server. The server analyzes the received image and identifies the intruder as a human. The server then determines an alarm sound (e.g., a loud dog barking) and an image (e.g., an image of a surveillance camera or a warning sign) that the intruder will dislike, and sends them to the device. The device then plays the received alarm sound from its speaker and displays the image on its display, effectively scaring the intruder away.

[1433] Furthermore, when the emotion engine is used, if the user is in a situation where they are feeling extremely stressed, the emotion engine can detect this and send instructions to the server to select stronger warning sounds or images, resulting in stronger responses being taken and increasing the effectiveness of the system.

[1434] Examples of prompts include:

[1435] "Design a system that uses image data captured by a camera to identify a suspicious individual and determine the optimal audible warning or visual image to scare them away."

[1436] In this way, the system of the present invention can realize real-time monitoring and effective repelling, and further provide flexible countermeasures that adapt to the user's emotional state.

[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 captures images of the surrounding area using a camera and sends the captured image data to a server. The input is the raw image data captured by the camera, and the output is the image data sent to the server. Specifically, the camera captures images at regular intervals and sends the image data to the server via the Internet. This allows the server to receive monitoring data in real time.

[1440] Step 2:

[1441] The server takes the received image data as input and uses a pre-trained generative AI model to identify the object in the image. Based on this identification result, it determines the next countermeasure. Specifically, the server analyzes the image using an image recognition algorithm (e.g., a deep learning model) and classifies the object as human, suspicious person, animal, etc. The output is the type of object identified.

[1442] Step 3:

[1443] Based on the type of identified object, the server retrieves from a database images and sounds that the object finds frightening and sends them to the device. The input here is the type of identified object, and the output is image and sound data that will induce fear in the object appropriately. Specifically, the server searches the database for corresponding sound and image files and sends this data to the device. At this time, the emotion engine analyzes the user's emotional state, and the selection of images and sounds may be adjusted based on this information.

[1444] Step 4:

[1445] The device receives image and sound data from the server as input, displays the image on the display, and plays the sound from the speaker. This has the effect of scaring away the target. Specifically, the device's display displays a frightening image, and the speaker plays a warning sound. The output is the displayed image and the played sound, with the ultimate goal being to make the target leave the area.

[1446] Step 5:

[1447] The server uses an emotion engine to monitor the user's emotional state in real time. The input is the user's facial expression data, and the output is the user's emotional state. Specifically, it analyzes the facial expression data captured by the user's camera and determines whether the user is feeling stressed or satisfied.

[1448] Step 6:

[1449] The server adjusts the response to the target as needed based on the user's emotional state. The adjusted response is sent back to the device and played. The input is the user's emotional state, and the output is adjusted image and sound data. Specifically, if the emotion engine determines that the user's stress level is high, it selects stronger warning sounds and images. This adjusted data is sent to the device and played.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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).

[1457] 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.

[1458] 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."

[1459] 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.

[1460] 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).

[1461] 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.

[1462] 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.

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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.

[1471] The following is further disclosed regarding the above embodiment.

[1472] (Claim 1)

[1473] a means for photographing approaching animals with a camera;

[1474] means for transmitting the image to a server;

[1475] means for identifying animals in the images by the server;

[1476] means for determining images and sounds that the animal dislikes based on the identified animal;

[1477] means for displaying the determined image on a display;

[1478] means for playing the determined sound from a speaker;

[1479] A system including:

[1480] (Claim 2)

[1481] 10. The system of claim 1, wherein the animal identification includes using a pre-trained artificial intelligence model.

[1482] (Claim 3)

[1483] 2. The system of claim 1, further comprising means for obtaining the determined images and sounds from a database preset corresponding to the type of animal.

[1484] "Example 1"

[1485] (Claim 1)

[1486] a means for photographing approaching animals with a camera;

[1487] means for transmitting the image to a server;

[1488] means for identifying animals in the images by the server;

[1489] means for determining images and sounds that the animal dislikes based on the identified animal;

[1490] means for displaying the determined image on a display;

[1491] means for playing the determined sound from a speaker;

[1492] A system including:

[1493] (Claim 2)

[1494] 2. The system according to claim 1, wherein a pre-trained artificial intelligence model is used to identify animals, and the system includes means for distributing the model to each terminal.

[1495] (Claim 3)

[1496] 2. The system of claim 1, further comprising means for obtaining the determined images and sounds from a database preset corresponding to the type of animal.

[1497] "Application Example 1"

[1498] (Claim 1)

[1499] a means for photographing an approaching object by a camera;

[1500] means for transmitting the image to a server;

[1501] means for identifying objects in the image by the server;

[1502] means for determining, based on the identified object, images and sounds to which the object is sensitive;

[1503] means for displaying the determined image on a display device;

[1504] means for playing the determined sound from an audio device;

[1505] a means for performing an action to remove an object when the object enters a specific area;

[1506] A system including:

[1507] (Claim 2)

[1508] 10. The system of claim 1, wherein the object identification includes using a pre-trained generative AI model.

[1509] (Claim 3)

[1510] 2. The system of claim 1, further comprising means for obtaining the determined images and sounds from a database preset in correspondence with the type of object.

[1511] "Example 2: Combining Emotion Engines"

[1512] (Claim 1)

[1513] a means for photographing approaching animals with a camera;

[1514] means for transmitting the image to a server;

[1515] means for identifying animals in the images by the server;

[1516] means for determining images and sounds that the animal dislikes based on the identified animal;

[1517] means for displaying the determined image on a display;

[1518] means for playing the determined sound from a speaker;

[1519] means for recognizing a user's emotion;

[1520] means for adjusting a response to the animal based on the emotional state of the user;

[1521] A system including:

[1522] (Claim 2)

[1523] 10. The system of claim 1, wherein the animal identification includes using a pre-trained artificial intelligence model.

[1524] (Claim 3)

[1525] 2. The system of claim 1, further comprising means for obtaining the determined images and sounds from a database preset corresponding to the type of animal.

[1526] "Application example 2 when combining emotion engines"

[1527] (Claim 1)

[1528] a means for photographing an approaching object by a camera;

[1529] means for transmitting the image to a server;

[1530] means for identifying objects in the image by the server;

[1531] means for determining images and sounds that are aversive to the identified subject;

[1532] means for displaying the determined image on a display;

[1533] means for playing the determined sound from a speaker;

[1534] a means for recognizing user emotions using an emotion engine;

[1535] a means of adjusting responses based on perceived emotions;

[1536] A system including:

[1537] (Claim 2)

[1538] 10. The system of claim 1, wherein the animal identification includes using a pre-trained artificial intelligence model.

[1539] (Claim 3)

[1540] 2. The system of claim 1, further comprising means for obtaining the determined images and sounds from a database preset corresponding to the type of object. [Explanation of symbols]

[1541] 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 photographing approaching animals with a camera; means for transmitting the image to a server; means for identifying animals in the images by the server; means for determining images and sounds that the animal dislikes based on the identified animal; means for displaying the determined image on a display; means for playing the determined sound from a speaker; A system including:

2. 10. The system of claim 1, wherein the animal identification includes using a pre-trained artificial intelligence model.

3. 2. The system according to claim 1, further comprising means for obtaining the determined images and sounds from a database preset in correspondence with the type of animal.

Images