System

Abstract

A system is provided.SOLUTION: The system includes a means for analyzing the cry of the pet by a voice analysis technique, a means for analyzing the gesture and expression of the pet by an image analysis technique, a means for translating the feeling and desire of the pet on the basis of the analysis result, and a means for notifying the user of the translated result.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] Existing pet translation tools are primarily specialized in analyzing the meows of dogs and cats, and are not compatible with the wide variety of other pets. Furthermore, because they only analyze meows, they are unable to fully understand the feelings and needs of pets. By incorporating pet gestures and facial expressions into the analysis, it is possible to more accurately understand pets' feelings and needs, thereby deepening the trust between pet owners and their pets. [Means for solving the problem]

[0005] The present invention provides a system including means for analyzing pet cries using audio analysis technology, means for analyzing pet gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, and means for notifying the user of the translation results.The system also includes means for analyzing the frequency and pattern of the cries, means for identifying movement patterns and changes in facial expressions, means for handling a wide variety of pets such as dogs, cats, small animals, and reptiles, means for notifying the user of the analysis results in real time, means for using a machine learning model to predict the pet's feelings and requests, means for the user to input the type of pet and basic information, and means for storing the data in a database, and solves the problems using these means.

[0006] "Means for analyzing pet cries using audio analysis technology" refers to devices or software that use technology to detect sounds made by pets and analyze the frequency and patterns of those sounds.

[0007] "Means for analyzing pets' gestures and facial expressions using image analysis technology" refers to devices or software that use technology to capture pets' movements and facial expressions with a camera and analyze the image data.

[0008] "Means for translating pets' feelings and requests based on analysis results" refers to devices or software that use technology to convert a pet's condition and requests into a format that humans can understand, based on data obtained from voice analysis and image analysis.

[0009] The "means for notifying the user of the translation results" refers to a means for sending the results of the analysis and translation to the user's device as a text message or voice message, allowing the user to check them.

[0010] The "means for analyzing the frequency and pattern of cries" refers to a technology that processes pet cries data using a specific algorithm and analyzes the frequency and sound generation pattern.

[0011] The "means for identifying movement patterns and changes in facial expression" refers to technology that analyzes data on a pet's gestures and facial expressions to detect specific movement patterns and changes in facial expression.

[0012] "Means to accommodate a wide variety of pets, including dogs, cats, small animals, and reptiles" refers to technology that uses different analytical models and algorithms to detect and analyze the unique sounds, gestures, and facial expressions of different types of pets.

[0013] "Means for notifying analysis results in real time" refers to technology that instantly notifies the user of analyzed data, and is a mechanism for communicating the pet's condition without delay.

[0014] A "machine learning model for predicting pet feelings and needs" is a type of artificial intelligence technology that learns data collected from many pets and infers and predicts pet feelings and needs based on new data.

[0015] "Means for users to input pet type and basic information" refers to a function that allows users to use an application or interface to input basic information such as pet type, name, age, and sex.

[0016] The "means for storing data in a database" refers to a database system for storing collected data on vocalizations, gestures, and facial expressions, as well as analysis results, for later reuse and analysis. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] System Overview

[0039] The pet translation system of the present invention analyzes the cries, gestures, and facial expressions of pets and translates their feelings and requests based on that data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify owners of the analysis results in real time.

[0040] Initial Setup and Data Collection

[0041] 1. User: After installing the dedicated application, an initial setup screen appears. The user enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, gender, etc.). This allows the system to use an analysis model optimized for that particular pet.

[0042] 2. Device: Prepare a camera and microphone to monitor your pet's behavior. The device captures your pet's sounds and movements in real time and sends the data to the server at specified intervals.

[0043] 3. Server: Receives data sent from the device and stores it in a database. The collected data is later used for analysis.

[0044] Data analysis

[0045] 4. Server: Performs audio analysis on the bark data. Specifically, it analyzes the frequency and pattern of the bark and extracts characteristics such as pitch and duration. From the bark pattern, data can be obtained to identify what the pet is trying to communicate.

[0046] 5. Server: Using the recorded data, image analysis of the pet's gestures and facial expressions is performed. Image analysis algorithms are used to detect patterns of pet movement and changes in facial expressions. This allows the pet's feelings and state to be inferred from its gestures and facial expressions.

[0047] 6. Server: Integrates data from sounds, gestures, and facial expressions and uses a machine learning model to predict your pet's feelings and needs. This model learns from data collected from many pets and makes highly accurate predictions about your pet's condition based on new data.

[0048] Providing results

[0049] 7. Server: Formats the analysis results as text or voice messages and sends them to the user interface, where the user can instantly view the results.

[0050] 8. Device: Displays the analysis results and notifies the user of their pet's feelings and needs. Notifications are sent using both text and voice, allowing users to quickly and reliably understand their pet's condition.

[0051] Specific examples

[0052] Consider the case where a user has a dog and a hamster.

[0053] 1. Initial Setup: The user enters information about their dog and hamster into the application.

[0054] 2. Data collection: A camera and microphone installed in the living room record the behavior of the dog and hamster. The data is automatically sent to a server.

[0055] 3. Data analysis: The server performs audio analysis of the dog's bark to detect the repeated "woof woof" sound, while image analysis of the hamster's movements confirms that it is moving back and forth to a specific location.

[0056] 4. Providing results: The server predicts that the dog is in a state of "wanting to play" and determines that the hamster is likely "stressed." These results are sent to the user's device.

[0057] 5. User notification: The device displays messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed" and notifies the user by voice. The user can play with the dog and improve the hamster's cage based on the messages.

[0058] This system allows users to understand their pets' feelings and desires in more detail and respond appropriately, deepening their relationship of trust with their pets.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user installs the dedicated application and enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, sex, etc.) on the initial setup screen. The application then sends the pet information to the server and prepares to select an analysis model specialized for the pet.

[0062] Step 2:

[0063] The device has a camera and microphone, and monitors, records, and records your pet's cries, movements, and facial expressions in real time. The device then sends the collected data to a server at set intervals.

[0064] Step 3:

[0065] The server receives the data sent from the device and stores it in a database, where audio and video data for each pet is organized and stored.

[0066] Step 4:

[0067] The server uses an audio analysis algorithm to analyze the collected call data, extracting sound frequencies and patterns, and analyzing the frequency, pitch, and duration of calls.

[0068] Step 5:

[0069] The server uses image analysis algorithms to analyze the recorded gestures and facial expressions, specifically detecting the pet's position, tracking its movements, and detecting changes in facial expressions.

[0070] Step 6:

[0071] The server integrates the results of audio and image analysis and uses a machine learning model to predict the pet's feelings and needs. The model is trained based on a large amount of collected data and predicts the pet's condition based on new data.

[0072] Step 7:

[0073] The server sends the analysis results to a user interface, where they are formatted into text or voice messages.

[0074] Step 8:

[0075] The device notifies the user of the analysis results, using text and voice notifications to provide specific messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed."

[0076] Step 9:

[0077] The user can check the notification on their device and take appropriate action, such as setting aside time to play with their dog or improving the hamster's cage environment to reduce stress for their pet.

[0078] Through this series of steps, users can understand their pet's feelings and needs in real time and respond appropriately, which helps deepen the trusting relationship between them and their pet.

[0079] Example 1

[0080] 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."

[0081] It is difficult for owners to accurately understand their pets' feelings and needs from their vocalizations, gestures, and facial expressions. Analyzing and interpreting this data becomes even more difficult when owners have multiple pets or pets of different species. Furthermore, conventional systems often lack efficient real-time data analysis and notifications, preventing owners from quickly understanding their pets' status.

[0082] 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.

[0083] In this invention, the server includes a means for receiving and storing data in real time, a means for analyzing the stored audio data, and a means for analyzing the stored video data, thereby enabling efficient analysis of the pet's cries, gestures, and facial expressions and prompt notification to the owner.

[0084] "Means for analyzing pet cries using audio analysis technology" refers to technology that has the function of collecting pet cries and analyzing the audio data based on frequency and patterns.

[0085] "Means for analyzing pets' gestures and facial expressions using image analysis technology" refers to technology that uses a camera or other imaging device to capture a pet's gestures and facial expressions and then analyzes the video data.

[0086] "Means for translating pets' feelings and requests based on analysis results" refers to an algorithm that integrates data obtained from audio analysis and image analysis to estimate a pet's feelings and requests.

[0087] "Means for notifying the user of the translated results" refers to technology for communicating the analyzed pet's feelings and requests in a format that is easy for the user to understand, and includes text messages and voice messages.

[0088] "Means for receiving and storing data in real time" refers to technology that has the function of collecting pet behavior data and vocalization data in real time and storing it in a database.

[0089] The "means for analyzing stored audio data" is a technology that extracts and analyzes information such as frequency, pitch, and duration based on stored pet cry data.

[0090] The "means for analyzing stored video data" refers to a technology that analyzes stored video data of a pet's behavior and facial expressions to detect changes in gestures and facial expressions.

[0091] "Means for integrating analyzed voice data and image data" refers to a technology for combining data obtained from voice analysis and data obtained from image analysis into one and performing a comprehensive analysis.

[0092] "Means for predicting pet feelings and needs using machine learning models" refers to technology that uses machine learning algorithms trained using a large number of datasets to predict pet feelings and needs with high accuracy.

[0093] "Means for formatting prediction results as text or voice messages" refers to technology that outputs the pet's feelings and requests predicted by the machine learning model in a format that is easy for humans to understand (text or voice).

[0094] The "means for sending formatted results to a user interface" is a technique for sending predicted results formatted as a text message or a voice message to a user's terminal.

[0095] The following hardware and software are used as an embodiment of this invention. A user installs a dedicated application on a device such as a smartphone or tablet and uses it. The terminal includes a camera, microphone, and network-connected device, which are used to monitor the behavior of the pet and send the data to a server. The server is a high-performance analysis server (equipped with a CPU, GPU, and storage) that processes and analyzes the data.

[0096] The software used includes Praat and TensorFlow for audio analysis, OpenCV and PyTorch for image analysis, and scikit-learn, TensorFlow and PyTorch for machine learning models.

[0097] 1. Initial Setup and Data Collection

[0098] User: After installing the dedicated application on their smartphone, they input basic information about their pet (species, name, age, sex, etc.), which allows the system to use an analysis model optimized for that particular pet.

[0099] Terminal: Monitors pet behavior and sounds in real time via camera and microphone, and automatically transmits this data to the server at regular intervals.

[0100] 2. Data Receipt and Storage

[0101] Server: Receives data sent from the device in real time and stores it in a database, including audio and video data.

[0102] 3. Audio and Image Analysis

[0103] Audio analysis: The server analyzes the received bird call data using an audio analysis algorithm (e.g., Praat or TensorFlow) to extract features such as frequency, pattern, pitch, and duration.

[0104] Image analysis: The server analyzes the video data using an image analysis algorithm (e.g., OpenCV or PyTorch) to detect changes in the pet's gestures and facial expressions.

[0105] 4. Data Integration and Application to Machine Learning Models

[0106] Server: Integrates audio and video data and inputs it into a machine learning model (e.g., scikit-learn or TensorFlow). This allows for highly accurate prediction of the pet's feelings and needs.

[0107] 5. Formatting and Notification of Results

[0108] Server: Formats the prediction results into a text or voice message and sends it to the user's device.

[0109] Device: Notifications are sent to smartphones and tablets, allowing users to keep track of their pet's status in real time.

[0110] Specific examples

[0111] Let's take an example where a user has a dog and a hamster. First, the user enters information about the dog and hamster into the application. Next, a camera and microphone installed in the living room record the dog and hamster's behavior. The data is automatically sent to the server. The server performs audio analysis of the dog's bark and identifies its frequency and pitch. Meanwhile, it performs image analysis of the hamster's behavior and confirms that it is going back and forth to a specific location. The server determines whether the dog wants to play and whether the hamster is possibly stressed, and sends these results to the user's device. The device then displays and notifies the user by voice, messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed." The user can then play with the dog and improve the hamster's cage based on the messages presented to them.

[0112] Prompt Sentence Examples

[0113] User: "Please use the system to tell me what my dog ​​is thinking right now."

[0114] System: "Analyzing data collected from camera and microphone. Please wait a moment."

[0115] System: "We analyzed the barks and movements of the dog Pochi. Pochi wants to play now."

[0116] The system allows users to quickly and accurately understand their pet's feelings and needs and respond appropriately. It uses a generative AI model to improve prompts for users and help them understand their pet's situation in real time.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] Initial Setup and Data Entry

[0120] User: The user installs a dedicated application on their smartphone or tablet. They launch the application and enter basic information about their pet, such as the type of pet (e.g., dog, cat, hamster, iguana, etc.), name, age, and gender. The input data is sent to the server and used to configure the model for each pet.

[0121] Input: Basic information about your pet, such as type, name, age, and gender.

[0122] Output: Basic information about the pet sent to the server.

[0123] Step 2:

[0124] Data collection

[0125] Device: The camera and microphone are installed in the living room or other areas where pets are active, and monitor the pet's movements and sounds in real time. Data is captured every 30 seconds and sent to the server.

[0126] Input: Video and audio data of pet.

[0127] Output: The captured data sent to the server.

[0128] Step 3:

[0129] Receiving and storing data

[0130] Server: Receives data sent from the device in real time and stores it in a database. Adds timestamps to video and audio data, and organizes and stores it for future analysis.

[0131] Specific operation: The server receives data sent at regular intervals and stores it in a database. For example, it stores dog video data and barking data sent every 30 seconds with a timestamp.

[0132] Input: Real-time data sent from the device.

[0133] Output: Video and audio data stored in a database.

[0134] Step 4:

[0135] Audio analysis

[0136] Server: Analyzes the collected audio data using an audio analysis algorithm (e.g., Praat or TensorFlow). Specifically, it extracts features such as the frequency, pattern, pitch, and duration of the calls.

[0137] How it works: The server analyzes audio data to identify the frequency of a dog's bark, and at the same time, infers the pet's emotions from the pitch and pattern of the sound.

[0138] Input: Audio data stored in a database.

[0139] Output: Audio characteristics such as frequency, pattern, pitch, and duration.

[0140] Step 5:

[0141] Image analysis

[0142] Server: Analyzes the video data captured by the camera using an image analysis algorithm (e.g., OpenCV or PyTorch) to detect changes in the pet's gestures and facial expressions.

[0143] How it works: The server analyzes the video of the cat and detects changes in its tail movements and eye expressions. This data is used to estimate the cat's emotions and state.

[0144] Input: Video data stored in a database.

[0145] Output: Gestures, facial expressions, and behavioral patterns.

[0146] Step 6:

[0147] Data integration and application to machine learning models

[0148] Server: Integrates feature data obtained from audio and image analysis and inputs it into a machine learning model (e.g., scikit-learn or TensorFlow). This allows for highly accurate prediction of pets' feelings and needs.

[0149] How it works: The server combines audio and visual data and feeds it into a machine learning model, for example, to predict if a dog wants to play based on its bark and tail wagging.

[0150] Input: Audio analysis data and image analysis data.

[0151] Output: Prediction results from the machine learning model (e.g., want to play, want to eat, stress, etc.).

[0152] Step 7:

[0153] Formatting and sending results

[0154] Server: Formats the predictions of the machine learning model as text or voice messages and sends them to the user interface.

[0155] Specific operation: The server generates a message saying "Pochi the dog wants to play" and sends it to the smartphone.

[0156] Input: Predictions made by machine learning models.

[0157] Output: Formatted text and audio messages.

[0158] Step 8:

[0159] User Notification

[0160] On your device: Notifications will appear on your smartphone or tablet, and you will receive text and voice messages, allowing you to keep up with your pet's status in real time.

[0161] Specific operation: The smartphone will display "Pochi the dog wants to play" along with a notification sound and notify you by voice.

[0162] Input: A text or voice message sent from the server.

[0163] Output: A notification message that is displayed on the user's terminal.

[0164] (Application example 1)

[0165] 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."

[0166] In today's busy lifestyles, it is not easy for pet owners to accurately understand their pets' feelings and needs. In particular, it is difficult to accurately infer a pet's emotions and needs from its behavior and cries, and responding incorrectly can cause stress to the pet. Problems also often arise when selecting the right products for pets. Technological solutions are needed to resolve these issues and build better relationships with pets.

[0167] 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.

[0168] In this invention, the server includes means for analyzing the pet's cries using voice analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for notifying the user of the translation results, means for recommending suitable products based on the translation results, and means for displaying information on the recommended products, thereby enabling pet owners to understand their pet's feelings and requests in real time and quickly purchase products suitable for their pets.

[0169] "Voice analysis technology" is a technology that converts pet cries into digital signals and analyzes their frequencies and patterns.

[0170] "Image analysis technology" is a technology that captures a pet's gestures and facial expressions as video data and analyzes changes in their movements and facial expressions.

[0171] The "translation method" is a method of converting a pet's feelings and requests into a form that humans can understand based on analyzed data on their cries, gestures, and facial expressions.

[0172] The "notification means" is a means for notifying the user in real time by sending the translation results to the user's terminal as a text or voice message.

[0173] The "recommendation method" is a method of selecting products suitable for pets based on the translated pet's feelings and requests using prompt sentences from the generative AI model and suggesting them to the user.

[0174] The "display means" is a means for presenting information about the recommended product on the screen of the user's terminal, making it easy to check detailed information.

[0175] The embodiments of the present invention will be described in detail below.

[0176] System Overview

[0177] The pet interpreter virtual shop system of the present invention includes the following components:

[0178] 1. Audio analysis technology: This technology converts pet sounds into digital signals and analyzes their frequencies and patterns.

[0179] 2. Image analysis technology: This is a technology that captures a pet's gestures and facial expressions as video data and analyzes changes in their movements and facial expressions.

[0180] 3. Translation method: This is a method that translates the feelings and requests of pets based on the results of voice and image analysis and converts them into a form that humans can understand.

[0181] 4. Notification: This is a means of notifying the user in real time by sending the translated results to the user's device as a text or voice message.

[0182] 5. Recommendation: This is a method of selecting suitable products for pets based on the translated pet's feelings and requests using prompts from the generative AI model and suggesting them to the user.

[0183] 6. Display method: This is a method for displaying information about recommended products on the screen of the user's device, making it easy for the user to check detailed information.

[0184] Technology used

[0185] Hardware: Smartphone (with built-in camera and microphone)

[0186] Software libraries: OpenCV (image processing library), Keras (deep learning library), Flask (web application framework)

[0187] Data processing and calculation

[0188] Speech analysis: The server extracts frequency and spectral features from the audio signal. This data is then analyzed using a speech recognition model using Keras.

[0189] Image analysis: Video data captured by the device camera is used to extract gestures and facial expressions using OpenCV, which are then analyzed using a model based on Keras.

[0190] Translation and Notifications: Your pet's feelings and requests are translated and sent to your smartphone as text and voice messages.

[0191] Selecting and displaying recommended products: Using a generative AI model, we select appropriate products, recommend products using prompts, and present the information to the user.

[0192] As a specific example, when a user analyzes a dog's bark and behavior, the following steps are performed.

[0193] 1. Audio analysis: Recognizes that a dog wants to play by hearing the repeated bark "woof woof."

[0194] 2. Image analysis: Images of a dog wagging its tail in excitement can also be analyzed to indicate that it wants to play.

[0195] 3. Notification and product recommendation: The user's smartphone will be notified that "your dog wants to play" and suitable toys will be recommended.

[0196] 4. Display: The message "Toy details are as follows: [More information]" is displayed, guiding the customer to proceed with the purchase without hesitation.

[0197] Example prompt sentence:

[0198] "My dog ​​wants to play. I recommend the following products:

[0199] Toys

[0200] snack

[0201] Please check the details and purchase."

[0202] This allows users to understand their pet's feelings and purchase appropriate products in a timely manner.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] Users install a dedicated app on their smartphone and enter basic information about their pet, such as its type, name, age, and gender. This information is sent to a server by the app, and an analysis model optimized for each pet is selected. The input is the user's basic information and pet information, and the output is a pet profile stored on the server.

[0206] Step 2:

[0207] The device's camera and microphone are used to capture the pet's cries, gestures, and facial expressions in real time. The input is the camera image and microphone audio, and the output is sent to the server at a specified time interval.

[0208] Step 3:

[0209] The server analyzes the received voice data using voice analysis technology. Specifically, it extracts frequency and spectral features from the voice signal and analyzes them using a voice recognition model. The input is the voice data from the microphone, and the output is the analysis results that can be used to infer the pet's feelings and requests.

[0210] Step 4:

[0211] The server uses image analysis technology to analyze the received image data. It extracts the pet's gestures and facial expressions from the video data and analyzes the changes in their movements and expressions using an image recognition model. The input is the camera video data, and the output is the analysis results that allow the pet's feelings and state to be estimated.

[0212] Step 5:

[0213] The server integrates the results of the audio and image analysis and uses a machine learning model to predict your pet's feelings and needs with high accuracy. This integrated analysis improves accuracy by combining individually obtained features. The audio and image analysis results are used as input, and the output is a confirmed prediction of your pet's feelings and needs.

[0214] Step 6:

[0215] Based on the analysis results, the server uses a generative AI model to recommend products suitable for pets. It generates a prompt sentence and selects appropriate products from a commercial database based on that sentence. The input is the confirmed pet's emotions and needs, and the output is a list of recommended products.

[0216] Step 7:

[0217] The server notifies the user's smartphone in real time of information about recommended products. It generates text and voice messages and sends them to the user's device. The input is a list of recommended products, and the output is a notification message that is displayed on the user's device.

[0218] Step 8:

[0219] The user can check the notification on their smartphone and view detailed information about the recommended product. If necessary, they can purchase the product directly in the virtual store. The input is the user's action, and the output is the completion of the product purchase or the presentation of detailed information.

[0220] This allows users to understand their pet's feelings and needs in real time and quickly purchase products that are suitable for their pet.

[0221] 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.

[0222] System Overview

[0223] The pet translation system of the present invention analyzes a pet's cries, gestures, and facial expressions, and uses this data to translate the pet's feelings and requests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a more appropriate response by linking the pet's feelings and requests with the user's emotional data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify the user of the analysis results in real time.

[0224] Initial Setup and Data Collection

[0225] 1. User: After installing the dedicated application, the user enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, gender, etc.) on the initial setup screen. In addition, the emotion engine is enabled. The emotion engine is configured to monitor the user's facial expressions and voice.

[0226] 2. Terminal: Equipped with a camera and microphone, it monitors your pet's real-time behavior. The terminal records your pet's cries, gestures, and facial expressions, and transmits the data to the server at set intervals.

[0227] 3. Server: Receives data sent from the device and stores it in a database. The collected data is later used for analysis.

[0228] Data analysis

[0229] 4. Server: Analyzes the collected bark data using sound analysis algorithms, extracting sound frequencies and patterns to obtain data that can identify what your pet is trying to communicate.

[0230] 5. Server: Analyzes the recorded gestures and facial expressions using image analysis algorithms, detecting patterns of pet movement and changes in facial expressions, and inferring the pet's feelings and state.

[0231] 6. Server: The results of audio and image analysis are integrated and a machine learning model is used to predict the pet's feelings and needs. This model is trained based on data collected from many pets and can predict the pet's condition with high accuracy based on new data.

[0232] Recognizing user emotions with an emotion engine

[0233] 7. Device: The user's facial expressions and voice are captured by a camera and microphone, and analyzed by the emotion engine, which determines the user's current emotional state from their facial movements and tone of voice.

[0234] 8. Server: Receives the user's emotional data, combines it with the analysis results of the pet's feelings and requests, and generates the most appropriate notification content.

[0235] Providing results

[0236] 9. Server: Based on the analysis results and the user's emotional data, the server formats text and voice messages and sends them to the user interface. For example, if the user is tired, the server might send a message like, "Your dog, Pochi, wants to play, but it's time for him to rest."

[0237] 10. Device: Displays the analysis results and sends messages that take into account the pet's feelings and the user's emotions. Notifications are sent using both text and voice, allowing users to quickly and reliably understand the status of their pet and the user.

[0238] Specific examples

[0239] Consider the case where a user has a dog and a hamster:

[0240] 1. Initial Setup: The user enters information about their dog and hamster into the application and enables the emotion engine.

[0241] 2. Data collection: A camera and microphone installed in the living room record the behavior of the dog and hamster. The data is automatically sent to a server.

[0242] 3. Data analysis: The server analyzes the dog's bark and detects that it is making a repeated "woof woof" sound, while simultaneously analyzing the hamster's movements to determine if it is moving back and forth to a specific location.

[0243] 4. User emotion recognition: The device captures the user's facial expressions and voice, and the emotion engine recognizes that the user is tired.

[0244] 5. Providing results: The server predicts that the dog is in a state of "wanting to play" and indicates that the hamster may be "stressed," and generates a message that takes into account the user's emotional state.

[0245] 6. User notification: The device will display a message saying, "Your dog, Pochi, wants to play, but your hamster, Ham, is stressed. You are tired, so please rest first before dealing with this." and will also notify you with a voice.

[0246] This system allows users to take appropriate action by considering their pet's feelings and their own, thereby deepening their relationship of trust with their pet.

[0247] The processing flow will be explained below.

[0248] Step 1:

[0249] The user installs the dedicated application and enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, sex, etc.) on the initial setup screen, which then sends the pet information to the server.

[0250] Step 2:

[0251] The device is equipped with a camera and microphone to monitor the pet's real-time behavior, recording the pet's cries, gestures, and facial expressions, and sending this data to a server at set intervals.

[0252] Step 3:

[0253] The server receives the data sent from the device and stores it in a database, where the collected bird call data and video data are organized and stored.

[0254] Step 4:

[0255] The server uses a sound analysis algorithm to analyze the pet's meow data, extracting the frequency and patterns of the pet's meows and analyzing the frequency, pitch, duration, etc.

[0256] Step 5:

[0257] The server uses an image analysis algorithm to analyze the recorded data, detecting the pet's movement patterns and facial expressions, and providing detailed analysis.

[0258] Step 6:

[0259] The server integrates the results of voice and image analysis and uses a machine learning model to predict the pet's feelings and needs. The model is trained based on data collected from many pets, and can predict the pet's condition with high accuracy based on new data.

[0260] Step 7:

[0261] The device captures the user's facial expressions and voice using a camera and microphone and sends this data to the emotion engine, which analyzes the user's facial movements and tone of voice to determine their current emotional state.

[0262] Step 8:

[0263] The server receives the user's emotional data and combines it with the analysis of the pet's feelings and needs to tailor the notification content. For example, if the server detects that the user is tired, the notification content will be adapted to that state.

[0264] Step 9:

[0265] The server sends the analysis results to the user interface, where they are formatted into text or voice messages that can be instantly understood by the user.

[0266] Step 10:

[0267] The device notifies the user of the analysis results. Specifically, using text and voice notification functions, it displays and notifies the user with a message such as, "Your dog Pochi wants to play, but you are tired, so please rest first before responding."

[0268] Step 11:

[0269] The user checks the notification on the device and takes appropriate action, such as taking a rest first, then playing with the dog, or improving the environment of the hamster's cage.

[0270] Through this series of steps, users can take appropriate action taking into consideration the emotional state of their pet and themselves, and can deepen their trusting relationship with their pet.

[0271] Example 2

[0272] 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."

[0273] Conventional pet translation systems can understand a pet's feelings and requests to some extent by analyzing the pet's cries, gestures, and facial expressions, but they lack the ability to suggest appropriate responses based on the user's emotional state. As a result, the pet's requests may be conveyed in a way that does not match the user's state, which can hinder the relationship between the pet and the user. In addition, it is difficult to provide real-time notifications and suggest appropriate responses, making it difficult to immediately understand and respond to a pet's feelings.

[0274] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for analyzing the pet's cries using audio analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for analyzing the user's facial expressions and voice to identify the emotional state, means for generating an appropriate notification based on the translation result and the user's emotional state, and means for displaying the generated notification in text and audio. This makes it possible to understand the pet's feelings and requests and, at the same time, to propose an appropriate response taking the user's emotional state into consideration.

[0275] "Voice analysis technology" is a means of analyzing voice data and identifying its content and characteristics.

[0276] "Image analysis technology" is a means of analyzing image data and identifying its content and characteristics.

[0277] "Means for translating pets' feelings and requests" refers to a means for expressing pets' emotions and requests in human language based on the results of voice analysis technology and image analysis technology.

[0278] The "means for identifying the emotional state of the user by analyzing the facial expression and voice of the user" is a means for analyzing the facial expression and voice data of the user and identifying the current emotional state of the user from the results.

[0279] The "means for generating an appropriate notification" is a means for generating a message to suggest an appropriate response to the user based on the translation results of the pet's feelings and requests and the user's emotional state.

[0280] The "means for displaying in text and voice" refers to a means for displaying the generated notification message to the user in text and voice.

[0281] System Overview

[0282] The pet translation system of the present invention analyzes a pet's cries, gestures, and facial expressions, and uses this data to translate the pet's feelings and requests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a more appropriate response by linking the pet's feelings and requests with the user's emotional data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify the user of the analysis results in real time.

[0283] Initial Setup and Data Collection

[0284] 1. User: Install the dedicated application on a smartphone or tablet and enter basic information about the pet (species, name, age, gender, etc.) on the initial setup screen. In addition, the emotion engine is enabled and monitoring of the user's facial expressions and voice is permitted.

[0285] 2. Device: A camera and microphone are installed to monitor the pet's real-time behavior. The camera records the pet's movements and facial expressions, and the microphone records its cries. The collected data is temporarily stored on the device and sent to the server at specified intervals.

[0286] 3. Server: Receives the data sent from the device and stores it in a database, facilitating subsequent analysis.

[0287] Data analysis

[0288] 1. Server: Using sound analysis algorithms, the collected bark data is analyzed, specifically extracting the frequencies and patterns of the barks to determine what the pet is trying to communicate.

[0289] 2. Server: Using image analysis algorithms, the recorded gestures and facial expressions are analyzed to detect changes in the pet's movements and facial expressions, and from these, the pet's feelings and state are inferred.

[0290] 3. Server: The results of audio analysis and image analysis are integrated, and a machine learning model is used to predict the pet's feelings and needs. This makes it possible to predict the pet's condition with high accuracy.

[0291] Recognizing user emotions with an emotion engine

[0292] 1. Device: The user's facial expressions and voice are captured by a camera and microphone, and analyzed by an emotion engine. For example, subtle changes in the user's facial expressions and tone of voice can be used to identify the user's emotional state.

[0293] 2. Server: Receives the user's emotional data and combines it with the pet's analysis results to generate the optimal notification content that matches the user's situation.

[0294] Providing results

[0295] 1. Server: Generates a specific notification message based on the pet analysis results and the user's emotional data. For example, it creates a message that reads, "Your dog Pochi wants to play with you, but you seem tired. Let's take a break and then play."

[0296] 2. Terminal: Notifies the user of the generated message. Text messages are displayed in a dedicated application, and audio messages are played through the speaker.

[0297] Specific examples

[0298] If the user has a dog and a hamster:

[0299] 1. Initial Setup: The user enters information about their dog and hamster into the application and enables the emotion engine.

[0300] 2. Data collection: A camera and microphone placed in the living room record the behavior of the dog and hamster.

[0301] 3. Data analysis: The server analyzes the dog's bark and detects that it is repeatedly barking "woof woof." At the same time, it analyzes the hamster's behavioral patterns and finds that it frequently returns to a specific location.

[0302] 4. User emotion recognition: The device captures the user's facial expressions and voice, and the emotion engine recognizes that the user is tired.

[0303] 5. Providing results: The server generates messages indicating that the dog "wants to play," the hamster "is stressed," and the user is tired.

[0304] 6. User notification: The device will display a message saying, "Your dog, Pochi, wants to play, but your hamster, Ham, is stressed. You are tired, so please rest first before dealing with this." and also notify you with a voice.

[0305] Example prompts for generative AI models

[0306] "I want to develop a system that analyzes a pet's barks and movements, and notifies the user of the pet's feelings and requests. When a dog barks "woof woof" repeatedly and the user becomes tired, what kind of notification message should be generated?"

[0307] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0308] Step 1:

[0309] User: Installs the dedicated application on a smartphone or tablet and launches it. On the initial setup screen, basic information about the pet (such as breed, name, age, and gender) is entered, and the emotion engine is enabled. This initial setup allows the system to determine which pet the user has and to monitor the user's facial expressions and voice.

[0310] Input: Basic information of pet (type, name, age, gender, etc.), Emotion engine activation

[0311] Output: The pet's basic information is registered and the user's emotion engine is enabled.

[0312] Step 2:

[0313] Device: Equipped with a camera and microphone, it monitors your pet's real-time behavior. The camera records their movements and facial expressions, and the microphone records their barks. The collected data is temporarily stored on the device.

[0314] Input: Pet's gestures, facial expressions, and cries

[0315] Output: Recorded gestures and facial expressions, recorded vocalizations

[0316] Step 3:

[0317] Terminal: Sends collected data to the server at a specified interval (e.g., every hour). Connects to the server and transmits the data securely. The server receives the data and stores it in a database.

[0318] Input: Recorded gestures and facial expressions, recorded animal sounds

[0319] Output: Data sent to server, data stored in database

[0320] Step 4:

[0321] Server: Using sound analysis algorithms, the collected bark data is analyzed to extract sound frequencies and patterns, providing data to identify what your pet is trying to communicate.

[0322] Input: Recorded bird call data

[0323] Output: Analyzed call frequency and pattern data

[0324] Step 5:

[0325] Server: Analyzes recorded gestures and facial expressions using image analysis algorithms, detects changes in pet movements and facial expressions, and infers the pet's feelings and state from them.

[0326] Input: Recorded gesture and facial expression data

[0327] Output: Analyzed gesture and facial expression pattern data

[0328] Step 6:

[0329] Server: Integrates the results of audio and image analysis and uses machine learning models to predict the pet's feelings and needs. This makes it possible to predict the pet's condition with high accuracy.

[0330] Input: Audio analysis results, image analysis results

[0331] Output: Prediction of pet's feelings and needs

[0332] Step 7:

[0333] On the device: The camera and microphone capture the user's facial expressions and voice, which are then analyzed by the emotion engine. For example, subtle changes in the user's facial expressions and tone of voice can be used to identify the user's emotional state.

[0334] Input: User's facial expression data, voice data

[0335] Output: Analyzed user emotion data

[0336] Step 8:

[0337] Server: Receives the user's emotional data and combines it with the pet's analysis results. This generates the optimal notification content that matches the user's situation.

[0338] Input: User's emotional data, predicted pet's feelings and requests

[0339] Output: Optimal notification content

[0340] Step 9:

[0341] Server: Generates a specific notification message based on the pet analysis results and the user's emotional data. For example, it creates a message like, "Your dog Pochi wants to play with you, but you seem tired. Let's rest a bit and then play."

[0342] Input: Optimal notification content

[0343] Output: The generated notification message

[0344] Step 10:

[0345] Terminal: Notifies the user of the generated message. Text messages are displayed in a dedicated application, and audio messages are played through the speaker.

[0346] Input: The generated notification message

[0347] Output: A text message that is displayed to the user and an audio message that is played

[0348] (Application example 2)

[0349] 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."

[0350] Currently, there are several systems that facilitate communication with pets, but these simply analyze the pet's cries and gestures and do not take into account the user's emotional state. Furthermore, there is a lack of systems that naturally link the user's and pet's behavior in a virtual environment, so the user experience is not sufficiently improved.

[0351] The specific processing by the specific 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 analyzing the pet's cries using audio analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for notifying the user of the translation results, emotion analysis means for recognizing the user's emotional state, means for generating notification content by integrating the pet's translation results with the user's emotional data, and means for linking the behavior of the user and the pet in the virtual environment. This enables natural and personalized communication in the virtual environment while taking the user's emotional state into consideration.

[0352] "Voice analysis technology" is a technology that analyzes voice data and extracts information by analyzing its patterns, frequencies, etc.

[0353] "Image analysis technology" is a technology that analyzes image data to identify objects and detect movement patterns.

[0354] "A means of translating pets' feelings and requests" is a system that uses data obtained from voice analysis and image analysis technology to infer and translate a pet's emotions and requests.

[0355] "Means for notifying the user" is a notification function for conveying the translated feelings and requests of the pet to the user.

[0356] "Emotion analysis means" is a technology that analyzes the user's facial expressions and voice data to identify their emotional state.

[0357] The "means for generating notification content" is a function that combines the pet's translation results with the user's emotional data to generate the optimal message.

[0358] "Means for linking the behavior of a user and a pet in a virtual environment" refers to technology that naturally links the behavior and emotions of a user with the behavior of a pet in a virtual space.

[0359] MODE FOR CARRYING OUT THE INVENTION

[0360] Specific hardware and software are required to implement the present invention. A specific system configuration and processing method will be described below.

[0361] System Configuration

[0362] Server: A server with high-performance computing power is required to analyze the data using voice and image analysis techniques and implement sentiment analysis methods, specifically using machine learning libraries such as Keras and TensorFlow.

[0363] Device: A device with a camera and microphone is required to capture the movements and sounds of both you and your pet in real time.

[0364] Notification system: A smartphone application or web application is required to notify users of the notification content.

[0365] Data processing and calculation

[0366] The server does the following:

[0367] 1. Pet Meow Analysis: Using audio analysis technology, pet meows are analyzed based on frequency and patterns, allowing you to identify what your pet is trying to communicate.

[0368] 2. Analysis of pet gestures and facial expressions: Using image analysis technology, the system analyzes pet movements and facial expressions, allowing it to infer the pet's feelings and state.

[0369] 3. User emotion recognition: Emotion analysis means identify the user's emotional state from their facial expressions and voice.

[0370] 4. Data integration and notification content generation: The pet analysis results and user emotion data are integrated to generate optimal notification content. This implementation uses an integrated machine learning model.

[0371] Specific examples

[0372] When a user is shopping in a virtual store, the system works as follows:

[0373] 1. When a user accesses the virtual store using the device's camera and microphone, the device captures the user's and pet's actions and voices in real time.

[0374] 2. The server analyzes the cries and recognizes that the pet wants to play, and at the same time, uses image analysis technology to analyze the pet's behavior and confirm that the pet is active.

[0375] 3. Using emotion analysis means, recognize when the user is tired.

[0376] 4. The server integrates the pet's behavior and the user's emotions and generates a notification message saying, "Pochi wants to play, but you seem tired. Let's take a break first."

[0377] 5. This notification will be displayed on the user's smartphone.

[0378] Prompt Sentence Examples

[0379] While the user is enjoying shopping in a virtual store, it is determined that the virtual pet wants to play, but at the same time it is recognized that the user is tired. In this situation, generate a notification to prompt the user to take an appropriate action.

[0380] This embodiment allows the user to take appropriate action taking into account their pet's feelings and their own emotions, allowing them to enjoy a natural and personalized experience even within the virtual environment.

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1:

[0383] The user accesses the virtual store using the device's camera and microphone. The device captures the user's and pet's movements and voices in real time. The input of this step is the user's and pet's movements and voice data, and the output is the captured video and voice data.

[0384] Step 2:

[0385] The terminal transmits the captured video and audio data to the server. The specific operation here is that the terminal collects data and transmits it to the server through the network. The input of this step is the captured data, and the output is the data transmitted to the server.

[0386] Step 3:

[0387] The server analyzes the pet's cries using voice analysis technology. Specifically, the server analyzes the frequency and pattern of the received voice data to identify what the pet is trying to communicate. The input for this step is the pet's voice data, and the output is the analysis result of the cries.

[0388] Step 4:

[0389] The server uses image analysis technology to analyze the pet's gestures and facial expressions. The server analyzes the received video data and recognizes the pet's movements and facial expressions. Specifically, it uses a deep learning model to identify movement patterns and changes in facial expressions. The input for this step is the video data, and the output is the analysis results of the gestures and facial expressions.

[0390] Step 5:

[0391] The server integrates the results of voice and image analysis to translate the pet's feelings and requests. This translation uses a pre-trained generative AI model. Specifically, it infers the pet's emotions and requests from its actions and words. The input for this step is the results of voice and image analysis, and the output is a translation of the pet's feelings and requests.

[0392] Step 6:

[0393] The device captures the user's facial expression and voice and sends them to the server. Specifically, the device monitors the user's emotional state in real time and transfers the data to the server. The input of this step is the user's facial expression and voice data, and the output is the emotional data sent to the server.

[0394] Step 7:

[0395] The server uses emotion analysis means to identify the user's emotional state. Specifically, it analyzes the received facial and voice data to recognize the user's current emotion. The input of this step is the user's emotion data, and the output is the user's emotion analysis result.

[0396] Step 8:

[0397] The server combines the pet's translation results with the user's sentiment analysis results to generate appropriate notification content. This uses the generative AI model and prompt text described above. Specifically, it combines the information "the user is tired" and "the pet wants to play" to create the optimal message for the user. The input for this step is the pet's translation results and the user's sentiment analysis results, and the output is the generated notification content.

[0398] Step 9:

[0399] The server sends the generated notification to the terminal. This notification is provided to the user in text and audio format. Specifically, it creates a message to be displayed on the terminal and plays it as an audio notification. The input here is the generated notification, and the output is the notification received by the user.

[0400] Step 10:

[0401] The user receives a notification from the system via their device and takes appropriate action. For example, if they receive a message saying "Let's take a break first," they will take a break. The input to this step is the notification from the device, and the output is the user's action.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] [Second embodiment]

[0406] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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."

[0418] System Overview

[0419] The pet translation system of the present invention analyzes the cries, gestures, and facial expressions of pets and translates their feelings and requests based on that data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify owners of the analysis results in real time.

[0420] Initial Setup and Data Collection

[0421] 1. User: After installing the dedicated application, an initial setup screen appears. The user enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, gender, etc.). This allows the system to use an analysis model optimized for that particular pet.

[0422] 2. Device: Prepare a camera and microphone to monitor your pet's behavior. The device captures your pet's sounds and movements in real time and sends the data to the server at specified intervals.

[0423] 3. Server: Receives data sent from the device and stores it in a database. The collected data is later used for analysis.

[0424] Data analysis

[0425] 4. Server: Performs audio analysis on the bark data. Specifically, it analyzes the frequency and pattern of the bark and extracts characteristics such as pitch and duration. From the bark pattern, data can be obtained to identify what the pet is trying to communicate.

[0426] 5. Server: Using the recorded data, image analysis of the pet's gestures and facial expressions is performed. Image analysis algorithms are used to detect patterns of pet movement and changes in facial expressions. This allows the pet's feelings and state to be inferred from its gestures and facial expressions.

[0427] 6. Server: Integrates data from sounds, gestures, and facial expressions and uses a machine learning model to predict your pet's feelings and needs. This model learns from data collected from many pets and makes highly accurate predictions about your pet's condition based on new data.

[0428] Providing results

[0429] 7. Server: Formats the analysis results as text or voice messages and sends them to the user interface, where the user can instantly view the results.

[0430] 8. Device: Displays the analysis results and notifies the user of their pet's feelings and needs. Notifications are sent using both text and voice, allowing users to quickly and reliably understand their pet's condition.

[0431] Specific examples

[0432] Consider the case where a user has a dog and a hamster.

[0433] 1. Initial Setup: The user enters information about their dog and hamster into the application.

[0434] 2. Data collection: A camera and microphone installed in the living room record the behavior of the dog and hamster. The data is automatically sent to a server.

[0435] 3. Data analysis: The server performs audio analysis of the dog's bark to detect the repeated "woof woof" sound, while image analysis of the hamster's movements confirms that it is moving back and forth to a specific location.

[0436] 4. Providing results: The server predicts that the dog is in a state of "wanting to play" and determines that the hamster is likely "stressed." These results are sent to the user's device.

[0437] 5. User notification: The device displays messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed" and notifies the user by voice. The user can play with the dog and improve the hamster's cage based on the messages.

[0438] This system allows users to understand their pets' feelings and desires in more detail and respond appropriately, deepening their relationship of trust with their pets.

[0439] The processing flow will be explained below.

[0440] Step 1:

[0441] The user installs the dedicated application and enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, sex, etc.) on the initial setup screen. The application then sends the pet information to the server and prepares to select an analysis model specialized for the pet.

[0442] Step 2:

[0443] The device has a camera and microphone, and monitors, records, and records your pet's cries, movements, and facial expressions in real time. The device then sends the collected data to a server at set intervals.

[0444] Step 3:

[0445] The server receives the data sent from the device and stores it in a database, where audio and video data for each pet is organized and stored.

[0446] Step 4:

[0447] The server uses an audio analysis algorithm to analyze the collected call data, extracting sound frequencies and patterns, and analyzing the frequency, pitch, and duration of calls.

[0448] Step 5:

[0449] The server uses image analysis algorithms to analyze the recorded gestures and facial expressions, specifically detecting the pet's position, tracking its movements, and detecting changes in facial expressions.

[0450] Step 6:

[0451] The server integrates the results of audio and image analysis and uses a machine learning model to predict the pet's feelings and needs. The model is trained based on a large amount of collected data and predicts the pet's condition based on new data.

[0452] Step 7:

[0453] The server sends the analysis results to a user interface, where they are formatted into text or voice messages.

[0454] Step 8:

[0455] The device notifies the user of the analysis results, using text and voice notifications to provide specific messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed."

[0456] Step 9:

[0457] The user can check the notification on their device and take appropriate action, such as setting aside time to play with their dog or improving the hamster's cage environment to reduce stress for their pet.

[0458] Through this series of steps, users can understand their pet's feelings and needs in real time and respond appropriately, which helps deepen the trusting relationship between them and their pet.

[0459] Example 1

[0460] 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."

[0461] It is difficult for owners to accurately understand their pets' feelings and needs from their vocalizations, gestures, and facial expressions. Analyzing and interpreting this data becomes even more difficult when owners have multiple pets or pets of different species. Furthermore, conventional systems often lack efficient real-time data analysis and notifications, preventing owners from quickly understanding their pets' status.

[0462] 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.

[0463] In this invention, the server includes a means for receiving and storing data in real time, a means for analyzing the stored audio data, and a means for analyzing the stored video data, thereby enabling efficient analysis of the pet's cries, gestures, and facial expressions and prompt notification to the owner.

[0464] "Means for analyzing pet cries using audio analysis technology" refers to technology that has the function of collecting pet cries and analyzing the audio data based on frequency and patterns.

[0465] "Means for analyzing pets' gestures and facial expressions using image analysis technology" refers to technology that uses a camera or other imaging device to capture a pet's gestures and facial expressions and then analyzes the video data.

[0466] "Means for translating pets' feelings and requests based on analysis results" refers to an algorithm that integrates data obtained from audio analysis and image analysis to estimate a pet's feelings and requests.

[0467] "Means for notifying the user of the translated results" refers to technology for communicating the analyzed pet's feelings and requests in a format that is easy for the user to understand, and includes text messages and voice messages.

[0468] "Means for receiving and storing data in real time" refers to technology that has the function of collecting pet behavior data and vocalization data in real time and storing it in a database.

[0469] The "means for analyzing stored audio data" is a technology that extracts and analyzes information such as frequency, pitch, and duration based on stored pet cry data.

[0470] The "means for analyzing stored video data" refers to a technology that analyzes stored video data of a pet's behavior and facial expressions to detect changes in gestures and facial expressions.

[0471] "Means for integrating analyzed voice data and image data" refers to a technology for combining data obtained from voice analysis and data obtained from image analysis into one and performing a comprehensive analysis.

[0472] "Means for predicting pet feelings and needs using machine learning models" refers to technology that uses machine learning algorithms trained using a large number of datasets to predict pet feelings and needs with high accuracy.

[0473] "Means for formatting prediction results as text or voice messages" refers to technology that outputs the pet's feelings and requests predicted by the machine learning model in a format that is easy for humans to understand (text or voice).

[0474] The "means for sending formatted results to a user interface" is a technique for sending predicted results formatted as a text message or a voice message to a user's terminal.

[0475] The following hardware and software are used as an embodiment of this invention. A user installs a dedicated application on a device such as a smartphone or tablet and uses it. The terminal includes a camera, microphone, and network-connected device, which are used to monitor the behavior of the pet and send the data to a server. The server is a high-performance analysis server (equipped with a CPU, GPU, and storage) that processes and analyzes the data.

[0476] The software used includes Praat and TensorFlow for audio analysis, OpenCV and PyTorch for image analysis, and scikit-learn, TensorFlow and PyTorch for machine learning models.

[0477] 1. Initial Setup and Data Collection

[0478] User: After installing the dedicated application on their smartphone, they input basic information about their pet (species, name, age, sex, etc.), which allows the system to use an analysis model optimized for that particular pet.

[0479] Terminal: Monitors pet behavior and sounds in real time via camera and microphone, and automatically transmits this data to the server at regular intervals.

[0480] 2. Data Receipt and Storage

[0481] Server: Receives data sent from the device in real time and stores it in a database, including audio and video data.

[0482] 3. Audio and Image Analysis

[0483] Audio analysis: The server analyzes the received bird call data using an audio analysis algorithm (e.g., Praat or TensorFlow) to extract features such as frequency, pattern, pitch, and duration.

[0484] Image analysis: The server analyzes the video data using an image analysis algorithm (e.g., OpenCV or PyTorch) to detect changes in the pet's gestures and facial expressions.

[0485] 4. Data Integration and Application to Machine Learning Models

[0486] Server: Integrates audio and video data and inputs it into a machine learning model (e.g., scikit-learn or TensorFlow). This allows for highly accurate prediction of the pet's feelings and needs.

[0487] 5. Formatting and Notification of Results

[0488] Server: Formats the prediction results into a text or voice message and sends it to the user's device.

[0489] Device: Notifications are sent to smartphones and tablets, allowing users to keep track of their pet's status in real time.

[0490] Specific examples

[0491] Let's take an example where a user has a dog and a hamster. First, the user enters information about the dog and hamster into the application. Next, a camera and microphone installed in the living room record the dog and hamster's behavior. The data is automatically sent to the server. The server performs audio analysis of the dog's bark and identifies its frequency and pitch. Meanwhile, it performs image analysis of the hamster's behavior and confirms that it is going back and forth to a specific location. The server determines whether the dog wants to play and whether the hamster is possibly stressed, and sends these results to the user's device. The device then displays and notifies the user by voice, messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed." The user can then play with the dog and improve the hamster's cage based on the messages presented to them.

[0492] Prompt Sentence Examples

[0493] User: "Please use the system to tell me what my dog ​​is thinking right now."

[0494] System: "Analyzing data collected from camera and microphone. Please wait a moment."

[0495] System: "We analyzed the barks and movements of the dog Pochi. Pochi wants to play now."

[0496] The system allows users to quickly and accurately understand their pet's feelings and needs and respond appropriately. It uses a generative AI model to improve prompts for users and help them understand their pet's situation in real time.

[0497] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0498] Step 1:

[0499] Initial Setup and Data Entry

[0500] User: The user installs a dedicated application on their smartphone or tablet. They launch the application and enter basic information about their pet, such as the type of pet (e.g., dog, cat, hamster, iguana, etc.), name, age, and gender. The input data is sent to the server and used to configure the model for each pet.

[0501] Input: Basic information about your pet, such as type, name, age, and gender.

[0502] Output: Basic information about the pet sent to the server.

[0503] Step 2:

[0504] Data collection

[0505] Device: The camera and microphone are installed in the living room or other areas where pets are active, and monitor the pet's movements and sounds in real time. Data is captured every 30 seconds and sent to the server.

[0506] Input: Video and audio data of pet.

[0507] Output: The captured data sent to the server.

[0508] Step 3:

[0509] Receiving and storing data

[0510] Server: Receives data sent from the device in real time and stores it in a database. Adds timestamps to video and audio data, and organizes and stores it for future analysis.

[0511] Specific operation: The server receives data sent at regular intervals and stores it in a database. For example, it stores dog video data and barking data sent every 30 seconds with a timestamp.

[0512] Input: Real-time data sent from the device.

[0513] Output: Video and audio data stored in a database.

[0514] Step 4:

[0515] Audio analysis

[0516] Server: Analyzes the collected audio data using an audio analysis algorithm (e.g., Praat or TensorFlow). Specifically, it extracts features such as the frequency, pattern, pitch, and duration of the calls.

[0517] How it works: The server analyzes audio data to identify the frequency of a dog's bark, and at the same time, infers the pet's emotions from the pitch and pattern of the sound.

[0518] Input: Audio data stored in a database.

[0519] Output: Audio characteristics such as frequency, pattern, pitch, and duration.

[0520] Step 5:

[0521] Image analysis

[0522] Server: Analyzes the video data captured by the camera using an image analysis algorithm (e.g., OpenCV or PyTorch) to detect changes in the pet's gestures and facial expressions.

[0523] How it works: The server analyzes the video of the cat and detects changes in its tail movements and eye expressions. This data is used to estimate the cat's emotions and state.

[0524] Input: Video data stored in a database.

[0525] Output: Gestures, facial expressions, and behavioral patterns.

[0526] Step 6:

[0527] Data integration and application to machine learning models

[0528] Server: Integrates feature data obtained from audio and image analysis and inputs it into a machine learning model (e.g., scikit-learn or TensorFlow). This allows for highly accurate prediction of pets' feelings and needs.

[0529] How it works: The server combines audio and visual data and feeds it into a machine learning model, for example, to predict if a dog wants to play based on its bark and tail wagging.

[0530] Input: Audio analysis data and image analysis data.

[0531] Output: Prediction results from the machine learning model (e.g., want to play, want to eat, stress, etc.).

[0532] Step 7:

[0533] Formatting and sending results

[0534] Server: Formats the predictions of the machine learning model as text or voice messages and sends them to the user interface.

[0535] Specific operation: The server generates a message saying "Pochi the dog wants to play" and sends it to the smartphone.

[0536] Input: Predictions made by machine learning models.

[0537] Output: Formatted text and audio messages.

[0538] Step 8:

[0539] User Notification

[0540] On your device: Notifications will appear on your smartphone or tablet, and you will receive text and voice messages, allowing you to keep up with your pet's status in real time.

[0541] Specific operation: The smartphone will display "Pochi the dog wants to play" along with a notification sound and notify you by voice.

[0542] Input: A text or voice message sent from the server.

[0543] Output: A notification message that is displayed on the user's terminal.

[0544] (Application example 1)

[0545] 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."

[0546] In today's busy lifestyles, it is not easy for pet owners to accurately understand their pets' feelings and needs. In particular, it is difficult to accurately infer a pet's emotions and needs from its behavior and cries, and responding incorrectly can cause stress to the pet. Problems also often arise when selecting the right products for pets. Technological solutions are needed to resolve these issues and build better relationships with pets.

[0547] 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.

[0548] In this invention, the server includes means for analyzing the pet's cries using voice analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for notifying the user of the translation results, means for recommending suitable products based on the translation results, and means for displaying information on the recommended products, thereby enabling pet owners to understand their pet's feelings and requests in real time and quickly purchase products suitable for their pets.

[0549] "Voice analysis technology" is a technology that converts pet cries into digital signals and analyzes their frequencies and patterns.

[0550] "Image analysis technology" is a technology that captures a pet's gestures and facial expressions as video data and analyzes changes in their movements and facial expressions.

[0551] The "translation method" is a method of converting a pet's feelings and requests into a form that humans can understand based on analyzed data on their cries, gestures, and facial expressions.

[0552] The "notification means" is a means for notifying the user in real time by sending the translation results to the user's terminal as a text or voice message.

[0553] The "recommendation method" is a method of selecting products suitable for pets based on the translated pet's feelings and requests using prompt sentences from the generative AI model and suggesting them to the user.

[0554] The "display means" is a means for presenting information about the recommended product on the screen of the user's terminal, making it easy to check detailed information.

[0555] The embodiments of the present invention will be described in detail below.

[0556] System Overview

[0557] The pet interpreter virtual shop system of the present invention includes the following components:

[0558] 1. Audio analysis technology: This technology converts pet sounds into digital signals and analyzes their frequencies and patterns.

[0559] 2. Image analysis technology: This is a technology that captures a pet's gestures and facial expressions as video data and analyzes changes in their movements and facial expressions.

[0560] 3. Translation method: This is a method that translates the feelings and requests of pets based on the results of voice and image analysis and converts them into a form that humans can understand.

[0561] 4. Notification: This is a means of notifying the user in real time by sending the translated results to the user's device as a text or voice message.

[0562] 5. Recommendation: This is a method of selecting suitable products for pets based on the translated pet's feelings and requests using prompts from the generative AI model and suggesting them to the user.

[0563] 6. Display method: This is a method for displaying information about recommended products on the screen of the user's device, making it easy for the user to check detailed information.

[0564] Technology used

[0565] Hardware: Smartphone (with built-in camera and microphone)

[0566] Software libraries: OpenCV (image processing library), Keras (deep learning library), Flask (web application framework)

[0567] Data processing and calculation

[0568] Speech analysis: The server extracts frequency and spectral features from the audio signal. This data is then analyzed using a speech recognition model using Keras.

[0569] Image analysis: Video data captured by the device camera is used to extract gestures and facial expressions using OpenCV, which are then analyzed using a model based on Keras.

[0570] Translation and Notifications: Your pet's feelings and requests are translated and sent to your smartphone as text and voice messages.

[0571] Selecting and displaying recommended products: Using a generative AI model, we select appropriate products, recommend products using prompts, and present the information to the user.

[0572] As a specific example, when a user analyzes a dog's bark and behavior, the following steps are performed.

[0573] 1. Audio analysis: Recognizes that a dog wants to play by hearing the repeated bark "woof woof."

[0574] 2. Image analysis: Images of a dog wagging its tail in excitement can also be analyzed to indicate that it wants to play.

[0575] 3. Notification and product recommendation: The user's smartphone will be notified that "your dog wants to play" and suitable toys will be recommended.

[0576] 4. Display: The message "Toy details are as follows: [More information]" is displayed, guiding the customer to proceed with the purchase without hesitation.

[0577] Example prompt sentence:

[0578] "My dog ​​wants to play. I recommend the following products:

[0579] Toys

[0580] snack

[0581] Please check the details and purchase."

[0582] This allows users to understand their pet's feelings and purchase appropriate products in a timely manner.

[0583] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0584] Step 1:

[0585] Users install a dedicated app on their smartphone and enter basic information about their pet, such as its type, name, age, and gender. This information is sent to a server by the app, and an analysis model optimized for each pet is selected. The input is the user's basic information and pet information, and the output is a pet profile stored on the server.

[0586] Step 2:

[0587] The device's camera and microphone are used to capture the pet's cries, gestures, and facial expressions in real time. The input is the camera image and microphone audio, and the output is sent to the server at a specified time interval.

[0588] Step 3:

[0589] The server analyzes the received voice data using voice analysis technology. Specifically, it extracts frequency and spectral features from the voice signal and analyzes them using a voice recognition model. The input is the voice data from the microphone, and the output is the analysis results that can be used to infer the pet's feelings and requests.

[0590] Step 4:

[0591] The server uses image analysis technology to analyze the received image data. It extracts the pet's gestures and facial expressions from the video data and analyzes the changes in their movements and expressions using an image recognition model. The input is the camera video data, and the output is the analysis results that allow the pet's feelings and state to be estimated.

[0592] Step 5:

[0593] The server integrates the results of the audio and image analysis and uses a machine learning model to predict your pet's feelings and needs with high accuracy. This integrated analysis improves accuracy by combining individually obtained features. The audio and image analysis results are used as input, and the output is a confirmed prediction of your pet's feelings and needs.

[0594] Step 6:

[0595] Based on the analysis results, the server uses a generative AI model to recommend products suitable for pets. It generates a prompt sentence and selects appropriate products from a commercial database based on that sentence. The input is the confirmed pet's emotions and needs, and the output is a list of recommended products.

[0596] Step 7:

[0597] The server notifies the user's smartphone in real time of information about recommended products. It generates text and voice messages and sends them to the user's device. The input is a list of recommended products, and the output is a notification message that is displayed on the user's device.

[0598] Step 8:

[0599] The user can check the notification on their smartphone and view detailed information about the recommended product. If necessary, they can purchase the product directly in the virtual store. The input is the user's action, and the output is the completion of the product purchase or the presentation of detailed information.

[0600] This allows users to understand their pet's feelings and needs in real time and quickly purchase products that are suitable for their pet.

[0601] 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.

[0602] System Overview

[0603] The pet translation system of the present invention analyzes a pet's cries, gestures, and facial expressions, and uses this data to translate the pet's feelings and requests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a more appropriate response by linking the pet's feelings and requests with the user's emotional data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify the user of the analysis results in real time.

[0604] Initial Setup and Data Collection

[0605] 1. User: After installing the dedicated application, the user enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, gender, etc.) on the initial setup screen. In addition, the emotion engine is enabled. The emotion engine is configured to monitor the user's facial expressions and voice.

[0606] 2. Terminal: Equipped with a camera and microphone, it monitors your pet's real-time behavior. The terminal records your pet's cries, gestures, and facial expressions, and transmits the data to the server at set intervals.

[0607] 3. Server: Receives data sent from the device and stores it in a database. The collected data is later used for analysis.

[0608] Data analysis

[0609] 4. Server: Analyzes the collected bark data using sound analysis algorithms, extracting sound frequencies and patterns to obtain data that can identify what your pet is trying to communicate.

[0610] 5. Server: Analyzes the recorded gestures and facial expressions using image analysis algorithms, detecting patterns of pet movement and changes in facial expressions, and inferring the pet's feelings and state.

[0611] 6. Server: The results of audio and image analysis are integrated and a machine learning model is used to predict the pet's feelings and needs. This model is trained based on data collected from many pets and can predict the pet's condition with high accuracy based on new data.

[0612] Recognizing user emotions with an emotion engine

[0613] 7. Device: The user's facial expressions and voice are captured by a camera and microphone, and analyzed by the emotion engine, which determines the user's current emotional state from their facial movements and tone of voice.

[0614] 8. Server: Receives the user's emotional data, combines it with the analysis results of the pet's feelings and requests, and generates the most appropriate notification content.

[0615] Providing results

[0616] 9. Server: Based on the analysis results and the user's emotional data, the server formats text and voice messages and sends them to the user interface. For example, if the user is tired, the server might send a message like, "Your dog, Pochi, wants to play, but it's time for him to rest."

[0617] 10. Device: Displays the analysis results and sends messages that take into account the pet's feelings and the user's emotions. Notifications are sent using both text and voice, allowing users to quickly and reliably understand the status of their pet and the user.

[0618] Specific examples

[0619] Consider the case where a user has a dog and a hamster:

[0620] 1. Initial Setup: The user enters information about their dog and hamster into the application and enables the emotion engine.

[0621] 2. Data collection: A camera and microphone installed in the living room record the behavior of the dog and hamster. The data is automatically sent to a server.

[0622] 3. Data analysis: The server analyzes the dog's bark and detects that it is making a repeated "woof woof" sound, while simultaneously analyzing the hamster's movements to determine if it is moving back and forth to a specific location.

[0623] 4. User emotion recognition: The device captures the user's facial expressions and voice, and the emotion engine recognizes that the user is tired.

[0624] 5. Providing results: The server predicts that the dog is in a state of "wanting to play" and indicates that the hamster may be "stressed," and generates a message that takes into account the user's emotional state.

[0625] 6. User notification: The device will display a message saying, "Your dog, Pochi, wants to play, but your hamster, Ham, is stressed. You are tired, so please rest first before dealing with this." and will also notify you with a voice.

[0626] This system allows users to take appropriate action by considering their pet's feelings and their own, thereby deepening their relationship of trust with their pet.

[0627] The processing flow will be explained below.

[0628] Step 1:

[0629] The user installs the dedicated application and enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, sex, etc.) on the initial setup screen, which then sends the pet information to the server.

[0630] Step 2:

[0631] The device is equipped with a camera and microphone to monitor the pet's real-time behavior, recording the pet's cries, gestures, and facial expressions, and sending this data to a server at set intervals.

[0632] Step 3:

[0633] The server receives the data sent from the device and stores it in a database, where the collected bird call data and video data are organized and stored.

[0634] Step 4:

[0635] The server uses a sound analysis algorithm to analyze the pet's meow data, extracting the frequency and patterns of the pet's meows and analyzing the frequency, pitch, duration, etc.

[0636] Step 5:

[0637] The server uses an image analysis algorithm to analyze the recorded data, detecting the pet's movement patterns and facial expressions, and providing detailed analysis.

[0638] Step 6:

[0639] The server integrates the results of voice and image analysis and uses a machine learning model to predict the pet's feelings and needs. The model is trained based on data collected from many pets, and can predict the pet's condition with high accuracy based on new data.

[0640] Step 7:

[0641] The device captures the user's facial expressions and voice using a camera and microphone and sends this data to the emotion engine, which analyzes the user's facial movements and tone of voice to determine their current emotional state.

[0642] Step 8:

[0643] The server receives the user's emotional data and combines it with the analysis of the pet's feelings and needs to tailor the notification content. For example, if the server detects that the user is tired, the notification content will be adapted to that state.

[0644] Step 9:

[0645] The server sends the analysis results to the user interface, where they are formatted into text or voice messages that can be instantly understood by the user.

[0646] Step 10:

[0647] The device notifies the user of the analysis results. Specifically, using text and voice notification functions, it displays and notifies the user with a message such as, "Your dog Pochi wants to play, but you are tired, so please rest first before responding."

[0648] Step 11:

[0649] The user checks the notification on the device and takes appropriate action, such as taking a rest first, then playing with the dog, or improving the environment of the hamster's cage.

[0650] Through this series of steps, users can take appropriate action taking into consideration the emotional state of their pet and themselves, and can deepen their trusting relationship with their pet.

[0651] Example 2

[0652] 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."

[0653] Conventional pet translation systems can understand a pet's feelings and requests to some extent by analyzing the pet's cries, gestures, and facial expressions, but they lack the ability to suggest appropriate responses based on the user's emotional state. As a result, the pet's requests may be conveyed in a way that does not match the user's state, which can hinder the relationship between the pet and the user. In addition, it is difficult to provide real-time notifications and suggest appropriate responses, making it difficult to immediately understand and respond to a pet's feelings.

[0654] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for analyzing the pet's cries using audio analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for analyzing the user's facial expressions and voice to identify the emotional state, means for generating an appropriate notification based on the translation result and the user's emotional state, and means for displaying the generated notification in text and audio. This makes it possible to understand the pet's feelings and requests and, at the same time, to propose an appropriate response taking the user's emotional state into consideration.

[0655] "Voice analysis technology" is a means of analyzing voice data and identifying its content and characteristics.

[0656] "Image analysis technology" is a means of analyzing image data and identifying its content and characteristics.

[0657] "Means for translating pets' feelings and requests" refers to a means for expressing pets' emotions and requests in human language based on the results of voice analysis technology and image analysis technology.

[0658] The "means for identifying the emotional state of the user by analyzing the facial expression and voice of the user" is a means for analyzing the facial expression and voice data of the user and identifying the current emotional state of the user from the results.

[0659] The "means for generating an appropriate notification" is a means for generating a message to suggest an appropriate response to the user based on the translation results of the pet's feelings and requests and the user's emotional state.

[0660] The "means for displaying in text and voice" refers to a means for displaying the generated notification message to the user in text and voice.

[0661] System Overview

[0662] The pet translation system of the present invention analyzes a pet's cries, gestures, and facial expressions, and uses this data to translate the pet's feelings and requests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a more appropriate response by linking the pet's feelings and requests with the user's emotional data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify the user of the analysis results in real time.

[0663] Initial Setup and Data Collection

[0664] 1. User: Install the dedicated application on a smartphone or tablet and enter basic information about the pet (species, name, age, gender, etc.) on the initial setup screen. In addition, the emotion engine is enabled and monitoring of the user's facial expressions and voice is permitted.

[0665] 2. Device: A camera and microphone are installed to monitor the pet's real-time behavior. The camera records the pet's movements and facial expressions, and the microphone records its cries. The collected data is temporarily stored on the device and sent to the server at specified intervals.

[0666] 3. Server: Receives the data sent from the device and stores it in a database, facilitating subsequent analysis.

[0667] Data analysis

[0668] 1. Server: Using sound analysis algorithms, the collected bark data is analyzed, specifically extracting the frequencies and patterns of the barks to determine what the pet is trying to communicate.

[0669] 2. Server: Using image analysis algorithms, the recorded gestures and facial expressions are analyzed to detect changes in the pet's movements and facial expressions, and from these, the pet's feelings and state are inferred.

[0670] 3. Server: The results of audio analysis and image analysis are integrated, and a machine learning model is used to predict the pet's feelings and needs. This makes it possible to predict the pet's condition with high accuracy.

[0671] Recognizing user emotions with an emotion engine

[0672] 1. Device: The user's facial expressions and voice are captured by a camera and microphone, and analyzed by an emotion engine. For example, subtle changes in the user's facial expressions and tone of voice can be used to identify the user's emotional state.

[0673] 2. Server: Receives the user's emotional data and combines it with the pet's analysis results to generate the optimal notification content that matches the user's situation.

[0674] Providing results

[0675] 1. Server: Generates a specific notification message based on the pet analysis results and the user's emotional data. For example, it creates a message that reads, "Your dog Pochi wants to play with you, but you seem tired. Let's take a break and then play."

[0676] 2. Terminal: Notifies the user of the generated message. Text messages are displayed in a dedicated application, and audio messages are played through the speaker.

[0677] Specific examples

[0678] If the user has a dog and a hamster:

[0679] 1. Initial Setup: The user enters information about their dog and hamster into the application and enables the emotion engine.

[0680] 2. Data collection: A camera and microphone placed in the living room record the behavior of the dog and hamster.

[0681] 3. Data analysis: The server analyzes the dog's bark and detects that it is repeatedly barking "woof woof." At the same time, it analyzes the hamster's behavioral patterns and finds that it frequently returns to a specific location.

[0682] 4. User emotion recognition: The device captures the user's facial expressions and voice, and the emotion engine recognizes that the user is tired.

[0683] 5. Providing results: The server generates messages indicating that the dog "wants to play," the hamster "is stressed," and the user is tired.

[0684] 6. User notification: The device will display a message saying, "Your dog, Pochi, wants to play, but your hamster, Ham, is stressed. You are tired, so please rest first before dealing with this." and also notify you with a voice.

[0685] Example prompts for generative AI models

[0686] "I want to develop a system that analyzes a pet's barks and movements, and notifies the user of the pet's feelings and requests. When a dog barks "woof woof" repeatedly and the user becomes tired, what kind of notification message should be generated?"

[0687] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0688] Step 1:

[0689] User: Installs the dedicated application on a smartphone or tablet and launches it. On the initial setup screen, basic information about the pet (such as breed, name, age, and gender) is entered, and the emotion engine is enabled. This initial setup allows the system to determine which pet the user has and to monitor the user's facial expressions and voice.

[0690] Input: Basic information of pet (type, name, age, gender, etc.), Emotion engine activation

[0691] Output: The pet's basic information is registered and the user's emotion engine is enabled.

[0692] Step 2:

[0693] Device: Equipped with a camera and microphone, it monitors your pet's real-time behavior. The camera records their movements and facial expressions, and the microphone records their barks. The collected data is temporarily stored on the device.

[0694] Input: Pet's gestures, facial expressions, and cries

[0695] Output: Recorded gestures and facial expressions, recorded vocalizations

[0696] Step 3:

[0697] Terminal: Sends collected data to the server at a specified interval (e.g., every hour). Connects to the server and transmits the data securely. The server receives the data and stores it in a database.

[0698] Input: Recorded gestures and facial expressions, recorded animal sounds

[0699] Output: Data sent to server, data stored in database

[0700] Step 4:

[0701] Server: Using sound analysis algorithms, the collected bark data is analyzed to extract sound frequencies and patterns, providing data to identify what your pet is trying to communicate.

[0702] Input: Recorded bird call data

[0703] Output: Analyzed call frequency and pattern data

[0704] Step 5:

[0705] Server: Analyzes recorded gestures and facial expressions using image analysis algorithms, detects changes in pet movements and facial expressions, and infers the pet's feelings and state from them.

[0706] Input: Recorded gesture and facial expression data

[0707] Output: Analyzed gesture and facial expression pattern data

[0708] Step 6:

[0709] Server: Integrates the results of audio and image analysis and uses machine learning models to predict the pet's feelings and needs. This makes it possible to predict the pet's condition with high accuracy.

[0710] Input: Audio analysis results, image analysis results

[0711] Output: Prediction of pet's feelings and needs

[0712] Step 7:

[0713] On the device: The camera and microphone capture the user's facial expressions and voice, which are then analyzed by the emotion engine. For example, subtle changes in the user's facial expressions and tone of voice can be used to identify the user's emotional state.

[0714] Input: User's facial expression data, voice data

[0715] Output: Analyzed user emotion data

[0716] Step 8:

[0717] Server: Receives the user's emotional data and combines it with the pet's analysis results. This generates the optimal notification content that matches the user's situation.

[0718] Input: User's emotional data, predicted pet's feelings and requests

[0719] Output: Optimal notification content

[0720] Step 9:

[0721] Server: Generates a specific notification message based on the pet analysis results and the user's emotional data. For example, it creates a message like, "Your dog Pochi wants to play with you, but you seem tired. Let's rest a bit and then play."

[0722] Input: Optimal notification content

[0723] Output: The generated notification message

[0724] Step 10:

[0725] Terminal: Notifies the user of the generated message. Text messages are displayed in a dedicated application, and audio messages are played through the speaker.

[0726] Input: The generated notification message

[0727] Output: A text message that is displayed to the user and an audio message that is played

[0728] (Application example 2)

[0729] 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."

[0730] Currently, there are several systems that facilitate communication with pets, but these simply analyze the pet's cries and gestures and do not take into account the user's emotional state. Furthermore, there is a lack of systems that naturally link the user's and pet's behavior in a virtual environment, so the user experience is not sufficiently improved.

[0731] The specific processing by the specific 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 analyzing the pet's cries using audio analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for notifying the user of the translation results, emotion analysis means for recognizing the user's emotional state, means for generating notification content by integrating the pet's translation results with the user's emotional data, and means for linking the behavior of the user and the pet in the virtual environment. This enables natural and personalized communication in the virtual environment while taking the user's emotional state into consideration.

[0732] "Voice analysis technology" is a technology that analyzes voice data and extracts information by analyzing its patterns, frequencies, etc.

[0733] "Image analysis technology" is a technology that analyzes image data to identify objects and detect movement patterns.

[0734] "A means of translating pets' feelings and requests" is a system that uses data obtained from voice analysis and image analysis technology to infer and translate a pet's emotions and requests.

[0735] "Means for notifying the user" is a notification function for conveying the translated feelings and requests of the pet to the user.

[0736] "Emotion analysis means" is a technology that analyzes the user's facial expressions and voice data to identify their emotional state.

[0737] The "means for generating notification content" is a function that combines the pet's translation results with the user's emotional data to generate the optimal message.

[0738] "Means for linking the behavior of a user and a pet in a virtual environment" refers to technology that naturally links the behavior and emotions of a user with the behavior of a pet in a virtual space.

[0739] MODE FOR CARRYING OUT THE INVENTION

[0740] Specific hardware and software are required to implement the present invention. A specific system configuration and processing method will be described below.

[0741] System Configuration

[0742] Server: A server with high-performance computing power is required to analyze the data using voice and image analysis techniques and implement sentiment analysis methods, specifically using machine learning libraries such as Keras and TensorFlow.

[0743] Device: A device with a camera and microphone is required to capture the movements and sounds of both you and your pet in real time.

[0744] Notification system: A smartphone application or web application is required to notify users of the notification content.

[0745] Data processing and calculation

[0746] The server does the following:

[0747] 1. Pet Meow Analysis: Using audio analysis technology, pet meows are analyzed based on frequency and patterns, allowing you to identify what your pet is trying to communicate.

[0748] 2. Analysis of pet gestures and facial expressions: Using image analysis technology, the system analyzes pet movements and facial expressions, allowing it to infer the pet's feelings and state.

[0749] 3. User emotion recognition: Emotion analysis means identify the user's emotional state from their facial expressions and voice.

[0750] 4. Data integration and notification content generation: The pet analysis results and user emotion data are integrated to generate optimal notification content. This implementation uses an integrated machine learning model.

[0751] Specific examples

[0752] When a user is shopping in a virtual store, the system works as follows:

[0753] 1. When a user accesses the virtual store using the device's camera and microphone, the device captures the user's and pet's actions and voices in real time.

[0754] 2. The server analyzes the cries and recognizes that the pet wants to play, and at the same time, uses image analysis technology to analyze the pet's behavior and confirm that the pet is active.

[0755] 3. Using emotion analysis means, recognize when the user is tired.

[0756] 4. The server integrates the pet's behavior and the user's emotions and generates a notification message saying, "Pochi wants to play, but you seem tired. Let's take a break first."

[0757] 5. This notification will be displayed on the user's smartphone.

[0758] Prompt Sentence Examples

[0759] While the user is enjoying shopping in a virtual store, it is determined that the virtual pet wants to play, but at the same time it is recognized that the user is tired. In this situation, generate a notification to prompt the user to take an appropriate action.

[0760] This embodiment allows the user to take appropriate action taking into account their pet's feelings and their own emotions, allowing them to enjoy a natural and personalized experience even within the virtual environment.

[0761] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0762] Step 1:

[0763] The user accesses the virtual store using the device's camera and microphone. The device captures the user's and pet's movements and voices in real time. The input of this step is the user's and pet's movements and voice data, and the output is the captured video and voice data.

[0764] Step 2:

[0765] The terminal transmits the captured video and audio data to the server. The specific operation here is that the terminal collects data and transmits it to the server through the network. The input of this step is the captured data, and the output is the data transmitted to the server.

[0766] Step 3:

[0767] The server analyzes the pet's cries using voice analysis technology. Specifically, the server analyzes the frequency and pattern of the received voice data to identify what the pet is trying to communicate. The input for this step is the pet's voice data, and the output is the analysis result of the cries.

[0768] Step 4:

[0769] The server uses image analysis technology to analyze the pet's gestures and facial expressions. The server analyzes the received video data and recognizes the pet's movements and facial expressions. Specifically, it uses a deep learning model to identify movement patterns and changes in facial expressions. The input for this step is the video data, and the output is the analysis results of the gestures and facial expressions.

[0770] Step 5:

[0771] The server integrates the results of voice and image analysis to translate the pet's feelings and requests. This translation uses a pre-trained generative AI model. Specifically, it infers the pet's emotions and requests from its actions and words. The input for this step is the results of voice and image analysis, and the output is a translation of the pet's feelings and requests.

[0772] Step 6:

[0773] The device captures the user's facial expression and voice and sends them to the server. Specifically, the device monitors the user's emotional state in real time and transfers the data to the server. The input of this step is the user's facial expression and voice data, and the output is the emotional data sent to the server.

[0774] Step 7:

[0775] The server uses emotion analysis means to identify the user's emotional state. Specifically, it analyzes the received facial and voice data to recognize the user's current emotion. The input of this step is the user's emotion data, and the output is the user's emotion analysis result.

[0776] Step 8:

[0777] The server combines the pet's translation results with the user's sentiment analysis results to generate appropriate notification content. This uses the generative AI model and prompt text described above. Specifically, it combines the information "the user is tired" and "the pet wants to play" to create the optimal message for the user. The input for this step is the pet's translation results and the user's sentiment analysis results, and the output is the generated notification content.

[0778] Step 9:

[0779] The server sends the generated notification to the terminal. This notification is provided to the user in text and audio format. Specifically, it creates a message to be displayed on the terminal and plays it as an audio notification. The input here is the generated notification, and the output is the notification received by the user.

[0780] Step 10:

[0781] The user receives a notification from the system via their device and takes appropriate action. For example, if they receive a message saying "Let's take a break first," they will take a break. The input to this step is the notification from the device, and the output is the user's action.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] [Third embodiment]

[0786] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0787] 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.

[0788] 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).

[0789] 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.

[0790] 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.

[0791] 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).

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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."

[0798] System Overview

[0799] The pet translation system of the present invention analyzes the cries, gestures, and facial expressions of pets and translates their feelings and requests based on that data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify owners of the analysis results in real time.

[0800] Initial Setup and Data Collection

[0801] 1. User: After installing the dedicated application, an initial setup screen appears. The user enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, gender, etc.). This allows the system to use an analysis model optimized for that particular pet.

[0802] 2. Device: Prepare a camera and microphone to monitor your pet's behavior. The device captures your pet's sounds and movements in real time and sends the data to the server at specified intervals.

[0803] 3. Server: Receives data sent from the device and stores it in a database. The collected data is later used for analysis.

[0804] Data analysis

[0805] 4. Server: Performs audio analysis on the bark data. Specifically, it analyzes the frequency and pattern of the bark and extracts characteristics such as pitch and duration. From the bark pattern, data can be obtained to identify what the pet is trying to communicate.

[0806] 5. Server: Using the recorded data, image analysis of the pet's gestures and facial expressions is performed. Image analysis algorithms are used to detect patterns of pet movement and changes in facial expressions. This allows the pet's feelings and state to be inferred from its gestures and facial expressions.

[0807] 6. Server: Integrates data from sounds, gestures, and facial expressions and uses a machine learning model to predict your pet's feelings and needs. This model learns from data collected from many pets and makes highly accurate predictions about your pet's condition based on new data.

[0808] Providing results

[0809] 7. Server: Formats the analysis results as text or voice messages and sends them to the user interface, where the user can instantly view the results.

[0810] 8. Device: Displays the analysis results and notifies the user of their pet's feelings and needs. Notifications are sent using both text and voice, allowing users to quickly and reliably understand their pet's condition.

[0811] Specific examples

[0812] Consider the case where a user has a dog and a hamster.

[0813] 1. Initial Setup: The user enters information about their dog and hamster into the application.

[0814] 2. Data collection: A camera and microphone installed in the living room record the behavior of the dog and hamster. The data is automatically sent to a server.

[0815] 3. Data analysis: The server performs audio analysis of the dog's bark to detect the repeated "woof woof" sound, while image analysis of the hamster's movements confirms that it is moving back and forth to a specific location.

[0816] 4. Providing results: The server predicts that the dog is in a state of "wanting to play" and determines that the hamster is likely "stressed." These results are sent to the user's device.

[0817] 5. User notification: The device displays messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed" and notifies the user by voice. The user can play with the dog and improve the hamster's cage based on the messages.

[0818] This system allows users to understand their pets' feelings and desires in more detail and respond appropriately, deepening their relationship of trust with their pets.

[0819] The processing flow will be explained below.

[0820] Step 1:

[0821] The user installs the dedicated application and enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, sex, etc.) on the initial setup screen. The application then sends the pet information to the server and prepares to select an analysis model specialized for the pet.

[0822] Step 2:

[0823] The device has a camera and microphone, and monitors, records, and records your pet's cries, movements, and facial expressions in real time. The device then sends the collected data to a server at set intervals.

[0824] Step 3:

[0825] The server receives the data sent from the device and stores it in a database, where audio and video data for each pet is organized and stored.

[0826] Step 4:

[0827] The server uses an audio analysis algorithm to analyze the collected call data, extracting sound frequencies and patterns, and analyzing the frequency, pitch, and duration of calls.

[0828] Step 5:

[0829] The server uses image analysis algorithms to analyze the recorded gestures and facial expressions, specifically detecting the pet's position, tracking its movements, and detecting changes in facial expressions.

[0830] Step 6:

[0831] The server integrates the results of audio and image analysis and uses a machine learning model to predict the pet's feelings and needs. The model is trained based on a large amount of collected data and predicts the pet's condition based on new data.

[0832] Step 7:

[0833] The server sends the analysis results to a user interface, where they are formatted into text or voice messages.

[0834] Step 8:

[0835] The device notifies the user of the analysis results, using text and voice notifications to provide specific messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed."

[0836] Step 9:

[0837] The user can check the notification on their device and take appropriate action, such as setting aside time to play with their dog or improving the hamster's cage environment to reduce stress for their pet.

[0838] Through this series of steps, users can understand their pet's feelings and needs in real time and respond appropriately, which helps deepen the trusting relationship between them and their pet.

[0839] Example 1

[0840] 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."

[0841] It is difficult for owners to accurately understand their pets' feelings and needs from their vocalizations, gestures, and facial expressions. Analyzing and interpreting this data becomes even more difficult when owners have multiple pets or pets of different species. Furthermore, conventional systems often lack efficient real-time data analysis and notifications, preventing owners from quickly understanding their pets' status.

[0842] 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.

[0843] In this invention, the server includes a means for receiving and storing data in real time, a means for analyzing the stored audio data, and a means for analyzing the stored video data, thereby enabling efficient analysis of the pet's cries, gestures, and facial expressions and prompt notification to the owner.

[0844] "Means for analyzing pet cries using audio analysis technology" refers to technology that has the function of collecting pet cries and analyzing the audio data based on frequency and patterns.

[0845] "Means for analyzing pets' gestures and facial expressions using image analysis technology" refers to technology that uses a camera or other imaging device to capture a pet's gestures and facial expressions and then analyzes the video data.

[0846] "Means for translating pets' feelings and requests based on analysis results" refers to an algorithm that integrates data obtained from audio analysis and image analysis to estimate a pet's feelings and requests.

[0847] "Means for notifying the user of the translated results" refers to technology for communicating the analyzed pet's feelings and requests in a format that is easy for the user to understand, and includes text messages and voice messages.

[0848] "Means for receiving and storing data in real time" refers to technology that has the function of collecting pet behavior data and vocalization data in real time and storing it in a database.

[0849] The "means for analyzing stored audio data" is a technology that extracts and analyzes information such as frequency, pitch, and duration based on stored pet cry data.

[0850] The "means for analyzing stored video data" refers to a technology that analyzes stored video data of a pet's behavior and facial expressions to detect changes in gestures and facial expressions.

[0851] "Means for integrating analyzed voice data and image data" refers to a technology for combining data obtained from voice analysis and data obtained from image analysis into one and performing a comprehensive analysis.

[0852] "Means for predicting pet feelings and needs using machine learning models" refers to technology that uses machine learning algorithms trained using a large number of datasets to predict pet feelings and needs with high accuracy.

[0853] "Means for formatting prediction results as text or voice messages" refers to technology that outputs the pet's feelings and requests predicted by the machine learning model in a format that is easy for humans to understand (text or voice).

[0854] The "means for sending formatted results to a user interface" is a technique for sending predicted results formatted as a text message or a voice message to a user's terminal.

[0855] The following hardware and software are used as an embodiment of this invention. A user installs a dedicated application on a device such as a smartphone or tablet and uses it. The terminal includes a camera, microphone, and network-connected device, which are used to monitor the behavior of the pet and send the data to a server. The server is a high-performance analysis server (equipped with a CPU, GPU, and storage) that processes and analyzes the data.

[0856] The software used includes Praat and TensorFlow for audio analysis, OpenCV and PyTorch for image analysis, and scikit-learn, TensorFlow and PyTorch for machine learning models.

[0857] 1. Initial Setup and Data Collection

[0858] User: After installing the dedicated application on their smartphone, they input basic information about their pet (species, name, age, sex, etc.), which allows the system to use an analysis model optimized for that particular pet.

[0859] Terminal: Monitors pet behavior and sounds in real time via camera and microphone, and automatically transmits this data to the server at regular intervals.

[0860] 2. Data Receipt and Storage

[0861] Server: Receives data sent from the device in real time and stores it in a database, including audio and video data.

[0862] 3. Audio and Image Analysis

[0863] Audio analysis: The server analyzes the received bird call data using an audio analysis algorithm (e.g., Praat or TensorFlow) to extract features such as frequency, pattern, pitch, and duration.

[0864] Image analysis: The server analyzes the video data using an image analysis algorithm (e.g., OpenCV or PyTorch) to detect changes in the pet's gestures and facial expressions.

[0865] 4. Data Integration and Application to Machine Learning Models

[0866] Server: Integrates audio and video data and inputs it into a machine learning model (e.g., scikit-learn or TensorFlow). This allows for highly accurate prediction of the pet's feelings and needs.

[0867] 5. Formatting and Notification of Results

[0868] Server: Formats the prediction results into a text or voice message and sends it to the user's device.

[0869] Device: Notifications are sent to smartphones and tablets, allowing users to keep track of their pet's status in real time.

[0870] Specific examples

[0871] Let's take an example where a user has a dog and a hamster. First, the user enters information about the dog and hamster into the application. Next, a camera and microphone installed in the living room record the dog and hamster's behavior. The data is automatically sent to the server. The server performs audio analysis of the dog's bark and identifies its frequency and pitch. Meanwhile, it performs image analysis of the hamster's behavior and confirms that it is going back and forth to a specific location. The server determines whether the dog wants to play and whether the hamster is possibly stressed, and sends these results to the user's device. The device then displays and notifies the user by voice, messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed." The user can then play with the dog and improve the hamster's cage based on the messages presented to them.

[0872] Prompt Sentence Examples

[0873] User: "Please use the system to tell me what my dog ​​is thinking right now."

[0874] System: "Analyzing data collected from camera and microphone. Please wait a moment."

[0875] System: "We analyzed the barks and movements of the dog Pochi. Pochi wants to play now."

[0876] The system allows users to quickly and accurately understand their pet's feelings and needs and respond appropriately. It uses a generative AI model to improve prompts for users and help them understand their pet's situation in real time.

[0877] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0878] Step 1:

[0879] Initial Setup and Data Entry

[0880] User: The user installs a dedicated application on their smartphone or tablet. They launch the application and enter basic information about their pet, such as the type of pet (e.g., dog, cat, hamster, iguana, etc.), name, age, and gender. The input data is sent to the server and used to configure the model for each pet.

[0881] Input: Basic information about your pet, such as type, name, age, and gender.

[0882] Output: Basic information about the pet sent to the server.

[0883] Step 2:

[0884] Data collection

[0885] Device: The camera and microphone are installed in the living room or other areas where pets are active, and monitor the pet's movements and sounds in real time. Data is captured every 30 seconds and sent to the server.

[0886] Input: Video and audio data of pet.

[0887] Output: The captured data sent to the server.

[0888] Step 3:

[0889] Receiving and storing data

[0890] Server: Receives data sent from the device in real time and stores it in a database. Adds timestamps to video and audio data, and organizes and stores it for future analysis.

[0891] Specific operation: The server receives data sent at regular intervals and stores it in a database. For example, it stores dog video data and barking data sent every 30 seconds with a timestamp.

[0892] Input: Real-time data sent from the device.

[0893] Output: Video and audio data stored in a database.

[0894] Step 4:

[0895] Audio analysis

[0896] Server: Analyzes the collected audio data using an audio analysis algorithm (e.g., Praat or TensorFlow). Specifically, it extracts features such as the frequency, pattern, pitch, and duration of the calls.

[0897] How it works: The server analyzes audio data to identify the frequency of a dog's bark, and at the same time, infers the pet's emotions from the pitch and pattern of the sound.

[0898] Input: Audio data stored in a database.

[0899] Output: Audio characteristics such as frequency, pattern, pitch, and duration.

[0900] Step 5:

[0901] Image analysis

[0902] Server: Analyzes the video data captured by the camera using an image analysis algorithm (e.g., OpenCV or PyTorch) to detect changes in the pet's gestures and facial expressions.

[0903] How it works: The server analyzes the video of the cat and detects changes in its tail movements and eye expressions. This data is used to estimate the cat's emotions and state.

[0904] Input: Video data stored in a database.

[0905] Output: Gestures, facial expressions, and behavioral patterns.

[0906] Step 6:

[0907] Data integration and application to machine learning models

[0908] Server: Integrates feature data obtained from audio and image analysis and inputs it into a machine learning model (e.g., scikit-learn or TensorFlow). This allows for highly accurate prediction of pets' feelings and needs.

[0909] How it works: The server combines audio and visual data and feeds it into a machine learning model, for example, to predict if a dog wants to play based on its bark and tail wagging.

[0910] Input: Audio analysis data and image analysis data.

[0911] Output: Prediction results from the machine learning model (e.g., want to play, want to eat, stress, etc.).

[0912] Step 7:

[0913] Formatting and sending results

[0914] Server: Formats the predictions of the machine learning model as text or voice messages and sends them to the user interface.

[0915] Specific operation: The server generates a message saying "Pochi the dog wants to play" and sends it to the smartphone.

[0916] Input: Predictions made by machine learning models.

[0917] Output: Formatted text and audio messages.

[0918] Step 8:

[0919] User Notification

[0920] On your device: Notifications will appear on your smartphone or tablet, and you will receive text and voice messages, allowing you to keep up with your pet's status in real time.

[0921] Specific operation: The smartphone will display "Pochi the dog wants to play" along with a notification sound and notify you by voice.

[0922] Input: A text or voice message sent from the server.

[0923] Output: A notification message that is displayed on the user's terminal.

[0924] (Application example 1)

[0925] 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."

[0926] In today's busy lifestyles, it is not easy for pet owners to accurately understand their pets' feelings and needs. In particular, it is difficult to accurately infer a pet's emotions and needs from its behavior and cries, and responding incorrectly can cause stress to the pet. Problems also often arise when selecting the right products for pets. Technological solutions are needed to resolve these issues and build better relationships with pets.

[0927] 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.

[0928] In this invention, the server includes means for analyzing the pet's cries using voice analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for notifying the user of the translation results, means for recommending suitable products based on the translation results, and means for displaying information on the recommended products, thereby enabling pet owners to understand their pet's feelings and requests in real time and quickly purchase products suitable for their pets.

[0929] "Voice analysis technology" is a technology that converts pet cries into digital signals and analyzes their frequencies and patterns.

[0930] "Image analysis technology" is a technology that captures a pet's gestures and facial expressions as video data and analyzes changes in their movements and facial expressions.

[0931] The "translation method" is a method of converting a pet's feelings and requests into a form that humans can understand based on analyzed data on their cries, gestures, and facial expressions.

[0932] The "notification means" is a means for notifying the user in real time by sending the translation results to the user's terminal as a text or voice message.

[0933] The "recommendation method" is a method of selecting products suitable for pets based on the translated pet's feelings and requests using prompt sentences from the generative AI model and suggesting them to the user.

[0934] The "display means" is a means for presenting information about the recommended product on the screen of the user's terminal, making it easy to check detailed information.

[0935] The embodiments of the present invention will be described in detail below.

[0936] System Overview

[0937] The pet interpreter virtual shop system of the present invention includes the following components:

[0938] 1. Audio analysis technology: This technology converts pet sounds into digital signals and analyzes their frequencies and patterns.

[0939] 2. Image analysis technology: This is a technology that captures a pet's gestures and facial expressions as video data and analyzes changes in their movements and facial expressions.

[0940] 3. Translation method: This is a method that translates the feelings and requests of pets based on the results of voice and image analysis and converts them into a form that humans can understand.

[0941] 4. Notification: This is a means of notifying the user in real time by sending the translated results to the user's device as a text or voice message.

[0942] 5. Recommendation: This is a method of selecting suitable products for pets based on the translated pet's feelings and requests using prompts from the generative AI model and suggesting them to the user.

[0943] 6. Display method: This is a method for displaying information about recommended products on the screen of the user's device, making it easy for the user to check detailed information.

[0944] Technology used

[0945] Hardware: Smartphone (with built-in camera and microphone)

[0946] Software libraries: OpenCV (image processing library), Keras (deep learning library), Flask (web application framework)

[0947] Data processing and calculation

[0948] Speech analysis: The server extracts frequency and spectral features from the audio signal. This data is then analyzed using a speech recognition model using Keras.

[0949] Image analysis: Video data captured by the device camera is used to extract gestures and facial expressions using OpenCV, which are then analyzed using a model based on Keras.

[0950] Translation and Notifications: Your pet's feelings and requests are translated and sent to your smartphone as text and voice messages.

[0951] Selecting and displaying recommended products: Using a generative AI model, we select appropriate products, recommend products using prompts, and present the information to the user.

[0952] As a specific example, when a user analyzes a dog's bark and behavior, the following steps are performed.

[0953] 1. Audio analysis: Recognizes that a dog wants to play by hearing the repeated bark "woof woof."

[0954] 2. Image analysis: Images of a dog wagging its tail in excitement can also be analyzed to indicate that it wants to play.

[0955] 3. Notification and product recommendation: The user's smartphone will be notified that "your dog wants to play" and suitable toys will be recommended.

[0956] 4. Display: The message "Toy details are as follows: [More information]" is displayed, guiding the customer to proceed with the purchase without hesitation.

[0957] Example prompt sentence:

[0958] "My dog ​​wants to play. I recommend the following products:

[0959] Toys

[0960] snack

[0961] Please check the details and purchase."

[0962] This allows users to understand their pet's feelings and purchase appropriate products in a timely manner.

[0963] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0964] Step 1:

[0965] Users install a dedicated app on their smartphone and enter basic information about their pet, such as its type, name, age, and gender. This information is sent to a server by the app, and an analysis model optimized for each pet is selected. The input is the user's basic information and pet information, and the output is a pet profile stored on the server.

[0966] Step 2:

[0967] The device's camera and microphone are used to capture the pet's cries, gestures, and facial expressions in real time. The input is the camera image and microphone audio, and the output is sent to the server at a specified time interval.

[0968] Step 3:

[0969] The server analyzes the received voice data using voice analysis technology. Specifically, it extracts frequency and spectral features from the voice signal and analyzes them using a voice recognition model. The input is the voice data from the microphone, and the output is the analysis results that can be used to infer the pet's feelings and requests.

[0970] Step 4:

[0971] The server uses image analysis technology to analyze the received image data. It extracts the pet's gestures and facial expressions from the video data and analyzes the changes in their movements and expressions using an image recognition model. The input is the camera video data, and the output is the analysis results that allow the pet's feelings and state to be estimated.

[0972] Step 5:

[0973] The server integrates the results of the audio and image analysis and uses a machine learning model to predict your pet's feelings and needs with high accuracy. This integrated analysis improves accuracy by combining individually obtained features. The audio and image analysis results are used as input, and the output is a confirmed prediction of your pet's feelings and needs.

[0974] Step 6:

[0975] Based on the analysis results, the server uses a generative AI model to recommend products suitable for pets. It generates a prompt sentence and selects appropriate products from a commercial database based on that sentence. The input is the confirmed pet's emotions and needs, and the output is a list of recommended products.

[0976] Step 7:

[0977] The server notifies the user's smartphone in real time of information about recommended products. It generates text and voice messages and sends them to the user's device. The input is a list of recommended products, and the output is a notification message that is displayed on the user's device.

[0978] Step 8:

[0979] The user can check the notification on their smartphone and view detailed information about the recommended product. If necessary, they can purchase the product directly in the virtual store. The input is the user's action, and the output is the completion of the product purchase or the presentation of detailed information.

[0980] This allows users to understand their pet's feelings and needs in real time and quickly purchase products that are suitable for their pet.

[0981] 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.

[0982] System Overview

[0983] The pet translation system of the present invention analyzes a pet's cries, gestures, and facial expressions, and uses this data to translate the pet's feelings and requests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a more appropriate response by linking the pet's feelings and requests with the user's emotional data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify the user of the analysis results in real time.

[0984] Initial Setup and Data Collection

[0985] 1. User: After installing the dedicated application, the user enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, gender, etc.) on the initial setup screen. In addition, the emotion engine is enabled. The emotion engine is configured to monitor the user's facial expressions and voice.

[0986] 2. Terminal: Equipped with a camera and microphone, it monitors your pet's real-time behavior. The terminal records your pet's cries, gestures, and facial expressions, and transmits the data to the server at set intervals.

[0987] 3. Server: Receives data sent from the device and stores it in a database. The collected data is later used for analysis.

[0988] Data analysis

[0989] 4. Server: Analyzes the collected bark data using sound analysis algorithms, extracting sound frequencies and patterns to obtain data that can identify what your pet is trying to communicate.

[0990] 5. Server: Analyzes the recorded gestures and facial expressions using image analysis algorithms, detecting patterns of pet movement and changes in facial expressions, and inferring the pet's feelings and state.

[0991] 6. Server: The results of audio and image analysis are integrated and a machine learning model is used to predict the pet's feelings and needs. This model is trained based on data collected from many pets and can predict the pet's condition with high accuracy based on new data.

[0992] Recognizing user emotions with an emotion engine

[0993] 7. Device: The user's facial expressions and voice are captured by a camera and microphone, and analyzed by the emotion engine, which determines the user's current emotional state from their facial movements and tone of voice.

[0994] 8. Server: Receives the user's emotional data, combines it with the analysis results of the pet's feelings and requests, and generates the most appropriate notification content.

[0995] Providing results

[0996] 9. Server: Based on the analysis results and the user's emotional data, the server formats text and voice messages and sends them to the user interface. For example, if the user is tired, the server might send a message like, "Your dog, Pochi, wants to play, but it's time for him to rest."

[0997] 10. Device: Displays the analysis results and sends messages that take into account the pet's feelings and the user's emotions. Notifications are sent using both text and voice, allowing users to quickly and reliably understand the status of their pet and the user.

[0998] Specific examples

[0999] Consider the case where a user has a dog and a hamster:

[1000] 1. Initial Setup: The user enters information about their dog and hamster into the application and enables the emotion engine.

[1001] 2. Data collection: A camera and microphone installed in the living room record the behavior of the dog and hamster. The data is automatically sent to a server.

[1002] 3. Data analysis: The server analyzes the dog's bark and detects that it is making a repeated "woof woof" sound, while simultaneously analyzing the hamster's movements to determine if it is moving back and forth to a specific location.

[1003] 4. User emotion recognition: The device captures the user's facial expressions and voice, and the emotion engine recognizes that the user is tired.

[1004] 5. Providing results: The server predicts that the dog is in a state of "wanting to play" and indicates that the hamster may be "stressed," and generates a message that takes into account the user's emotional state.

[1005] 6. User notification: The device will display a message saying, "Your dog, Pochi, wants to play, but your hamster, Ham, is stressed. You are tired, so please rest first before dealing with this." and will also notify you with a voice.

[1006] This system allows users to take appropriate action by considering their pet's feelings and their own, thereby deepening their relationship of trust with their pet.

[1007] The processing flow will be explained below.

[1008] Step 1:

[1009] The user installs the dedicated application and enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, sex, etc.) on the initial setup screen, which then sends the pet information to the server.

[1010] Step 2:

[1011] The device is equipped with a camera and microphone to monitor the pet's real-time behavior, recording the pet's cries, gestures, and facial expressions, and sending this data to a server at set intervals.

[1012] Step 3:

[1013] The server receives the data sent from the device and stores it in a database, where the collected bird call data and video data are organized and stored.

[1014] Step 4:

[1015] The server uses a sound analysis algorithm to analyze the pet's meow data, extracting the frequency and patterns of the pet's meows and analyzing the frequency, pitch, duration, etc.

[1016] Step 5:

[1017] The server uses an image analysis algorithm to analyze the recorded data, detecting the pet's movement patterns and facial expressions, and providing detailed analysis.

[1018] Step 6:

[1019] The server integrates the results of voice and image analysis and uses a machine learning model to predict the pet's feelings and needs. The model is trained based on data collected from many pets, and can predict the pet's condition with high accuracy based on new data.

[1020] Step 7:

[1021] The device captures the user's facial expressions and voice using a camera and microphone and sends this data to the emotion engine, which analyzes the user's facial movements and tone of voice to determine their current emotional state.

[1022] Step 8:

[1023] The server receives the user's emotional data and combines it with the analysis of the pet's feelings and needs to tailor the notification content. For example, if the server detects that the user is tired, the notification content will be adapted to that state.

[1024] Step 9:

[1025] The server sends the analysis results to the user interface, where they are formatted into text or voice messages that can be instantly understood by the user.

[1026] Step 10:

[1027] The device notifies the user of the analysis results. Specifically, using text and voice notification functions, it displays and notifies the user with a message such as, "Your dog Pochi wants to play, but you are tired, so please rest first before responding."

[1028] Step 11:

[1029] The user checks the notification on the device and takes appropriate action, such as taking a rest first, then playing with the dog, or improving the environment of the hamster's cage.

[1030] Through this series of steps, users can take appropriate action taking into consideration the emotional state of their pet and themselves, and can deepen their trusting relationship with their pet.

[1031] Example 2

[1032] 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."

[1033] Conventional pet translation systems can understand a pet's feelings and requests to some extent by analyzing the pet's cries, gestures, and facial expressions, but they lack the ability to suggest appropriate responses based on the user's emotional state. As a result, the pet's requests may be conveyed in a way that does not match the user's state, which can hinder the relationship between the pet and the user. In addition, it is difficult to provide real-time notifications and suggest appropriate responses, making it difficult to immediately understand and respond to a pet's feelings.

[1034] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for analyzing the pet's cries using audio analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for analyzing the user's facial expressions and voice to identify the emotional state, means for generating an appropriate notification based on the translation result and the user's emotional state, and means for displaying the generated notification in text and audio. This makes it possible to understand the pet's feelings and requests and, at the same time, to propose an appropriate response taking the user's emotional state into consideration.

[1035] "Voice analysis technology" is a means of analyzing voice data and identifying its content and characteristics.

[1036] "Image analysis technology" is a means of analyzing image data and identifying its content and characteristics.

[1037] "Means for translating pets' feelings and requests" refers to a means for expressing pets' emotions and requests in human language based on the results of voice analysis technology and image analysis technology.

[1038] The "means for identifying the emotional state of the user by analyzing the facial expression and voice of the user" is a means for analyzing the facial expression and voice data of the user and identifying the current emotional state of the user from the results.

[1039] The "means for generating an appropriate notification" is a means for generating a message to suggest an appropriate response to the user based on the translation results of the pet's feelings and requests and the user's emotional state.

[1040] The "means for displaying in text and voice" refers to a means for displaying the generated notification message to the user in text and voice.

[1041] System Overview

[1042] The pet translation system of the present invention analyzes a pet's cries, gestures, and facial expressions, and uses this data to translate the pet's feelings and requests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a more appropriate response by linking the pet's feelings and requests with the user's emotional data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify the user of the analysis results in real time.

[1043] Initial Setup and Data Collection

[1044] 1. User: Install the dedicated application on a smartphone or tablet and enter basic information about the pet (species, name, age, gender, etc.) on the initial setup screen. In addition, the emotion engine is enabled and monitoring of the user's facial expressions and voice is permitted.

[1045] 2. Device: A camera and microphone are installed to monitor the pet's real-time behavior. The camera records the pet's movements and facial expressions, and the microphone records its cries. The collected data is temporarily stored on the device and sent to the server at specified intervals.

[1046] 3. Server: Receives the data sent from the device and stores it in a database, facilitating subsequent analysis.

[1047] Data analysis

[1048] 1. Server: Using sound analysis algorithms, the collected bark data is analyzed, specifically extracting the frequencies and patterns of the barks to determine what the pet is trying to communicate.

[1049] 2. Server: Using image analysis algorithms, the recorded gestures and facial expressions are analyzed to detect changes in the pet's movements and facial expressions, and from these, the pet's feelings and state are inferred.

[1050] 3. Server: The results of audio analysis and image analysis are integrated, and a machine learning model is used to predict the pet's feelings and needs. This makes it possible to predict the pet's condition with high accuracy.

[1051] Recognizing user emotions with an emotion engine

[1052] 1. Device: The user's facial expressions and voice are captured by a camera and microphone, and analyzed by an emotion engine. For example, subtle changes in the user's facial expressions and tone of voice can be used to identify the user's emotional state.

[1053] 2. Server: Receives the user's emotional data and combines it with the pet's analysis results to generate the optimal notification content that matches the user's situation.

[1054] Providing results

[1055] 1. Server: Generates a specific notification message based on the pet analysis results and the user's emotional data. For example, it creates a message that reads, "Your dog Pochi wants to play with you, but you seem tired. Let's take a break and then play."

[1056] 2. Terminal: Notifies the user of the generated message. Text messages are displayed in a dedicated application, and audio messages are played through the speaker.

[1057] Specific examples

[1058] If the user has a dog and a hamster:

[1059] 1. Initial Setup: The user enters information about their dog and hamster into the application and enables the emotion engine.

[1060] 2. Data collection: A camera and microphone placed in the living room record the behavior of the dog and hamster.

[1061] 3. Data analysis: The server analyzes the dog's bark and detects that it is repeatedly barking "woof woof." At the same time, it analyzes the hamster's behavioral patterns and finds that it frequently returns to a specific location.

[1062] 4. User emotion recognition: The device captures the user's facial expressions and voice, and the emotion engine recognizes that the user is tired.

[1063] 5. Providing results: The server generates messages indicating that the dog "wants to play," the hamster "is stressed," and the user is tired.

[1064] 6. User notification: The device will display a message saying, "Your dog, Pochi, wants to play, but your hamster, Ham, is stressed. You are tired, so please rest first before dealing with this." and also notify you with a voice.

[1065] Example prompts for generative AI models

[1066] "I want to develop a system that analyzes a pet's barks and movements, and notifies the user of the pet's feelings and requests. When a dog barks "woof woof" repeatedly and the user becomes tired, what kind of notification message should be generated?"

[1067] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1068] Step 1:

[1069] User: Installs the dedicated application on a smartphone or tablet and launches it. On the initial setup screen, basic information about the pet (such as breed, name, age, and gender) is entered, and the emotion engine is enabled. This initial setup allows the system to determine which pet the user has and to monitor the user's facial expressions and voice.

[1070] Input: Basic information of pet (type, name, age, gender, etc.), Emotion engine activation

[1071] Output: The pet's basic information is registered and the user's emotion engine is enabled.

[1072] Step 2:

[1073] Device: Equipped with a camera and microphone, it monitors your pet's real-time behavior. The camera records their movements and facial expressions, and the microphone records their barks. The collected data is temporarily stored on the device.

[1074] Input: Pet's gestures, facial expressions, and cries

[1075] Output: Recorded gestures and facial expressions, recorded vocalizations

[1076] Step 3:

[1077] Terminal: Sends collected data to the server at a specified interval (e.g., every hour). Connects to the server and transmits the data securely. The server receives the data and stores it in a database.

[1078] Input: Recorded gestures and facial expressions, recorded animal sounds

[1079] Output: Data sent to server, data stored in database

[1080] Step 4:

[1081] Server: Using sound analysis algorithms, the collected bark data is analyzed to extract sound frequencies and patterns, providing data to identify what your pet is trying to communicate.

[1082] Input: Recorded bird call data

[1083] Output: Analyzed call frequency and pattern data

[1084] Step 5:

[1085] Server: Analyzes recorded gestures and facial expressions using image analysis algorithms, detects changes in pet movements and facial expressions, and infers the pet's feelings and state from them.

[1086] Input: Recorded gesture and facial expression data

[1087] Output: Analyzed gesture and facial expression pattern data

[1088] Step 6:

[1089] Server: Integrates the results of audio and image analysis and uses machine learning models to predict the pet's feelings and needs. This makes it possible to predict the pet's condition with high accuracy.

[1090] Input: Audio analysis results, image analysis results

[1091] Output: Prediction of pet's feelings and needs

[1092] Step 7:

[1093] On the device: The camera and microphone capture the user's facial expressions and voice, which are then analyzed by the emotion engine. For example, subtle changes in the user's facial expressions and tone of voice can be used to identify the user's emotional state.

[1094] Input: User's facial expression data, voice data

[1095] Output: Analyzed user emotion data

[1096] Step 8:

[1097] Server: Receives the user's emotional data and combines it with the pet's analysis results. This generates the optimal notification content that matches the user's situation.

[1098] Input: User's emotional data, predicted pet's feelings and requests

[1099] Output: Optimal notification content

[1100] Step 9:

[1101] Server: Generates a specific notification message based on the pet analysis results and the user's emotional data. For example, it creates a message like, "Your dog Pochi wants to play with you, but you seem tired. Let's rest a bit and then play."

[1102] Input: Optimal notification content

[1103] Output: The generated notification message

[1104] Step 10:

[1105] Terminal: Notifies the user of the generated message. Text messages are displayed in a dedicated application, and audio messages are played through the speaker.

[1106] Input: The generated notification message

[1107] Output: A text message that is displayed to the user and an audio message that is played

[1108] (Application example 2)

[1109] 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."

[1110] Currently, there are several systems that facilitate communication with pets, but these simply analyze the pet's cries and gestures and do not take into account the user's emotional state. Furthermore, there is a lack of systems that naturally link the user's and pet's behavior in a virtual environment, so the user experience is not sufficiently improved.

[1111] The specific processing by the specific 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 analyzing the pet's cries using audio analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for notifying the user of the translation results, emotion analysis means for recognizing the user's emotional state, means for generating notification content by integrating the pet's translation results with the user's emotional data, and means for linking the behavior of the user and the pet in the virtual environment. This enables natural and personalized communication in the virtual environment while taking the user's emotional state into consideration.

[1112] "Voice analysis technology" is a technology that analyzes voice data and extracts information by analyzing its patterns, frequencies, etc.

[1113] "Image analysis technology" is a technology that analyzes image data to identify objects and detect movement patterns.

[1114] "A means of translating pets' feelings and requests" is a system that uses data obtained from voice analysis and image analysis technology to infer and translate a pet's emotions and requests.

[1115] "Means for notifying the user" is a notification function for conveying the translated feelings and requests of the pet to the user.

[1116] "Emotion analysis means" is a technology that analyzes the user's facial expressions and voice data to identify their emotional state.

[1117] The "means for generating notification content" is a function that combines the pet's translation results with the user's emotional data to generate the optimal message.

[1118] "Means for linking the behavior of a user and a pet in a virtual environment" refers to technology that naturally links the behavior and emotions of a user with the behavior of a pet in a virtual space.

[1119] MODE FOR CARRYING OUT THE INVENTION

[1120] Specific hardware and software are required to implement the present invention. A specific system configuration and processing method will be described below.

[1121] System Configuration

[1122] Server: A server with high-performance computing power is required to analyze the data using voice and image analysis techniques and implement sentiment analysis methods, specifically using machine learning libraries such as Keras and TensorFlow.

[1123] Device: A device with a camera and microphone is required to capture the movements and sounds of both you and your pet in real time.

[1124] Notification system: A smartphone application or web application is required to notify users of the notification content.

[1125] Data processing and calculation

[1126] The server does the following:

[1127] 1. Pet Meow Analysis: Using audio analysis technology, pet meows are analyzed based on frequency and patterns, allowing you to identify what your pet is trying to communicate.

[1128] 2. Analysis of pet gestures and facial expressions: Using image analysis technology, the system analyzes pet movements and facial expressions, allowing it to infer the pet's feelings and state.

[1129] 3. User emotion recognition: Emotion analysis means identify the user's emotional state from their facial expressions and voice.

[1130] 4. Data integration and notification content generation: The pet analysis results and user emotion data are integrated to generate optimal notification content. This implementation uses an integrated machine learning model.

[1131] Specific examples

[1132] When a user is shopping in a virtual store, the system works as follows:

[1133] 1. When a user accesses the virtual store using the device's camera and microphone, the device captures the user's and pet's actions and voices in real time.

[1134] 2. The server analyzes the cries and recognizes that the pet wants to play, and at the same time, uses image analysis technology to analyze the pet's behavior and confirm that the pet is active.

[1135] 3. Using emotion analysis means, recognize when the user is tired.

[1136] 4. The server integrates the pet's behavior and the user's emotions and generates a notification message saying, "Pochi wants to play, but you seem tired. Let's take a break first."

[1137] 5. This notification will be displayed on the user's smartphone.

[1138] Prompt Sentence Examples

[1139] While the user is enjoying shopping in a virtual store, it is determined that the virtual pet wants to play, but at the same time it is recognized that the user is tired. In this situation, generate a notification to prompt the user to take an appropriate action.

[1140] This embodiment allows the user to take appropriate action taking into account their pet's feelings and their own emotions, allowing them to enjoy a natural and personalized experience even within the virtual environment.

[1141] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1142] Step 1:

[1143] The user accesses the virtual store using the device's camera and microphone. The device captures the user's and pet's movements and voices in real time. The input of this step is the user's and pet's movements and voice data, and the output is the captured video and voice data.

[1144] Step 2:

[1145] The terminal transmits the captured video and audio data to the server. The specific operation here is that the terminal collects data and transmits it to the server through the network. The input of this step is the captured data, and the output is the data transmitted to the server.

[1146] Step 3:

[1147] The server analyzes the pet's cries using voice analysis technology. Specifically, the server analyzes the frequency and pattern of the received voice data to identify what the pet is trying to communicate. The input for this step is the pet's voice data, and the output is the analysis result of the cries.

[1148] Step 4:

[1149] The server uses image analysis technology to analyze the pet's gestures and facial expressions. The server analyzes the received video data and recognizes the pet's movements and facial expressions. Specifically, it uses a deep learning model to identify movement patterns and changes in facial expressions. The input for this step is the video data, and the output is the analysis results of the gestures and facial expressions.

[1150] Step 5:

[1151] The server integrates the results of voice and image analysis to translate the pet's feelings and requests. This translation uses a pre-trained generative AI model. Specifically, it infers the pet's emotions and requests from its actions and words. The input for this step is the results of voice and image analysis, and the output is a translation of the pet's feelings and requests.

[1152] Step 6:

[1153] The device captures the user's facial expression and voice and sends them to the server. Specifically, the device monitors the user's emotional state in real time and transfers the data to the server. The input of this step is the user's facial expression and voice data, and the output is the emotional data sent to the server.

[1154] Step 7:

[1155] The server uses emotion analysis means to identify the user's emotional state. Specifically, it analyzes the received facial and voice data to recognize the user's current emotion. The input of this step is the user's emotion data, and the output is the user's emotion analysis result.

[1156] Step 8:

[1157] The server combines the pet's translation results with the user's sentiment analysis results to generate appropriate notification content. This uses the generative AI model and prompt text described above. Specifically, it combines the information "the user is tired" and "the pet wants to play" to create the optimal message for the user. The input for this step is the pet's translation results and the user's sentiment analysis results, and the output is the generated notification content.

[1158] Step 9:

[1159] The server sends the generated notification to the terminal. This notification is provided to the user in text and audio format. Specifically, it creates a message to be displayed on the terminal and plays it as an audio notification. The input here is the generated notification, and the output is the notification received by the user.

[1160] Step 10:

[1161] The user receives a notification from the system via their device and takes appropriate action. For example, if they receive a message saying "Let's take a break first," they will take a break. The input to this step is the notification from the device, and the output is the user's action.

[1162] 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.

[1163] 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.

[1164] 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.

[1165] [Fourth embodiment]

[1166] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1167] 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.

[1168] 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).

[1169] 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.

[1170] 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.

[1171] 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).

[1172] 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.

[1173] 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.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] 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.

[1178] 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."

[1179] System Overview

[1180] The pet translation system of the present invention analyzes the cries, gestures, and facial expressions of pets and translates their feelings and requests based on that data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify owners of the analysis results in real time.

[1181] Initial Setup and Data Collection

[1182] 1. User: After installing the dedicated application, an initial setup screen appears. The user enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, gender, etc.). This allows the system to use an analysis model optimized for that particular pet.

[1183] 2. Device: Prepare a camera and microphone to monitor your pet's behavior. The device captures your pet's sounds and movements in real time and sends the data to the server at specified intervals.

[1184] 3. Server: Receives data sent from the device and stores it in a database. The collected data is later used for analysis.

[1185] Data analysis

[1186] 4. Server: Performs audio analysis on the bark data. Specifically, it analyzes the frequency and pattern of the bark and extracts characteristics such as pitch and duration. From the bark pattern, data can be obtained to identify what the pet is trying to communicate.

[1187] 5. Server: Using the recorded data, image analysis of the pet's gestures and facial expressions is performed. Image analysis algorithms are used to detect patterns of pet movement and changes in facial expressions. This allows the pet's feelings and state to be inferred from its gestures and facial expressions.

[1188] 6. Server: Integrates data from sounds, gestures, and facial expressions and uses a machine learning model to predict your pet's feelings and needs. This model learns from data collected from many pets and makes highly accurate predictions about your pet's condition based on new data.

[1189] Providing results

[1190] 7. Server: Formats the analysis results as text or voice messages and sends them to the user interface, where the user can instantly view the results.

[1191] 8. Device: Displays the analysis results and notifies the user of their pet's feelings and needs. Notifications are sent using both text and voice, allowing users to quickly and reliably understand their pet's condition.

[1192] Specific examples

[1193] Consider the case where a user has a dog and a hamster.

[1194] 1. Initial Setup: The user enters information about their dog and hamster into the application.

[1195] 2. Data collection: A camera and microphone installed in the living room record the behavior of the dog and hamster. The data is automatically sent to a server.

[1196] 3. Data analysis: The server performs audio analysis of the dog's bark to detect the repeated "woof woof" sound, while image analysis of the hamster's movements confirms that it is moving back and forth to a specific location.

[1197] 4. Providing results: The server predicts that the dog is in a state of "wanting to play" and determines that the hamster is likely "stressed." These results are sent to the user's device.

[1198] 5. User notification: The device displays messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed" and notifies the user by voice. The user can play with the dog and improve the hamster's cage based on the messages.

[1199] This system allows users to understand their pets' feelings and desires in more detail and respond appropriately, deepening their relationship of trust with their pets.

[1200] The processing flow will be explained below.

[1201] Step 1:

[1202] The user installs the dedicated application and enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, sex, etc.) on the initial setup screen. The application then sends the pet information to the server and prepares to select an analysis model specialized for the pet.

[1203] Step 2:

[1204] The device has a camera and microphone, and monitors, records, and records your pet's cries, movements, and facial expressions in real time. The device then sends the collected data to a server at set intervals.

[1205] Step 3:

[1206] The server receives the data sent from the device and stores it in a database, where audio and video data for each pet is organized and stored.

[1207] Step 4:

[1208] The server uses an audio analysis algorithm to analyze the collected call data, extracting sound frequencies and patterns, and analyzing the frequency, pitch, and duration of calls.

[1209] Step 5:

[1210] The server uses image analysis algorithms to analyze the recorded gestures and facial expressions, specifically detecting the pet's position, tracking its movements, and detecting changes in facial expressions.

[1211] Step 6:

[1212] The server integrates the results of audio and image analysis and uses a machine learning model to predict the pet's feelings and needs. The model is trained based on a large amount of collected data and predicts the pet's condition based on new data.

[1213] Step 7:

[1214] The server sends the analysis results to a user interface, where they are formatted into text or voice messages.

[1215] Step 8:

[1216] The device notifies the user of the analysis results, using text and voice notifications to provide specific messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed."

[1217] Step 9:

[1218] The user can check the notification on their device and take appropriate action, such as setting aside time to play with their dog or improving the hamster's cage environment to reduce stress for their pet.

[1219] Through this series of steps, users can understand their pet's feelings and needs in real time and respond appropriately, which helps deepen the trusting relationship between them and their pet.

[1220] Example 1

[1221] 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."

[1222] It is difficult for owners to accurately understand their pets' feelings and needs from their vocalizations, gestures, and facial expressions. Analyzing and interpreting this data becomes even more difficult when owners have multiple pets or pets of different species. Furthermore, conventional systems often lack efficient real-time data analysis and notifications, preventing owners from quickly understanding their pets' status.

[1223] 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.

[1224] In this invention, the server includes a means for receiving and storing data in real time, a means for analyzing the stored audio data, and a means for analyzing the stored video data, thereby enabling efficient analysis of the pet's cries, gestures, and facial expressions and prompt notification to the owner.

[1225] "Means for analyzing pet cries using audio analysis technology" refers to technology that has the function of collecting pet cries and analyzing the audio data based on frequency and patterns.

[1226] "Means for analyzing pets' gestures and facial expressions using image analysis technology" refers to technology that uses a camera or other imaging device to capture a pet's gestures and facial expressions and then analyzes the video data.

[1227] "Means for translating pets' feelings and requests based on analysis results" refers to an algorithm that integrates data obtained from audio analysis and image analysis to estimate a pet's feelings and requests.

[1228] "Means for notifying the user of the translated results" refers to technology for communicating the analyzed pet's feelings and requests in a format that is easy for the user to understand, and includes text messages and voice messages.

[1229] "Means for receiving and storing data in real time" refers to technology that has the function of collecting pet behavior data and vocalization data in real time and storing it in a database.

[1230] The "means for analyzing stored audio data" is a technology that extracts and analyzes information such as frequency, pitch, and duration based on stored pet cry data.

[1231] The "means for analyzing stored video data" refers to a technology that analyzes stored video data of a pet's behavior and facial expressions to detect changes in gestures and facial expressions.

[1232] "Means for integrating analyzed voice data and image data" refers to a technology for combining data obtained from voice analysis and data obtained from image analysis into one and performing a comprehensive analysis.

[1233] "Means for predicting pet feelings and needs using machine learning models" refers to technology that uses machine learning algorithms trained using a large number of datasets to predict pet feelings and needs with high accuracy.

[1234] "Means for formatting prediction results as text or voice messages" refers to technology that outputs the pet's feelings and requests predicted by the machine learning model in a format that is easy for humans to understand (text or voice).

[1235] The "means for sending formatted results to a user interface" is a technique for sending predicted results formatted as a text message or a voice message to a user's terminal.

[1236] The following hardware and software are used as an embodiment of this invention. A user installs a dedicated application on a device such as a smartphone or tablet and uses it. The terminal includes a camera, microphone, and network-connected device, which are used to monitor the behavior of the pet and send the data to a server. The server is a high-performance analysis server (equipped with a CPU, GPU, and storage) that processes and analyzes the data.

[1237] The software used includes Praat and TensorFlow for audio analysis, OpenCV and PyTorch for image analysis, and scikit-learn, TensorFlow and PyTorch for machine learning models.

[1238] 1. Initial Setup and Data Collection

[1239] User: After installing the dedicated application on their smartphone, they input basic information about their pet (species, name, age, sex, etc.), which allows the system to use an analysis model optimized for that particular pet.

[1240] Terminal: Monitors pet behavior and sounds in real time via camera and microphone, and automatically transmits this data to the server at regular intervals.

[1241] 2. Data Receipt and Storage

[1242] Server: Receives data sent from the device in real time and stores it in a database, including audio and video data.

[1243] 3. Audio and Image Analysis

[1244] Audio analysis: The server analyzes the received bird call data using an audio analysis algorithm (e.g., Praat or TensorFlow) to extract features such as frequency, pattern, pitch, and duration.

[1245] Image analysis: The server analyzes the video data using an image analysis algorithm (e.g., OpenCV or PyTorch) to detect changes in the pet's gestures and facial expressions.

[1246] 4. Data Integration and Application to Machine Learning Models

[1247] Server: Integrates audio and video data and inputs it into a machine learning model (e.g., scikit-learn or TensorFlow). This allows for highly accurate prediction of the pet's feelings and needs.

[1248] 5. Formatting and Notification of Results

[1249] Server: Formats the prediction results into a text or voice message and sends it to the user's device.

[1250] Device: Notifications are sent to smartphones and tablets, allowing users to keep track of their pet's status in real time.

[1251] Specific examples

[1252] Let's take an example where a user has a dog and a hamster. First, the user enters information about the dog and hamster into the application. Next, a camera and microphone installed in the living room record the dog and hamster's behavior. The data is automatically sent to the server. The server performs audio analysis of the dog's bark and identifies its frequency and pitch. Meanwhile, it performs image analysis of the hamster's behavior and confirms that it is going back and forth to a specific location. The server determines whether the dog wants to play and whether the hamster is possibly stressed, and sends these results to the user's device. The device then displays and notifies the user by voice, messages such as "Pochi the dog wants to play" and "Ham the hamster is stressed." The user can then play with the dog and improve the hamster's cage based on the messages presented to them.

[1253] Prompt Sentence Examples

[1254] User: "Please use the system to tell me what my dog ​​is thinking right now."

[1255] System: "Analyzing data collected from camera and microphone. Please wait a moment."

[1256] System: "We analyzed the barks and movements of the dog Pochi. Pochi wants to play now."

[1257] The system allows users to quickly and accurately understand their pet's feelings and needs and respond appropriately. It uses a generative AI model to improve prompts for users and help them understand their pet's situation in real time.

[1258] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1259] Step 1:

[1260] Initial Setup and Data Entry

[1261] User: The user installs a dedicated application on their smartphone or tablet. They launch the application and enter basic information about their pet, such as the type of pet (e.g., dog, cat, hamster, iguana, etc.), name, age, and gender. The input data is sent to the server and used to configure the model for each pet.

[1262] Input: Basic information about your pet, such as type, name, age, and gender.

[1263] Output: Basic information about the pet sent to the server.

[1264] Step 2:

[1265] Data collection

[1266] Device: The camera and microphone are installed in the living room or other areas where pets are active, and monitor the pet's movements and sounds in real time. Data is captured every 30 seconds and sent to the server.

[1267] Input: Video and audio data of pet.

[1268] Output: The captured data sent to the server.

[1269] Step 3:

[1270] Receiving and storing data

[1271] Server: Receives data sent from the device in real time and stores it in a database. Adds timestamps to video and audio data, and organizes and stores it for future analysis.

[1272] Specific operation: The server receives data sent at regular intervals and stores it in a database. For example, it stores dog video data and barking data sent every 30 seconds with a timestamp.

[1273] Input: Real-time data sent from the device.

[1274] Output: Video and audio data stored in a database.

[1275] Step 4:

[1276] Audio analysis

[1277] Server: Analyzes the collected audio data using an audio analysis algorithm (e.g., Praat or TensorFlow). Specifically, it extracts features such as the frequency, pattern, pitch, and duration of the calls.

[1278] How it works: The server analyzes audio data to identify the frequency of a dog's bark, and at the same time, infers the pet's emotions from the pitch and pattern of the sound.

[1279] Input: Audio data stored in a database.

[1280] Output: Audio characteristics such as frequency, pattern, pitch, and duration.

[1281] Step 5:

[1282] Image analysis

[1283] Server: Analyzes the video data captured by the camera using an image analysis algorithm (e.g., OpenCV or PyTorch) to detect changes in the pet's gestures and facial expressions.

[1284] How it works: The server analyzes the video of the cat and detects changes in its tail movements and eye expressions. This data is used to estimate the cat's emotions and state.

[1285] Input: Video data stored in a database.

[1286] Output: Gestures, facial expressions, and behavioral patterns.

[1287] Step 6:

[1288] Data integration and application to machine learning models

[1289] Server: Integrates feature data obtained from audio and image analysis and inputs it into a machine learning model (e.g., scikit-learn or TensorFlow). This allows for highly accurate prediction of pets' feelings and needs.

[1290] How it works: The server combines audio and visual data and feeds it into a machine learning model, for example, to predict if a dog wants to play based on its bark and tail wagging.

[1291] Input: Audio analysis data and image analysis data.

[1292] Output: Prediction results from the machine learning model (e.g., want to play, want to eat, stress, etc.).

[1293] Step 7:

[1294] Formatting and sending results

[1295] Server: Formats the predictions of the machine learning model as text or voice messages and sends them to the user interface.

[1296] Specific operation: The server generates a message saying "Pochi the dog wants to play" and sends it to the smartphone.

[1297] Input: Predictions made by machine learning models.

[1298] Output: Formatted text and audio messages.

[1299] Step 8:

[1300] User Notification

[1301] On your device: Notifications will appear on your smartphone or tablet, and you will receive text and voice messages, allowing you to keep up with your pet's status in real time.

[1302] Specific operation: The smartphone will display "Pochi the dog wants to play" along with a notification sound and notify you by voice.

[1303] Input: A text or voice message sent from the server.

[1304] Output: A notification message that is displayed on the user's terminal.

[1305] (Application example 1)

[1306] 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."

[1307] In today's busy lifestyles, it is not easy for pet owners to accurately understand their pets' feelings and needs. In particular, it is difficult to accurately infer a pet's emotions and needs from its behavior and cries, and responding incorrectly can cause stress to the pet. Problems also often arise when selecting the right products for pets. Technological solutions are needed to resolve these issues and build better relationships with pets.

[1308] 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.

[1309] In this invention, the server includes means for analyzing the pet's cries using voice analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for notifying the user of the translation results, means for recommending suitable products based on the translation results, and means for displaying information on the recommended products, thereby enabling pet owners to understand their pet's feelings and requests in real time and quickly purchase products suitable for their pets.

[1310] "Voice analysis technology" is a technology that converts pet cries into digital signals and analyzes their frequencies and patterns.

[1311] "Image analysis technology" is a technology that captures a pet's gestures and facial expressions as video data and analyzes changes in their movements and facial expressions.

[1312] The "translation method" is a method of converting a pet's feelings and requests into a form that humans can understand based on analyzed data on their cries, gestures, and facial expressions.

[1313] The "notification means" is a means for notifying the user in real time by sending the translation results to the user's terminal as a text or voice message.

[1314] The "recommendation method" is a method of selecting products suitable for pets based on the translated pet's feelings and requests using prompt sentences from the generative AI model and suggesting them to the user.

[1315] The "display means" is a means for presenting information about the recommended product on the screen of the user's terminal, making it easy to check detailed information.

[1316] The embodiments of the present invention will be described in detail below.

[1317] System Overview

[1318] The pet interpreter virtual shop system of the present invention includes the following components:

[1319] 1. Audio analysis technology: This technology converts pet sounds into digital signals and analyzes their frequencies and patterns.

[1320] 2. Image analysis technology: This is a technology that captures a pet's gestures and facial expressions as video data and analyzes changes in their movements and facial expressions.

[1321] 3. Translation method: This is a method that translates the feelings and requests of pets based on the results of voice and image analysis and converts them into a form that humans can understand.

[1322] 4. Notification: This is a means of notifying the user in real time by sending the translated results to the user's device as a text or voice message.

[1323] 5. Recommendation: This is a method of selecting suitable products for pets based on the translated pet's feelings and requests using prompts from the generative AI model and suggesting them to the user.

[1324] 6. Display method: This is a method for displaying information about recommended products on the screen of the user's device, making it easy for the user to check detailed information.

[1325] Technology used

[1326] Hardware: Smartphone (with built-in camera and microphone)

[1327] Software libraries: OpenCV (image processing library), Keras (deep learning library), Flask (web application framework)

[1328] Data processing and calculation

[1329] Speech analysis: The server extracts frequency and spectral features from the audio signal. This data is then analyzed using a speech recognition model using Keras.

[1330] Image analysis: Video data captured by the device camera is used to extract gestures and facial expressions using OpenCV, which are then analyzed using a model based on Keras.

[1331] Translation and Notifications: Your pet's feelings and requests are translated and sent to your smartphone as text and voice messages.

[1332] Selecting and displaying recommended products: Using a generative AI model, we select appropriate products, recommend products using prompts, and present the information to the user.

[1333] As a specific example, when a user analyzes a dog's bark and behavior, the following steps are performed.

[1334] 1. Audio analysis: Recognizes that a dog wants to play by hearing the repeated bark "woof woof."

[1335] 2. Image analysis: Images of a dog wagging its tail in excitement can also be analyzed to indicate that it wants to play.

[1336] 3. Notification and product recommendation: The user's smartphone will be notified that "your dog wants to play" and suitable toys will be recommended.

[1337] 4. Display: The message "Toy details are as follows: [More information]" is displayed, guiding the customer to proceed with the purchase without hesitation.

[1338] Example prompt sentence:

[1339] "My dog ​​wants to play. I recommend the following products:

[1340] Toys

[1341] snack

[1342] Please check the details and purchase."

[1343] This allows users to understand their pet's feelings and purchase appropriate products in a timely manner.

[1344] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1345] Step 1:

[1346] Users install a dedicated app on their smartphone and enter basic information about their pet, such as its type, name, age, and gender. This information is sent to a server by the app, and an analysis model optimized for each pet is selected. The input is the user's basic information and pet information, and the output is a pet profile stored on the server.

[1347] Step 2:

[1348] The device's camera and microphone are used to capture the pet's cries, gestures, and facial expressions in real time. The input is the camera image and microphone audio, and the output is sent to the server at a specified time interval.

[1349] Step 3:

[1350] The server analyzes the received voice data using voice analysis technology. Specifically, it extracts frequency and spectral features from the voice signal and analyzes them using a voice recognition model. The input is the voice data from the microphone, and the output is the analysis results that can be used to infer the pet's feelings and requests.

[1351] Step 4:

[1352] The server uses image analysis technology to analyze the received image data. It extracts the pet's gestures and facial expressions from the video data and analyzes the changes in their movements and expressions using an image recognition model. The input is the camera video data, and the output is the analysis results that allow the pet's feelings and state to be estimated.

[1353] Step 5:

[1354] The server integrates the results of the audio and image analysis and uses a machine learning model to predict your pet's feelings and needs with high accuracy. This integrated analysis improves accuracy by combining individually obtained features. The audio and image analysis results are used as input, and the output is a confirmed prediction of your pet's feelings and needs.

[1355] Step 6:

[1356] Based on the analysis results, the server uses a generative AI model to recommend products suitable for pets. It generates a prompt sentence and selects appropriate products from a commercial database based on that sentence. The input is the confirmed pet's emotions and needs, and the output is a list of recommended products.

[1357] Step 7:

[1358] The server notifies the user's smartphone in real time of information about recommended products. It generates text and voice messages and sends them to the user's device. The input is a list of recommended products, and the output is a notification message that is displayed on the user's device.

[1359] Step 8:

[1360] The user can check the notification on their smartphone and view detailed information about the recommended product. If necessary, they can purchase the product directly in the virtual store. The input is the user's action, and the output is the completion of the product purchase or the presentation of detailed information.

[1361] This allows users to understand their pet's feelings and needs in real time and quickly purchase products that are suitable for their pet.

[1362] 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.

[1363] System Overview

[1364] The pet translation system of the present invention analyzes a pet's cries, gestures, and facial expressions, and uses this data to translate the pet's feelings and requests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a more appropriate response by linking the pet's feelings and requests with the user's emotional data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify the user of the analysis results in real time.

[1365] Initial Setup and Data Collection

[1366] 1. User: After installing the dedicated application, the user enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, gender, etc.) on the initial setup screen. In addition, the emotion engine is enabled. The emotion engine is configured to monitor the user's facial expressions and voice.

[1367] 2. Terminal: Equipped with a camera and microphone, it monitors your pet's real-time behavior. The terminal records your pet's cries, gestures, and facial expressions, and transmits the data to the server at set intervals.

[1368] 3. Server: Receives data sent from the device and stores it in a database. The collected data is later used for analysis.

[1369] Data analysis

[1370] 4. Server: Analyzes the collected bark data using sound analysis algorithms, extracting sound frequencies and patterns to obtain data that can identify what your pet is trying to communicate.

[1371] 5. Server: Analyzes the recorded gestures and facial expressions using image analysis algorithms, detecting patterns of pet movement and changes in facial expressions, and inferring the pet's feelings and state.

[1372] 6. Server: The results of audio and image analysis are integrated and a machine learning model is used to predict the pet's feelings and needs. This model is trained based on data collected from many pets and can predict the pet's condition with high accuracy based on new data.

[1373] Recognizing user emotions with an emotion engine

[1374] 7. Device: The user's facial expressions and voice are captured by a camera and microphone, and analyzed by the emotion engine, which determines the user's current emotional state from their facial movements and tone of voice.

[1375] 8. Server: Receives the user's emotional data, combines it with the analysis results of the pet's feelings and requests, and generates the most appropriate notification content.

[1376] Providing results

[1377] 9. Server: Based on the analysis results and the user's emotional data, the server formats text and voice messages and sends them to the user interface. For example, if the user is tired, the server might send a message like, "Your dog, Pochi, wants to play, but it's time for him to rest."

[1378] 10. Device: Displays the analysis results and sends messages that take into account the pet's feelings and the user's emotions. Notifications are sent using both text and voice, allowing users to quickly and reliably understand the status of their pet and the user.

[1379] Specific examples

[1380] Consider the case where a user has a dog and a hamster:

[1381] 1. Initial Setup: The user enters information about their dog and hamster into the application and enables the emotion engine.

[1382] 2. Data collection: A camera and microphone installed in the living room record the behavior of the dog and hamster. The data is automatically sent to a server.

[1383] 3. Data analysis: The server analyzes the dog's bark and detects that it is making a repeated "woof woof" sound, while simultaneously analyzing the hamster's movements to determine if it is moving back and forth to a specific location.

[1384] 4. User emotion recognition: The device captures the user's facial expressions and voice, and the emotion engine recognizes that the user is tired.

[1385] 5. Providing results: The server predicts that the dog is in a state of "wanting to play" and indicates that the hamster may be "stressed," and generates a message that takes into account the user's emotional state.

[1386] 6. User notification: The device will display a message saying, "Your dog, Pochi, wants to play, but your hamster, Ham, is stressed. You are tired, so please rest first before dealing with this." and will also notify you with a voice.

[1387] This system allows users to take appropriate action by considering their pet's feelings and their own, thereby deepening their relationship of trust with their pet.

[1388] The processing flow will be explained below.

[1389] Step 1:

[1390] The user installs the dedicated application and enters the type of pet (dog, cat, hamster, iguana, etc.) and basic information (name, age, sex, etc.) on the initial setup screen, which then sends the pet information to the server.

[1391] Step 2:

[1392] The device is equipped with a camera and microphone to monitor the pet's real-time behavior, recording the pet's cries, gestures, and facial expressions, and sending this data to a server at set intervals.

[1393] Step 3:

[1394] The server receives the data sent from the device and stores it in a database, where the collected bird call data and video data are organized and stored.

[1395] Step 4:

[1396] The server uses a sound analysis algorithm to analyze the pet's meow data, extracting the frequency and patterns of the pet's meows and analyzing the frequency, pitch, duration, etc.

[1397] Step 5:

[1398] The server uses an image analysis algorithm to analyze the recorded data, detecting the pet's movement patterns and facial expressions, and providing detailed analysis.

[1399] Step 6:

[1400] The server integrates the results of voice and image analysis and uses a machine learning model to predict the pet's feelings and needs. The model is trained based on data collected from many pets, and can predict the pet's condition with high accuracy based on new data.

[1401] Step 7:

[1402] The device captures the user's facial expressions and voice using a camera and microphone and sends this data to the emotion engine, which analyzes the user's facial movements and tone of voice to determine their current emotional state.

[1403] Step 8:

[1404] The server receives the user's emotional data and combines it with the analysis of the pet's feelings and needs to tailor the notification content. For example, if the server detects that the user is tired, the notification content will be adapted to that state.

[1405] Step 9:

[1406] The server sends the analysis results to the user interface, where they are formatted into text or voice messages that can be instantly understood by the user.

[1407] Step 10:

[1408] The device notifies the user of the analysis results. Specifically, using text and voice notification functions, it displays and notifies the user with a message such as, "Your dog Pochi wants to play, but you are tired, so please rest first before responding."

[1409] Step 11:

[1410] The user checks the notification on the device and takes appropriate action, such as taking a rest first, then playing with the dog, or improving the environment of the hamster's cage.

[1411] Through this series of steps, users can take appropriate action taking into consideration the emotional state of their pet and themselves, and can deepen their trusting relationship with their pet.

[1412] Example 2

[1413] 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."

[1414] Conventional pet translation systems can understand a pet's feelings and requests to some extent by analyzing the pet's cries, gestures, and facial expressions, but they lack the ability to suggest appropriate responses based on the user's emotional state. As a result, the pet's requests may be conveyed in a way that does not match the user's state, which can hinder the relationship between the pet and the user. In addition, it is difficult to provide real-time notifications and suggest appropriate responses, making it difficult to immediately understand and respond to a pet's feelings.

[1415] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for analyzing the pet's cries using audio analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for analyzing the user's facial expressions and voice to identify the emotional state, means for generating an appropriate notification based on the translation result and the user's emotional state, and means for displaying the generated notification in text and audio. This makes it possible to understand the pet's feelings and requests and, at the same time, to propose an appropriate response taking the user's emotional state into consideration.

[1416] "Voice analysis technology" is a means of analyzing voice data and identifying its content and characteristics.

[1417] "Image analysis technology" is a means of analyzing image data and identifying its content and characteristics.

[1418] "Means for translating pets' feelings and requests" refers to a means for expressing pets' emotions and requests in human language based on the results of voice analysis technology and image analysis technology.

[1419] The "means for identifying the emotional state of the user by analyzing the facial expression and voice of the user" is a means for analyzing the facial expression and voice data of the user and identifying the current emotional state of the user from the results.

[1420] The "means for generating an appropriate notification" is a means for generating a message to suggest an appropriate response to the user based on the translation results of the pet's feelings and requests and the user's emotional state.

[1421] The "means for displaying in text and voice" refers to a means for displaying the generated notification message to the user in text and voice.

[1422] System Overview

[1423] The pet translation system of the present invention analyzes a pet's cries, gestures, and facial expressions, and uses this data to translate the pet's feelings and requests. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system provides a more appropriate response by linking the pet's feelings and requests with the user's emotional data. This system combines voice analysis technology and image analysis technology to support a wide variety of pets and notify the user of the analysis results in real time.

[1424] Initial Setup and Data Collection

[1425] 1. User: Install the dedicated application on a smartphone or tablet and enter basic information about the pet (species, name, age, gender, etc.) on the initial setup screen. In addition, the emotion engine is enabled and monitoring of the user's facial expressions and voice is permitted.

[1426] 2. Device: A camera and microphone are installed to monitor the pet's real-time behavior. The camera records the pet's movements and facial expressions, and the microphone records its cries. The collected data is temporarily stored on the device and sent to the server at specified intervals.

[1427] 3. Server: Receives the data sent from the device and stores it in a database, facilitating subsequent analysis.

[1428] Data analysis

[1429] 1. Server: Using sound analysis algorithms, the collected bark data is analyzed, specifically extracting the frequencies and patterns of the barks to determine what the pet is trying to communicate.

[1430] 2. Server: Using image analysis algorithms, the recorded gestures and facial expressions are analyzed to detect changes in the pet's movements and facial expressions, and from these, the pet's feelings and state are inferred.

[1431] 3. Server: The results of audio analysis and image analysis are integrated, and a machine learning model is used to predict the pet's feelings and needs. This makes it possible to predict the pet's condition with high accuracy.

[1432] Recognizing user emotions with an emotion engine

[1433] 1. Device: The user's facial expressions and voice are captured by a camera and microphone, and analyzed by an emotion engine. For example, subtle changes in the user's facial expressions and tone of voice can be used to identify the user's emotional state.

[1434] 2. Server: Receives the user's emotional data and combines it with the pet's analysis results to generate the optimal notification content that matches the user's situation.

[1435] Providing results

[1436] 1. Server: Generates a specific notification message based on the pet analysis results and the user's emotional data. For example, it creates a message that reads, "Your dog Pochi wants to play with you, but you seem tired. Let's take a break and then play."

[1437] 2. Terminal: Notifies the user of the generated message. Text messages are displayed in a dedicated application, and audio messages are played through the speaker.

[1438] Specific examples

[1439] If the user has a dog and a hamster:

[1440] 1. Initial Setup: The user enters information about their dog and hamster into the application and enables the emotion engine.

[1441] 2. Data collection: A camera and microphone placed in the living room record the behavior of the dog and hamster.

[1442] 3. Data analysis: The server analyzes the dog's bark and detects that it is repeatedly barking "woof woof." At the same time, it analyzes the hamster's behavioral patterns and finds that it frequently returns to a specific location.

[1443] 4. User emotion recognition: The device captures the user's facial expressions and voice, and the emotion engine recognizes that the user is tired.

[1444] 5. Providing results: The server generates messages indicating that the dog "wants to play," the hamster "is stressed," and the user is tired.

[1445] 6. User notification: The device will display a message saying, "Your dog, Pochi, wants to play, but your hamster, Ham, is stressed. You are tired, so please rest first before dealing with this." and also notify you with a voice.

[1446] Example prompts for generative AI models

[1447] "I want to develop a system that analyzes a pet's barks and movements, and notifies the user of the pet's feelings and requests. When a dog barks "woof woof" repeatedly and the user becomes tired, what kind of notification message should be generated?"

[1448] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1449] Step 1:

[1450] User: Installs the dedicated application on a smartphone or tablet and launches it. On the initial setup screen, basic information about the pet (such as breed, name, age, and gender) is entered, and the emotion engine is enabled. This initial setup allows the system to determine which pet the user has and to monitor the user's facial expressions and voice.

[1451] Input: Basic information of pet (type, name, age, gender, etc.), Emotion engine activation

[1452] Output: The pet's basic information is registered and the user's emotion engine is enabled.

[1453] Step 2:

[1454] Device: Equipped with a camera and microphone, it monitors your pet's real-time behavior. The camera records their movements and facial expressions, and the microphone records their barks. The collected data is temporarily stored on the device.

[1455] Input: Pet's gestures, facial expressions, and cries

[1456] Output: Recorded gestures and facial expressions, recorded vocalizations

[1457] Step 3:

[1458] Terminal: Sends collected data to the server at a specified interval (e.g., every hour). Connects to the server and transmits the data securely. The server receives the data and stores it in a database.

[1459] Input: Recorded gestures and facial expressions, recorded animal sounds

[1460] Output: Data sent to server, data stored in database

[1461] Step 4:

[1462] Server: Using sound analysis algorithms, the collected bark data is analyzed to extract sound frequencies and patterns, providing data to identify what your pet is trying to communicate.

[1463] Input: Recorded bird call data

[1464] Output: Analyzed call frequency and pattern data

[1465] Step 5:

[1466] Server: Analyzes recorded gestures and facial expressions using image analysis algorithms, detects changes in pet movements and facial expressions, and infers the pet's feelings and state from them.

[1467] Input: Recorded gesture and facial expression data

[1468] Output: Analyzed gesture and facial expression pattern data

[1469] Step 6:

[1470] Server: Integrates the results of audio and image analysis and uses machine learning models to predict the pet's feelings and needs. This makes it possible to predict the pet's condition with high accuracy.

[1471] Input: Audio analysis results, image analysis results

[1472] Output: Prediction of pet's feelings and needs

[1473] Step 7:

[1474] On the device: The camera and microphone capture the user's facial expressions and voice, which are then analyzed by the emotion engine. For example, subtle changes in the user's facial expressions and tone of voice can be used to identify the user's emotional state.

[1475] Input: User's facial expression data, voice data

[1476] Output: Analyzed user emotion data

[1477] Step 8:

[1478] Server: Receives the user's emotional data and combines it with the pet's analysis results. This generates the optimal notification content that matches the user's situation.

[1479] Input: User's emotional data, predicted pet's feelings and requests

[1480] Output: Optimal notification content

[1481] Step 9:

[1482] Server: Generates a specific notification message based on the pet analysis results and the user's emotional data. For example, it creates a message like, "Your dog Pochi wants to play with you, but you seem tired. Let's rest a bit and then play."

[1483] Input: Optimal notification content

[1484] Output: The generated notification message

[1485] Step 10:

[1486] Terminal: Notifies the user of the generated message. Text messages are displayed in a dedicated application, and audio messages are played through the speaker.

[1487] Input: The generated notification message

[1488] Output: A text message that is displayed to the user and an audio message that is played

[1489] (Application example 2)

[1490] 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."

[1491] Currently, there are several systems that facilitate communication with pets, but these simply analyze the pet's cries and gestures and do not take into account the user's emotional state. Furthermore, there is a lack of systems that naturally link the user's and pet's behavior in a virtual environment, so the user experience is not sufficiently improved.

[1492] The specific processing by the specific 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 analyzing the pet's cries using audio analysis technology, means for analyzing the pet's gestures and facial expressions using image analysis technology, means for translating the pet's feelings and requests based on the analysis results, means for notifying the user of the translation results, emotion analysis means for recognizing the user's emotional state, means for generating notification content by integrating the pet's translation results with the user's emotional data, and means for linking the behavior of the user and the pet in the virtual environment. This enables natural and personalized communication in the virtual environment while taking the user's emotional state into consideration.

[1493] "Voice analysis technology" is a technology that analyzes voice data and extracts information by analyzing its patterns, frequencies, etc.

[1494] "Image analysis technology" is a technology that analyzes image data to identify objects and detect movement patterns.

[1495] "A means of translating pets' feelings and requests" is a system that uses data obtained from voice analysis and image analysis technology to infer and translate a pet's emotions and requests.

[1496] "Means for notifying the user" is a notification function for conveying the translated feelings and requests of the pet to the user.

[1497] "Emotion analysis means" is a technology that analyzes the user's facial expressions and voice data to identify their emotional state.

[1498] The "means for generating notification content" is a function that combines the pet's translation results with the user's emotional data to generate the optimal message.

[1499] "Means for linking the behavior of a user and a pet in a virtual environment" refers to technology that naturally links the behavior and emotions of a user with the behavior of a pet in a virtual space.

[1500] MODE FOR CARRYING OUT THE INVENTION

[1501] Specific hardware and software are required to implement the present invention. A specific system configuration and processing method will be described below.

[1502] System Configuration

[1503] Server: A server with high-performance computing power is required to analyze the data using voice and image analysis techniques and implement sentiment analysis methods, specifically using machine learning libraries such as Keras and TensorFlow.

[1504] Device: A device with a camera and microphone is required to capture the movements and sounds of both you and your pet in real time.

[1505] Notification system: A smartphone application or web application is required to notify users of the notification content.

[1506] Data processing and calculation

[1507] The server does the following:

[1508] 1. Pet Meow Analysis: Using audio analysis technology, pet meows are analyzed based on frequency and patterns, allowing you to identify what your pet is trying to communicate.

[1509] 2. Analysis of pet gestures and facial expressions: Using image analysis technology, the system analyzes pet movements and facial expressions, allowing it to infer the pet's feelings and state.

[1510] 3. User emotion recognition: Emotion analysis means identify the user's emotional state from their facial expressions and voice.

[1511] 4. Data integration and notification content generation: The pet analysis results and user emotion data are integrated to generate optimal notification content. This implementation uses an integrated machine learning model.

[1512] Specific examples

[1513] When a user is shopping in a virtual store, the system works as follows:

[1514] 1. When a user accesses the virtual store using the device's camera and microphone, the device captures the user's and pet's actions and voices in real time.

[1515] 2. The server analyzes the cries and recognizes that the pet wants to play, and at the same time, uses image analysis technology to analyze the pet's behavior and confirm that the pet is active.

[1516] 3. Using emotion analysis means, recognize when the user is tired.

[1517] 4. The server integrates the pet's behavior and the user's emotions and generates a notification message saying, "Pochi wants to play, but you seem tired. Let's take a break first."

[1518] 5. This notification will be displayed on the user's smartphone.

[1519] Prompt Sentence Examples

[1520] While the user is enjoying shopping in a virtual store, it is determined that the virtual pet wants to play, but at the same time it is recognized that the user is tired. In this situation, generate a notification to prompt the user to take an appropriate action.

[1521] This embodiment allows the user to take appropriate action taking into account their pet's feelings and their own emotions, allowing them to enjoy a natural and personalized experience even within the virtual environment.

[1522] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1523] Step 1:

[1524] The user accesses the virtual store using the device's camera and microphone. The device captures the user's and pet's movements and voices in real time. The input of this step is the user's and pet's movements and voice data, and the output is the captured video and voice data.

[1525] Step 2:

[1526] The terminal transmits the captured video and audio data to the server. The specific operation here is that the terminal collects data and transmits it to the server through the network. The input of this step is the captured data, and the output is the data transmitted to the server.

[1527] Step 3:

[1528] The server analyzes the pet's cries using voice analysis technology. Specifically, the server analyzes the frequency and pattern of the received voice data to identify what the pet is trying to communicate. The input for this step is the pet's voice data, and the output is the analysis result of the cries.

[1529] Step 4:

[1530] The server uses image analysis technology to analyze the pet's gestures and facial expressions. The server analyzes the received video data and recognizes the pet's movements and facial expressions. Specifically, it uses a deep learning model to identify movement patterns and changes in facial expressions. The input for this step is the video data, and the output is the analysis results of the gestures and facial expressions.

[1531] Step 5:

[1532] The server integrates the results of voice and image analysis to translate the pet's feelings and requests. This translation uses a pre-trained generative AI model. Specifically, it infers the pet's emotions and requests from its actions and words. The input for this step is the results of voice and image analysis, and the output is a translation of the pet's feelings and requests.

[1533] Step 6:

[1534] The device captures the user's facial expression and voice and sends them to the server. Specifically, the device monitors the user's emotional state in real time and transfers the data to the server. The input of this step is the user's facial expression and voice data, and the output is the emotional data sent to the server.

[1535] Step 7:

[1536] The server uses emotion analysis means to identify the user's emotional state. Specifically, it analyzes the received facial and voice data to recognize the user's current emotion. The input of this step is the user's emotion data, and the output is the user's emotion analysis result.

[1537] Step 8:

[1538] The server combines the pet's translation results with the user's sentiment analysis results to generate appropriate notification content. This uses the generative AI model and prompt text described above. Specifically, it combines the information "the user is tired" and "the pet wants to play" to create the optimal message for the user. The input for this step is the pet's translation results and the user's sentiment analysis results, and the output is the generated notification content.

[1539] Step 9:

[1540] The server sends the generated notification to the terminal. This notification is provided to the user in text and audio format. Specifically, it creates a message to be displayed on the terminal and plays it as an audio notification. The input here is the generated notification, and the output is the notification received by the user.

[1541] Step 10:

[1542] The user receives a notification from the system via their device and takes appropriate action. For example, if they receive a message saying "Let's take a break first," they will take a break. The input to this step is the notification from the device, and the output is the user's action.

[1543] 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.

[1544] 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.

[1545] 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.

[1546] 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.

[1547] 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.

[1548] 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.

[1549] 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).

[1550] 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.

[1551] 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."

[1552] 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.

[1553] 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).

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] 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.

[1560] 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.

[1561] 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.

[1562] 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.

[1563] 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.

[1564] The following is further disclosed regarding the above embodiment.

[1565] (Claim 1)

[1566] A means of analyzing pet cries using voice analysis technology,

[1567] A method to analyze pets' gestures and facial expressions using image analysis technology,

[1568] A means to translate your pet's feelings and requests based on the analysis results,

[1569] a means for notifying the user of the translation result;

[1570] A system including:

[1571] (Claim 2)

[1572] 10. The system of claim 1, further comprising means for analyzing the frequency and pattern of the calls.

[1573] (Claim 3)

[1574] 10. The system of claim 1, further comprising means for identifying movement patterns and facial expression changes.

[1575] (Claim 4)

[1576] 10. The system of claim 1, further comprising means for formatting the analysis results as a text message or a voice message.

[1577] (Claim 5)

[1578] 10. The system of claim 1, including means for accommodating a wide variety of pets, including dogs, cats, small animals, and reptiles.

[1579] (Claim 6)

[1580] 10. The system of claim 1, further comprising means for notifying analysis results in real time.

[1581] (Claim 7)

[1582] 10. The system of claim 1, comprising means for using a machine learning model to predict the pet's moods and needs.

[1583] (Claim 8)

[1584] 10. The system of claim 1, further comprising means for a user to input the type and basic information of the pet.

[1585] (Claim 9)

[1586] 10. The system of claim 1, further comprising means for storing the data in a database.

[1587] "Example 1"

[1588] (Claim 1)

[1589] A means of analyzing pet cries using voice analysis technology,

[1590] A method to analyze pets' gestures and facial expressions using image analysis technology,

[1591] A means to translate your pet's feelings and requests based on the analysis results,

[1592] a means for notifying the user of the translation result;

[1593] a means for receiving and storing data in real time;

[1594] means for analyzing the stored audio data;

[1595] means for analyzing the stored video data;

[1596] means for integrating the analyzed voice data and image data;

[1597] A means of predicting pets' feelings and needs using machine learning models;

[1598] means for formatting the prediction results as a text or voice message;

[1599] means for transmitting the formatted results to a user interface;

[1600] A system including:

[1601] (Claim 2)

[1602] 10. The system of claim 1, further comprising means for analyzing the frequency and pattern of the calls.

[1603] (Claim 3)

[1604] 10. The system of claim 1, further comprising means for identifying movement patterns and facial expression changes.

[1605] "Application Example 1"

[1606] (Claim 1)

[1607] A means of analyzing pet cries using voice analysis technology,

[1608] A method to analyze pets' gestures and facial expressions using image analysis technology,

[1609] A means to translate your pet's feelings and requests based on the analysis results,

[1610] a means for notifying the user of the translation result;

[1611] A means for recommending suitable products based on the translated results;

[1612] a means for displaying information about the recommended product;

[1613] A system including:

[1614] (Claim 2)

[1615] 10. The system of claim 1, further comprising means for analyzing the frequency and pattern of the calls.

[1616] (Claim 3)

[1617] 10. The system of claim 1, further comprising means for identifying movement patterns and facial expression changes.

[1618] "Example 2: Combining Emotion Engines"

[1619] (Claim 1)

[1620] A means of analyzing pet cries using voice analysis technology,

[1621] A method to analyze pets' gestures and facial expressions using image analysis technology,

[1622] A means to translate your pet's feelings and requests based on the analysis results,

[1623] means for analyzing a user's facial expression and voice to identify their emotional state;

[1624] means for generating an appropriate notification based on the translated result and the user's emotional state;

[1625] means for displaying the generated notification in text and audio;

[1626] A system including:

[1627] (Claim 2)

[1628] 10. The system of claim 1, further comprising means for analyzing the frequency and pattern of the calls.

[1629] (Claim 3)

[1630] 10. The system of claim 1, further comprising means for identifying movement patterns and facial expression changes.

[1631] "Application example 2 when combining emotion engines"

[1632] (Claim 1)

[1633] A means of analyzing pet cries using voice analysis technology,

[1634] A method to analyze pets' gestures and facial expressions using image analysis technology,

[1635] A means to translate your pet's feelings and requests based on the analysis results,

[1636] a means for notifying the user of the translation result;

[1637] emotion analysis means for recognizing the emotional state of a user;

[1638] a means for generating notification content by integrating the translation result of the pet and the user's emotion data;

[1639] A means for linking the actions of a user and a pet in a virtual environment;

[1640] A system including:

[1641] (Claim 2)

[1642] 10. The system of claim 1, further comprising means for analyzing the frequency and pattern of the calls.

[1643] (Claim 3)

[1644] 10. The system of claim 1, further comprising means for identifying movement patterns and facial expression changes. [Explanation of symbols]

[1645] 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 of analyzing pet cries using voice analysis technology, A method to analyze pets' gestures and facial expressions using image analysis technology, A means to translate your pet's feelings and requests based on the analysis results, a means for notifying the user of the translation result; A system including:

2. 10. The system of claim 1, further comprising means for analyzing the frequency and pattern of the calls.

3. 10. The system of claim 1, further comprising means for identifying movement patterns and facial expression changes.

4. 10. The system of claim 1, further comprising means for formatting the analysis results as a text message or a voice message.

5. 10. The system of claim 1, including means for accommodating a wide variety of pets, including dogs, cats, small animals, and reptiles.

6. The system according to claim 1 , further comprising means for notifying the analysis results in real time.

7. The system of claim 1 , further comprising means for using machine learning models to predict the pet's moods and needs.

8. 10. The system of claim 1, further comprising means for a user to input the type and basic information of the pet.

9. 10. The system of claim 1, further comprising means for storing the data in a database.

Images