System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting audio of animals in a particular area; means for running a AI model that analyzes the collected audio and identifies characteristics and patterns of the animals' calls; means for generating a new call based on the results of the AI model; and means for playing the generated call at a particular time and condition.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In general, pest birds such as crows and starlings cause significant damage to people's living environments and agricultural areas in certain areas. These birds are highly intelligent, making existing extermination methods difficult to address. Furthermore, because they communicate closely with each other using different calls in each area, the effectiveness of typical extermination sounds is limited. Furthermore, in some cases, attracting pest birds is necessary in addition to repelling them. Therefore, the present invention aims to provide technology that uses AI to analyze the calls of pest birds in each area and effectively control them, thereby presenting a new solution to pest bird control. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. It provides a means for collecting animal sound data in a specific area using a microphone device. It also provides a means for transmitting the collected sound data to a server, where it performs preprocessing such as noise reduction and sampling rate adjustment. It also provides a means for inputting the preprocessed sound data into an AI model to identify the characteristics and patterns of animal sounds. It also provides a means for generating new sounds based on the results of this AI analysis. The generated sounds are transmitted to a terminal for playback at specific times and under specific conditions, and are played in the actual area via a speaker or other device. This series of processes makes it possible to effectively repel nuisance birds in a specific area, or to attract birds as needed. It also provides a management screen and application for adjusting the type of generated sounds and the playback timing.

[0006] "Specified geographic area" refers to a physical area selected for collecting and processing audio data.

[0007] "Animal audio data" refers to data containing animal calls and audio information (mainly birds) collected in a specific area.

[0008] "Means of collection" refers to the technical means for obtaining animal audio data, such as using a microphone device.

[0009] "AI Model" refers to the artificial intelligence algorithms and their implementations used to analyze collected voice data and identify its features and patterns.

[0010] "Means of generation" refers to the technical means for creating new bird calls based on the analysis results of the AI ​​model.

[0011] "Means for playing" refers to the technical means for playing the generated call through an audio device at a specified timing.

[0012] "Noise reduction" refers to a signal processing technology that removes unnecessary sounds from audio data to clarify the target audio.

[0013] "Sampling rate adjustment" refers to a technical means for setting the sampling frequency used in digitizing audio data.

[0014] "Preprocessing" refers to the process of performing initial processing on collected audio data, such as noise reduction and sampling rate adjustment.

[0015] "Characteristics and patterns" refer to characteristics such as frequency, pitch, rhythm, and combinations of these in animal sounds.

[0016] "Terminal" refers to the electronic device used to play audio data and propagate the generated sounds of the calls.

[0017] "Administrative screen or application" refers to the interface through which a user configures the system and adjusts the type of sounds generated and the timing of their playback. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention relates to a system that collects the calls of animals such as crows and starlings, which are considered pest birds, in a specific area, analyzes and processes the data, and generates new calls. This system has the function of replaying the generated calls in order to control the behavior of the animals.

[0040] System Configuration

[0041] Collection Method

[0042] Users install microphone devices in specific areas (e.g., urban parks or agricultural areas), which collect real-time animal audio data within the area. The microphone devices are capable of transmitting the audio data to a server via the Internet.

[0043] Pretreatment

[0044] The server receives the collected audio data and performs noise reduction and sampling rate adjustment, improving the quality of the data and increasing the accuracy of analysis by the AI ​​model.

[0045] AI-powered analysis

[0046] The AI ​​model implemented on the server receives pre-processed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of the calls, allowing it to identify which calls signal danger and which calls attract.

[0047] generation means

[0048] The server generates new sounds based on the analysis results of the AI ​​model. These sounds can be used for specific purposes, such as warning of danger or attracting specific animals.

[0049] Regeneration means

[0050] The generated sounds are played back through the device (speaker) at the specified time and under the specified conditions. Users can set and adjust the type of sound and playback timing using the management screen or application.

[0051] Specific examples

[0052] Collecting bird calls

[0053] Users install high-performance microphone devices around markets and agricultural areas, which collect voice data 24 hours a day and send the audio files to a server every hour.

[0054] Preprocessing and AI analysis

[0055] The server receives the transmitted audio data, reduces noise and adjusts the sampling rate, then feeds it into an AI model that identifies specific sounds that crows make when they sense danger, or when they find food, for example.

[0056] Call generation

[0057] Users can send requests to the server to generate specific sounds based on the analysis results of the AI ​​model, for example, sounds that crows perceive as dangerous, to scare them away from the market.

[0058] Playback of bird calls

[0059] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the generated sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and they will avoid it.

[0060] In this way, the present invention can effectively solve the problem of pest birds in a specific area, minimizing economic losses and improving people's quality of life.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Users install microphone devices in specific areas, such as parks, farmland, and areas around markets where pest birds tend to gather. The microphone devices are used to collect animal audio data in real time.

[0064] Step 2:

[0065] The terminal (microphone device) collects animal voice data in real time and sends it to the server. The transmission frequency is, for example, once every hour or at a specified interval. The voice data is sent in the form of an audio file.

[0066] Step 3:

[0067] The server receives the voice data sent from the device and stores it in a database. The received data is organized by region and managed in a folder structure.

[0068] Step 4:

[0069] The server then performs noise reduction on the received audio data, which removes environmental noise and makes the target animal's call clearer. Noise reduction is performed using a signal processing algorithm.

[0070] Step 5:

[0071] The server adjusts the sampling rate of the noise-reduced data, ensuring that the audio data is input to the AI ​​model with consistent quality. The sampling rate is the process of setting the sampling frequency.

[0072] Step 6:

[0073] The server then inputs the pre-processed audio data into an AI model, which uses a trained deep learning algorithm to analyze the characteristics and patterns of animal calls, identifying calls that signal danger or attract animals.

[0074] Step 7:

[0075] The server generates new crow calls based on the analysis results obtained from the AI ​​model. For example, it uses synthetic voice technology to reproduce specific call patterns, generating calls that crows perceive as dangerous or calls that attract them.

[0076] Step 8:

[0077] The server sends the generated sound file to the device (speaker) based on specific settings, including the playback time and playback conditions.

[0078] Step 9:

[0079] The device (speaker) plays the bird sound file at the specified time and under the specified conditions. The bird sound is automatically played according to the playback schedule set by the user.

[0080] Step 10:

[0081] Users can use the system's control screen or application to adjust the type of calls generated and the timing of their playback, monitor the effectiveness, and change settings as needed to quickly and effectively resolve pest bird problems in a specific area.

[0082] Example 1

[0083] 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."

[0084] Conventional methods for controlling pest birds typically involve the use of physical barriers or chemical repellents. However, these methods are costly and can have a negative impact on the environment. Furthermore, these measures only provide temporary results and do not provide a fundamental solution. Furthermore, the lack of precise methods for controlling animal behavior makes it difficult to effectively control pest birds.

[0085] 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.

[0086] In this invention, the server includes means for collecting animal sound data in a specific area, means for preprocessing the collected sound data, means for analyzing the preprocessed sound data and executing an AI model that identifies its features and patterns, means for generating new calls based on the analysis results of the AI ​​model, and means for playing the generated calls at specific times and under specific conditions, thereby making it possible to effectively solve the problem of pest birds in a specific area and minimize economic losses.

[0087] "Specific region" refers to a specific area set aside for collecting animal sound data.

[0088] "Animal audio data" refers to audio information such as sounds and cries made by animals.

[0089] "Collection means" refers to the equipment or technology used to obtain animal audio data, including microphones and audio collection devices.

[0090] The "pre-processing means" refers to processing performed to improve the quality of collected audio data. Specifically, this includes noise reduction and sampling rate adjustment.

[0091] "Means for implementing artificial intelligence models" refers to algorithms or programs that analyze collected audio data to identify features and patterns, including models that use deep learning or neural networks.

[0092] "Means for generating new bird calls" refers to technology for creating new bird call data based on the analysis results of an artificial intelligence model.

[0093] "Means for playing" refers to a device or program for playing the generated call at a specified time and under specified conditions. Specifically, this includes a speaker and playback control software.

[0094] "Noise reduction" refers to the process of removing unnecessary noise from audio data.

[0095] "Sampling rate adjustment" refers to the process of appropriately setting or changing the sampling frequency of audio data.

[0096] "Administration screen or application" refers to the user interface for configuring and managing the system. Specifically, this includes web applications and mobile applications.

[0097] This invention relates to a system that collects animal calls, such as those of pest birds, in a specific area, analyzes and processes the data, and generates and plays back new calls. This system has the function of playing back the generated calls in order to control the behavior of animals.

[0098] System Configuration

[0099] Collection Method

[0100] A user installs a high-performance microphone device in a specific area (e.g., a city park or an agricultural area). The microphone device has the function of transmitting collected voice data to a server via the Internet. The user installs the microphone device in an appropriate location and uses a setting application to configure the Internet connection and the server address.

[0101] Pretreatment means

[0102] The server performs noise reduction and sampling rate adjustment on the audio data received from the microphone device. Specifically, the server uses the Python library "librosa" to read the audio data, perform noise reduction, and adjust the sampling rate to 44.1 kHz.

[0103] AI analysis means

[0104] The server then feeds the preprocessed audio data into an AI model, which is trained using TensorFlow to analyze the features (such as frequency, pitch, and rhythm) and patterns of the calls, and determines the meaning of a particular call (for example, whether it signals danger or attracts a mate).

[0105] generation means

[0106] The server generates new sounds based on the analysis results of the AI ​​model. Generative adversarial networks (GANs) can be used for generation. For example, it can generate danger sounds to scare off specific animals.

[0107] Regeneration means

[0108] The generated sounds are played through the device (speaker) under conditions specified by the user. The device receives the sound files sent from the server and plays them automatically at the set time (for example, 6:00 every morning). The user can adjust the playback timing and type of sound using the management screen or application.

[0109] Specific examples

[0110] Collecting bird calls

[0111] Users install microphone devices around markets and agricultural areas, which collect audio data 24 hours a day and send the audio files to a server every hour.

[0112] Preprocessing and AI analysis

[0113] The server receives the collected audio data, performs noise reduction and sampling rate adjustment, and then feeds the pre-processed data into an AI model to identify specific sounds that crows make when they sense danger or find food.

[0114] Call generation

[0115] The user sends a request to the server based on the analysis results of the AI ​​model. For example, the user can request that a sound be generated that will scare crows away from the market.

[0116] Playback of bird calls

[0117] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and discourage them from coming near it.

[0118] Example prompts for generative AI models

[0119] "Generate a sound that makes crows feel threatened."

[0120] In this way, the present invention can effectively solve the problem of pest birds in a specific area, minimize economic losses, and contribute to improving people's quality of life.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Program processing flow

[0123] Step 1: Collecting audio data

[0124] Users install high-performance microphone devices in specific areas (for example, around markets or agricultural areas). These microphone devices collect animal sounds 24 hours a day. The collected audio data is sent to a server via the Internet. Users connect the microphone devices to the network using a dedicated configuration application and set the server address.

[0125] Input: Ambient audio data

[0126] Output: Raw audio data

[0127] Specifically, the user places the microphone device in an appropriate position, establishes an Internet connection, and then starts collecting voice data.

[0128] Step 2: Preprocessing the audio data

[0129] The server receives the transmitted audio data and performs pre-processing: it applies a noise reduction algorithm (e.g., spectral subtraction) and adjusts the sampling rate to 44.1 kHz.

[0130] Input: Raw audio data

[0131] Output: Preprocessed audio data

[0132] Specifically, the server uses the Python library "librosa" to read the audio data, perform noise reduction, and reset the sampling rate.

[0133] Step 3: AI analysis of voice data

[0134] The server feeds the preprocessed audio data into an AI model, trained using TensorFlow, that analyzes the call features (such as frequency, pitch, and rhythm) and patterns to identify the meaning of a particular call.

[0135] Input: Preprocessed audio data

[0136] Output: Call feature data and classification results

[0137] Specifically, the server inputs the preprocessed data into the AI ​​model, which then performs feature extraction and pattern recognition and outputs the analysis results.

[0138] Step 4: Generate the call

[0139] The server generates new sounds based on the analysis results of the AI ​​model. For example, it can use GAN (generative adversarial network) to generate sounds that crows sense are dangerous.

[0140] Input: Call feature data and classification results

[0141] Output: Generated bird sounds file

[0142] Specifically, the server runs a sound generation algorithm based on the analysis results, converts the generated audio data into WAV format, and saves it in a specified folder.

[0143] Step 5: Play the sound

[0144] The generated sound files are sent to terminals (speakers installed around the market). The terminals automatically play the sounds at specified times and under specified conditions. Users can adjust the playback timing and type of sound using the management screen or application.

[0145] Input: Generated bird sound file

[0146] Output: Played cry

[0147] Specifically, the device receives the sound file sent from the server and automatically plays it at the set time. The user accesses the management screen and makes requests to change the playback timing or type of sound.

[0148] In this way, by clearly indicating the specific operations, inputs, and outputs at each processing step, the operation of the entire system can be understood in concrete detail.

[0149] (Application example 1)

[0150] 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."

[0151] In the past, the problem of pest birds in specific areas has been a headache for many people. Especially around brick-and-mortar stores, pest birds damage merchandise and facilities, so effective means of preventing this have been sought. However, existing measures have been limited and not sustainably effective. This has caused significant stress and economic losses for store managers and customers. The present invention aims to solve this problem, effectively manage the problem of pest birds in specific areas, and minimize economic losses.

[0152] 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.

[0153] In this invention, the server includes an acoustic data collection means for collecting animal sound data, a means for analyzing the collected acoustic data and executing an artificial intelligence model for identifying characteristics and patterns of animal cries, a generation means for generating new animal cries based on the analysis results of the artificial intelligence model, an acoustic output means for playing the generated cries at specific times and under specific conditions, and an acoustic output device for playing the generated cries in the vicinity of a specific area. This makes it possible to play the generated warning cries from the acoustic output devices installed in the vicinity of a store, thereby effectively repelling harmful birds.

[0154] "Animals" refers to wildlife such as crows and starlings that live in a particular area.

[0155] "Audio data" refers to audio information such as animal sounds recorded in digital format.

[0156] "Acoustic data collection means" refers to equipment or technology for collecting animal sounds using devices such as microphones.

[0157] "Artificial intelligence models" are algorithms such as machine learning models and deep learning models that identify the characteristics and patterns of animal sounds.

[0158] "Generation means" refers to the technology or equipment used to synthesize new bird calls based on the analysis results of the artificial intelligence model.

[0159] "Audio output means" refers to a device such as a speaker for playing back the generated sounds.

[0160] "Sound output devices" are sound equipment such as speakers and PA systems that are installed around the store to play sounds generated to scare away animals.

[0161] The "operation screen" is an interface that allows the user to adjust the type of generated sounds and their playback timing.

[0162] An "application" is software that is installed on a smartphone, tablet, etc. and provides an operating screen.

[0163] To implement this invention, a system is required to collect and analyze animal sound data from a specific area, and generate and play new animal sounds. The main components of this system and their operation are described in detail below.

[0164] First, sound data is collected using acoustic data collection means, specifically, high-performance microphone devices. The microphone devices are installed in specific areas and collect animal sounds 24 hours a day. The devices transmit the sound data in real time to a server via the Internet.

[0165] The server then receives the collected audio data and performs preprocessing, which includes noise reduction and sampling rate adjustment. Specifically, Python libraries (e.g., Sounddevice and pyaudio) are used to reduce noise and adjust the sampling rate to a uniform level. This preprocessing improves the quality of the data and increases the accuracy of analysis by the artificial intelligence model.

[0166] The pre-processed audio data is then analyzed by an artificial intelligence model, which analyzes the characteristics (e.g., frequency, pitch, rhythm) and patterns of animal calls. This analysis can identify which calls signal danger or attract specific animals. The artificial intelligence model uses deep learning models (e.g., TensorFlow and PyTorch).

[0167] Next, based on the analysis results of the AI ​​model, the server generates new sounds. These sounds are used for specific purposes (e.g., to scare away animals or attract animals). Python libraries (e.g., librosa, pydub) are used to generate audio files based on the analysis results.

[0168] Finally, the generated sounds are played back by the audio output means, specifically speakers installed around the store. The speakers play the sounds according to pre-set times and conditions. The user can set and adjust the type of sounds generated and the timing of their playback through a smartphone application. This application provides the user with an operation screen and runs on the smartphone.

[0169] As a concrete example, consider the problem of crows gathering around a city park. By deploying this system, it is possible to generate sounds that crows dislike and play them from speakers at a specific time each day to scare them away.

[0170] Examples of prompts include:

[0171] "We are having trouble with crows gathering around a market in Tokyo. We would like to create a system that generates sounds that crows dislike in this area and plays them periodically. Please place microphones and speakers around the store and generate prompt sentences that collect, analyze, generate, and play back the sounds of crows."

[0172] As a result, the present invention can effectively solve the problem of pest birds in a particular area and minimize economic losses.

[0173] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0174] Step 1:

[0175] A user installs a high-performance microphone device in a specific area and starts collecting audio data.

[0176] Input: Animal sounds

[0177] Output: Raw audio data

[0178] How it works: A microphone device collects and temporarily stores audio data 24 / 7, then transmits the data to a server over the Internet in real time.

[0179] Step 2:

[0180] The server receives the audio data in real time and performs preprocessing.

[0181] Input: Raw audio data

[0182] Output: Preprocessed audio data

[0183] What it does: Improve data quality by performing noise reduction (removing unwanted noise) and adjusting the sampling rate. This is done using Python libraries (e.g. Sounddevice, pyaudio).

[0184] Step 3:

[0185] The server inputs the pre-processed speech data into an artificial intelligence model to analyze speech features and patterns.

[0186] Input: Preprocessed audio data

[0187] Output: Analysis results on call characteristics and patterns

[0188] What it does: Runs an artificial intelligence model (e.g., TensorFlow or PyTorch) to extract features such as frequency, pitch, and rhythm from animal sounds, thereby identifying which sounds have meaning.

[0189] Step 4:

[0190] The server generates new sounds based on the analysis results.

[0191] Input: Analysis results of call characteristics and patterns

[0192] Output: Generated bird sounds file

[0193] What it does: It uses Python libraries (e.g., librosa, pydub) to generate audio files based on the analysis results, tailored to specific purposes, such as scaring or attracting animals.

[0194] Step 5:

[0195] The generated sound file is sent to speakers installed around the store and played back.

[0196] Input: Generated bird sound file

[0197] Output: Played cry

[0198] Specific operation: The generated sound file is sent to a speaker and automatically played at a specified time and under specified conditions. Users can set and adjust the playback timing and sound type via a smartphone application.

[0199] Step 6:

[0200] The user operates a smartphone application to adjust the type of generated sounds and their playback timing.

[0201] Input: User settings and operations

[0202] Output: Change the playback timing and sound type settings

[0203] How it works: The type of bird call generated and the timing of its playback can be changed in real time through the smartphone application's operation screen, making it possible to effectively repel pest birds with the optimal timing and sound.

[0204] 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.

[0205] This invention relates to a system that collects animal calls, such as those of pest birds like crows and starlings, in a specific area, analyzes and processes the data, and generates new animal calls. This system is combined with an emotion engine that recognizes the user's emotions, and has the function of playing back the generated animal calls to control the animal's behavior.

[0206] System Configuration

[0207] Collection Method

[0208] Users install microphone devices in specific areas (e.g., urban parks or agricultural areas), which collect real-time animal audio data within the area. The microphone devices are capable of transmitting the audio data to a server via the Internet.

[0209] Pretreatment

[0210] The server receives the collected audio data and performs noise reduction and sampling rate adjustment, improving the quality of the data and increasing the accuracy of analysis by the AI ​​model.

[0211] AI-powered analysis

[0212] The AI ​​model implemented on the server receives preprocessed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of the calls to determine which calls signal danger and which calls attract.

[0213] generation means

[0214] The server generates new bird calls based on the results of the AI ​​model's analysis. These calls can be used for specific purposes, such as to scare away harmful birds or to attract specific animals.

[0215] Emotion Engine

[0216] The emotion engine receives the user's voice and facial expression data as input and analyzes the user's emotional state. Based on the results of this emotion engine, the server can dynamically adjust the sounds it generates and the timing of their playback.

[0217] Regeneration means

[0218] The generated sounds are played back through the device (speaker) at the specified time and under the specified conditions. Users can use the management screen or application to adjust the type of sound, playback timing, and emotion engine settings.

[0219] Specific examples

[0220] Collecting bird calls

[0221] Users install high-performance microphone devices around markets and agricultural areas, which collect voice data 24 hours a day and send the audio files to a server every hour.

[0222] Preprocessing and AI analysis

[0223] The server receives the transmitted audio data, reduces noise and adjusts the sampling rate, then feeds it into an AI model that identifies specific sounds that crows make when they sense danger, or when they find food, for example.

[0224] Call generation

[0225] Users can send requests to the server to generate specific sounds based on the analysis results of the AI ​​model, for example, sounds that crows perceive as dangerous, to scare them away from the market.

[0226] Using the Emotion Engine

[0227] The server uses an emotion engine to analyze the user's emotional state: for example, if the user is feeling anxious or irritated, it generates a stronger danger sound accordingly and plays it immediately.

[0228] Playback of bird calls

[0229] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the generated sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and they will avoid it.

[0230] In this way, the present invention can effectively solve the problem of pest birds in a specific area. By using this system, economic losses can be minimized and people's quality of life can be improved. By combining it with an emotion engine, more effective measures can be implemented according to the user's emotions.

[0231] The processing flow will be explained below.

[0232] Step 1:

[0233] Users install high-performance microphone devices in specific areas, such as parks, farmland, and around markets where pest birds tend to gather. The microphone devices are designed to collect animal sounds and sounds.

[0234] Step 2:

[0235] The terminal (microphone device) collects animal sounds in real time and sends them to the server in the form of audio files. The frequency of transmission is, for example, once every hour. This allows for continuous data collection.

[0236] Step 3:

[0237] The server receives the voice data sent from the device and stores it in a database. The data is organized and managed by specific area.

[0238] Step 4:

[0239] The server applies noise reduction to the received audio data, eliminating environmental noise and making the target animal's call clearer. Noise reduction is performed using specific signal processing algorithms.

[0240] Step 5:

[0241] The server adjusts the sampling rate of the data after noise reduction processing, thereby unifying the quality of the audio data and converting it into a format suitable for the AI ​​model.

[0242] Step 6:

[0243] The server then inputs the pre-processed audio data into the AI ​​model, which uses deep learning algorithms to analyze the features (such as frequency, pitch, and rhythm) and patterns of the bird's calls.

[0244] Step 7:

[0245] The server generates new cries based on the analysis results of the AI ​​model. For example, it uses synthetic voice technology to generate cries that crows make when they sense danger, or cries that attract specific animals.

[0246] Step 8:

[0247] The server sends the generated sound file to the terminal (speaker) along with specific conditions (e.g., playback time and playback conditions).

[0248] Step 9:

[0249] The device (speaker) plays the received sound file at the specified time and under the specified conditions. Playback is automatic, but users can also set a playback schedule via the management screen or application.

[0250] Step 10:

[0251] The server analyzes the user's emotional state using an emotion engine, which receives the user's voice and facial expression data as input and determines the user's emotional state (e.g., anxiety, irritation, joy, etc.).

[0252] Step 11:

[0253] The server dynamically adjusts the type and timing of the sounds it generates based on the analysis results of the emotion engine. For example, if the user feels anxious, it will generate a stronger sound that signals danger and play it immediately.

[0254] Step 12:

[0255] Using the system's control screen or application, users can adjust the type of calls generated, their timing, and even the emotion engine settings, allowing for quick and effective solutions to pest bird problems in specific areas.

[0256] Example 2

[0257] 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."

[0258] In conventional animal behavior control systems, it is difficult to respond to the user's emotions and real-time situations when generating and playing back specific bird sounds after collecting and analyzing them. As a result, it is not possible to effectively repel pest birds and to alleviate the user's anxiety and frustration. The present invention aims to solve these problems.

[0259] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0260] In this invention, the server includes means for collecting animal sound data in a specific area, preprocessing means for performing noise reduction and sampling rate adjustment on the collected sound data, means for analyzing the preprocessed sound data and executing an AI model for identifying the characteristics and patterns of animal sounds, means for generating new sounds based on the analysis results of the AI ​​model, means for executing an emotion recognition engine for dynamically adjusting the type and playback timing of the generated sounds, and means for playing the generated sounds at specific times and under specific conditions. This makes it possible to generate and play optimal sounds in real time according to the user's emotions and situation, thereby effectively preventing damage caused by pest birds.

[0261] "Specific areas" refer to areas such as urban parks, agricultural areas, and around markets where animal behavior and sounds are frequently observed.

[0262] "Animal audio data" refers to data collected from the cries and sounds made by animals, including pest birds such as crows and starlings.

[0263] "Means of collection" refers to the function of using microphone devices and sensors to collect animal sounds in a specific area and send them to a server.

[0264] "Preprocessing means" refers to a function that performs noise reduction and sampling rate adjustment on collected audio data to improve data quality.

[0265] "AI model" refers to an algorithm or machine learning model that analyzes the characteristics and patterns of animal sounds and uses them for classification or specific purposes.

[0266] "Means for executing an AI model" refers to the functionality that receives preprocessed audio data as input and performs analysis using an AI model.

[0267] "Means for generating new bird calls" refers to the function of generating new bird calls for specific purposes (such as repelling harmful birds or attracting animals) based on the analysis results of the AI ​​model.

[0268] An "emotion recognition engine" refers to a function that analyzes the user's voice and facial expression data and recognizes the user's emotional state in real time.

[0269] "Means for playback" refers to the function of playing the generated sounds through a terminal (e.g., speaker) at a specified time and under specified conditions.

[0270] "Control Screen or Application" refers to the interface or software that a user uses to adjust the type of sounds generated, their playback timing, and the settings of the emotion recognition engine.

[0271] This invention relates to a system that collects, analyzes, generates, and plays back animal sound data in a specific area. This system collects the calls of pest birds such as crows and starlings, analyzes them using an AI model, generates new calls, and plays them back at specific times and under specific conditions. It also incorporates an emotion recognition engine that recognizes the user's emotions, enabling the system to dynamically generate and play back animal sounds according to the user's emotions and circumstances.

[0272] System configuration

[0273] 1. Collection of audio data

[0274] Users install high-performance microphone devices in specific areas (such as urban parks or agricultural areas), which collect animal sounds 24 hours a day and transmit the audio data to a server via the Internet at regular intervals.

[0275] 2. Preprocessing of audio data

[0276] The server performs noise reduction and sampling rate adjustment on the received audio data, improving the quality of the audio data and increasing the accuracy of analysis by the AI ​​model. Specifically, preprocessing is performed using Python and libraries (e.g., librosa).

[0277] 3. Analysis using AI models

[0278] Using the preprocessed audio data as input, an AI model implemented on the server analyzes the characteristics of the bird's calls (frequency, pitch, rhythm, etc.) and identifies specific call patterns using TensorFlow or PyTorch.

[0279] 4. Sound production

[0280] The user requests the server to generate a new bird cry based on the analysis results of the AI ​​model. The server then uses a generative AI model (e.g., GAN or WaveNet) to generate a bird cry with specific characteristics.

[0281] 5. Use of Emotion Recognition Engine

[0282] The emotion recognition engine analyzes the user's voice and facial expression data to recognize their emotional state. The server dynamically adjusts the sounds generated and the playback timing based on this emotional information. A deep learning model is used for emotion recognition.

[0283] 6. Playback of bird calls

[0284] The generated sounds are played back through the device (speaker) at specific times and under specific conditions. Users can adjust the type of sound and playback timing using the management screen or application. Specifically, the speaker uses an RTC (real-time clock) to play sounds at set times.

[0285] Examples and prompts

[0286] Specific examples

[0287] 1. Audio data collection:

[0288] A microphone device installed by a user in a city park transmits bird call data to a server every hour.

[0289] 2. Preprocessing the audio data:

[0290] The data received by the server is noise reduced using the librosa library and adjusted to a sampling rate of 16kHz.

[0291] 3. Analysis by AI model:

[0292] The server uses a TensorFlow model to extract features from the audio data and identify specific call patterns.

[0293] 4. Sound production:

[0294] The user sends a request to generate a "sound that makes a crow feel threatened" via a web interface, and the server generates it using GAN.

[0295] 5. Use of Emotion Recognition Engine:

[0296] The emotion engine analyzes the user's voice data, detects when the user is feeling irritated, and generates a powerful warning sound.

[0297] 6. Playback of the call:

[0298] The speakers automatically play a warning call every morning before the market opens to discourage crows from approaching the market area.

[0299] Prompt Sentence Examples

[0300] Please provide a program that generates a strong warning sound to scare away pest birds based on data on crow calls collected by microphone devices installed in agricultural areas. If the user's emotion is "anxiety," the program will generate an even stronger sound.

[0301] In this way, the present invention can effectively solve the problem of pest birds in a specific area, enabling real-time responses based on user emotions, minimizing economic losses, and contributing to improving the quality of life of users.

[0302] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0303] Step 1:

[0304] Audio data collection

[0305] Input: A specific area where a microphone device is installed (such as a city park or agricultural area).

[0306] Data processing: The microphone device collects animal sounds 24 hours a day and stores the data in a buffer at regular intervals.

[0307] What it does: The microphone device compresses and temporarily stores the audio data, then sends it to the server using the HTTPS protocol.

[0308] Output: The audio data file sent to the server.

[0309] Step 2:

[0310] Audio data preprocessing

[0311] Input: The audio data file received by the server.

[0312] Data processing: The server uses the librosa library to perform noise reduction and sampling rate adjustment.

[0313] What happens: The server applies an algorithm to remove noise from the audio data and adjust it to a 16kHz sampling rate.

[0314] Output: Preprocessed high-quality audio data.

[0315] Step 3:

[0316] Analysis by AI model

[0317] Input: Preprocessed audio data.

[0318] Data calculation: An AI model (e.g., TensorFlow or PyTorch) on the server extracts features (frequency, pitch, rhythm) from the audio data and performs clustering and classification.

[0319] What it does: The server uses a Convolutional Neural Network (CNN) to analyze specific call patterns.

[0320] Output: Classification results for each call and corresponding feature data.

[0321] Step 4:

[0322] Call generation

[0323] Input: The analysis results of the AI ​​model and the user's request.

[0324] Data computation: The server uses a generative AI model (e.g., GAN or WaveNet) to generate new calls.

[0325] Specific operation: The server uses GAN to generate a new audio file with the specified features.

[0326] Output: Generated call sound files.

[0327] Step 5:

[0328] Using the Emotion Recognition Engine

[0329] Input: User's voice and facial expression data.

[0330] Data calculation: The server uses an emotion recognition engine to analyze the user's emotional state.

[0331] How it works: The server uses a deep learning model to detect emotions from the user's voice and facial expressions in real time.

[0332] Output: User's emotional state data (e.g., anxious, irritated, calm).

[0333] Step 6:

[0334] Playback of bird calls

[0335] Input: Generated sound files and user emotional state data.

[0336] Data processing: Dynamically adjust the type and timing of generated sounds based on the user's emotional state.

[0337] Specific behavior: The speaker uses RTC to play a chirp at the set time. Users can also set the value from the management screen.

[0338] Output: The actual sound played.

[0339] In this way, the system effectively solves the problem of pest birds in a specific area through each step of collecting, preprocessing, analyzing, generating, emotion-recognizing, and playing back animal sounds. The specific processing flow allows for the generation and playback of appropriate animal sounds in real time, enabling advanced countermeasures tailored to user needs.

[0340] (Application example 2)

[0341] 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."

[0342] The present invention relates to a system that collects and analyzes animal sounds and generates and plays appropriate animal sounds, particularly in industrial environments, to prevent animal intrusion and improve work efficiency and safety. Specifically, the present invention aims to provide a system that uses robots working in factories to generate sounds to efficiently repel nuisance birds and other animals and plays them in real time according to the emotional state of employees. Another challenge is to dynamically adjust and play animal sounds based on the user's emotions, which was not possible with conventional systems.

[0343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0344] In this invention, the server includes means for collecting animal sound data in a specific area, means for analyzing the collected sound data and executing an artificial intelligence model that identifies characteristics and patterns of animal sounds, means for generating new sounds based on the analysis results of the artificial intelligence model, means for playing the generated sounds at specific times and under specific conditions, means for playing the generated sounds in real time using an application installed on the robot, and means for dynamically adjusting the generated sounds and their playback timing based on an emotion engine that recognizes the user's emotions. This makes it possible to efficiently repel harmful birds and other animals using robots working in factories, and to adjust and play appropriate sounds in real time according to the emotional state of employees.

[0345] definition statement

[0346] "Means for collecting animal sound data" is a general term for devices and associated technologies for recording animal sounds and sounds in a specific area.

[0347] The "means for implementing the artificial intelligence model" is a computer system that applies machine learning algorithms to analyze audio data and identify characteristics and patterns in animal sounds.

[0348] The "means for generating new animal sounds" refers to a technology that uses the analysis results of an artificial intelligence model to programmatically create animal sounds for specific purposes.

[0349] The "means for playing at a specific time or under specific conditions" refers to a device and a program for playing the generated sounds through an audio device according to a predetermined time or conditions.

[0350] "Means for playing back in real time sounds generated using an application installed on the robot" refers to technology that allows for instant playback of generated sounds through a software application within the robot.

[0351] "Means for dynamically adjusting the sounds generated and their playback timing based on an emotion engine" is a technology that recognizes the user's emotional state and changes the sounds generated and their playback timing in real time based on that data.

[0352] MODE FOR CARRYING OUT THE INVENTION

[0353] A specific method for carrying out the present invention will now be described.

[0354] In this invention, we will build a system that collects, analyzes, generates, and plays animal sounds using an application installed on a factory robot. The overall system consists of the following steps:

[0355] 1. Collection of audio data

[0356] High-performance microphone devices are installed inside the factory to collect animal sounds and cries in real time, and the collected audio data is sent to a server via the internet.

[0357] 2. Preprocessing of audio data

[0358] The server then applies noise reduction and sampling rate adjustment to the received audio data to improve the quality of the data, which improves the accuracy of subsequent analysis by the AI ​​model.

[0359] 3. Analysis of bird calls

[0360] The artificial intelligence model (e.g., bird_sound_model.h5) implemented on the server receives preprocessed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of bird calls. This analysis determines the meaning of a particular call.

[0361] 4. Sound production

[0362] Based on the analysis of the AI ​​model, the server generates new sounds to scare away animals or attract specific animals.

[0363] 5. Use of Emotion Engine

[0364] The server is equipped with an emotion engine that receives human voice and facial expression data as input and analyzes the user's emotional state. Based on the results of the emotion engine, the generated sounds and their playback timing are dynamically adjusted.

[0365] 6. Playback of bird calls

[0366] The generated sounds are played back through speakers in the factory at specified times and under specified conditions, and users can use the application to adjust the type and timing of the sounds, as well as the emotion engine settings.

[0367] Specific examples

[0368] For example, if a crow is cawing in a factory, the audio data is collected through a microphone device and analyzed by the server. Based on the analysis results, a sound that the crow perceives as dangerous is generated and played through the speakers to scare the crow away. Furthermore, the emotion engine dynamically adjusts the audio to be more effective when an employee feels irritated or anxious.

[0369] Prompt Sentence Examples

[0370] "Collect the sounds of crows cawing and generate a call that signals danger."

[0371] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0372] Program processing steps

[0373] Step 1:

[0374] Audio data collection

[0375] Input: A microphone device to collect animal sounds in a specific area

[0376] How it works: Microphone devices installed in factories record animal sounds and voices 24 hours a day.

[0377] Output: The collected audio data is sent to a server via the Internet.

[0378] Step 2:

[0379] Audio data preprocessing

[0380] Input: Collected audio data

[0381] Operation: The server performs noise reduction on the received audio data and adjusts the sampling rate appropriately. Specifically, it removes noise and resamples the data to improve its quality.

[0382] Output: Pre-processed high-quality audio data

[0383] Step 3:

[0384] Analysis of bird calls

[0385] Input: Preprocessed audio data

[0386] How it works: An AI model implemented on the server receives preprocessed audio data as input and analyzes it, extracting features such as frequency, pitch, and rhythm to analyze the bird's call patterns.

[0387] Output: Analysis results, including characteristics and patterns of bird calls

[0388] Step 4:

[0389] Call generation

[0390] Input: Analysis results from an artificial intelligence model

[0391] How it works: The server generates new sounds based on the analysis results, such as a specific sound to scare away crows or a sound to attract specific animals.

[0392] Output: The new call generated.

[0393] Step 5:

[0394] Using the Emotion Engine

[0395] Input: User's voice and facial expression data

[0396] How it works: The server uses an emotion engine to analyze the user's emotional state, including the user's tone of voice and facial expressions. For example, if it determines that the user is feeling anxious or irritated, it dynamically adjusts the sounds it generates and the timing of their playback based on that information.

[0397] Output: Optimal sound generation and playback settings based on the user's emotional state

[0398] Step 6:

[0399] Playback of bird calls

[0400] Input: Generated sounds and the results of adjustments made by the emotion engine

[0401] How it works: The generated sounds are played through speakers in the factory based on preset times and conditions. The timing and type of sounds are set and adjusted through the application.

[0402] Output: Animal noises played in real time through speakers in the factory, resulting in animals being chased away from the factory.

[0403] An example of a prompt to ensure proper behavior is: "Collect the sounds of crows cawing and generate a call that indicates danger."

[0404] In this way, by performing appropriate data processing and calculations at each step, a system that efficiently controls animal behavior can be realized.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] [Second embodiment]

[0409] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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."

[0421] This invention relates to a system that collects the calls of animals such as crows and starlings, which are considered pest birds, in a specific area, analyzes and processes the data, and generates new calls. This system has the function of replaying the generated calls in order to control the behavior of the animals.

[0422] System Configuration

[0423] Collection Method

[0424] Users install microphone devices in specific areas (e.g., urban parks or agricultural areas), which collect real-time animal audio data within the area. The microphone devices are capable of transmitting the audio data to a server via the Internet.

[0425] Pretreatment

[0426] The server receives the collected audio data and performs noise reduction and sampling rate adjustment, improving the quality of the data and increasing the accuracy of analysis by the AI ​​model.

[0427] AI-powered analysis

[0428] The AI ​​model implemented on the server receives pre-processed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of the calls, allowing it to identify which calls signal danger and which calls attract.

[0429] generation means

[0430] The server generates new sounds based on the analysis results of the AI ​​model. These sounds can be used for specific purposes, such as warning of danger or attracting specific animals.

[0431] Regeneration means

[0432] The generated sounds are played back through the device (speaker) at the specified time and under the specified conditions. Users can set and adjust the type of sound and playback timing using the management screen or application.

[0433] Specific examples

[0434] Collecting bird calls

[0435] Users install high-performance microphone devices around markets and agricultural areas, which collect voice data 24 hours a day and send the audio files to a server every hour.

[0436] Preprocessing and AI analysis

[0437] The server receives the transmitted audio data, reduces noise and adjusts the sampling rate, then feeds it into an AI model that identifies specific sounds that crows make when they sense danger, or when they find food, for example.

[0438] Call generation

[0439] Users can send requests to the server to generate specific sounds based on the analysis results of the AI ​​model, for example, sounds that crows perceive as dangerous, to scare them away from the market.

[0440] Playback of bird calls

[0441] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the generated sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and they will avoid it.

[0442] In this way, the present invention can effectively solve the problem of pest birds in a specific area, minimizing economic losses and improving people's quality of life.

[0443] The processing flow will be explained below.

[0444] Step 1:

[0445] Users install microphone devices in specific areas, such as parks, farmland, and areas around markets where pest birds tend to gather. The microphone devices are used to collect animal audio data in real time.

[0446] Step 2:

[0447] The terminal (microphone device) collects animal voice data in real time and sends it to the server. The transmission frequency is, for example, once every hour or at a specified interval. The voice data is sent in the form of an audio file.

[0448] Step 3:

[0449] The server receives the voice data sent from the device and stores it in a database. The received data is organized by region and managed in a folder structure.

[0450] Step 4:

[0451] The server then performs noise reduction on the received audio data, which removes environmental noise and makes the target animal's call clearer. Noise reduction is performed using a signal processing algorithm.

[0452] Step 5:

[0453] The server adjusts the sampling rate of the noise-reduced data, ensuring that the audio data is input to the AI ​​model with consistent quality. The sampling rate is the process of setting the sampling frequency.

[0454] Step 6:

[0455] The server then inputs the pre-processed audio data into an AI model, which uses a trained deep learning algorithm to analyze the characteristics and patterns of animal calls, identifying calls that signal danger or attract animals.

[0456] Step 7:

[0457] The server generates new crow calls based on the analysis results obtained from the AI ​​model. For example, it uses synthetic voice technology to reproduce specific call patterns, generating calls that crows perceive as dangerous or calls that attract them.

[0458] Step 8:

[0459] The server sends the generated sound file to the device (speaker) based on specific settings, including the playback time and playback conditions.

[0460] Step 9:

[0461] The device (speaker) plays the bird sound file at the specified time and under the specified conditions. The bird sound is automatically played according to the playback schedule set by the user.

[0462] Step 10:

[0463] Users can use the system's control screen or application to adjust the type of calls generated and the timing of their playback, monitor the effectiveness, and change settings as needed to quickly and effectively resolve pest bird problems in a specific area.

[0464] Example 1

[0465] 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."

[0466] Conventional methods for controlling pest birds typically involve the use of physical barriers or chemical repellents. However, these methods are costly and can have a negative impact on the environment. Furthermore, these measures only provide temporary results and do not provide a fundamental solution. Furthermore, the lack of precise methods for controlling animal behavior makes it difficult to effectively control pest birds.

[0467] 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.

[0468] In this invention, the server includes means for collecting animal sound data in a specific area, means for preprocessing the collected sound data, means for analyzing the preprocessed sound data and executing an AI model that identifies its features and patterns, means for generating new calls based on the analysis results of the AI ​​model, and means for playing the generated calls at specific times and under specific conditions, thereby making it possible to effectively solve the problem of pest birds in a specific area and minimize economic losses.

[0469] "Specific region" refers to a specific area set aside for collecting animal sound data.

[0470] "Animal audio data" refers to audio information such as sounds and cries made by animals.

[0471] "Collection means" refers to the equipment or technology used to obtain animal audio data, including microphones and audio collection devices.

[0472] The "pre-processing means" refers to processing performed to improve the quality of collected audio data. Specifically, this includes noise reduction and sampling rate adjustment.

[0473] "Means for implementing artificial intelligence models" refers to algorithms or programs that analyze collected audio data to identify features and patterns, including models that use deep learning or neural networks.

[0474] "Means for generating new bird calls" refers to technology for creating new bird call data based on the analysis results of an artificial intelligence model.

[0475] "Means for playing" refers to a device or program for playing the generated call at a specified time and under specified conditions. Specifically, this includes a speaker and playback control software.

[0476] "Noise reduction" refers to the process of removing unnecessary noise from audio data.

[0477] "Sampling rate adjustment" refers to the process of appropriately setting or changing the sampling frequency of audio data.

[0478] "Administration screen or application" refers to the user interface for configuring and managing the system. Specifically, this includes web applications and mobile applications.

[0479] This invention relates to a system that collects animal calls, such as those of pest birds, in a specific area, analyzes and processes the data, and generates and plays back new calls. This system has the function of playing back the generated calls in order to control the behavior of animals.

[0480] System Configuration

[0481] Collection Method

[0482] A user installs a high-performance microphone device in a specific area (e.g., a city park or an agricultural area). The microphone device has the function of transmitting collected voice data to a server via the Internet. The user installs the microphone device in an appropriate location and uses a setting application to configure the Internet connection and the server address.

[0483] Pretreatment means

[0484] The server performs noise reduction and sampling rate adjustment on the audio data received from the microphone device. Specifically, the server uses the Python library "librosa" to read the audio data, perform noise reduction, and adjust the sampling rate to 44.1 kHz.

[0485] AI analysis means

[0486] The server then feeds the preprocessed audio data into an AI model, which is trained using TensorFlow to analyze the features (such as frequency, pitch, and rhythm) and patterns of the calls, and determines the meaning of a particular call (for example, whether it signals danger or attracts a mate).

[0487] generation means

[0488] The server generates new sounds based on the analysis results of the AI ​​model. Generative adversarial networks (GANs) can be used for generation. For example, it can generate danger sounds to scare off specific animals.

[0489] Regeneration means

[0490] The generated sounds are played through the device (speaker) under conditions specified by the user. The device receives the sound files sent from the server and plays them automatically at the set time (for example, 6:00 every morning). The user can adjust the playback timing and type of sound using the management screen or application.

[0491] Specific examples

[0492] Collecting bird calls

[0493] Users install microphone devices around markets and agricultural areas, which collect audio data 24 hours a day and send the audio files to a server every hour.

[0494] Preprocessing and AI analysis

[0495] The server receives the collected audio data, performs noise reduction and sampling rate adjustment, and then feeds the pre-processed data into an AI model to identify specific sounds that crows make when they sense danger or find food.

[0496] Call generation

[0497] The user sends a request to the server based on the analysis results of the AI ​​model. For example, the user can request that a sound be generated that will scare crows away from the market.

[0498] Playback of bird calls

[0499] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and discourage them from coming near it.

[0500] Example prompts for generative AI models

[0501] "Generate a sound that makes crows feel threatened."

[0502] In this way, the present invention can effectively solve the problem of pest birds in a specific area, minimize economic losses, and contribute to improving people's quality of life.

[0503] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0504] Program processing flow

[0505] Step 1: Collecting audio data

[0506] Users install high-performance microphone devices in specific areas (for example, around markets or agricultural areas). These microphone devices collect animal sounds 24 hours a day. The collected audio data is sent to a server via the Internet. Users connect the microphone devices to the network using a dedicated configuration application and set the server address.

[0507] Input: Ambient audio data

[0508] Output: Raw audio data

[0509] Specifically, the user places the microphone device in an appropriate position, establishes an Internet connection, and then starts collecting voice data.

[0510] Step 2: Preprocessing the audio data

[0511] The server receives the transmitted audio data and performs pre-processing: it applies a noise reduction algorithm (e.g., spectral subtraction) and adjusts the sampling rate to 44.1 kHz.

[0512] Input: Raw audio data

[0513] Output: Preprocessed audio data

[0514] Specifically, the server uses the Python library "librosa" to read the audio data, perform noise reduction, and reset the sampling rate.

[0515] Step 3: AI analysis of voice data

[0516] The server feeds the preprocessed audio data into an AI model, trained using TensorFlow, that analyzes the call features (such as frequency, pitch, and rhythm) and patterns to identify the meaning of a particular call.

[0517] Input: Preprocessed audio data

[0518] Output: Call feature data and classification results

[0519] Specifically, the server inputs the preprocessed data into the AI ​​model, which then performs feature extraction and pattern recognition and outputs the analysis results.

[0520] Step 4: Generate the call

[0521] The server generates new sounds based on the analysis results of the AI ​​model. For example, it can use GAN (generative adversarial network) to generate sounds that crows sense are dangerous.

[0522] Input: Call feature data and classification results

[0523] Output: Generated bird sounds file

[0524] Specifically, the server runs a sound generation algorithm based on the analysis results, converts the generated audio data into WAV format, and saves it in a specified folder.

[0525] Step 5: Play the sound

[0526] The generated sound files are sent to terminals (speakers installed around the market). The terminals automatically play the sounds at specified times and under specified conditions. Users can adjust the playback timing and type of sound using the management screen or application.

[0527] Input: Generated bird sound file

[0528] Output: Played cry

[0529] Specifically, the device receives the sound file sent from the server and automatically plays it at the set time. The user accesses the management screen and makes requests to change the playback timing or type of sound.

[0530] In this way, by clearly indicating the specific operations, inputs, and outputs at each processing step, the operation of the entire system can be understood in concrete detail.

[0531] (Application example 1)

[0532] 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."

[0533] In the past, the problem of pest birds in specific areas has been a headache for many people. Especially around brick-and-mortar stores, pest birds damage merchandise and facilities, so effective means of preventing this have been sought. However, existing measures have been limited and not sustainably effective. This has caused significant stress and economic losses for store managers and customers. The present invention aims to solve this problem, effectively manage the problem of pest birds in specific areas, and minimize economic losses.

[0534] 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.

[0535] In this invention, the server includes an acoustic data collection means for collecting animal sound data, a means for analyzing the collected acoustic data and executing an artificial intelligence model for identifying characteristics and patterns of animal cries, a generation means for generating new animal cries based on the analysis results of the artificial intelligence model, an acoustic output means for playing the generated cries at specific times and under specific conditions, and an acoustic output device for playing the generated cries in the vicinity of a specific area. This makes it possible to play the generated warning cries from the acoustic output devices installed in the vicinity of a store, thereby effectively repelling harmful birds.

[0536] "Animals" refers to wildlife such as crows and starlings that live in a particular area.

[0537] "Audio data" refers to audio information such as animal sounds recorded in digital format.

[0538] "Acoustic data collection means" refers to equipment or technology for collecting animal sounds using devices such as microphones.

[0539] "Artificial intelligence models" are algorithms such as machine learning models and deep learning models that identify the characteristics and patterns of animal sounds.

[0540] "Generation means" refers to the technology or equipment used to synthesize new bird calls based on the analysis results of the artificial intelligence model.

[0541] "Audio output means" refers to a device such as a speaker for playing back the generated sounds.

[0542] "Sound output devices" are sound equipment such as speakers and PA systems that are installed around the store to play sounds generated to scare away animals.

[0543] The "operation screen" is an interface that allows the user to adjust the type of generated sounds and their playback timing.

[0544] An "application" is software that is installed on a smartphone, tablet, etc. and provides an operating screen.

[0545] To implement this invention, a system is required to collect and analyze animal sound data from a specific area, and generate and play new animal sounds. The main components of this system and their operation are described in detail below.

[0546] First, sound data is collected using acoustic data collection means, specifically, high-performance microphone devices. The microphone devices are installed in specific areas and collect animal sounds 24 hours a day. The devices transmit the sound data in real time to a server via the Internet.

[0547] The server then receives the collected audio data and performs preprocessing, which includes noise reduction and sampling rate adjustment. Specifically, Python libraries (e.g., Sounddevice and pyaudio) are used to reduce noise and adjust the sampling rate to a uniform level. This preprocessing improves the quality of the data and increases the accuracy of analysis by the artificial intelligence model.

[0548] The pre-processed audio data is then analyzed by an artificial intelligence model, which analyzes the characteristics (e.g., frequency, pitch, rhythm) and patterns of animal calls. This analysis can identify which calls signal danger or attract specific animals. The artificial intelligence model uses deep learning models (e.g., TensorFlow and PyTorch).

[0549] Next, based on the analysis results of the AI ​​model, the server generates new sounds. These sounds are used for specific purposes (e.g., to scare away animals or attract animals). Python libraries (e.g., librosa, pydub) are used to generate audio files based on the analysis results.

[0550] Finally, the generated sounds are played back by the audio output means, specifically speakers installed around the store. The speakers play the sounds according to pre-set times and conditions. The user can set and adjust the type of sounds generated and the timing of their playback through a smartphone application. This application provides the user with an operation screen and runs on the smartphone.

[0551] As a concrete example, consider the problem of crows gathering around a city park. By deploying this system, it is possible to generate sounds that crows dislike and play them from speakers at a specific time each day to scare them away.

[0552] Examples of prompts include:

[0553] "We are having trouble with crows gathering around a market in Tokyo. We would like to create a system that generates sounds that crows dislike in this area and plays them periodically. Please place microphones and speakers around the store and generate prompt sentences that collect, analyze, generate, and play back the sounds of crows."

[0554] As a result, the present invention can effectively solve the problem of pest birds in a particular area and minimize economic losses.

[0555] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0556] Step 1:

[0557] A user installs a high-performance microphone device in a specific area and starts collecting audio data.

[0558] Input: Animal sounds

[0559] Output: Raw audio data

[0560] How it works: A microphone device collects and temporarily stores audio data 24 / 7, then transmits the data to a server over the Internet in real time.

[0561] Step 2:

[0562] The server receives the audio data in real time and performs preprocessing.

[0563] Input: Raw audio data

[0564] Output: Preprocessed audio data

[0565] What it does: Improve data quality by performing noise reduction (removing unwanted noise) and adjusting the sampling rate. This is done using Python libraries (e.g. Sounddevice, pyaudio).

[0566] Step 3:

[0567] The server inputs the pre-processed speech data into an artificial intelligence model to analyze speech features and patterns.

[0568] Input: Preprocessed audio data

[0569] Output: Analysis results on call characteristics and patterns

[0570] What it does: Runs an artificial intelligence model (e.g., TensorFlow or PyTorch) to extract features such as frequency, pitch, and rhythm from animal sounds, thereby identifying which sounds have meaning.

[0571] Step 4:

[0572] The server generates new sounds based on the analysis results.

[0573] Input: Analysis results of call characteristics and patterns

[0574] Output: Generated bird sounds file

[0575] What it does: It uses Python libraries (e.g., librosa, pydub) to generate audio files based on the analysis results, tailored to specific purposes, such as scaring or attracting animals.

[0576] Step 5:

[0577] The generated sound file is sent to speakers installed around the store and played back.

[0578] Input: Generated bird sound file

[0579] Output: Played cry

[0580] Specific operation: The generated sound file is sent to a speaker and automatically played at a specified time and under specified conditions. Users can set and adjust the playback timing and sound type via a smartphone application.

[0581] Step 6:

[0582] The user operates a smartphone application to adjust the type of generated sounds and their playback timing.

[0583] Input: User settings and operations

[0584] Output: Change the playback timing and sound type settings

[0585] How it works: The type of bird call generated and the timing of its playback can be changed in real time through the smartphone application's operation screen, making it possible to effectively repel pest birds with the optimal timing and sound.

[0586] 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.

[0587] This invention relates to a system that collects animal calls, such as those of pest birds like crows and starlings, in a specific area, analyzes and processes the data, and generates new animal calls. This system is combined with an emotion engine that recognizes the user's emotions, and has the function of playing back the generated animal calls to control the animal's behavior.

[0588] System Configuration

[0589] Collection Method

[0590] Users install microphone devices in specific areas (e.g., urban parks or agricultural areas), which collect real-time animal audio data within the area. The microphone devices are capable of transmitting the audio data to a server via the Internet.

[0591] Pretreatment

[0592] The server receives the collected audio data and performs noise reduction and sampling rate adjustment, improving the quality of the data and increasing the accuracy of analysis by the AI ​​model.

[0593] AI-powered analysis

[0594] The AI ​​model implemented on the server receives preprocessed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of the calls to determine which calls signal danger and which calls attract.

[0595] generation means

[0596] The server generates new bird calls based on the results of the AI ​​model's analysis. These calls can be used for specific purposes, such as to scare away harmful birds or to attract specific animals.

[0597] Emotion Engine

[0598] The emotion engine receives the user's voice and facial expression data as input and analyzes the user's emotional state. Based on the results of this emotion engine, the server can dynamically adjust the sounds it generates and the timing of their playback.

[0599] Regeneration means

[0600] The generated sounds are played back through the device (speaker) at the specified time and under the specified conditions. Users can use the management screen or application to adjust the type of sound, playback timing, and emotion engine settings.

[0601] Specific examples

[0602] Collecting bird calls

[0603] Users install high-performance microphone devices around markets and agricultural areas, which collect voice data 24 hours a day and send the audio files to a server every hour.

[0604] Preprocessing and AI analysis

[0605] The server receives the transmitted audio data, reduces noise and adjusts the sampling rate, then feeds it into an AI model that identifies specific sounds that crows make when they sense danger, or when they find food, for example.

[0606] Call generation

[0607] Users can send requests to the server to generate specific sounds based on the analysis results of the AI ​​model, for example, sounds that crows perceive as dangerous, to scare them away from the market.

[0608] Using the Emotion Engine

[0609] The server uses an emotion engine to analyze the user's emotional state: for example, if the user is feeling anxious or irritated, it generates a stronger danger sound accordingly and plays it immediately.

[0610] Playback of bird calls

[0611] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the generated sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and they will avoid it.

[0612] In this way, the present invention can effectively solve the problem of pest birds in a specific area. By using this system, economic losses can be minimized and people's quality of life can be improved. By combining it with an emotion engine, more effective measures can be implemented according to the user's emotions.

[0613] The processing flow will be explained below.

[0614] Step 1:

[0615] Users install high-performance microphone devices in specific areas, such as parks, farmland, and around markets where pest birds tend to gather. The microphone devices are designed to collect animal sounds and sounds.

[0616] Step 2:

[0617] The terminal (microphone device) collects animal sounds in real time and sends them to the server in the form of audio files. The frequency of transmission is, for example, once every hour. This allows for continuous data collection.

[0618] Step 3:

[0619] The server receives the voice data sent from the device and stores it in a database. The data is organized and managed by specific area.

[0620] Step 4:

[0621] The server applies noise reduction to the received audio data, eliminating environmental noise and making the target animal's call clearer. Noise reduction is performed using specific signal processing algorithms.

[0622] Step 5:

[0623] The server adjusts the sampling rate of the data after noise reduction processing, thereby unifying the quality of the audio data and converting it into a format suitable for the AI ​​model.

[0624] Step 6:

[0625] The server then inputs the pre-processed audio data into the AI ​​model, which uses deep learning algorithms to analyze the features (such as frequency, pitch, and rhythm) and patterns of the bird's calls.

[0626] Step 7:

[0627] The server generates new cries based on the analysis results of the AI ​​model. For example, it uses synthetic voice technology to generate cries that crows make when they sense danger, or cries that attract specific animals.

[0628] Step 8:

[0629] The server sends the generated sound file to the terminal (speaker) along with specific conditions (e.g., playback time and playback conditions).

[0630] Step 9:

[0631] The device (speaker) plays the received sound file at the specified time and under the specified conditions. Playback is automatic, but users can also set a playback schedule via the management screen or application.

[0632] Step 10:

[0633] The server analyzes the user's emotional state using an emotion engine, which receives the user's voice and facial expression data as input and determines the user's emotional state (e.g., anxiety, irritation, joy, etc.).

[0634] Step 11:

[0635] The server dynamically adjusts the type and timing of the sounds it generates based on the analysis results of the emotion engine. For example, if the user feels anxious, it will generate a stronger sound that signals danger and play it immediately.

[0636] Step 12:

[0637] Using the system's control screen or application, users can adjust the type of calls generated, their timing, and even the emotion engine settings, allowing for quick and effective solutions to pest bird problems in specific areas.

[0638] Example 2

[0639] 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."

[0640] In conventional animal behavior control systems, it is difficult to respond to the user's emotions and real-time situations when generating and playing back specific bird sounds after collecting and analyzing them. As a result, it is not possible to effectively repel pest birds and to alleviate the user's anxiety and frustration. The present invention aims to solve these problems.

[0641] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0642] In this invention, the server includes means for collecting animal sound data in a specific area, preprocessing means for performing noise reduction and sampling rate adjustment on the collected sound data, means for analyzing the preprocessed sound data and executing an AI model for identifying the characteristics and patterns of animal sounds, means for generating new sounds based on the analysis results of the AI ​​model, means for executing an emotion recognition engine for dynamically adjusting the type and playback timing of the generated sounds, and means for playing the generated sounds at specific times and under specific conditions. This makes it possible to generate and play optimal sounds in real time according to the user's emotions and situation, thereby effectively preventing damage caused by pest birds.

[0643] "Specific areas" refer to areas such as urban parks, agricultural areas, and around markets where animal behavior and sounds are frequently observed.

[0644] "Animal audio data" refers to data collected from the cries and sounds made by animals, including pest birds such as crows and starlings.

[0645] "Means of collection" refers to the function of using microphone devices and sensors to collect animal sounds in a specific area and send them to a server.

[0646] "Preprocessing means" refers to a function that performs noise reduction and sampling rate adjustment on collected audio data to improve data quality.

[0647] "AI model" refers to an algorithm or machine learning model that analyzes the characteristics and patterns of animal sounds and uses them for classification or specific purposes.

[0648] "Means for executing an AI model" refers to the functionality that receives preprocessed audio data as input and performs analysis using an AI model.

[0649] "Means for generating new bird calls" refers to the function of generating new bird calls for specific purposes (such as repelling harmful birds or attracting animals) based on the analysis results of the AI ​​model.

[0650] An "emotion recognition engine" refers to a function that analyzes the user's voice and facial expression data and recognizes the user's emotional state in real time.

[0651] "Means for playback" refers to the function of playing the generated sounds through a terminal (e.g., speaker) at a specified time and under specified conditions.

[0652] "Control Screen or Application" refers to the interface or software that a user uses to adjust the type of sounds generated, their playback timing, and the settings of the emotion recognition engine.

[0653] This invention relates to a system that collects, analyzes, generates, and plays back animal sound data in a specific area. This system collects the calls of pest birds such as crows and starlings, analyzes them using an AI model, generates new calls, and plays them back at specific times and under specific conditions. It also incorporates an emotion recognition engine that recognizes the user's emotions, enabling the system to dynamically generate and play back animal sounds according to the user's emotions and circumstances.

[0654] System configuration

[0655] 1. Collection of audio data

[0656] Users install high-performance microphone devices in specific areas (such as urban parks or agricultural areas), which collect animal sounds 24 hours a day and transmit the audio data to a server via the Internet at regular intervals.

[0657] 2. Preprocessing of audio data

[0658] The server performs noise reduction and sampling rate adjustment on the received audio data, improving the quality of the audio data and increasing the accuracy of analysis by the AI ​​model. Specifically, preprocessing is performed using Python and libraries (e.g., librosa).

[0659] 3. Analysis using AI models

[0660] Using the preprocessed audio data as input, an AI model implemented on the server analyzes the characteristics of the bird's calls (frequency, pitch, rhythm, etc.) and identifies specific call patterns using TensorFlow or PyTorch.

[0661] 4. Sound production

[0662] The user requests the server to generate a new bird cry based on the analysis results of the AI ​​model. The server then uses a generative AI model (e.g., GAN or WaveNet) to generate a bird cry with specific characteristics.

[0663] 5. Use of Emotion Recognition Engine

[0664] The emotion recognition engine analyzes the user's voice and facial expression data to recognize their emotional state. The server dynamically adjusts the sounds generated and the playback timing based on this emotional information. A deep learning model is used for emotion recognition.

[0665] 6. Playback of bird calls

[0666] The generated sounds are played back through the device (speaker) at specific times and under specific conditions. Users can adjust the type of sound and playback timing using the management screen or application. Specifically, the speaker uses an RTC (real-time clock) to play sounds at set times.

[0667] Examples and prompts

[0668] Specific examples

[0669] 1. Audio data collection:

[0670] A microphone device installed by a user in a city park transmits bird call data to a server every hour.

[0671] 2. Preprocessing the audio data:

[0672] The data received by the server is noise reduced using the librosa library and adjusted to a sampling rate of 16kHz.

[0673] 3. Analysis by AI model:

[0674] The server uses a TensorFlow model to extract features from the audio data and identify specific call patterns.

[0675] 4. Sound production:

[0676] The user sends a request to generate a "sound that makes a crow feel threatened" via a web interface, and the server generates it using GAN.

[0677] 5. Use of Emotion Recognition Engine:

[0678] The emotion engine analyzes the user's voice data, detects when the user is feeling irritated, and generates a powerful warning sound.

[0679] 6. Playback of the call:

[0680] The speakers automatically play a warning call every morning before the market opens to discourage crows from approaching the market area.

[0681] Prompt Sentence Examples

[0682] Please provide a program that generates a strong warning sound to scare away pest birds based on data on crow calls collected by microphone devices installed in agricultural areas. If the user's emotion is "anxiety," the program will generate an even stronger sound.

[0683] In this way, the present invention can effectively solve the problem of pest birds in a specific area, enabling real-time responses based on user emotions, minimizing economic losses, and contributing to improving the quality of life of users.

[0684] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0685] Step 1:

[0686] Audio data collection

[0687] Input: A specific area where a microphone device is installed (such as a city park or agricultural area).

[0688] Data processing: The microphone device collects animal sounds 24 hours a day and stores the data in a buffer at regular intervals.

[0689] What it does: The microphone device compresses and temporarily stores the audio data, then sends it to the server using the HTTPS protocol.

[0690] Output: The audio data file sent to the server.

[0691] Step 2:

[0692] Audio data preprocessing

[0693] Input: The audio data file received by the server.

[0694] Data processing: The server uses the librosa library to perform noise reduction and sampling rate adjustment.

[0695] What happens: The server applies an algorithm to remove noise from the audio data and adjust it to a 16kHz sampling rate.

[0696] Output: Preprocessed high-quality audio data.

[0697] Step 3:

[0698] Analysis by AI model

[0699] Input: Preprocessed audio data.

[0700] Data calculation: An AI model (e.g., TensorFlow or PyTorch) on the server extracts features (frequency, pitch, rhythm) from the audio data and performs clustering and classification.

[0701] What it does: The server uses a Convolutional Neural Network (CNN) to analyze specific call patterns.

[0702] Output: Classification results for each call and corresponding feature data.

[0703] Step 4:

[0704] Call generation

[0705] Input: The analysis results of the AI ​​model and the user's request.

[0706] Data computation: The server uses a generative AI model (e.g., GAN or WaveNet) to generate new calls.

[0707] Specific operation: The server uses GAN to generate a new audio file with the specified features.

[0708] Output: Generated call sound files.

[0709] Step 5:

[0710] Using the Emotion Recognition Engine

[0711] Input: User's voice and facial expression data.

[0712] Data calculation: The server uses an emotion recognition engine to analyze the user's emotional state.

[0713] How it works: The server uses a deep learning model to detect emotions from the user's voice and facial expressions in real time.

[0714] Output: User's emotional state data (e.g., anxious, irritated, calm).

[0715] Step 6:

[0716] Playback of bird calls

[0717] Input: Generated sound files and user emotional state data.

[0718] Data processing: Dynamically adjust the type and timing of generated sounds based on the user's emotional state.

[0719] Specific behavior: The speaker uses RTC to play a chirp at the set time. Users can also set the value from the management screen.

[0720] Output: The actual sound played.

[0721] In this way, the system effectively solves the problem of pest birds in a specific area through each step of collecting, preprocessing, analyzing, generating, emotion-recognizing, and playing back animal sounds. The specific processing flow allows for the generation and playback of appropriate animal sounds in real time, enabling advanced countermeasures tailored to user needs.

[0722] (Application example 2)

[0723] 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."

[0724] The present invention relates to a system that collects and analyzes animal sounds and generates and plays appropriate animal sounds, particularly in industrial environments, to prevent animal intrusion and improve work efficiency and safety. Specifically, the present invention aims to provide a system that uses robots working in factories to generate sounds to efficiently repel nuisance birds and other animals and plays them in real time according to the emotional state of employees. Another challenge is to dynamically adjust and play animal sounds based on the user's emotions, which was not possible with conventional systems.

[0725] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0726] In this invention, the server includes means for collecting animal sound data in a specific area, means for analyzing the collected sound data and executing an artificial intelligence model that identifies characteristics and patterns of animal sounds, means for generating new sounds based on the analysis results of the artificial intelligence model, means for playing the generated sounds at specific times and under specific conditions, means for playing the generated sounds in real time using an application installed on the robot, and means for dynamically adjusting the generated sounds and their playback timing based on an emotion engine that recognizes the user's emotions. This makes it possible to efficiently repel harmful birds and other animals using robots working in factories, and to adjust and play appropriate sounds in real time according to the emotional state of employees.

[0727] definition statement

[0728] "Means for collecting animal sound data" is a general term for devices and associated technologies for recording animal sounds and sounds in a specific area.

[0729] The "means for implementing the artificial intelligence model" is a computer system that applies machine learning algorithms to analyze audio data and identify characteristics and patterns in animal sounds.

[0730] The "means for generating new animal sounds" refers to a technology that uses the analysis results of an artificial intelligence model to programmatically create animal sounds for specific purposes.

[0731] The "means for playing at a specific time or under specific conditions" refers to a device and a program for playing the generated sounds through an audio device according to a predetermined time or conditions.

[0732] "Means for playing back in real time sounds generated using an application installed on the robot" refers to technology that allows for instant playback of generated sounds through a software application within the robot.

[0733] "Means for dynamically adjusting the sounds generated and their playback timing based on an emotion engine" is a technology that recognizes the user's emotional state and changes the sounds generated and their playback timing in real time based on that data.

[0734] MODE FOR CARRYING OUT THE INVENTION

[0735] A specific method for carrying out the present invention will now be described.

[0736] In this invention, we will build a system that collects, analyzes, generates, and plays animal sounds using an application installed on a factory robot. The overall system consists of the following steps:

[0737] 1. Collection of audio data

[0738] High-performance microphone devices are installed inside the factory to collect animal sounds and cries in real time, and the collected audio data is sent to a server via the internet.

[0739] 2. Preprocessing of audio data

[0740] The server then applies noise reduction and sampling rate adjustment to the received audio data to improve the quality of the data, which improves the accuracy of subsequent analysis by the AI ​​model.

[0741] 3. Analysis of bird calls

[0742] The artificial intelligence model (e.g., bird_sound_model.h5) implemented on the server receives preprocessed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of bird calls. This analysis determines the meaning of a particular call.

[0743] 4. Sound production

[0744] Based on the analysis of the AI ​​model, the server generates new sounds to scare away animals or attract specific animals.

[0745] 5. Use of Emotion Engine

[0746] The server is equipped with an emotion engine that receives human voice and facial expression data as input and analyzes the user's emotional state. Based on the results of the emotion engine, the generated sounds and their playback timing are dynamically adjusted.

[0747] 6. Playback of bird calls

[0748] The generated sounds are played back through speakers in the factory at specified times and under specified conditions, and users can use the application to adjust the type and timing of the sounds, as well as the emotion engine settings.

[0749] Specific examples

[0750] For example, if a crow is cawing in a factory, the audio data is collected through a microphone device and analyzed by the server. Based on the analysis results, a sound that the crow perceives as dangerous is generated and played through the speakers to scare the crow away. Furthermore, the emotion engine dynamically adjusts the audio to be more effective when an employee feels irritated or anxious.

[0751] Prompt Sentence Examples

[0752] "Collect the sounds of crows cawing and generate a call that signals danger."

[0753] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0754] Program processing steps

[0755] Step 1:

[0756] Audio data collection

[0757] Input: A microphone device to collect animal sounds in a specific area

[0758] How it works: Microphone devices installed in factories record animal sounds and voices 24 hours a day.

[0759] Output: The collected audio data is sent to a server via the Internet.

[0760] Step 2:

[0761] Audio data preprocessing

[0762] Input: Collected audio data

[0763] Operation: The server performs noise reduction on the received audio data and adjusts the sampling rate appropriately. Specifically, it removes noise and resamples the data to improve its quality.

[0764] Output: Pre-processed high-quality audio data

[0765] Step 3:

[0766] Analysis of bird calls

[0767] Input: Preprocessed audio data

[0768] How it works: An AI model implemented on the server receives preprocessed audio data as input and analyzes it, extracting features such as frequency, pitch, and rhythm to analyze the bird's call patterns.

[0769] Output: Analysis results, including characteristics and patterns of bird calls

[0770] Step 4:

[0771] Call generation

[0772] Input: Analysis results from an artificial intelligence model

[0773] How it works: The server generates new sounds based on the analysis results, such as a specific sound to scare away crows or a sound to attract specific animals.

[0774] Output: The new call generated.

[0775] Step 5:

[0776] Using the Emotion Engine

[0777] Input: User's voice and facial expression data

[0778] How it works: The server uses an emotion engine to analyze the user's emotional state, including the user's tone of voice and facial expressions. For example, if it determines that the user is feeling anxious or irritated, it dynamically adjusts the sounds it generates and the timing of their playback based on that information.

[0779] Output: Optimal sound generation and playback settings based on the user's emotional state

[0780] Step 6:

[0781] Playback of bird calls

[0782] Input: Generated sounds and the results of adjustments made by the emotion engine

[0783] How it works: The generated sounds are played through speakers in the factory based on preset times and conditions. The timing and type of sounds are set and adjusted through the application.

[0784] Output: Animal noises played in real time through speakers in the factory, resulting in animals being chased away from the factory.

[0785] An example of a prompt to ensure proper behavior is: "Collect the sounds of crows cawing and generate a call that indicates danger."

[0786] In this way, by performing appropriate data processing and calculations at each step, a system that efficiently controls animal behavior can be realized.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] [Third embodiment]

[0791] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0792] 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.

[0793] 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).

[0794] 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.

[0795] 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.

[0796] 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).

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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."

[0803] This invention relates to a system that collects the calls of animals such as crows and starlings, which are considered pest birds, in a specific area, analyzes and processes the data, and generates new calls. This system has the function of replaying the generated calls in order to control the behavior of the animals.

[0804] System Configuration

[0805] Collection Method

[0806] Users install microphone devices in specific areas (e.g., urban parks or agricultural areas), which collect real-time animal audio data within the area. The microphone devices are capable of transmitting the audio data to a server via the Internet.

[0807] Pretreatment

[0808] The server receives the collected audio data and performs noise reduction and sampling rate adjustment, improving the quality of the data and increasing the accuracy of analysis by the AI ​​model.

[0809] AI-powered analysis

[0810] The AI ​​model implemented on the server receives pre-processed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of the calls, allowing it to identify which calls signal danger and which calls attract.

[0811] generation means

[0812] The server generates new sounds based on the analysis results of the AI ​​model. These sounds can be used for specific purposes, such as warning of danger or attracting specific animals.

[0813] Regeneration means

[0814] The generated sounds are played back through the device (speaker) at the specified time and under the specified conditions. Users can set and adjust the type of sound and playback timing using the management screen or application.

[0815] Specific examples

[0816] Collecting bird calls

[0817] Users install high-performance microphone devices around markets and agricultural areas, which collect voice data 24 hours a day and send the audio files to a server every hour.

[0818] Preprocessing and AI analysis

[0819] The server receives the transmitted audio data, reduces noise and adjusts the sampling rate, then feeds it into an AI model that identifies specific sounds that crows make when they sense danger, or when they find food, for example.

[0820] Call generation

[0821] Users can send requests to the server to generate specific sounds based on the analysis results of the AI ​​model, for example, sounds that crows perceive as dangerous, to scare them away from the market.

[0822] Playback of bird calls

[0823] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the generated sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and they will avoid it.

[0824] In this way, the present invention can effectively solve the problem of pest birds in a specific area, minimizing economic losses and improving people's quality of life.

[0825] The processing flow will be explained below.

[0826] Step 1:

[0827] Users install microphone devices in specific areas, such as parks, farmland, and areas around markets where pest birds tend to gather. The microphone devices are used to collect animal audio data in real time.

[0828] Step 2:

[0829] The terminal (microphone device) collects animal voice data in real time and sends it to the server. The transmission frequency is, for example, once every hour or at a specified interval. The voice data is sent in the form of an audio file.

[0830] Step 3:

[0831] The server receives the voice data sent from the device and stores it in a database. The received data is organized by region and managed in a folder structure.

[0832] Step 4:

[0833] The server then performs noise reduction on the received audio data, which removes environmental noise and makes the target animal's call clearer. Noise reduction is performed using a signal processing algorithm.

[0834] Step 5:

[0835] The server adjusts the sampling rate of the noise-reduced data, ensuring that the audio data is input to the AI ​​model with consistent quality. The sampling rate is the process of setting the sampling frequency.

[0836] Step 6:

[0837] The server then inputs the pre-processed audio data into an AI model, which uses a trained deep learning algorithm to analyze the characteristics and patterns of animal calls, identifying calls that signal danger or attract animals.

[0838] Step 7:

[0839] The server generates new crow calls based on the analysis results obtained from the AI ​​model. For example, it uses synthetic voice technology to reproduce specific call patterns, generating calls that crows perceive as dangerous or calls that attract them.

[0840] Step 8:

[0841] The server sends the generated sound file to the device (speaker) based on specific settings, including the playback time and playback conditions.

[0842] Step 9:

[0843] The device (speaker) plays the bird sound file at the specified time and under the specified conditions. The bird sound is automatically played according to the playback schedule set by the user.

[0844] Step 10:

[0845] Users can use the system's control screen or application to adjust the type of calls generated and the timing of their playback, monitor the effectiveness, and change settings as needed to quickly and effectively resolve pest bird problems in a specific area.

[0846] Example 1

[0847] 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."

[0848] Conventional methods for controlling pest birds typically involve the use of physical barriers or chemical repellents. However, these methods are costly and can have a negative impact on the environment. Furthermore, these measures only provide temporary results and do not provide a fundamental solution. Furthermore, the lack of precise methods for controlling animal behavior makes it difficult to effectively control pest birds.

[0849] 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.

[0850] In this invention, the server includes means for collecting animal sound data in a specific area, means for preprocessing the collected sound data, means for analyzing the preprocessed sound data and executing an AI model that identifies its features and patterns, means for generating new calls based on the analysis results of the AI ​​model, and means for playing the generated calls at specific times and under specific conditions, thereby making it possible to effectively solve the problem of pest birds in a specific area and minimize economic losses.

[0851] "Specific region" refers to a specific area set aside for collecting animal sound data.

[0852] "Animal audio data" refers to audio information such as sounds and cries made by animals.

[0853] "Collection means" refers to the equipment or technology used to obtain animal audio data, including microphones and audio collection devices.

[0854] The "pre-processing means" refers to processing performed to improve the quality of collected audio data. Specifically, this includes noise reduction and sampling rate adjustment.

[0855] "Means for implementing artificial intelligence models" refers to algorithms or programs that analyze collected audio data to identify features and patterns, including models that use deep learning or neural networks.

[0856] "Means for generating new bird calls" refers to technology for creating new bird call data based on the analysis results of an artificial intelligence model.

[0857] "Means for playing" refers to a device or program for playing the generated call at a specified time and under specified conditions. Specifically, this includes a speaker and playback control software.

[0858] "Noise reduction" refers to the process of removing unnecessary noise from audio data.

[0859] "Sampling rate adjustment" refers to the process of appropriately setting or changing the sampling frequency of audio data.

[0860] "Administration screen or application" refers to the user interface for configuring and managing the system. Specifically, this includes web applications and mobile applications.

[0861] This invention relates to a system that collects animal calls, such as those of pest birds, in a specific area, analyzes and processes the data, and generates and plays back new calls. This system has the function of playing back the generated calls in order to control the behavior of animals.

[0862] System Configuration

[0863] Collection Method

[0864] A user installs a high-performance microphone device in a specific area (e.g., a city park or an agricultural area). The microphone device has the function of transmitting collected voice data to a server via the Internet. The user installs the microphone device in an appropriate location and uses a setting application to configure the Internet connection and the server address.

[0865] Pretreatment means

[0866] The server performs noise reduction and sampling rate adjustment on the audio data received from the microphone device. Specifically, the server uses the Python library "librosa" to read the audio data, perform noise reduction, and adjust the sampling rate to 44.1 kHz.

[0867] AI analysis means

[0868] The server then feeds the preprocessed audio data into an AI model, which is trained using TensorFlow to analyze the features (such as frequency, pitch, and rhythm) and patterns of the calls, and determines the meaning of a particular call (for example, whether it signals danger or attracts a mate).

[0869] generation means

[0870] The server generates new sounds based on the analysis results of the AI ​​model. Generative adversarial networks (GANs) can be used for generation. For example, it can generate danger sounds to scare off specific animals.

[0871] Regeneration means

[0872] The generated sounds are played through the device (speaker) under conditions specified by the user. The device receives the sound files sent from the server and plays them automatically at the set time (for example, 6:00 every morning). The user can adjust the playback timing and type of sound using the management screen or application.

[0873] Specific examples

[0874] Collecting bird calls

[0875] Users install microphone devices around markets and agricultural areas, which collect audio data 24 hours a day and send the audio files to a server every hour.

[0876] Preprocessing and AI analysis

[0877] The server receives the collected audio data, performs noise reduction and sampling rate adjustment, and then feeds the pre-processed data into an AI model to identify specific sounds that crows make when they sense danger or find food.

[0878] Call generation

[0879] The user sends a request to the server based on the analysis results of the AI ​​model. For example, the user can request that a sound be generated that will scare crows away from the market.

[0880] Playback of bird calls

[0881] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and discourage them from coming near it.

[0882] Example prompts for generative AI models

[0883] "Generate a sound that makes crows feel threatened."

[0884] In this way, the present invention can effectively solve the problem of pest birds in a specific area, minimize economic losses, and contribute to improving people's quality of life.

[0885] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0886] Program processing flow

[0887] Step 1: Collecting audio data

[0888] Users install high-performance microphone devices in specific areas (for example, around markets or agricultural areas). These microphone devices collect animal sounds 24 hours a day. The collected audio data is sent to a server via the Internet. Users connect the microphone devices to the network using a dedicated configuration application and set the server address.

[0889] Input: Ambient audio data

[0890] Output: Raw audio data

[0891] Specifically, the user places the microphone device in an appropriate position, establishes an Internet connection, and then starts collecting voice data.

[0892] Step 2: Preprocessing the audio data

[0893] The server receives the transmitted audio data and performs pre-processing: it applies a noise reduction algorithm (e.g., spectral subtraction) and adjusts the sampling rate to 44.1 kHz.

[0894] Input: Raw audio data

[0895] Output: Preprocessed audio data

[0896] Specifically, the server uses the Python library "librosa" to read the audio data, perform noise reduction, and reset the sampling rate.

[0897] Step 3: AI analysis of voice data

[0898] The server feeds the preprocessed audio data into an AI model, trained using TensorFlow, that analyzes the call features (such as frequency, pitch, and rhythm) and patterns to identify the meaning of a particular call.

[0899] Input: Preprocessed audio data

[0900] Output: Call feature data and classification results

[0901] Specifically, the server inputs the preprocessed data into the AI ​​model, which then performs feature extraction and pattern recognition and outputs the analysis results.

[0902] Step 4: Generate the call

[0903] The server generates new sounds based on the analysis results of the AI ​​model. For example, it can use GAN (generative adversarial network) to generate sounds that crows sense are dangerous.

[0904] Input: Call feature data and classification results

[0905] Output: Generated bird sounds file

[0906] Specifically, the server runs a sound generation algorithm based on the analysis results, converts the generated audio data into WAV format, and saves it in a specified folder.

[0907] Step 5: Play the sound

[0908] The generated sound files are sent to terminals (speakers installed around the market). The terminals automatically play the sounds at specified times and under specified conditions. Users can adjust the playback timing and type of sound using the management screen or application.

[0909] Input: Generated bird sound file

[0910] Output: Played cry

[0911] Specifically, the device receives the sound file sent from the server and automatically plays it at the set time. The user accesses the management screen and makes requests to change the playback timing or type of sound.

[0912] In this way, by clearly indicating the specific operations, inputs, and outputs at each processing step, the operation of the entire system can be understood in concrete detail.

[0913] (Application example 1)

[0914] 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."

[0915] In the past, the problem of pest birds in specific areas has been a headache for many people. Especially around brick-and-mortar stores, pest birds damage merchandise and facilities, so effective means of preventing this have been sought. However, existing measures have been limited and not sustainably effective. This has caused significant stress and economic losses for store managers and customers. The present invention aims to solve this problem, effectively manage the problem of pest birds in specific areas, and minimize economic losses.

[0916] 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.

[0917] In this invention, the server includes an acoustic data collection means for collecting animal sound data, a means for analyzing the collected acoustic data and executing an artificial intelligence model for identifying characteristics and patterns of animal cries, a generation means for generating new animal cries based on the analysis results of the artificial intelligence model, an acoustic output means for playing the generated cries at specific times and under specific conditions, and an acoustic output device for playing the generated cries in the vicinity of a specific area. This makes it possible to play the generated warning cries from the acoustic output devices installed in the vicinity of a store, thereby effectively repelling harmful birds.

[0918] "Animals" refers to wildlife such as crows and starlings that live in a particular area.

[0919] "Audio data" refers to audio information such as animal sounds recorded in digital format.

[0920] "Acoustic data collection means" refers to equipment or technology for collecting animal sounds using devices such as microphones.

[0921] "Artificial intelligence models" are algorithms such as machine learning models and deep learning models that identify the characteristics and patterns of animal sounds.

[0922] "Generation means" refers to the technology or equipment used to synthesize new bird calls based on the analysis results of the artificial intelligence model.

[0923] "Audio output means" refers to a device such as a speaker for playing back the generated sounds.

[0924] "Sound output devices" are sound equipment such as speakers and PA systems that are installed around the store to play sounds generated to scare away animals.

[0925] The "operation screen" is an interface that allows the user to adjust the type of generated sounds and their playback timing.

[0926] An "application" is software that is installed on a smartphone, tablet, etc. and provides an operating screen.

[0927] To implement this invention, a system is required to collect and analyze animal sound data from a specific area, and generate and play new animal sounds. The main components of this system and their operation are described in detail below.

[0928] First, sound data is collected using acoustic data collection means, specifically, high-performance microphone devices. The microphone devices are installed in specific areas and collect animal sounds 24 hours a day. The devices transmit the sound data in real time to a server via the Internet.

[0929] The server then receives the collected audio data and performs preprocessing, which includes noise reduction and sampling rate adjustment. Specifically, Python libraries (e.g., Sounddevice and pyaudio) are used to reduce noise and adjust the sampling rate to a uniform level. This preprocessing improves the quality of the data and increases the accuracy of analysis by the artificial intelligence model.

[0930] The pre-processed audio data is then analyzed by an artificial intelligence model, which analyzes the characteristics (e.g., frequency, pitch, rhythm) and patterns of animal calls. This analysis can identify which calls signal danger or attract specific animals. The artificial intelligence model uses deep learning models (e.g., TensorFlow and PyTorch).

[0931] Next, based on the analysis results of the AI ​​model, the server generates new sounds. These sounds are used for specific purposes (e.g., to scare away animals or attract animals). Python libraries (e.g., librosa, pydub) are used to generate audio files based on the analysis results.

[0932] Finally, the generated sounds are played back by the audio output means, specifically speakers installed around the store. The speakers play the sounds according to pre-set times and conditions. The user can set and adjust the type of sounds generated and the timing of their playback through a smartphone application. This application provides the user with an operation screen and runs on the smartphone.

[0933] As a concrete example, consider the problem of crows gathering around a city park. By deploying this system, it is possible to generate sounds that crows dislike and play them from speakers at a specific time each day to scare them away.

[0934] Examples of prompts include:

[0935] "We are having trouble with crows gathering around a market in Tokyo. We would like to create a system that generates sounds that crows dislike in this area and plays them periodically. Please place microphones and speakers around the store and generate prompt sentences that collect, analyze, generate, and play back the sounds of crows."

[0936] As a result, the present invention can effectively solve the problem of pest birds in a particular area and minimize economic losses.

[0937] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0938] Step 1:

[0939] A user installs a high-performance microphone device in a specific area and starts collecting audio data.

[0940] Input: Animal sounds

[0941] Output: Raw audio data

[0942] How it works: A microphone device collects and temporarily stores audio data 24 / 7, then transmits the data to a server over the Internet in real time.

[0943] Step 2:

[0944] The server receives the audio data in real time and performs preprocessing.

[0945] Input: Raw audio data

[0946] Output: Preprocessed audio data

[0947] What it does: Improve data quality by performing noise reduction (removing unwanted noise) and adjusting the sampling rate. This is done using Python libraries (e.g. Sounddevice, pyaudio).

[0948] Step 3:

[0949] The server inputs the pre-processed speech data into an artificial intelligence model to analyze speech features and patterns.

[0950] Input: Preprocessed audio data

[0951] Output: Analysis results on call characteristics and patterns

[0952] What it does: Runs an artificial intelligence model (e.g., TensorFlow or PyTorch) to extract features such as frequency, pitch, and rhythm from animal sounds, thereby identifying which sounds have meaning.

[0953] Step 4:

[0954] The server generates new sounds based on the analysis results.

[0955] Input: Analysis results of call characteristics and patterns

[0956] Output: Generated bird sounds file

[0957] What it does: It uses Python libraries (e.g., librosa, pydub) to generate audio files based on the analysis results, tailored to specific purposes, such as scaring or attracting animals.

[0958] Step 5:

[0959] The generated sound file is sent to speakers installed around the store and played back.

[0960] Input: Generated bird sound file

[0961] Output: Played cry

[0962] Specific operation: The generated sound file is sent to a speaker and automatically played at a specified time and under specified conditions. Users can set and adjust the playback timing and sound type via a smartphone application.

[0963] Step 6:

[0964] The user operates a smartphone application to adjust the type of generated sounds and their playback timing.

[0965] Input: User settings and operations

[0966] Output: Change the playback timing and sound type settings

[0967] How it works: The type of bird call generated and the timing of its playback can be changed in real time through the smartphone application's operation screen, making it possible to effectively repel pest birds with the optimal timing and sound.

[0968] 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.

[0969] This invention relates to a system that collects animal calls, such as those of pest birds like crows and starlings, in a specific area, analyzes and processes the data, and generates new animal calls. This system is combined with an emotion engine that recognizes the user's emotions, and has the function of playing back the generated animal calls to control the animal's behavior.

[0970] System Configuration

[0971] Collection Method

[0972] Users install microphone devices in specific areas (e.g., urban parks or agricultural areas), which collect real-time animal audio data within the area. The microphone devices are capable of transmitting the audio data to a server via the Internet.

[0973] Pretreatment

[0974] The server receives the collected audio data and performs noise reduction and sampling rate adjustment, improving the quality of the data and increasing the accuracy of analysis by the AI ​​model.

[0975] AI-powered analysis

[0976] The AI ​​model implemented on the server receives preprocessed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of the calls to determine which calls signal danger and which calls attract.

[0977] generation means

[0978] The server generates new bird calls based on the results of the AI ​​model's analysis. These calls can be used for specific purposes, such as to scare away harmful birds or to attract specific animals.

[0979] Emotion Engine

[0980] The emotion engine receives the user's voice and facial expression data as input and analyzes the user's emotional state. Based on the results of this emotion engine, the server can dynamically adjust the sounds it generates and the timing of their playback.

[0981] Regeneration means

[0982] The generated sounds are played back through the device (speaker) at the specified time and under the specified conditions. Users can use the management screen or application to adjust the type of sound, playback timing, and emotion engine settings.

[0983] Specific examples

[0984] Collecting bird calls

[0985] Users install high-performance microphone devices around markets and agricultural areas, which collect voice data 24 hours a day and send the audio files to a server every hour.

[0986] Preprocessing and AI analysis

[0987] The server receives the transmitted audio data, reduces noise and adjusts the sampling rate, then feeds it into an AI model that identifies specific sounds that crows make when they sense danger, or when they find food, for example.

[0988] Call generation

[0989] Users can send requests to the server to generate specific sounds based on the analysis results of the AI ​​model, for example, sounds that crows perceive as dangerous, to scare them away from the market.

[0990] Using the Emotion Engine

[0991] The server uses an emotion engine to analyze the user's emotional state: for example, if the user is feeling anxious or irritated, it generates a stronger danger sound accordingly and plays it immediately.

[0992] Playback of bird calls

[0993] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the generated sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and they will avoid it.

[0994] In this way, the present invention can effectively solve the problem of pest birds in a specific area. By using this system, economic losses can be minimized and people's quality of life can be improved. By combining it with an emotion engine, more effective measures can be implemented according to the user's emotions.

[0995] The processing flow will be explained below.

[0996] Step 1:

[0997] Users install high-performance microphone devices in specific areas, such as parks, farmland, and around markets where pest birds tend to gather. The microphone devices are designed to collect animal sounds and sounds.

[0998] Step 2:

[0999] The terminal (microphone device) collects animal sounds in real time and sends them to the server in the form of audio files. The frequency of transmission is, for example, once every hour. This allows for continuous data collection.

[1000] Step 3:

[1001] The server receives the voice data sent from the device and stores it in a database. The data is organized and managed by specific area.

[1002] Step 4:

[1003] The server applies noise reduction to the received audio data, eliminating environmental noise and making the target animal's call clearer. Noise reduction is performed using specific signal processing algorithms.

[1004] Step 5:

[1005] The server adjusts the sampling rate of the data after noise reduction processing, thereby unifying the quality of the audio data and converting it into a format suitable for the AI ​​model.

[1006] Step 6:

[1007] The server then inputs the pre-processed audio data into the AI ​​model, which uses deep learning algorithms to analyze the features (such as frequency, pitch, and rhythm) and patterns of the bird's calls.

[1008] Step 7:

[1009] The server generates new cries based on the analysis results of the AI ​​model. For example, it uses synthetic voice technology to generate cries that crows make when they sense danger, or cries that attract specific animals.

[1010] Step 8:

[1011] The server sends the generated sound file to the terminal (speaker) along with specific conditions (e.g., playback time and playback conditions).

[1012] Step 9:

[1013] The device (speaker) plays the received sound file at the specified time and under the specified conditions. Playback is automatic, but users can also set a playback schedule via the management screen or application.

[1014] Step 10:

[1015] The server analyzes the user's emotional state using an emotion engine, which receives the user's voice and facial expression data as input and determines the user's emotional state (e.g., anxiety, irritation, joy, etc.).

[1016] Step 11:

[1017] The server dynamically adjusts the type and timing of the sounds it generates based on the analysis results of the emotion engine. For example, if the user feels anxious, it will generate a stronger sound that signals danger and play it immediately.

[1018] Step 12:

[1019] Using the system's control screen or application, users can adjust the type of calls generated, their timing, and even the emotion engine settings, allowing for quick and effective solutions to pest bird problems in specific areas.

[1020] Example 2

[1021] 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."

[1022] In conventional animal behavior control systems, it is difficult to respond to the user's emotions and real-time situations when generating and playing back specific bird sounds after collecting and analyzing them. As a result, it is not possible to effectively repel pest birds and to alleviate the user's anxiety and frustration. The present invention aims to solve these problems.

[1023] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1024] In this invention, the server includes means for collecting animal sound data in a specific area, preprocessing means for performing noise reduction and sampling rate adjustment on the collected sound data, means for analyzing the preprocessed sound data and executing an AI model for identifying the characteristics and patterns of animal sounds, means for generating new sounds based on the analysis results of the AI ​​model, means for executing an emotion recognition engine for dynamically adjusting the type and playback timing of the generated sounds, and means for playing the generated sounds at specific times and under specific conditions. This makes it possible to generate and play optimal sounds in real time according to the user's emotions and situation, thereby effectively preventing damage caused by pest birds.

[1025] "Specific areas" refer to areas such as urban parks, agricultural areas, and around markets where animal behavior and sounds are frequently observed.

[1026] "Animal audio data" refers to data collected from the cries and sounds made by animals, including pest birds such as crows and starlings.

[1027] "Means of collection" refers to the function of using microphone devices and sensors to collect animal sounds in a specific area and send them to a server.

[1028] "Preprocessing means" refers to a function that performs noise reduction and sampling rate adjustment on collected audio data to improve data quality.

[1029] "AI model" refers to an algorithm or machine learning model that analyzes the characteristics and patterns of animal sounds and uses them for classification or specific purposes.

[1030] "Means for executing an AI model" refers to the functionality that receives preprocessed audio data as input and performs analysis using an AI model.

[1031] "Means for generating new bird calls" refers to the function of generating new bird calls for specific purposes (such as repelling harmful birds or attracting animals) based on the analysis results of the AI ​​model.

[1032] An "emotion recognition engine" refers to a function that analyzes the user's voice and facial expression data and recognizes the user's emotional state in real time.

[1033] "Means for playback" refers to the function of playing the generated sounds through a terminal (e.g., speaker) at a specified time and under specified conditions.

[1034] "Control Screen or Application" refers to the interface or software that a user uses to adjust the type of sounds generated, their playback timing, and the settings of the emotion recognition engine.

[1035] This invention relates to a system that collects, analyzes, generates, and plays back animal sound data in a specific area. This system collects the calls of pest birds such as crows and starlings, analyzes them using an AI model, generates new calls, and plays them back at specific times and under specific conditions. It also incorporates an emotion recognition engine that recognizes the user's emotions, enabling the system to dynamically generate and play back animal sounds according to the user's emotions and circumstances.

[1036] System configuration

[1037] 1. Collection of audio data

[1038] Users install high-performance microphone devices in specific areas (such as urban parks or agricultural areas), which collect animal sounds 24 hours a day and transmit the audio data to a server via the Internet at regular intervals.

[1039] 2. Preprocessing of audio data

[1040] The server performs noise reduction and sampling rate adjustment on the received audio data, improving the quality of the audio data and increasing the accuracy of analysis by the AI ​​model. Specifically, preprocessing is performed using Python and libraries (e.g., librosa).

[1041] 3. Analysis using AI models

[1042] Using the preprocessed audio data as input, an AI model implemented on the server analyzes the characteristics of the bird's calls (frequency, pitch, rhythm, etc.) and identifies specific call patterns using TensorFlow or PyTorch.

[1043] 4. Sound production

[1044] The user requests the server to generate a new bird cry based on the analysis results of the AI ​​model. The server then uses a generative AI model (e.g., GAN or WaveNet) to generate a bird cry with specific characteristics.

[1045] 5. Use of Emotion Recognition Engine

[1046] The emotion recognition engine analyzes the user's voice and facial expression data to recognize their emotional state. The server dynamically adjusts the sounds generated and the playback timing based on this emotional information. A deep learning model is used for emotion recognition.

[1047] 6. Playback of bird calls

[1048] The generated sounds are played back through the device (speaker) at specific times and under specific conditions. Users can adjust the type of sound and playback timing using the management screen or application. Specifically, the speaker uses an RTC (real-time clock) to play sounds at set times.

[1049] Examples and prompts

[1050] Specific examples

[1051] 1. Audio data collection:

[1052] A microphone device installed by a user in a city park transmits bird call data to a server every hour.

[1053] 2. Preprocessing the audio data:

[1054] The data received by the server is noise reduced using the librosa library and adjusted to a sampling rate of 16kHz.

[1055] 3. Analysis by AI model:

[1056] The server uses a TensorFlow model to extract features from the audio data and identify specific call patterns.

[1057] 4. Sound production:

[1058] The user sends a request to generate a "sound that makes a crow feel threatened" via a web interface, and the server generates it using GAN.

[1059] 5. Use of Emotion Recognition Engine:

[1060] The emotion engine analyzes the user's voice data, detects when the user is feeling irritated, and generates a powerful warning sound.

[1061] 6. Playback of the call:

[1062] The speakers automatically play a warning call every morning before the market opens to discourage crows from approaching the market area.

[1063] Prompt Sentence Examples

[1064] Please provide a program that generates a strong warning sound to scare away pest birds based on data on crow calls collected by microphone devices installed in agricultural areas. If the user's emotion is "anxiety," the program will generate an even stronger sound.

[1065] In this way, the present invention can effectively solve the problem of pest birds in a specific area, enabling real-time responses based on user emotions, minimizing economic losses, and contributing to improving the quality of life of users.

[1066] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1067] Step 1:

[1068] Audio data collection

[1069] Input: A specific area where a microphone device is installed (such as a city park or agricultural area).

[1070] Data processing: The microphone device collects animal sounds 24 hours a day and stores the data in a buffer at regular intervals.

[1071] What it does: The microphone device compresses and temporarily stores the audio data, then sends it to the server using the HTTPS protocol.

[1072] Output: The audio data file sent to the server.

[1073] Step 2:

[1074] Audio data preprocessing

[1075] Input: The audio data file received by the server.

[1076] Data processing: The server uses the librosa library to perform noise reduction and sampling rate adjustment.

[1077] What happens: The server applies an algorithm to remove noise from the audio data and adjust it to a 16kHz sampling rate.

[1078] Output: Preprocessed high-quality audio data.

[1079] Step 3:

[1080] Analysis by AI model

[1081] Input: Preprocessed audio data.

[1082] Data calculation: An AI model (e.g., TensorFlow or PyTorch) on the server extracts features (frequency, pitch, rhythm) from the audio data and performs clustering and classification.

[1083] What it does: The server uses a Convolutional Neural Network (CNN) to analyze specific call patterns.

[1084] Output: Classification results for each call and corresponding feature data.

[1085] Step 4:

[1086] Call generation

[1087] Input: The analysis results of the AI ​​model and the user's request.

[1088] Data computation: The server uses a generative AI model (e.g., GAN or WaveNet) to generate new calls.

[1089] Specific operation: The server uses GAN to generate a new audio file with the specified features.

[1090] Output: Generated call sound files.

[1091] Step 5:

[1092] Using the Emotion Recognition Engine

[1093] Input: User's voice and facial expression data.

[1094] Data calculation: The server uses an emotion recognition engine to analyze the user's emotional state.

[1095] How it works: The server uses a deep learning model to detect emotions from the user's voice and facial expressions in real time.

[1096] Output: User's emotional state data (e.g., anxious, irritated, calm).

[1097] Step 6:

[1098] Playback of bird calls

[1099] Input: Generated sound files and user emotional state data.

[1100] Data processing: Dynamically adjust the type and timing of generated sounds based on the user's emotional state.

[1101] Specific behavior: The speaker uses RTC to play a chirp at the set time. Users can also set the value from the management screen.

[1102] Output: The actual sound played.

[1103] In this way, the system effectively solves the problem of pest birds in a specific area through each step of collecting, preprocessing, analyzing, generating, emotion-recognizing, and playing back animal sounds. The specific processing flow allows for the generation and playback of appropriate animal sounds in real time, enabling advanced countermeasures tailored to user needs.

[1104] (Application example 2)

[1105] 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."

[1106] The present invention relates to a system that collects and analyzes animal sounds and generates and plays appropriate animal sounds, particularly in industrial environments, to prevent animal intrusion and improve work efficiency and safety. Specifically, the present invention aims to provide a system that uses robots working in factories to generate sounds to efficiently repel nuisance birds and other animals and plays them in real time according to the emotional state of employees. Another challenge is to dynamically adjust and play animal sounds based on the user's emotions, which was not possible with conventional systems.

[1107] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1108] In this invention, the server includes means for collecting animal sound data in a specific area, means for analyzing the collected sound data and executing an artificial intelligence model that identifies characteristics and patterns of animal sounds, means for generating new sounds based on the analysis results of the artificial intelligence model, means for playing the generated sounds at specific times and under specific conditions, means for playing the generated sounds in real time using an application installed on the robot, and means for dynamically adjusting the generated sounds and their playback timing based on an emotion engine that recognizes the user's emotions. This makes it possible to efficiently repel harmful birds and other animals using robots working in factories, and to adjust and play appropriate sounds in real time according to the emotional state of employees.

[1109] definition statement

[1110] "Means for collecting animal sound data" is a general term for devices and associated technologies for recording animal sounds and sounds in a specific area.

[1111] The "means for implementing the artificial intelligence model" is a computer system that applies machine learning algorithms to analyze audio data and identify characteristics and patterns in animal sounds.

[1112] The "means for generating new animal sounds" refers to a technology that uses the analysis results of an artificial intelligence model to programmatically create animal sounds for specific purposes.

[1113] The "means for playing at a specific time or under specific conditions" refers to a device and a program for playing the generated sounds through an audio device according to a predetermined time or conditions.

[1114] "Means for playing back in real time sounds generated using an application installed on the robot" refers to technology that allows for instant playback of generated sounds through a software application within the robot.

[1115] "Means for dynamically adjusting the sounds generated and their playback timing based on an emotion engine" is a technology that recognizes the user's emotional state and changes the sounds generated and their playback timing in real time based on that data.

[1116] MODE FOR CARRYING OUT THE INVENTION

[1117] A specific method for carrying out the present invention will now be described.

[1118] In this invention, we will build a system that collects, analyzes, generates, and plays animal sounds using an application installed on a factory robot. The overall system consists of the following steps:

[1119] 1. Collection of audio data

[1120] High-performance microphone devices are installed inside the factory to collect animal sounds and cries in real time, and the collected audio data is sent to a server via the internet.

[1121] 2. Preprocessing of audio data

[1122] The server then applies noise reduction and sampling rate adjustment to the received audio data to improve the quality of the data, which improves the accuracy of subsequent analysis by the AI ​​model.

[1123] 3. Analysis of bird calls

[1124] The artificial intelligence model (e.g., bird_sound_model.h5) implemented on the server receives preprocessed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of bird calls. This analysis determines the meaning of a particular call.

[1125] 4. Sound production

[1126] Based on the analysis of the AI ​​model, the server generates new sounds to scare away animals or attract specific animals.

[1127] 5. Use of Emotion Engine

[1128] The server is equipped with an emotion engine that receives human voice and facial expression data as input and analyzes the user's emotional state. Based on the results of the emotion engine, the generated sounds and their playback timing are dynamically adjusted.

[1129] 6. Playback of bird calls

[1130] The generated sounds are played back through speakers in the factory at specified times and under specified conditions, and users can use the application to adjust the type and timing of the sounds, as well as the emotion engine settings.

[1131] Specific examples

[1132] For example, if a crow is cawing in a factory, the audio data is collected through a microphone device and analyzed by the server. Based on the analysis results, a sound that the crow perceives as dangerous is generated and played through the speakers to scare the crow away. Furthermore, the emotion engine dynamically adjusts the audio to be more effective when an employee feels irritated or anxious.

[1133] Prompt Sentence Examples

[1134] "Collect the sounds of crows cawing and generate a call that signals danger."

[1135] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1136] Program processing steps

[1137] Step 1:

[1138] Audio data collection

[1139] Input: A microphone device to collect animal sounds in a specific area

[1140] How it works: Microphone devices installed in factories record animal sounds and voices 24 hours a day.

[1141] Output: The collected audio data is sent to a server via the Internet.

[1142] Step 2:

[1143] Audio data preprocessing

[1144] Input: Collected audio data

[1145] Operation: The server performs noise reduction on the received audio data and adjusts the sampling rate appropriately. Specifically, it removes noise and resamples the data to improve its quality.

[1146] Output: Pre-processed high-quality audio data

[1147] Step 3:

[1148] Analysis of bird calls

[1149] Input: Preprocessed audio data

[1150] How it works: An AI model implemented on the server receives preprocessed audio data as input and analyzes it, extracting features such as frequency, pitch, and rhythm to analyze the bird's call patterns.

[1151] Output: Analysis results, including characteristics and patterns of bird calls

[1152] Step 4:

[1153] Call generation

[1154] Input: Analysis results from an artificial intelligence model

[1155] How it works: The server generates new sounds based on the analysis results, such as a specific sound to scare away crows or a sound to attract specific animals.

[1156] Output: The new call generated.

[1157] Step 5:

[1158] Using the Emotion Engine

[1159] Input: User's voice and facial expression data

[1160] How it works: The server uses an emotion engine to analyze the user's emotional state, including the user's tone of voice and facial expressions. For example, if it determines that the user is feeling anxious or irritated, it dynamically adjusts the sounds it generates and the timing of their playback based on that information.

[1161] Output: Optimal sound generation and playback settings based on the user's emotional state

[1162] Step 6:

[1163] Playback of bird calls

[1164] Input: Generated sounds and the results of adjustments made by the emotion engine

[1165] How it works: The generated sounds are played through speakers in the factory based on preset times and conditions. The timing and type of sounds are set and adjusted through the application.

[1166] Output: Animal noises played in real time through speakers in the factory, resulting in animals being chased away from the factory.

[1167] An example of a prompt to ensure proper behavior is: "Collect the sounds of crows cawing and generate a call that indicates danger."

[1168] In this way, by performing appropriate data processing and calculations at each step, a system that efficiently controls animal behavior can be realized.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] [Fourth embodiment]

[1173] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1174] 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.

[1175] 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).

[1176] 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.

[1177] 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.

[1178] 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).

[1179] 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.

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] 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.

[1185] 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."

[1186] This invention relates to a system that collects the calls of animals such as crows and starlings, which are considered pest birds, in a specific area, analyzes and processes the data, and generates new calls. This system has the function of replaying the generated calls in order to control the behavior of the animals.

[1187] System Configuration

[1188] Collection Method

[1189] Users install microphone devices in specific areas (e.g., urban parks or agricultural areas), which collect real-time animal audio data within the area. The microphone devices are capable of transmitting the audio data to a server via the Internet.

[1190] Pretreatment

[1191] The server receives the collected audio data and performs noise reduction and sampling rate adjustment, improving the quality of the data and increasing the accuracy of analysis by the AI ​​model.

[1192] AI-powered analysis

[1193] The AI ​​model implemented on the server receives pre-processed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of the calls, allowing it to identify which calls signal danger and which calls attract.

[1194] generation means

[1195] The server generates new sounds based on the analysis results of the AI ​​model. These sounds can be used for specific purposes, such as warning of danger or attracting specific animals.

[1196] Regeneration means

[1197] The generated sounds are played back through the device (speaker) at the specified time and under the specified conditions. Users can set and adjust the type of sound and playback timing using the management screen or application.

[1198] Specific examples

[1199] Collecting bird calls

[1200] Users install high-performance microphone devices around markets and agricultural areas, which collect voice data 24 hours a day and send the audio files to a server every hour.

[1201] Preprocessing and AI analysis

[1202] The server receives the transmitted audio data, reduces noise and adjusts the sampling rate, then feeds it into an AI model that identifies specific sounds that crows make when they sense danger, or when they find food, for example.

[1203] Call generation

[1204] Users can send requests to the server to generate specific sounds based on the analysis results of the AI ​​model, for example, sounds that crows perceive as dangerous, to scare them away from the market.

[1205] Playback of bird calls

[1206] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the generated sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and they will avoid it.

[1207] In this way, the present invention can effectively solve the problem of pest birds in a specific area, minimizing economic losses and improving people's quality of life.

[1208] The processing flow will be explained below.

[1209] Step 1:

[1210] Users install microphone devices in specific areas, such as parks, farmland, and areas around markets where pest birds tend to gather. The microphone devices are used to collect animal audio data in real time.

[1211] Step 2:

[1212] The terminal (microphone device) collects animal voice data in real time and sends it to the server. The transmission frequency is, for example, once every hour or at a specified interval. The voice data is sent in the form of an audio file.

[1213] Step 3:

[1214] The server receives the voice data sent from the device and stores it in a database. The received data is organized by region and managed in a folder structure.

[1215] Step 4:

[1216] The server then performs noise reduction on the received audio data, which removes environmental noise and makes the target animal's call clearer. Noise reduction is performed using a signal processing algorithm.

[1217] Step 5:

[1218] The server adjusts the sampling rate of the noise-reduced data, ensuring that the audio data is input to the AI ​​model with consistent quality. The sampling rate is the process of setting the sampling frequency.

[1219] Step 6:

[1220] The server then inputs the pre-processed audio data into an AI model, which uses a trained deep learning algorithm to analyze the characteristics and patterns of animal calls, identifying calls that signal danger or attract animals.

[1221] Step 7:

[1222] The server generates new crow calls based on the analysis results obtained from the AI ​​model. For example, it uses synthetic voice technology to reproduce specific call patterns, generating calls that crows perceive as dangerous or calls that attract them.

[1223] Step 8:

[1224] The server sends the generated sound file to the device (speaker) based on specific settings, including the playback time and playback conditions.

[1225] Step 9:

[1226] The device (speaker) plays the bird sound file at the specified time and under the specified conditions. The bird sound is automatically played according to the playback schedule set by the user.

[1227] Step 10:

[1228] Users can use the system's control screen or application to adjust the type of calls generated and the timing of their playback, monitor the effectiveness, and change settings as needed to quickly and effectively resolve pest bird problems in a specific area.

[1229] Example 1

[1230] 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."

[1231] Conventional methods for controlling pest birds typically involve the use of physical barriers or chemical repellents. However, these methods are costly and can have a negative impact on the environment. Furthermore, these measures only provide temporary results and do not provide a fundamental solution. Furthermore, the lack of precise methods for controlling animal behavior makes it difficult to effectively control pest birds.

[1232] 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.

[1233] In this invention, the server includes means for collecting animal sound data in a specific area, means for preprocessing the collected sound data, means for analyzing the preprocessed sound data and executing an AI model that identifies its features and patterns, means for generating new calls based on the analysis results of the AI ​​model, and means for playing the generated calls at specific times and under specific conditions, thereby making it possible to effectively solve the problem of pest birds in a specific area and minimize economic losses.

[1234] "Specific region" refers to a specific area set aside for collecting animal sound data.

[1235] "Animal audio data" refers to audio information such as sounds and cries made by animals.

[1236] "Collection means" refers to the equipment or technology used to obtain animal audio data, including microphones and audio collection devices.

[1237] The "pre-processing means" refers to processing performed to improve the quality of collected audio data. Specifically, this includes noise reduction and sampling rate adjustment.

[1238] "Means for implementing artificial intelligence models" refers to algorithms or programs that analyze collected audio data to identify features and patterns, including models that use deep learning or neural networks.

[1239] "Means for generating new bird calls" refers to technology for creating new bird call data based on the analysis results of an artificial intelligence model.

[1240] "Means for playing" refers to a device or program for playing the generated call at a specified time and under specified conditions. Specifically, this includes a speaker and playback control software.

[1241] "Noise reduction" refers to the process of removing unnecessary noise from audio data.

[1242] "Sampling rate adjustment" refers to the process of appropriately setting or changing the sampling frequency of audio data.

[1243] "Administration screen or application" refers to the user interface for configuring and managing the system. Specifically, this includes web applications and mobile applications.

[1244] This invention relates to a system that collects animal calls, such as those of pest birds, in a specific area, analyzes and processes the data, and generates and plays back new calls. This system has the function of playing back the generated calls in order to control the behavior of animals.

[1245] System Configuration

[1246] Collection Method

[1247] A user installs a high-performance microphone device in a specific area (e.g., a city park or an agricultural area). The microphone device has the function of transmitting collected voice data to a server via the Internet. The user installs the microphone device in an appropriate location and uses a setting application to configure the Internet connection and the server address.

[1248] Pretreatment means

[1249] The server performs noise reduction and sampling rate adjustment on the audio data received from the microphone device. Specifically, the server uses the Python library "librosa" to read the audio data, perform noise reduction, and adjust the sampling rate to 44.1 kHz.

[1250] AI analysis means

[1251] The server then feeds the preprocessed audio data into an AI model, which is trained using TensorFlow to analyze the features (such as frequency, pitch, and rhythm) and patterns of the calls, and determines the meaning of a particular call (for example, whether it signals danger or attracts a mate).

[1252] generation means

[1253] The server generates new sounds based on the analysis results of the AI ​​model. Generative adversarial networks (GANs) can be used for generation. For example, it can generate danger sounds to scare off specific animals.

[1254] Regeneration means

[1255] The generated sounds are played through the device (speaker) under conditions specified by the user. The device receives the sound files sent from the server and plays them automatically at the set time (for example, 6:00 every morning). The user can adjust the playback timing and type of sound using the management screen or application.

[1256] Specific examples

[1257] Collecting bird calls

[1258] Users install microphone devices around markets and agricultural areas, which collect audio data 24 hours a day and send the audio files to a server every hour.

[1259] Preprocessing and AI analysis

[1260] The server receives the collected audio data, performs noise reduction and sampling rate adjustment, and then feeds the pre-processed data into an AI model to identify specific sounds that crows make when they sense danger or find food.

[1261] Call generation

[1262] The user sends a request to the server based on the analysis results of the AI ​​model. For example, the user can request that a sound be generated that will scare crows away from the market.

[1263] Playback of bird calls

[1264] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and discourage them from coming near it.

[1265] Example prompts for generative AI models

[1266] "Generate a sound that makes crows feel threatened."

[1267] In this way, the present invention can effectively solve the problem of pest birds in a specific area, minimize economic losses, and contribute to improving people's quality of life.

[1268] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1269] Program processing flow

[1270] Step 1: Collecting audio data

[1271] Users install high-performance microphone devices in specific areas (for example, around markets or agricultural areas). These microphone devices collect animal sounds 24 hours a day. The collected audio data is sent to a server via the Internet. Users connect the microphone devices to the network using a dedicated configuration application and set the server address.

[1272] Input: Ambient audio data

[1273] Output: Raw audio data

[1274] Specifically, the user places the microphone device in an appropriate position, establishes an Internet connection, and then starts collecting voice data.

[1275] Step 2: Preprocessing the audio data

[1276] The server receives the transmitted audio data and performs pre-processing: it applies a noise reduction algorithm (e.g., spectral subtraction) and adjusts the sampling rate to 44.1 kHz.

[1277] Input: Raw audio data

[1278] Output: Preprocessed audio data

[1279] Specifically, the server uses the Python library "librosa" to read the audio data, perform noise reduction, and reset the sampling rate.

[1280] Step 3: AI analysis of voice data

[1281] The server feeds the preprocessed audio data into an AI model, trained using TensorFlow, that analyzes the call features (such as frequency, pitch, and rhythm) and patterns to identify the meaning of a particular call.

[1282] Input: Preprocessed audio data

[1283] Output: Call feature data and classification results

[1284] Specifically, the server inputs the preprocessed data into the AI ​​model, which then performs feature extraction and pattern recognition and outputs the analysis results.

[1285] Step 4: Generate the call

[1286] The server generates new sounds based on the analysis results of the AI ​​model. For example, it can use GAN (generative adversarial network) to generate sounds that crows sense are dangerous.

[1287] Input: Call feature data and classification results

[1288] Output: Generated bird sounds file

[1289] Specifically, the server runs a sound generation algorithm based on the analysis results, converts the generated audio data into WAV format, and saves it in a specified folder.

[1290] Step 5: Play the sound

[1291] The generated sound files are sent to terminals (speakers installed around the market). The terminals automatically play the sounds at specified times and under specified conditions. Users can adjust the playback timing and type of sound using the management screen or application.

[1292] Input: Generated bird sound file

[1293] Output: Played cry

[1294] Specifically, the device receives the sound file sent from the server and automatically plays it at the set time. The user accesses the management screen and makes requests to change the playback timing or type of sound.

[1295] In this way, by clearly indicating the specific operations, inputs, and outputs at each processing step, the operation of the entire system can be understood in concrete detail.

[1296] (Application example 1)

[1297] 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."

[1298] In the past, the problem of pest birds in specific areas has been a headache for many people. Especially around brick-and-mortar stores, pest birds damage merchandise and facilities, so effective means of preventing this have been sought. However, existing measures have been limited and not sustainably effective. This has caused significant stress and economic losses for store managers and customers. The present invention aims to solve this problem, effectively manage the problem of pest birds in specific areas, and minimize economic losses.

[1299] 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.

[1300] In this invention, the server includes an acoustic data collection means for collecting animal sound data, a means for analyzing the collected acoustic data and executing an artificial intelligence model for identifying characteristics and patterns of animal cries, a generation means for generating new animal cries based on the analysis results of the artificial intelligence model, an acoustic output means for playing the generated cries at specific times and under specific conditions, and an acoustic output device for playing the generated cries in the vicinity of a specific area. This makes it possible to play the generated warning cries from the acoustic output devices installed in the vicinity of a store, thereby effectively repelling harmful birds.

[1301] "Animals" refers to wildlife such as crows and starlings that live in a particular area.

[1302] "Audio data" refers to audio information such as animal sounds recorded in digital format.

[1303] "Acoustic data collection means" refers to equipment or technology for collecting animal sounds using devices such as microphones.

[1304] "Artificial intelligence models" are algorithms such as machine learning models and deep learning models that identify the characteristics and patterns of animal sounds.

[1305] "Generation means" refers to the technology or equipment used to synthesize new bird calls based on the analysis results of the artificial intelligence model.

[1306] "Audio output means" refers to a device such as a speaker for playing back the generated sounds.

[1307] "Sound output devices" are sound equipment such as speakers and PA systems that are installed around the store to play sounds generated to scare away animals.

[1308] The "operation screen" is an interface that allows the user to adjust the type of generated sounds and their playback timing.

[1309] An "application" is software that is installed on a smartphone, tablet, etc. and provides an operating screen.

[1310] To implement this invention, a system is required to collect and analyze animal sound data from a specific area, and generate and play new animal sounds. The main components of this system and their operation are described in detail below.

[1311] First, sound data is collected using acoustic data collection means, specifically, high-performance microphone devices. The microphone devices are installed in specific areas and collect animal sounds 24 hours a day. The devices transmit the sound data in real time to a server via the Internet.

[1312] The server then receives the collected audio data and performs preprocessing, which includes noise reduction and sampling rate adjustment. Specifically, Python libraries (e.g., Sounddevice and pyaudio) are used to reduce noise and adjust the sampling rate to a uniform level. This preprocessing improves the quality of the data and increases the accuracy of analysis by the artificial intelligence model.

[1313] The pre-processed audio data is then analyzed by an artificial intelligence model, which analyzes the characteristics (e.g., frequency, pitch, rhythm) and patterns of animal calls. This analysis can identify which calls signal danger or attract specific animals. The artificial intelligence model uses deep learning models (e.g., TensorFlow and PyTorch).

[1314] Next, based on the analysis results of the AI ​​model, the server generates new sounds. These sounds are used for specific purposes (e.g., to scare away animals or attract animals). Python libraries (e.g., librosa, pydub) are used to generate audio files based on the analysis results.

[1315] Finally, the generated sounds are played back by the audio output means, specifically speakers installed around the store. The speakers play the sounds according to pre-set times and conditions. The user can set and adjust the type of sounds generated and the timing of their playback through a smartphone application. This application provides the user with an operation screen and runs on the smartphone.

[1316] As a concrete example, consider the problem of crows gathering around a city park. By deploying this system, it is possible to generate sounds that crows dislike and play them from speakers at a specific time each day to scare them away.

[1317] Examples of prompts include:

[1318] "We are having trouble with crows gathering around a market in Tokyo. We would like to create a system that generates sounds that crows dislike in this area and plays them periodically. Please place microphones and speakers around the store and generate prompt sentences that collect, analyze, generate, and play back the sounds of crows."

[1319] As a result, the present invention can effectively solve the problem of pest birds in a particular area and minimize economic losses.

[1320] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1321] Step 1:

[1322] A user installs a high-performance microphone device in a specific area and starts collecting audio data.

[1323] Input: Animal sounds

[1324] Output: Raw audio data

[1325] How it works: A microphone device collects and temporarily stores audio data 24 / 7, then transmits the data to a server over the Internet in real time.

[1326] Step 2:

[1327] The server receives the audio data in real time and performs preprocessing.

[1328] Input: Raw audio data

[1329] Output: Preprocessed audio data

[1330] What it does: Improve data quality by performing noise reduction (removing unwanted noise) and adjusting the sampling rate. This is done using Python libraries (e.g. Sounddevice, pyaudio).

[1331] Step 3:

[1332] The server inputs the pre-processed speech data into an artificial intelligence model to analyze speech features and patterns.

[1333] Input: Preprocessed audio data

[1334] Output: Analysis results on call characteristics and patterns

[1335] What it does: Runs an artificial intelligence model (e.g., TensorFlow or PyTorch) to extract features such as frequency, pitch, and rhythm from animal sounds, thereby identifying which sounds have meaning.

[1336] Step 4:

[1337] The server generates new sounds based on the analysis results.

[1338] Input: Analysis results of call characteristics and patterns

[1339] Output: Generated bird sounds file

[1340] What it does: It uses Python libraries (e.g., librosa, pydub) to generate audio files based on the analysis results, tailored to specific purposes, such as scaring or attracting animals.

[1341] Step 5:

[1342] The generated sound file is sent to speakers installed around the store and played back.

[1343] Input: Generated bird sound file

[1344] Output: Played cry

[1345] Specific operation: The generated sound file is sent to a speaker and automatically played at a specified time and under specified conditions. Users can set and adjust the playback timing and sound type via a smartphone application.

[1346] Step 6:

[1347] The user operates a smartphone application to adjust the type of generated sounds and their playback timing.

[1348] Input: User settings and operations

[1349] Output: Change the playback timing and sound type settings

[1350] How it works: The type of bird call generated and the timing of its playback can be changed in real time through the smartphone application's operation screen, making it possible to effectively repel pest birds with the optimal timing and sound.

[1351] 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.

[1352] This invention relates to a system that collects animal calls, such as those of pest birds like crows and starlings, in a specific area, analyzes and processes the data, and generates new animal calls. This system is combined with an emotion engine that recognizes the user's emotions, and has the function of playing back the generated animal calls to control the animal's behavior.

[1353] System Configuration

[1354] Collection Method

[1355] Users install microphone devices in specific areas (e.g., urban parks or agricultural areas), which collect real-time animal audio data within the area. The microphone devices are capable of transmitting the audio data to a server via the Internet.

[1356] Pretreatment

[1357] The server receives the collected audio data and performs noise reduction and sampling rate adjustment, improving the quality of the data and increasing the accuracy of analysis by the AI ​​model.

[1358] AI-powered analysis

[1359] The AI ​​model implemented on the server receives preprocessed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of the calls to determine which calls signal danger and which calls attract.

[1360] generation means

[1361] The server generates new bird calls based on the results of the AI ​​model's analysis. These calls can be used for specific purposes, such as to scare away harmful birds or to attract specific animals.

[1362] Emotion Engine

[1363] The emotion engine receives the user's voice and facial expression data as input and analyzes the user's emotional state. Based on the results of this emotion engine, the server can dynamically adjust the sounds it generates and the timing of their playback.

[1364] Regeneration means

[1365] The generated sounds are played back through the device (speaker) at the specified time and under the specified conditions. Users can use the management screen or application to adjust the type of sound, playback timing, and emotion engine settings.

[1366] Specific examples

[1367] Collecting bird calls

[1368] Users install high-performance microphone devices around markets and agricultural areas, which collect voice data 24 hours a day and send the audio files to a server every hour.

[1369] Preprocessing and AI analysis

[1370] The server receives the transmitted audio data, reduces noise and adjusts the sampling rate, then feeds it into an AI model that identifies specific sounds that crows make when they sense danger, or when they find food, for example.

[1371] Call generation

[1372] Users can send requests to the server to generate specific sounds based on the analysis results of the AI ​​model, for example, sounds that crows perceive as dangerous, to scare them away from the market.

[1373] Using the Emotion Engine

[1374] The server uses an emotion engine to analyze the user's emotional state: for example, if the user is feeling anxious or irritated, it generates a stronger danger sound accordingly and plays it immediately.

[1375] Playback of bird calls

[1376] The generated crow sound file is sent to a terminal (a speaker installed around the market). The speaker automatically plays the generated sound every morning before the market opens. This makes the crows perceive the area around the market as a dangerous zone and they will avoid it.

[1377] In this way, the present invention can effectively solve the problem of pest birds in a specific area. By using this system, economic losses can be minimized and people's quality of life can be improved. By combining it with an emotion engine, more effective measures can be implemented according to the user's emotions.

[1378] The processing flow will be explained below.

[1379] Step 1:

[1380] Users install high-performance microphone devices in specific areas, such as parks, farmland, and around markets where pest birds tend to gather. The microphone devices are designed to collect animal sounds and sounds.

[1381] Step 2:

[1382] The terminal (microphone device) collects animal sounds in real time and sends them to the server in the form of audio files. The frequency of transmission is, for example, once every hour. This allows for continuous data collection.

[1383] Step 3:

[1384] The server receives the voice data sent from the device and stores it in a database. The data is organized and managed by specific area.

[1385] Step 4:

[1386] The server applies noise reduction to the received audio data, eliminating environmental noise and making the target animal's call clearer. Noise reduction is performed using specific signal processing algorithms.

[1387] Step 5:

[1388] The server adjusts the sampling rate of the data after noise reduction processing, thereby unifying the quality of the audio data and converting it into a format suitable for the AI ​​model.

[1389] Step 6:

[1390] The server then inputs the pre-processed audio data into the AI ​​model, which uses deep learning algorithms to analyze the features (such as frequency, pitch, and rhythm) and patterns of the bird's calls.

[1391] Step 7:

[1392] The server generates new cries based on the analysis results of the AI ​​model. For example, it uses synthetic voice technology to generate cries that crows make when they sense danger, or cries that attract specific animals.

[1393] Step 8:

[1394] The server sends the generated sound file to the terminal (speaker) along with specific conditions (e.g., playback time and playback conditions).

[1395] Step 9:

[1396] The device (speaker) plays the received sound file at the specified time and under the specified conditions. Playback is automatic, but users can also set a playback schedule via the management screen or application.

[1397] Step 10:

[1398] The server analyzes the user's emotional state using an emotion engine, which receives the user's voice and facial expression data as input and determines the user's emotional state (e.g., anxiety, irritation, joy, etc.).

[1399] Step 11:

[1400] The server dynamically adjusts the type and timing of the sounds it generates based on the analysis results of the emotion engine. For example, if the user feels anxious, it will generate a stronger sound that signals danger and play it immediately.

[1401] Step 12:

[1402] Using the system's control screen or application, users can adjust the type of calls generated, their timing, and even the emotion engine settings, allowing for quick and effective solutions to pest bird problems in specific areas.

[1403] Example 2

[1404] 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."

[1405] In conventional animal behavior control systems, it is difficult to respond to the user's emotions and real-time situations when generating and playing back specific bird sounds after collecting and analyzing them. As a result, it is not possible to effectively repel pest birds and to alleviate the user's anxiety and frustration. The present invention aims to solve these problems.

[1406] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1407] In this invention, the server includes means for collecting animal sound data in a specific area, preprocessing means for performing noise reduction and sampling rate adjustment on the collected sound data, means for analyzing the preprocessed sound data and executing an AI model for identifying the characteristics and patterns of animal sounds, means for generating new sounds based on the analysis results of the AI ​​model, means for executing an emotion recognition engine for dynamically adjusting the type and playback timing of the generated sounds, and means for playing the generated sounds at specific times and under specific conditions. This makes it possible to generate and play optimal sounds in real time according to the user's emotions and situation, thereby effectively preventing damage caused by pest birds.

[1408] "Specific areas" refer to areas such as urban parks, agricultural areas, and around markets where animal behavior and sounds are frequently observed.

[1409] "Animal audio data" refers to data collected from the cries and sounds made by animals, including pest birds such as crows and starlings.

[1410] "Means of collection" refers to the function of using microphone devices and sensors to collect animal sounds in a specific area and send them to a server.

[1411] "Preprocessing means" refers to a function that performs noise reduction and sampling rate adjustment on collected audio data to improve data quality.

[1412] "AI model" refers to an algorithm or machine learning model that analyzes the characteristics and patterns of animal sounds and uses them for classification or specific purposes.

[1413] "Means for executing an AI model" refers to the functionality that receives preprocessed audio data as input and performs analysis using an AI model.

[1414] "Means for generating new bird calls" refers to the function of generating new bird calls for specific purposes (such as repelling harmful birds or attracting animals) based on the analysis results of the AI ​​model.

[1415] An "emotion recognition engine" refers to a function that analyzes the user's voice and facial expression data and recognizes the user's emotional state in real time.

[1416] "Means for playback" refers to the function of playing the generated sounds through a terminal (e.g., speaker) at a specified time and under specified conditions.

[1417] "Control Screen or Application" refers to the interface or software that a user uses to adjust the type of sounds generated, their playback timing, and the settings of the emotion recognition engine.

[1418] This invention relates to a system that collects, analyzes, generates, and plays back animal sound data in a specific area. This system collects the calls of pest birds such as crows and starlings, analyzes them using an AI model, generates new calls, and plays them back at specific times and under specific conditions. It also incorporates an emotion recognition engine that recognizes the user's emotions, enabling the system to dynamically generate and play back animal sounds according to the user's emotions and circumstances.

[1419] System configuration

[1420] 1. Collection of audio data

[1421] Users install high-performance microphone devices in specific areas (such as urban parks or agricultural areas), which collect animal sounds 24 hours a day and transmit the audio data to a server via the Internet at regular intervals.

[1422] 2. Preprocessing of audio data

[1423] The server performs noise reduction and sampling rate adjustment on the received audio data, improving the quality of the audio data and increasing the accuracy of analysis by the AI ​​model. Specifically, preprocessing is performed using Python and libraries (e.g., librosa).

[1424] 3. Analysis using AI models

[1425] Using the preprocessed audio data as input, an AI model implemented on the server analyzes the characteristics of the bird's calls (frequency, pitch, rhythm, etc.) and identifies specific call patterns using TensorFlow or PyTorch.

[1426] 4. Sound production

[1427] The user requests the server to generate a new bird cry based on the analysis results of the AI ​​model. The server then uses a generative AI model (e.g., GAN or WaveNet) to generate a bird cry with specific characteristics.

[1428] 5. Use of Emotion Recognition Engine

[1429] The emotion recognition engine analyzes the user's voice and facial expression data to recognize their emotional state. The server dynamically adjusts the sounds generated and the playback timing based on this emotional information. A deep learning model is used for emotion recognition.

[1430] 6. Playback of bird calls

[1431] The generated sounds are played back through the device (speaker) at specific times and under specific conditions. Users can adjust the type of sound and playback timing using the management screen or application. Specifically, the speaker uses an RTC (real-time clock) to play sounds at set times.

[1432] Examples and prompts

[1433] Specific examples

[1434] 1. Audio data collection:

[1435] A microphone device installed by a user in a city park transmits bird call data to a server every hour.

[1436] 2. Preprocessing the audio data:

[1437] The data received by the server is noise reduced using the librosa library and adjusted to a sampling rate of 16kHz.

[1438] 3. Analysis by AI model:

[1439] The server uses a TensorFlow model to extract features from the audio data and identify specific call patterns.

[1440] 4. Sound production:

[1441] The user sends a request to generate a "sound that makes a crow feel threatened" via a web interface, and the server generates it using GAN.

[1442] 5. Use of Emotion Recognition Engine:

[1443] The emotion engine analyzes the user's voice data, detects when the user is feeling irritated, and generates a powerful warning sound.

[1444] 6. Playback of the call:

[1445] The speakers automatically play a warning call every morning before the market opens to discourage crows from approaching the market area.

[1446] Prompt Sentence Examples

[1447] Please provide a program that generates a strong warning sound to scare away pest birds based on data on crow calls collected by microphone devices installed in agricultural areas. If the user's emotion is "anxiety," the program will generate an even stronger sound.

[1448] In this way, the present invention can effectively solve the problem of pest birds in a specific area, enabling real-time responses based on user emotions, minimizing economic losses, and contributing to improving the quality of life of users.

[1449] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1450] Step 1:

[1451] Audio data collection

[1452] Input: A specific area where a microphone device is installed (such as a city park or agricultural area).

[1453] Data processing: The microphone device collects animal sounds 24 hours a day and stores the data in a buffer at regular intervals.

[1454] What it does: The microphone device compresses and temporarily stores the audio data, then sends it to the server using the HTTPS protocol.

[1455] Output: The audio data file sent to the server.

[1456] Step 2:

[1457] Audio data preprocessing

[1458] Input: The audio data file received by the server.

[1459] Data processing: The server uses the librosa library to perform noise reduction and sampling rate adjustment.

[1460] What happens: The server applies an algorithm to remove noise from the audio data and adjust it to a 16kHz sampling rate.

[1461] Output: Preprocessed high-quality audio data.

[1462] Step 3:

[1463] Analysis by AI model

[1464] Input: Preprocessed audio data.

[1465] Data calculation: An AI model (e.g., TensorFlow or PyTorch) on the server extracts features (frequency, pitch, rhythm) from the audio data and performs clustering and classification.

[1466] What it does: The server uses a Convolutional Neural Network (CNN) to analyze specific call patterns.

[1467] Output: Classification results for each call and corresponding feature data.

[1468] Step 4:

[1469] Call generation

[1470] Input: The analysis results of the AI ​​model and the user's request.

[1471] Data computation: The server uses a generative AI model (e.g., GAN or WaveNet) to generate new calls.

[1472] Specific operation: The server uses GAN to generate a new audio file with the specified features.

[1473] Output: Generated call sound files.

[1474] Step 5:

[1475] Using the Emotion Recognition Engine

[1476] Input: User's voice and facial expression data.

[1477] Data calculation: The server uses an emotion recognition engine to analyze the user's emotional state.

[1478] How it works: The server uses a deep learning model to detect emotions from the user's voice and facial expressions in real time.

[1479] Output: User's emotional state data (e.g., anxious, irritated, calm).

[1480] Step 6:

[1481] Playback of bird calls

[1482] Input: Generated sound files and user emotional state data.

[1483] Data processing: Dynamically adjust the type and timing of generated sounds based on the user's emotional state.

[1484] Specific behavior: The speaker uses RTC to play a chirp at the set time. Users can also set the value from the management screen.

[1485] Output: The actual sound played.

[1486] In this way, the system effectively solves the problem of pest birds in a specific area through each step of collecting, preprocessing, analyzing, generating, emotion-recognizing, and playing back animal sounds. The specific processing flow allows for the generation and playback of appropriate animal sounds in real time, enabling advanced countermeasures tailored to user needs.

[1487] (Application example 2)

[1488] 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."

[1489] The present invention relates to a system that collects and analyzes animal sounds and generates and plays appropriate animal sounds, particularly in industrial environments, to prevent animal intrusion and improve work efficiency and safety. Specifically, the present invention aims to provide a system that uses robots working in factories to generate sounds to efficiently repel nuisance birds and other animals and plays them in real time according to the emotional state of employees. Another challenge is to dynamically adjust and play animal sounds based on the user's emotions, which was not possible with conventional systems.

[1490] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1491] In this invention, the server includes means for collecting animal sound data in a specific area, means for analyzing the collected sound data and executing an artificial intelligence model that identifies characteristics and patterns of animal sounds, means for generating new sounds based on the analysis results of the artificial intelligence model, means for playing the generated sounds at specific times and under specific conditions, means for playing the generated sounds in real time using an application installed on the robot, and means for dynamically adjusting the generated sounds and their playback timing based on an emotion engine that recognizes the user's emotions. This makes it possible to efficiently repel harmful birds and other animals using robots working in factories, and to adjust and play appropriate sounds in real time according to the emotional state of employees.

[1492] definition statement

[1493] "Means for collecting animal sound data" is a general term for devices and associated technologies for recording animal sounds and sounds in a specific area.

[1494] The "means for implementing the artificial intelligence model" is a computer system that applies machine learning algorithms to analyze audio data and identify characteristics and patterns in animal sounds.

[1495] The "means for generating new animal sounds" refers to a technology that uses the analysis results of an artificial intelligence model to programmatically create animal sounds for specific purposes.

[1496] The "means for playing at a specific time or under specific conditions" refers to a device and a program for playing the generated sounds through an audio device according to a predetermined time or conditions.

[1497] "Means for playing back in real time sounds generated using an application installed on the robot" refers to technology that allows for instant playback of generated sounds through a software application within the robot.

[1498] "Means for dynamically adjusting the sounds generated and their playback timing based on an emotion engine" is a technology that recognizes the user's emotional state and changes the sounds generated and their playback timing in real time based on that data.

[1499] MODE FOR CARRYING OUT THE INVENTION

[1500] A specific method for carrying out the present invention will now be described.

[1501] In this invention, we will build a system that collects, analyzes, generates, and plays animal sounds using an application installed on a factory robot. The overall system consists of the following steps:

[1502] 1. Collection of audio data

[1503] High-performance microphone devices are installed inside the factory to collect animal sounds and cries in real time, and the collected audio data is sent to a server via the internet.

[1504] 2. Preprocessing of audio data

[1505] The server then applies noise reduction and sampling rate adjustment to the received audio data to improve the quality of the data, which improves the accuracy of subsequent analysis by the AI ​​model.

[1506] 3. Analysis of bird calls

[1507] The artificial intelligence model (e.g., bird_sound_model.h5) implemented on the server receives preprocessed audio data as input and analyzes the characteristics (frequency, pitch, rhythm, etc.) and patterns of bird calls. This analysis determines the meaning of a particular call.

[1508] 4. Sound production

[1509] Based on the analysis of the AI ​​model, the server generates new sounds to scare away animals or attract specific animals.

[1510] 5. Use of Emotion Engine

[1511] The server is equipped with an emotion engine that receives human voice and facial expression data as input and analyzes the user's emotional state. Based on the results of the emotion engine, the generated sounds and their playback timing are dynamically adjusted.

[1512] 6. Playback of bird calls

[1513] The generated sounds are played back through speakers in the factory at specified times and under specified conditions, and users can use the application to adjust the type and timing of the sounds, as well as the emotion engine settings.

[1514] Specific examples

[1515] For example, if a crow is cawing in a factory, the audio data is collected through a microphone device and analyzed by the server. Based on the analysis results, a sound that the crow perceives as dangerous is generated and played through the speakers to scare the crow away. Furthermore, the emotion engine dynamically adjusts the audio to be more effective when an employee feels irritated or anxious.

[1516] Prompt Sentence Examples

[1517] "Collect the sounds of crows cawing and generate a call that signals danger."

[1518] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1519] Program processing steps

[1520] Step 1:

[1521] Audio data collection

[1522] Input: A microphone device to collect animal sounds in a specific area

[1523] How it works: Microphone devices installed in factories record animal sounds and voices 24 hours a day.

[1524] Output: The collected audio data is sent to a server via the Internet.

[1525] Step 2:

[1526] Audio data preprocessing

[1527] Input: Collected audio data

[1528] Operation: The server performs noise reduction on the received audio data and adjusts the sampling rate appropriately. Specifically, it removes noise and resamples the data to improve its quality.

[1529] Output: Pre-processed high-quality audio data

[1530] Step 3:

[1531] Analysis of bird calls

[1532] Input: Preprocessed audio data

[1533] How it works: An AI model implemented on the server receives preprocessed audio data as input and analyzes it, extracting features such as frequency, pitch, and rhythm to analyze the bird's call patterns.

[1534] Output: Analysis results, including characteristics and patterns of bird calls

[1535] Step 4:

[1536] Call generation

[1537] Input: Analysis results from an artificial intelligence model

[1538] How it works: The server generates new sounds based on the analysis results, such as a specific sound to scare away crows or a sound to attract specific animals.

[1539] Output: The new call generated.

[1540] Step 5:

[1541] Using the Emotion Engine

[1542] Input: User's voice and facial expression data

[1543] How it works: The server uses an emotion engine to analyze the user's emotional state, including the user's tone of voice and facial expressions. For example, if it determines that the user is feeling anxious or irritated, it dynamically adjusts the sounds it generates and the timing of their playback based on that information.

[1544] Output: Optimal sound generation and playback settings based on the user's emotional state

[1545] Step 6:

[1546] Playback of bird calls

[1547] Input: Generated sounds and the results of adjustments made by the emotion engine

[1548] How it works: The generated sounds are played through speakers in the factory based on preset times and conditions. The timing and type of sounds are set and adjusted through the application.

[1549] Output: Animal noises played in real time through speakers in the factory, resulting in animals being chased away from the factory.

[1550] An example of a prompt to ensure proper behavior is: "Collect the sounds of crows cawing and generate a call that indicates danger."

[1551] In this way, by performing appropriate data processing and calculations at each step, a system that efficiently controls animal behavior can be realized.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] FIG. 9 illustrates 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 behaviors 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.

[1557] 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.

[1558] 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).

[1559] 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.

[1560] 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."

[1561] 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.

[1562] 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).

[1563] 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.

[1564] 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.

[1565] 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.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] The following is further disclosed regarding the above embodiment.

[1574] (Claim 1)

[1575] a means for collecting animal sound data in a specific area;

[1576] A means to run an AI model that analyzes the collected audio data and identifies characteristics and patterns in animal sounds; and

[1577] A means of generating new calls based on the analysis results of the AI ​​model;

[1578] A means for playing the generated call at a specific time or under specific conditions;

[1579] A system including:

[1580] (Claim 2)

[1581] 10. The system according to claim 1, further comprising a pre-processing means for performing noise reduction and sampling rate adjustment on the collected audio data.

[1582] (Claim 3)

[1583] 2. The system according to claim 1, further comprising means for providing a management screen or application for adjusting the type of generated sounds and playback timing.

[1584] "Example 1"

[1585] (Claim 1)

[1586] a means for collecting animal sound data in a specific area;

[1587] means for pre-processing the collected audio data;

[1588] means for executing an artificial intelligence model to analyze the preprocessed speech data and identify features and patterns therein;

[1589] A means for generating new calls based on the analysis results of the artificial intelligence model;

[1590] A means for playing the generated call at a specific time or under specific conditions;

[1591] A system including:

[1592] (Claim 2)

[1593] 10. The system of claim 1, further comprising pre-processing means for performing noise reduction and sampling rate adjustment.

[1594] (Claim 3)

[1595] 2. The system according to claim 1, further comprising means for providing a management screen or application for adjusting the type of generated sounds and playback timing.

[1596] "Application Example 1"

[1597] (Claim 1)

[1598] an acoustic data collection means for collecting animal sound data;

[1599] means for running an artificial intelligence model that analyzes the collected acoustic data and identifies characteristics and patterns in animal calls; and

[1600] A generating means for generating new cries based on the analysis results of the artificial intelligence model;

[1601] an audio output means for reproducing the generated cry at a specific time or under specific conditions;

[1602] an audio output device for playing the generated calls in a specific area;

[1603] A system including:

[1604] (Claim 2)

[1605] 10. The system of claim 1, further comprising a pre-processing means for performing noise reduction and sampling rate adjustment on the collected acoustic data.

[1606] (Claim 3)

[1607] 2. The system according to claim 1, further comprising means for providing an operation screen or application for adjusting the type and playback timing of the generated sounds.

[1608] "Example 2: Combining Emotion Engines"

[1609] (Claim 1)

[1610] a means for collecting animal sound data in a specific area;

[1611] a pre-processing means for performing noise reduction and sampling rate adjustment on the collected voice data;

[1612] a means for running an AI model that analyzes the pre-processed audio data and identifies features and patterns in animal sounds; and

[1613] A means of generating new calls based on the analysis results of the AI ​​model;

[1614] means for executing an emotion recognition engine to dynamically adjust the type and timing of the generated calls;

[1615] A means for playing the generated call at a specific time or under specific conditions;

[1616] A system including:

[1617] (Claim 2)

[1618] 10. The system of claim 1, further comprising means for providing a management screen or application.

[1619] (Claim 3)

[1620] 10. The system of claim 1, further comprising means for adjusting the type and timing of the generated calls.

[1621] "Application example 2 when combining emotion engines"

[1622] (Claim 1)

[1623] a means for collecting animal sound data in a specific area;

[1624] means for running an artificial intelligence model that analyzes the collected audio data and identifies characteristics and patterns in animal sounds; and

[1625] A means for generating new calls based on the analysis results of the artificial intelligence model;

[1626] A means for playing the generated call at a specific time or under specific conditions;

[1627] means for playing back in real time the sounds generated using an application installed on the robot;

[1628] A means for dynamically adjusting the sounds generated and their playback timing based on an emotion engine that recognizes the user's emotions;

[1629] A system including:

[1630] (Claim 2)

[1631] 10. The system according to claim 1, further comprising a pre-processing means for performing noise reduction and sampling rate adjustment on the collected audio data.

[1632] (Claim 3)

[1633] 10. The system according to claim 1, further comprising means for providing a management screen or application for adjusting the type of generated call and the timing of its reproduction. [Explanation of symbols]

[1634] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting animal sound data in a specific area; A means to run an AI model that analyzes the collected audio data and identifies characteristics and patterns in animal sounds; and A means of generating new calls based on the analysis results of the AI ​​model; A means for playing the generated call at a specific time or under specific conditions; A system including:

2. 2. The system according to claim 1, further comprising a pre-processing means for performing noise reduction and sampling rate adjustment on the collected audio data.

3. The system according to claim 1, further comprising means for providing a management screen or application for adjusting the type of generated cry and the timing of its reproduction.

Images