system

Abstract

We provide the system. [Solution] A means of filtering noise, A means of amplifying a specific sound, A means of analyzing audio data to report on the situation of disaster victims, A means of synchronizing multiple devices to determine the location of the sound source, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In rescue operations during large-scale disasters, noise emitted from aerial moving bodies and large machinery has become a factor hindering the rescue of disaster victims. Specifically, there is a problem that faint voices and breathing sounds of disaster victims are masked by the noise, making rapid rescue difficult.

Means for Solving the Problems

[0005] The present invention has means for effectively filtering noise and amplifying specific sounds derived from disaster victims. Further, it is provided with means for analyzing voice data and reporting the situation of disaster victims, whereby rescue team members can concentrate on important sounds. Also, by providing means for synchronizing a plurality of devices to accurately identify the position of a sound source, a system is constructed to enable rapid discovery of disaster victims.

[0006] "Methods for filtering noise" refer to functions that remove unwanted noise components from ambient sounds, allowing important sounds to be heard clearly.

[0007] "Means of amplifying specific sounds" refers to a function that picks up specific sounds, such as the voices and breathing sounds of disaster victims, and amplifies their volume to make them easier to hear.

[0008] "Means of analyzing audio data to report on the situation of disaster victims" refers to a function that analyzes audio data to derive information about the presence and situation of disaster victims, and applies the results to rescue operations.

[0009] "Means for synchronizing multiple devices to determine the location of a sound source" refers to a function that shares data among multiple sound detection devices and calculates the precise location of the sound source based on that location information. [Brief explanation of the drawing]

[0010] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0011] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0012] First, let's explain the terminology used in the following explanation.

[0013] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0014] In the following embodiments, a tagged RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by a processor.

[0015] In the following embodiments, a tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0016] In the following embodiments, a tagged communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages 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), or Bluetooth (registered trademark).

[0017] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0018] [First Embodiment]

[0019] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0020] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0021] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0022] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0023] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0024] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0025] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0026] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0027] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0028] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0029] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0030] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0031] The system for implementing the present invention integrates multiple earphone-type devices and a backend server system to filter noise during rescue operations and amplify specific sounds such as the voices and breathing sounds of victims for use by rescue workers. Each device collects ambient sounds in real time and transmits the data to the server via wireless communication.

[0032] The server is responsible for processing the collected audio data, effectively removing noise components using a generative AI model. During this process, time-frequency analysis techniques are used to filter and pick up faint voice signals from victims. Next, the detected specific sounds are amplified and retransmitted to earphones worn by rescue workers. This audio processing makes it possible to hear the voices of victims more clearly from beneath the rubble.

[0033] The server also has analytical capabilities, which allow it to report on the likelihood of victims and their situation based on audio data. For example, it can filter out sounds that are mistakenly identified as noise and convert sounds that appear to be human voices into text data for rescue workers.

[0034] Furthermore, this system synchronizes multiple earphones, thereby using triangulation technology to pinpoint the location of the sound source. This location information is plotted on a map, allowing rescue teams to quickly receive the precise location of victims.

[0035] As a concrete example, if rescue teams use this system on-site after a major earthquake, each team member can wear earphones and search for rubble while relying on the clear voices of victims transmitted from the server. Furthermore, based on the analyzed report data, it becomes possible to understand the situation of the victims and carry out more efficient rescue operations.

[0036] The present invention, possessing the above-described functions, has the effect of improving the success rate of life-saving operations by promptly providing important clues during rescue activities.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] When a user begins a rescue operation, each device (earphone) collects ambient sounds in real time. The microphone built into the earphone detects the sound, digitizes it, and saves it as data.

[0040] Step 2:

[0041] The terminal compresses the collected audio data and transmits it to the server using wireless communication technology. An audio codec is used to reduce data volume and enable rapid transfer.

[0042] Step 3:

[0043] The server analyzes the received audio data and applies a generative AI model to filter out ambient noise. By performing a Fourier transform and removing noise components in the frequency domain, it emphasizes important sounds.

[0044] Step 4:

[0045] The server amplifies specific sounds and transmits the amplified audio data to the terminal. It plays a particularly important role in making the voices and breathing sounds of disaster victims clearer and delivering them directly to rescue workers.

[0046] Step 5:

[0047] The server further analyzes the amplified audio data, converting human voice components and sounds that convey the situation into text, and informing the user. An AI model is used to estimate the presence and number of victims.

[0048] Step 6:

[0049] All devices worn by the user synchronize voice data detection information with each other and transmit location information to a server. Bluetooth or Wi-Fi is used to maintain synchronization between devices.

[0050] Step 7:

[0051] The server uses triangulation technology to pinpoint the location of the sound source based on the data transmitted from each terminal. It calculates the time difference and sound intensity difference of the received data and displays the estimated location of the victims on a map.

[0052] Step 8:

[0053] The server sends location information and analysis results to rescue workers' earphones, supporting rapid and efficient rescue operations. It provides necessary data in real time via voice and text information.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] At natural disaster and accident sites, there is a need to effectively detect faint sounds such as the voices and breathing sounds of victims and to quickly pinpoint their location. However, these specific sounds can be masked by surrounding noise, potentially significantly reducing the efficiency of rescue operations. It is necessary to solve this problem and increase the success rate of rescue operations.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for acquiring environmental information, means for removing noise using a generative model, and means for analyzing sound information and reporting the state of an individual. This makes it possible to effectively filter ambient noise, clearly detect the voice of a victim, and quickly pinpoint their location.

[0059] "Means for acquiring environmental information" refers to a function that collects surrounding conditions, including sound, in real time using sensors and microphones.

[0060] "Means of transmitting data to a central device via a communication network" refers to a system that transfers collected data to a central management device using wireless technologies such as Bluetooth or Wi-Fi.

[0061] "A method of removing noise using a generative model" is a process that utilizes machine learning models to effectively eliminate unwanted noise from collected audio data and extract only the important sounds.

[0062] "Means for amplifying processed audio information and retransmitting it to a receiving device" refers to a technology that amplifies a specific audio signal to an appropriate level before distributing it again to the user's device.

[0063] "A means of analyzing sound information to report the status of individuals" refers to a system that analyzes audio data to determine the presence and condition of disaster victims and reports the results to the rescue team.

[0064] "Means for synchronizing multiple receiving devices to determine the location of a sound source" refers to a method for synchronously processing audio data from multiple devices to identify the source of the sound.

[0065] A "means for visually displaying the location of a sound source" is a tool that displays the location of an identified sound source on a visual medium such as a map, and immediately provides location information to rescue teams.

[0066] This system is composed of three main components: a terminal, a server, and a user. The terminal plays a crucial role in implementing the invention. Designed as an earphone-type device, it is equipped with a high-sensitivity microphone. This microphone allows for real-time acquisition of environmental information from the rescue site.

[0067] Next, the audio data collected by the terminal is transmitted to a server via a communication network. Wireless communication technologies such as Bluetooth and Wi-Fi are used here. The server uses a generative AI model to remove noise from the received audio data. This AI model utilizes machine learning techniques, and in particular, it is responsible for the phase of extracting the necessary audio signals using time-frequency analysis.

[0068] The server also amplifies the processed audio and sends it back to the terminal. Users can then listen to this cleared audio through earphones to confirm the presence of victims. Furthermore, the server has a function to analyze the sound information, converting the audio data into text format and reporting the victim's condition to the rescue team. This information plays a crucial role in making decisions regarding rescue operations.

[0069] The rescue team, as the user, can then use this amplified and analyzed audio and location information to pinpoint the exact location of victims. To achieve this, the server synchronizes multiple receiving devices and uses triangulation technology to identify the sound source's location. The sound source's location is visually displayed and quickly communicated to the user.

[0070] As a concrete example, the prompt text to be input to the generative AI model can be written as follows: "Please tell me how to identify human voices from audio data collected at a disaster site, remove noise, and then amplify them."

[0071] This system utilizes advanced technology to quickly and accurately detect the voices of disaster victims and pinpoint their location, even in noisy environments.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The device uses a microphone to acquire environmental information in real time. The input is ambient sound, which the microphone converts into digital data and outputs. This data also contains noise.

[0075] Step 2:

[0076] The terminal packets the digitized voice data and sends it to the server using Bluetooth or Wi-Fi. The input is the digital voice data obtained in step 1, and the output is data packets transmitted wirelessly.

[0077] Step 3:

[0078] The server applies a generative AI model to the received audio data to remove noise. The input is the audio data sent in step 2, and the AI ​​model uses time-frequency analysis to extract specific sounds, resulting in filtered, clean audio data as output.

[0079] Step 4:

[0080] The server amplifies the identified audio data and then retransmits it to the terminal. The input is the filtered audio data, which is the output from step 3. The server adjusts the data to a constant volume and outputs it. The output is the amplified audio signal.

[0081] Step 5:

[0082] The device provides the user with the received audio signal through earphones. The input is amplified audio data retransmitted from the server, and the output is the audio the user actually hears. In this step, the user can hear the voices of disaster victims more clearly.

[0083] Step 6:

[0084] The server analyzes the audio data, converts it to text format, and reports information about the victims to the user. The input is filtered audio data, and natural language processing technology is used to convert the audio to text and output it.

[0085] Step 7:

[0086] A server synchronizes data across multiple earphone devices and uses triangulation technology to pinpoint the location of the sound source. The input is audio information from each earphone, and the output is visually plotted location information. This information is quickly provided to the user to aid in rescue operations.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Current emergency response systems have problems with detecting specific sounds in noisy environments and immediately pinpointing their location, which hinders a rapid response. Furthermore, abnormal sounds and danger signals are not detected in real time, leading to delays in detection and increased risk.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for filtering noise, means for amplifying specific sounds, means for analyzing audio data and reporting specific situations, means for synchronizing multiple information terminals to identify the location of a sound source, means for detecting abnormal sounds and danger signals, and means for displaying the location of specific sounds based on map information. This makes it possible to quickly and accurately detect abnormal sounds and danger signals, and to identify and display their locations.

[0092] "Means of filtering noise" are functions that remove unnecessary background noise and clarify important audio signals.

[0093] "Means for amplifying specific sounds" refers to techniques that increase the volume of detected specific sounds in order to make them easier to hear.

[0094] "Means of analyzing audio data to report specific situations" refers to a function that analyzes audio data and uses the obtained information to report on specific situations or events.

[0095] "A means of synchronizing multiple information terminals to pinpoint the location of a sound source" refers to a function that performs data exchange between multiple devices to accurately identify the location from which the sound was emitted.

[0096] "Means for detecting abnormal sounds and danger signals" refers to technologies for identifying sounds that are unusual or indicate danger from within the ambient noise.

[0097] "Means for displaying the location of a specific sound based on map information" refers to a function for visualizing the location where the detected sound originated on a map.

[0098] The system realizing this invention rapidly detects abnormal sounds and danger signals by linking smart devices with a central processing unit, and displays their location based on map information. This system consists of smart devices (e.g., smart glasses, headsets, etc.) for collecting ambient sounds and a central server for processing the data.

[0099] Smart devices collect ambient audio data in real time using their built-in microphones and transmit it to a server using wireless communication technology. The collected audio data is digitized on the server using audio processing libraries such as Librosa, and noise is filtered by a generative AI model. This model detects abnormal sounds and danger signals, amplifies specific sounds, and identifies their location using triangulation technology. The location information is visualized and plotted on a map using a map plotting library such as Leaflet.js.

[0100] In this way, users such as security guards and rescue workers can instantly detect abnormal sounds and danger signals and accurately pinpoint their location. For example, during a nighttime patrol of a large facility, the system can detect the sound of breaking glass and display its location on a map, allowing users to respond quickly. This system effectively incorporates a generative AI model, and prompt messages such as "If an abnormal sound is detected on the premises, immediately issue an alert and display the location on the map" can be used.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The device uses its built-in microphone to collect ambient sounds. This audio data is temporarily stored within the device.

[0104] Step 2:

[0105] The terminal transmits the collected audio data to the server using wireless communication technology. The input is audio data, and the output is data transferred to the server.

[0106] Step 3:

[0107] The server digitizes the received audio data using the Librosa library. The input is the audio data transmitted from the terminal, and the output is the audio data converted into digital format.

[0108] Step 4:

[0109] The server uses a generative AI model to filter out noise and amplify specific sounds from digitized audio data. The input is digitized audio data, and the output is filtered audio data.

[0110] Step 5:

[0111] The server uses triangulation technology to identify the sound source location of the amplified audio data. The input is filtered audio data, and the output is sound source location information.

[0112] Step 6:

[0113] The server uses Leaflet.js to plot and visualize the location of sound sources on a map. The input is the location information of the sound sources, and the output is the visualized map information.

[0114] Step 7:

[0115] Users can view map information through their device's display and respond quickly to on-site incidents based on the location of abnormal sounds or danger signals.

[0116] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0117] The system for implementing this invention integrates hardware that effectively filters noise and amplifies the voices and breathing sounds of victims, along with software equipped with an emotion engine. The aim of this system is to enable more precise and humane responses in rescue operations.

[0118] The earphone-type device worn by the user collects ambient sounds in real time and uses a generative AI model to remove unwanted noise. The filtered audio data is sent to a server, where specific sounds originating from the victim are amplified. Using the amplified audio data, the server analyzes the victim's situation and further examines it using an emotion engine. The emotion engine estimates the victim's emotional state from the tone and patterns of their voice and generates psychological support information necessary for saving lives. This allows rescue workers to understand the victim's emotional state and provide support quickly.

[0119] As a concrete example, if rescue workers use this system during post-earthquake rescue operations, voice analysis will clearly reveal cries for help, and the emotion engine will estimate that these cries are based on feelings of tension and fear. Based on this, rescue workers can flexibly adjust their approach to the victims and carry out rescue operations while calming them down.

[0120] This system also features a triangulation function that enables highly accurate location identification of disaster victims through real-time processing and digitization of audio data. Multiple terminals send data on the direction of the sound source to a server, which then calculates the location. This result is visualized on a map and provided to each rescue team member.

[0121] As a result, rescue operations can provide a new dimension of support that not only is swift but also addresses the emotions of the victims.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] When a user begins a rescue operation, each device (earphone) collects ambient sounds in real time. The built-in microphone in the device detects the sound and generates data as a digital signal.

[0125] Step 2:

[0126] The terminal compresses the collected audio data and transmits it to the server using wireless communication technology. The data is efficiently compressed and configured to arrive at the server immediately.

[0127] Step 3:

[0128] The server processes the received audio data and filters out noise components using a generative AI model. It converts the audio signal to the frequency domain, removing unwanted noise and clarifying important sounds.

[0129] Step 4:

[0130] The server amplifies specific sounds originating from disaster victims and transmits them to the terminal. These specific sounds, such as voices or breathing sounds, are amplified and returned to the user's earphones.

[0131] Step 5:

[0132] The server analyzes the amplified audio data and uses an emotion engine to analyze the tone and patterns of the voice. This allows it to estimate the emotional state of the victims.

[0133] Step 6:

[0134] Based on the emotional information generated by the emotion engine, the server provides users with appropriate information and guidance for action. It outputs psychological support information tailored to the emotional state of disaster victims.

[0135] Step 7:

[0136] The user's device receives information from the server via voice or text, which is then used in rescue operations. This information is used to facilitate communication with disaster victims and to inform rescue operation strategies.

[0137] Step 8:

[0138] The devices share detection information for audio data, and the server obtains location information from multiple devices. Triangulation technology is used to pinpoint the location of the sound source, and this information is provided to the user.

[0139] Step 9:

[0140] The server transmits data combining analysis results and location information to the user in real time, providing comprehensive support to facilitate rescue operations.

[0141] (Example 2)

[0142] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0143] In disaster areas, ambient noise makes it difficult to pinpoint the location and condition of victims. This problem reduces the efficiency of rescue operations and causes delays in saving lives. Furthermore, understanding the psychological state of victims is crucial for rescue workers to respond appropriately, but conventional techniques make it difficult to do this accurately.

[0144] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0145] In this invention, the server includes means for collecting audio data and removing scattered noise, means for processing the collected audio data and amplifying important sounds, and means for analyzing the received audio information and estimating the psychological state of individuals. This enables the rapid and accurate location and understanding of the psychological state of victims during rescue operations.

[0146] "Audio data" refers to a collection of information captured as an acoustic signal and represented in electrical or digital format.

[0147] "Noise" refers to unwanted acoustic elements that degrade the quality of the intended signal or information.

[0148] A "sound source" refers to the physical starting point or device that generates sound waves.

[0149] "Amplification" is the process of increasing the strength and magnitude of a signal to make it clearer.

[0150] "Psychological state" refers to the mental condition of an individual from the perspective of their cognitive, emotional, and behavioral responses.

[0151] "Encoding" is the process of converting analog or digital information into a specific format.

[0152] A "central control unit" refers to a central computer or server that manages information for the entire system and is responsible for data processing and issuing commands.

[0153] The system for implementing this invention is an advanced acoustic processing and analysis system that efficiently extracts and analyzes the voices of disaster victims in noisy environments. The terminal used by the user is an earphone-type device equipped with a high-sensitivity microphone that collects ambient sound data in real time. This terminal uses a generative AI model to remove noise and amplify the voices of disaster victims, for example, using "Whisper" technology.

[0154] The amplified audio data is analyzed by a server. The server further processes the audio data, picking out and emphasizing specific audio signals. Advanced algorithms are used for the analysis to identify important audio, which is then stored in a database.

[0155] The server also uses an emotion analysis engine to estimate the psychological state of victims from the tone and patterns of their voices. Software such as "EmotionXtract" is used to analyze emotional states and generate psychological support information useful for rescue operations. This allows rescue workers to respond flexibly to the psychological situation of victims.

[0156] Furthermore, this system aggregates sound source direction data from multiple terminals to a server and uses triangulation technology to pinpoint the precise location of victims. This location data is visualized on a map and provided to each rescue team member, supporting rapid and appropriate rescue operations.

[0157] As a concrete example, in rescue operations after an earthquake, rescue workers can use this system to clearly separate cries for help from other noise and determine that the emotion behind those cries is urgent. Based on this information, rescue workers can provide support while psychologically empathizing with the victims.

[0158] An example of a prompt might be: "Filter the audio collected at the scene and amplify the 'help me' cries. Then, describe the procedure for estimating the emotional state of those cries and generating necessary psychological support information." This allows for more humane and effective rescue operations.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The device, worn by the user as an earphone-type device, collects ambient sound using a high-sensitivity microphone. This input audio data is converted into a digital format. The converted result is output in a format suitable for information processing.

[0162] Step 2:

[0163] The device analyzes the collected digital audio data using a generating AI model and removes noise. In this process, the AI ​​model evaluates the frequency characteristics of each sound and filters out unnecessary sounds to generate clear audio. Clear audio data after filtering is output.

[0164] Step 3:

[0165] The terminal immediately sends the filtered audio data to the server. This transmission is performed using a low-latency, highly efficient communication protocol, and the output is stored in the server's receive buffer.

[0166] Step 4:

[0167] The server analyzes the received audio data and amplifies certain important sounds. In this process, the analysis algorithm selects and emphasizes sounds based on specific patterns and volume thresholds. The amplified audio is output in a format that can be used in rescue operations.

[0168] Step 5:

[0169] The server inputs the amplified audio data into an emotion analysis engine, which estimates the psychological state from the tone and patterns of the voice. The emotion engine analyzes features such as pitch, intensity, and speed of the voice and labels them with emotion categories. The generated emotion data is output and provided to the rescue team.

[0170] Step 6:

[0171] The server integrates sound source direction data received from multiple terminals and calculates the precise location of the sound source using triangulation. Each direction data is analyzed using geometric calculations to pinpoint the location of the victim. The identified location data is output and visualized on a map for rescue workers to see.

[0172] (Application Example 2)

[0173] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0174] In order to respond quickly and accurately to sudden emergencies in public transportation and large facilities, it is essential to efficiently filter important auditory information from the surrounding noise environment and analyze emotional states. However, conventional methods have been hindered by the large amount of noise, making it difficult to accurately capture urgent voices and emotional states, thus limiting the effectiveness of a rapid response.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0176] In this invention, the server includes a device for filtering noise, a device for amplifying specific sounds, a device for analyzing audio data and reporting the situation, a device for synchronizing multiple terminals to identify the location of the sound source, software for analyzing the emotional state of the voice and generating psychological instructions, and a device for detecting events in emergencies and providing warning information. This enables the rapid collection of necessary information and appropriate security responses even in emergencies in public places.

[0177] "Device" refers to mechanical or electrical equipment designed to perform a specific function.

[0178] A "terminal" is an input / output device used for information processing and communication.

[0179] "Synchronization" refers to the process of coordinating multiple devices or systems to operate simultaneously in the same state or at the same time.

[0180] "Software" is a collection of programmed instructions that enable a computer to perform tasks and operations.

[0181] "Audio data" refers to digitally recorded audio information and is one of the data formats used for analysis and processing.

[0182] "Emotional state" refers to a person's psychological state, inferred from the tone and pattern of their voice.

[0183] "Warning information" refers to information indicating that security measures or caution are necessary in response to an emergency or unusual event.

[0184] The system required to implement this invention mainly includes the following components. First, the user wears a device that collects sound, thereby acquiring ambient sounds in real time. The device processes the sound data using a generating AI model to filter out noise and identify and amplify the desired sounds. The processed sound data is sent to a server, which uses an emotion engine to analyze the emotional state of the voice based on this data.

[0185] The server uses a Python®-based speech analysis library (e.g., Librosa) and a generative AI model (e.g., a model from OpenAI®) to perform noise filtering and sentiment analysis on speech data. Based on the analysis results, the server provides alert information to security guards and relevant staff in public spaces, enabling a quick and appropriate response.

[0186] For example, if a sudden abnormal sound is detected on a train, the server analyzes the sound to identify emotional states such as urgency or fear. This information is immediately notified to the relevant parties, and necessary measures are taken. An example of a prompt message is, "Analyze the emotional states that can be identified from this audio and assess whether a rapid security response is required." Using this prompt message, a generative AI model analyzes the audio data and derives the optimal action.

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The user wears a device that collects audio. The device acquires ambient sounds in real time and outputs the data as digital audio data. The input here is ambient sound, and the output is raw, unprocessed audio data before filtering.

[0190] Step 2:

[0191] The device processes digital audio data using a generative AI model to remove background noise. The input is digital audio data, and noise filtering is performed using prompt text. The output is clean audio data with the noise removed.

[0192] Step 3:

[0193] Clean audio data is analyzed to amplify specific sounds. The terminal uses this analysis to highlight sounds containing specific emergency or anomaly signals, generating amplified audio data. The input is noise-free audio data, and the output is audio data with specific sounds amplified.

[0194] Step 4:

[0195] The terminal sends amplified audio data to the server. Here, the input is amplified audio data, and the processed output is analyzable audio data sent to the server.

[0196] Step 5:

[0197] The server processes the amplified audio data through an emotion engine and uses a generative AI model to analyze the emotional state of the audio. The input is amplified audio data, and emotion analysis is performed using prompt text. The output is the estimated emotional state based on the analysis.

[0198] Step 6:

[0199] Based on the analysis results, the server notifies security or relevant parties of the necessary information. The input is the estimated result of the emotional state, and the output is an instruction or alarm that is sent as warning information.

[0200] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0201] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0202] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0206] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0207] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0208] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0209] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0210] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0211] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0212] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0213] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0214] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0215] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0216] The system for implementing the present invention integrates multiple earphone-type devices and a backend server system to filter noise during rescue operations and amplify specific sounds such as the voices and breathing sounds of victims for use by rescue workers. Each device collects ambient sounds in real time and transmits the data to the server via wireless communication.

[0217] The server is responsible for processing the collected audio data, effectively removing noise components using a generative AI model. During this process, time-frequency analysis techniques are used to filter and pick up faint voice signals from victims. Next, the detected specific sounds are amplified and retransmitted to earphones worn by rescue workers. This audio processing makes it possible to hear the voices of victims more clearly from beneath the rubble.

[0218] The server also has analytical capabilities, which allow it to report on the likelihood of victims and their situation based on audio data. For example, it can filter out sounds that are mistakenly identified as noise and convert sounds that appear to be human voices into text data for rescue workers.

[0219] Furthermore, this system synchronizes multiple earphones, thereby using triangulation technology to pinpoint the location of the sound source. This location information is plotted on a map, allowing rescue teams to quickly receive the precise location of victims.

[0220] As a concrete example, if rescue teams use this system on-site after a major earthquake, each team member can wear earphones and search for rubble while relying on the clear voices of victims transmitted from the server. Furthermore, based on the analyzed report data, it becomes possible to understand the situation of the victims and carry out more efficient rescue operations.

[0221] The present invention, possessing the above-described functions, has the effect of improving the success rate of life-saving operations by promptly providing important clues during rescue activities.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] When a user begins a rescue operation, each device (earphone) collects ambient sounds in real time. The microphone built into the earphone detects the sound, digitizes it, and saves it as data.

[0225] Step 2:

[0226] The terminal compresses the collected audio data and transmits it to the server using wireless communication technology. An audio codec is used to reduce data volume and enable rapid transfer.

[0227] Step 3:

[0228] The server analyzes the received audio data and applies a generative AI model to filter out ambient noise. By performing a Fourier transform and removing noise components in the frequency domain, it emphasizes important sounds.

[0229] Step 4:

[0230] The server amplifies specific sounds and transmits the amplified audio data to the terminal. It plays a particularly important role in making the voices and breathing sounds of disaster victims clearer and delivering them directly to rescue workers.

[0231] Step 5:

[0232] The server further analyzes the amplified audio data, converting human voice components and sounds that convey the situation into text, and informing the user. An AI model is used to estimate the presence and number of victims.

[0233] Step 6:

[0234] All devices worn by the user synchronize voice data detection information with each other and transmit location information to a server. Bluetooth or Wi-Fi is used to maintain synchronization between devices.

[0235] Step 7:

[0236] The server uses triangulation technology to pinpoint the location of the sound source based on the data transmitted from each terminal. It calculates the time difference and sound intensity difference of the received data and displays the estimated location of the victims on a map.

[0237] Step 8:

[0238] The server sends location information and analysis results to rescue workers' earphones, supporting rapid and efficient rescue operations. It provides necessary data in real time via voice and text information.

[0239] (Example 1)

[0240] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0241] At natural disaster and accident sites, there is a need to effectively detect faint sounds such as the voices and breathing sounds of victims and to quickly pinpoint their location. However, these specific sounds can be masked by surrounding noise, potentially significantly reducing the efficiency of rescue operations. It is necessary to solve this problem and increase the success rate of rescue operations.

[0242] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0243] In this invention, the server includes means for acquiring environmental information, means for removing noise using a generative model, and means for analyzing sound information and reporting the state of an individual. This makes it possible to effectively filter ambient noise, clearly detect the voice of a victim, and quickly pinpoint their location.

[0244] "Means for acquiring environmental information" refers to a function that collects surrounding conditions, including sound, in real time using sensors and microphones.

[0245] "Means of transmitting data to a central device via a communication network" refers to a system that transfers collected data to a central management device using wireless technologies such as Bluetooth or Wi-Fi.

[0246] "A method of removing noise using a generative model" is a process that utilizes machine learning models to effectively eliminate unwanted noise from collected audio data and extract only the important sounds.

[0247] "Means for amplifying processed audio information and retransmitting it to a receiving device" refers to a technology that amplifies a specific audio signal to an appropriate level before distributing it again to the user's device.

[0248] "A means of analyzing sound information to report the status of individuals" refers to a system that analyzes audio data to determine the presence and condition of disaster victims and reports the results to the rescue team.

[0249] "Means for synchronizing multiple receiving devices to determine the location of a sound source" refers to a method for synchronously processing audio data from multiple devices to identify the source of the sound.

[0250] A "means for visually displaying the location of a sound source" is a tool that displays the location of an identified sound source on a visual medium such as a map, and immediately provides location information to rescue teams.

[0251] This system is composed of three main components: a terminal, a server, and a user. The terminal plays a crucial role in implementing the invention. Designed as an earphone-type device, it is equipped with a high-sensitivity microphone. This microphone allows for real-time acquisition of environmental information from the rescue site.

[0252] Next, the audio data collected by the terminal is transmitted to a server via a communication network. Wireless communication technologies such as Bluetooth and Wi-Fi are used here. The server uses a generative AI model to remove noise from the received audio data. This AI model utilizes machine learning techniques, and in particular, it is responsible for the phase of extracting the necessary audio signals using time-frequency analysis.

[0253] The server also amplifies the processed audio and sends it back to the terminal. Users can then listen to this cleared audio through earphones to confirm the presence of victims. Furthermore, the server has a function to analyze the sound information, converting the audio data into text format and reporting the victim's condition to the rescue team. This information plays a crucial role in making decisions regarding rescue operations.

[0254] The rescue team, as the user, can then use this amplified and analyzed audio and location information to pinpoint the exact location of victims. To achieve this, the server synchronizes multiple receiving devices and uses triangulation technology to identify the sound source's location. The sound source's location is visually displayed and quickly communicated to the user.

[0255] As a concrete example, the prompt text to be input to the generative AI model can be written as follows: "Please tell me how to identify human voices from audio data collected at a disaster site, remove noise, and then amplify them."

[0256] This system utilizes advanced technology to quickly and accurately detect the voices of disaster victims and pinpoint their location, even in noisy environments.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The device uses a microphone to acquire environmental information in real time. The input is ambient sound, which the microphone converts into digital data and outputs. This data also contains noise.

[0260] Step 2:

[0261] The terminal packets the digitized voice data and sends it to the server using Bluetooth or Wi-Fi. The input is the digital voice data obtained in step 1, and the output is data packets transmitted wirelessly.

[0262] Step 3:

[0263] The server applies a generative AI model to the received audio data to remove noise. The input is the audio data sent in step 2, and the AI ​​model uses time-frequency analysis to extract specific sounds, resulting in filtered, clean audio data as output.

[0264] Step 4:

[0265] The server amplifies the identified audio data and then retransmits it to the terminal. The input is the filtered audio data, which is the output from step 3. The server adjusts the data to a constant volume and outputs it. The output is the amplified audio signal.

[0266] Step 5:

[0267] The device provides the user with the received audio signal through earphones. The input is amplified audio data retransmitted from the server, and the output is the audio the user actually hears. In this step, the user can hear the voices of disaster victims more clearly.

[0268] Step 6:

[0269] The server analyzes the audio data, converts it to text format, and reports information about the victims to the user. The input is filtered audio data, and natural language processing technology is used to convert the audio to text and output it.

[0270] Step 7:

[0271] A server synchronizes data across multiple earphone devices and uses triangulation technology to pinpoint the location of the sound source. The input is audio information from each earphone, and the output is visually plotted location information. This information is quickly provided to the user to aid in rescue operations.

[0272] (Application Example 1)

[0273] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] Current emergency response systems have problems with detecting specific sounds in noisy environments and immediately pinpointing their location, which hinders a rapid response. Furthermore, abnormal sounds and danger signals are not detected in real time, leading to delays in detection and increased risk.

[0275] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0276] In this invention, the server includes means for filtering noise, means for amplifying specific sounds, means for analyzing audio data and reporting specific situations, means for synchronizing multiple information terminals to identify the location of a sound source, means for detecting abnormal sounds and danger signals, and means for displaying the location of specific sounds based on map information. This makes it possible to quickly and accurately detect abnormal sounds and danger signals, and to identify and display their locations.

[0277] "Means of filtering noise" are functions that remove unnecessary background noise and clarify important audio signals.

[0278] "Means for amplifying specific sounds" refers to techniques that increase the volume of detected specific sounds in order to make them easier to hear.

[0279] The means of "analyzing voice data and reporting specific situations" is a function that analyzes voice data and reports on specific situations or events based on the information obtained.

[0280] The means of "synchronizing multiple information terminals to identify the position of the sound source" is a function that performs data linkage between multiple devices and accurately identifies the position where the sound is emitted.

[0281] The means of "detecting abnormal sounds and danger signals" is a technology for identifying sounds that are different from normal or sounds indicating danger from environmental sounds.

[0282] The means of "displaying the position of a specific sound based on map information" is a function for visualizing the occurrence position of the detected voice on a map.

[0283] The system that realizes this invention is one that quickly detects abnormal sounds and danger signals by linking a smart device and a central processing unit and displays their positions based on map information. This system consists of a smart device (e.g., smart glasses, headset, etc.) for collecting environmental sounds and a central server for data processing.

[0284] The smart device uses a built-in microphone to collect ambient voice data in real time and transmits this using wireless communication technology to the server. The collected voice data is digitized on the server using a voice processing library such as Librosa, and noise is filtered by a generated AI model. The same model detects abnormal sounds and danger signals, amplifies specific sounds, and identifies the position information of the sound using triangulation technology. Using a map plotting library such as Leaflet.js, the position information is visualized and plotted on the map.

[0285] In this way, users such as security guards and rescue team members can immediately detect abnormal sounds and danger signals and accurately grasp their occurrence locations. For example, during the patrol of a large facility at night, when the system detects the sound of broken glass and displays its location on a map, the user can respond quickly. This system effectively incorporates a generative AI model, and prompts such as "When an abnormal sound is detected within the site, quickly send an alert and display the location on the map" can be used.

[0286] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0287] Step 1:

[0288] The terminal uses the built-in microphone to collect the ambient environmental sound. This audio data is temporarily stored inside the terminal.

[0289] Step 2:

[0290] The terminal transmits the collected audio data to the server using wireless communication technology. The input is the audio data, and the data is transferred to the server as the output.

[0291] Step 3:

[0292] The server digitizes the received audio data using the Librosa library. The input is the audio data transmitted from the terminal, and the output is the audio data converted into a digital format.

[0293] Step 4:

[0294] The server uses the generative AI model to filter out noise from the digitized audio data and amplify specific sounds. The input is the digitized audio data, and the output is the filtered audio data.

[0295] Step 5:

[0296] The server uses triangulation technology to identify the sound source location of the amplified audio data. The input is filtered audio data, and the output is sound source location information.

[0297] Step 6:

[0298] The server uses Leaflet.js to plot and visualize the location of sound sources on a map. The input is the location information of the sound sources, and the output is the visualized map information.

[0299] Step 7:

[0300] Users can view map information through their device's display and respond quickly to on-site incidents based on the location of abnormal sounds or danger signals.

[0301] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0302] The system for implementing this invention integrates hardware that effectively filters noise and amplifies the voices and breathing sounds of victims, along with software equipped with an emotion engine. The aim of this system is to enable more precise and humane responses in rescue operations.

[0303] The earphone-type device worn by the user collects ambient sounds in real time and uses a generative AI model to remove unwanted noise. The filtered audio data is sent to a server, where specific sounds originating from the victim are amplified. Using the amplified audio data, the server analyzes the victim's situation and further examines it using an emotion engine. The emotion engine estimates the victim's emotional state from the tone and patterns of their voice and generates psychological support information necessary for saving lives. This allows rescue workers to understand the victim's emotional state and provide support quickly.

[0304] As a specific example, in the rescue operation after an earthquake, when rescue team members use this system, the voice of "Help" can be clearly heard through voice analysis, and it is further estimated by the emotion engine that the voice is based on emotions such as tension and fear. Based on this, the rescue team members can flexibly adjust their approach to the victims and carry out rescue activities while calming them down.

[0305] This system also has a triangulation function that can accurately identify the location of the victims by performing real-time processing and digitization of voice data. Multiple terminals send data on the sound source direction to the server, and the location is calculated based on them. This result is visualized on a map and provided to each rescue team member.

[0306] As described above, in rescue operations, not only can it be just rapid, but it can also provide a new dimension of support that can address the emotions of the victims.

[0307] The following describes the processing flow.

[0308] Step 1:

[0309] When the user starts a rescue operation, each terminal (earphone) collects ambient environmental sounds in real time. The built-in microphone in the terminal senses the voice and generates data as a digital signal.

[0310] Step 2:

[0311] The terminal compresses the collected voice data and transmits it to the server using wireless communication technology. The data is efficiently compressed and set to reach the server immediately.

[0312] Step 3:

[0313] The server processes the received voice data and filters out noise components using a generated AI model. The voice signal is converted into the frequency domain, and unnecessary noise is removed to clarify important sounds.

[0314] Step 4:

[0315] The server amplifies specific sounds originating from disaster victims and transmits them to the terminal. These specific sounds, such as voices or breathing sounds, are amplified and returned to the user's earphones.

[0316] Step 5:

[0317] The server analyzes the amplified audio data and uses an emotion engine to analyze the tone and patterns of the voice. This allows it to estimate the emotional state of the victims.

[0318] Step 6:

[0319] Based on the emotional information generated by the emotion engine, the server provides users with appropriate information and guidance for action. It outputs psychological support information tailored to the emotional state of disaster victims.

[0320] Step 7:

[0321] The user's device receives information from the server via voice or text, which is then used in rescue operations. This information is used to facilitate communication with disaster victims and to inform rescue operation strategies.

[0322] Step 8:

[0323] The devices share detection information for audio data, and the server obtains location information from multiple devices. Triangulation technology is used to pinpoint the location of the sound source, and this information is provided to the user.

[0324] Step 9:

[0325] The server transmits data combining analysis results and location information to the user in real time, providing comprehensive support to facilitate rescue operations.

[0326] (Example 2)

[0327] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0328] In disaster areas, ambient noise makes it difficult to pinpoint the location and condition of victims. This problem reduces the efficiency of rescue operations and causes delays in saving lives. Furthermore, understanding the psychological state of victims is crucial for rescue workers to respond appropriately, but conventional techniques make it difficult to do this accurately.

[0329] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0330] In this invention, the server includes means for collecting audio data and removing scattered noise, means for processing the collected audio data and amplifying important sounds, and means for analyzing the received audio information and estimating the psychological state of individuals. This enables the rapid and accurate location and understanding of the psychological state of victims during rescue operations.

[0331] "Audio data" refers to a collection of information captured as an acoustic signal and represented in electrical or digital format.

[0332] "Noise" refers to unwanted acoustic elements that degrade the quality of the intended signal or information.

[0333] A "sound source" refers to the physical starting point or device that generates sound waves.

[0334] "Amplification" is the process of increasing the strength and magnitude of a signal to make it clearer.

[0335] "Psychological state" refers to the mental condition of an individual from the perspective of their cognitive, emotional, and behavioral responses.

[0336] "Encoding" is the process of converting analog or digital information into a specific format.

[0337] A "central control unit" refers to a central computer or server that manages information for the entire system and is responsible for data processing and issuing commands.

[0338] The system for implementing this invention is an advanced acoustic processing and analysis system that efficiently extracts and analyzes the voices of disaster victims in noisy environments. The terminal used by the user is an earphone-type device equipped with a high-sensitivity microphone that collects ambient sound data in real time. This terminal uses a generative AI model to remove noise and amplify the voices of disaster victims, for example, using "Whisper" technology.

[0339] The amplified audio data is analyzed by a server. The server further processes the audio data, picking out and emphasizing specific audio signals. Advanced algorithms are used for the analysis to identify important audio, which is then stored in a database.

[0340] The server also uses an emotion analysis engine to estimate the psychological state of victims from the tone and patterns of their voices. Software such as "EmotionXtract" is used to analyze emotional states and generate psychological support information useful for rescue operations. This allows rescue workers to respond flexibly to the psychological situation of victims.

[0341] Furthermore, this system aggregates sound source direction data from multiple terminals to a server and uses triangulation technology to pinpoint the precise location of victims. This location data is visualized on a map and provided to each rescue team member, supporting rapid and appropriate rescue operations.

[0342] As a concrete example, in rescue operations after an earthquake, rescue workers can use this system to clearly separate cries for help from other noise and determine that the emotion behind those cries is urgent. Based on this information, rescue workers can provide support while psychologically empathizing with the victims.

[0343] An example of a prompt might be: "Filter the audio collected at the scene and amplify the 'help me' cries. Then, describe the procedure for estimating the emotional state of those cries and generating necessary psychological support information." This allows for more humane and effective rescue operations.

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1:

[0346] The device, worn by the user as an earphone-type device, collects ambient sound using a high-sensitivity microphone. This input audio data is converted into a digital format. The converted result is output in a format suitable for information processing.

[0347] Step 2:

[0348] The device analyzes the collected digital audio data using a generating AI model and removes noise. In this process, the AI ​​model evaluates the frequency characteristics of each sound and filters out unnecessary sounds to generate clear audio. Clear audio data after filtering is output.

[0349] Step 3:

[0350] The terminal immediately sends the filtered audio data to the server. This transmission is performed using a low-latency, highly efficient communication protocol, and the output is stored in the server's receive buffer.

[0351] Step 4:

[0352] The server analyzes the received audio data and amplifies certain important sounds. In this process, the analysis algorithm selects and emphasizes sounds based on specific patterns and volume thresholds. The amplified audio is output in a format that can be used in rescue operations.

[0353] Step 5:

[0354] The server inputs the amplified audio data into an emotion analysis engine, which estimates the psychological state from the tone and patterns of the voice. The emotion engine analyzes features such as pitch, intensity, and speed of the voice and labels them with emotion categories. The generated emotion data is output and provided to the rescue team.

[0355] Step 6:

[0356] The server integrates sound source direction data received from multiple terminals and calculates the precise location of the sound source using triangulation. Each direction data is analyzed using geometric calculations to pinpoint the location of the victim. The identified location data is output and visualized on a map for rescue workers to see.

[0357] (Application Example 2)

[0358] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0359] In order to respond quickly and accurately to sudden emergencies in public transportation and large facilities, it is essential to efficiently filter important auditory information from the surrounding noise environment and analyze emotional states. However, conventional methods have been hindered by the large amount of noise, making it difficult to accurately capture urgent voices and emotional states, thus limiting the effectiveness of a rapid response.

[0360] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0361] In this invention, the server includes a device for filtering noise, a device for amplifying specific sounds, a device for analyzing audio data and reporting the situation, a device for synchronizing multiple terminals to identify the location of the sound source, software for analyzing the emotional state of the voice and generating psychological instructions, and a device for detecting events in emergencies and providing warning information. This enables the rapid collection of necessary information and appropriate security responses even in emergencies in public places.

[0362] "Device" refers to mechanical or electrical equipment designed to perform a specific function.

[0363] A "terminal" is an input / output device used for information processing and communication.

[0364] "Synchronization" refers to the process of coordinating multiple devices or systems to operate simultaneously in the same state or at the same time.

[0365] "Software" is a collection of programmed instructions that enable a computer to perform tasks and operations.

[0366] "Audio data" refers to digitally recorded audio information and is one of the data formats used for analysis and processing.

[0367] "Emotional state" refers to a person's psychological state, inferred from the tone and pattern of their voice.

[0368] "Warning information" refers to information indicating that security measures or caution are necessary in response to an emergency or unusual event.

[0369] The system required to implement this invention mainly includes the following components. First, the user wears a device that collects sound, thereby acquiring ambient sounds in real time. The device processes the sound data using a generating AI model to filter out noise and identify and amplify the desired sounds. The processed sound data is sent to a server, which uses an emotion engine to analyze the emotional state of the voice based on this data.

[0370] The server uses a Python-based speech analysis library (e.g., Librosa) and a generative AI model (e.g., an OpenAI model) to perform noise filtering and sentiment analysis on speech data. Based on the analysis results, the server provides alert information to security guards and relevant staff in public spaces, enabling a quick and appropriate response.

[0371] For example, if a sudden abnormal sound is detected on a train, the server analyzes the sound to identify emotional states such as urgency or fear. This information is immediately notified to the relevant parties, and necessary measures are taken. An example of a prompt message is, "Analyze the emotional states that may be identifiable from this audio and assess whether a rapid security response is required." Using this prompt message, a generative AI model analyzes the audio data and derives the optimal action.

[0372] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0373] Step 1:

[0374] The user wears a device that collects audio. The device acquires ambient sounds in real time and outputs the data as digital audio data. The input here is ambient sound, and the output is raw, unprocessed audio data before filtering.

[0375] Step 2:

[0376] The device processes digital audio data using a generative AI model to remove background noise. The input is digital audio data, and noise filtering is performed using prompt text. The output is clean audio data with the noise removed.

[0377] Step 3:

[0378] Clean audio data is analyzed to amplify specific sounds. The terminal uses this analysis to highlight sounds containing specific emergency or anomaly signals, generating amplified audio data. The input is noise-free audio data, and the output is audio data with specific sounds amplified.

[0379] Step 4:

[0380] The terminal sends the amplified audio data to the server. Here, the input is the amplified audio data, and the processed output is the analyzable audio data sent to the server.

[0381] Step 5:

[0382] The server processes the amplified audio data through an emotion engine and uses a generative AI model to analyze the emotional state of the audio. The input is amplified audio data, and emotion analysis is performed using prompt text. The output is the estimated emotional state based on the analysis.

[0383] Step 6:

[0384] Based on the analysis results, the server notifies security or relevant parties of the necessary information. The input is the estimated result of the emotional state, and the output is an instruction or alarm that is sent as warning information.

[0385] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0386] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0387] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0388] [Third Embodiment]

[0389] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0390] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0391] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0392] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0393] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0394] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0395] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0396] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0397] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0398] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0399] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0400] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0401] The system for implementing the present invention integrates multiple earphone-type devices and a backend server system to filter noise during rescue operations and amplify specific sounds such as the voices and breathing sounds of victims for use by rescue workers. Each device collects ambient sounds in real time and transmits the data to the server via wireless communication.

[0402] The server is responsible for processing the collected audio data, effectively removing noise components using a generative AI model. During this process, time-frequency analysis techniques are used to filter and pick up faint voice signals from victims. Next, the detected specific sounds are amplified and retransmitted to earphones worn by rescue workers. This audio processing makes it possible to hear the voices of victims more clearly from beneath the rubble.

[0403] The server also has analytical capabilities, which allow it to report on the likelihood of victims and their situation based on audio data. For example, it can filter out sounds that are mistakenly identified as noise and convert sounds that appear to be human voices into text data for rescue workers.

[0404] Furthermore, this system synchronizes multiple earphones, thereby using triangulation technology to pinpoint the location of the sound source. This location information is plotted on a map, allowing rescue teams to quickly receive the precise location of victims.

[0405] As a concrete example, if rescue teams use this system on-site after a major earthquake, each team member can wear earphones and search for rubble while relying on the clear voices of victims transmitted from the server. Furthermore, based on the analyzed report data, it becomes possible to understand the situation of the victims and carry out more efficient rescue operations.

[0406] The present invention, possessing the above-described functions, has the effect of improving the success rate of life-saving operations by promptly providing important clues during rescue activities.

[0407] The following describes the processing flow.

[0408] Step 1:

[0409] When a user begins a rescue operation, each device (earphone) collects ambient sounds in real time. The microphone built into the earphone detects the sound, digitizes it, and saves it as data.

[0410] Step 2:

[0411] The terminal compresses the collected audio data and transmits it to the server using wireless communication technology. An audio codec is used to reduce data volume and enable rapid transfer.

[0412] Step 3:

[0413] The server analyzes the received audio data and applies a generative AI model to filter out ambient noise. By performing a Fourier transform and removing noise components in the frequency domain, it emphasizes important sounds.

[0414] Step 4:

[0415] The server amplifies specific sounds and transmits the amplified audio data to the terminal. It plays a particularly important role in making the voices and breathing sounds of disaster victims clearer and delivering them directly to rescue workers.

[0416] Step 5:

[0417] The server further analyzes the amplified audio data, converting human voice components and sounds that convey the situation into text, and informing the user. An AI model is used to estimate the presence and number of victims.

[0418] Step 6:

[0419] All devices worn by the user synchronize voice data detection information with each other and transmit location information to a server. Bluetooth or Wi-Fi is used to maintain synchronization between devices.

[0420] Step 7:

[0421] The server uses triangulation technology to pinpoint the location of the sound source based on the data transmitted from each terminal. It calculates the time difference and sound intensity difference of the received data and displays the estimated location of the victims on a map.

[0422] Step 8:

[0423] The server sends location information and analysis results to rescue workers' earphones, supporting rapid and efficient rescue operations. It provides necessary data in real time via voice and text information.

[0424] (Example 1)

[0425] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0426] At natural disaster and accident sites, there is a need to effectively detect faint sounds such as the voices and breathing sounds of victims and to quickly pinpoint their location. However, these specific sounds can be masked by surrounding noise, potentially significantly reducing the efficiency of rescue operations. It is necessary to solve this problem and increase the success rate of rescue operations.

[0427] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0428] In this invention, the server includes means for acquiring environmental information, means for removing noise using a generative model, and means for analyzing sound information and reporting the state of an individual. This makes it possible to effectively filter ambient noise, clearly detect the voice of a victim, and quickly pinpoint their location.

[0429] "Means for acquiring environmental information" refers to a function that collects surrounding conditions, including sound, in real time using sensors and microphones.

[0430] "Means of transmitting data to a central device via a communication network" refers to a system that transfers collected data to a central management device using wireless technologies such as Bluetooth or Wi-Fi.

[0431] "A method of removing noise using a generative model" is a process that utilizes machine learning models to effectively eliminate unwanted noise from collected audio data and extract only the important sounds.

[0432] "Means for amplifying processed audio information and retransmitting it to a receiving device" refers to a technology that amplifies a specific audio signal to an appropriate level before distributing it again to the user's device.

[0433] "A means of analyzing sound information to report the status of individuals" refers to a system that analyzes audio data to determine the presence and condition of disaster victims and reports the results to the rescue team.

[0434] "Means for synchronizing multiple receiving devices to determine the location of a sound source" refers to a method for synchronously processing audio data from multiple devices to identify the source of the sound.

[0435] A "means for visually displaying the location of a sound source" is a tool that displays the location of an identified sound source on a visual medium such as a map, and immediately provides location information to rescue teams.

[0436] This system is composed of three main components: a terminal, a server, and a user. The terminal plays a crucial role in implementing the invention. Designed as an earphone-type device, it is equipped with a high-sensitivity microphone. This microphone allows for real-time acquisition of environmental information from the rescue site.

[0437] Next, the audio data collected by the terminal is transmitted to a server via a communication network. Wireless communication technologies such as Bluetooth and Wi-Fi are used here. The server uses a generative AI model to remove noise from the received audio data. This AI model utilizes machine learning techniques, and in particular, it is responsible for the phase of extracting the necessary audio signals using time-frequency analysis.

[0438] The server also amplifies the processed audio and sends it back to the terminal. Users can then listen to this cleared audio through earphones to confirm the presence of victims. Furthermore, the server has a function to analyze the sound information, converting the audio data into text format and reporting the victim's condition to the rescue team. This information plays a crucial role in making decisions regarding rescue operations.

[0439] The rescue team, as the user, can then use this amplified and analyzed audio and location information to pinpoint the exact location of victims. To achieve this, the server synchronizes multiple receiving devices and uses triangulation technology to identify the sound source's location. The sound source's location is visually displayed and quickly communicated to the user.

[0440] As a concrete example, the prompt text to be input to the generative AI model can be written as follows: "Please tell me how to identify human voices from audio data collected at a disaster site, remove noise, and then amplify them."

[0441] This system utilizes advanced technology to quickly and accurately detect the voices of disaster victims and pinpoint their location, even in noisy environments.

[0442] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0443] Step 1:

[0444] The device uses a microphone to acquire environmental information in real time. The input is ambient sound, which the microphone converts into digital data and outputs. This data also contains noise.

[0445] Step 2:

[0446] The terminal packets the digitized voice data and sends it to the server using Bluetooth or Wi-Fi. The input is the digital voice data obtained in step 1, and the output is data packets transmitted wirelessly.

[0447] Step 3:

[0448] The server applies a generative AI model to the received audio data to remove noise. The input is the audio data sent in step 2, and the AI ​​model uses time-frequency analysis to extract specific sounds, resulting in filtered, clean audio data as output.

[0449] Step 4:

[0450] The server amplifies the identified audio data and then retransmits it to the terminal. The input is the filtered audio data, which is the output from step 3. The server adjusts the data to a constant volume and outputs it. The output is the amplified audio signal.

[0451] Step 5:

[0452] The device provides the user with the received audio signal through earphones. The input is amplified audio data retransmitted from the server, and the output is the audio the user actually hears. In this step, the user can hear the voices of disaster victims more clearly.

[0453] Step 6:

[0454] The server analyzes the audio data, converts it to text format, and reports information about the victims to the user. The input is filtered audio data, and natural language processing technology is used to convert the audio to text and output it.

[0455] Step 7:

[0456] A server synchronizes data across multiple earphone devices and uses triangulation technology to pinpoint the location of the sound source. The input is audio information from each earphone, and the output is visually plotted location information. This information is quickly provided to the user to aid in rescue operations.

[0457] (Application Example 1)

[0458] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0459] Current emergency response systems have problems with rapid response, such as difficulty in detecting specific sounds in noisy environments and in immediately identifying their location. Furthermore, abnormal sounds and danger signals are not detected in real time, leading to delays in detection and increased risk.

[0460] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0461] In this invention, the server includes means for filtering noise, means for amplifying specific sounds, means for analyzing audio data and reporting specific situations, means for synchronizing multiple information terminals to identify the location of a sound source, means for detecting abnormal sounds and danger signals, and means for displaying the location of specific sounds based on map information. This makes it possible to quickly and accurately detect abnormal sounds and danger signals, and to identify and display their locations.

[0462] "Means of filtering noise" are functions that remove unnecessary background noise and clarify important audio signals.

[0463] "Means for amplifying specific sounds" refers to techniques that increase the volume of detected specific sounds in order to make them easier to hear.

[0464] "Means of analyzing audio data to report specific situations" refers to a function that analyzes audio data and uses the obtained information to report on specific situations or events.

[0465] "A means of synchronizing multiple information terminals to pinpoint the location of a sound source" refers to a function that performs data exchange between multiple devices to accurately identify the location from which the sound was emitted.

[0466] "Means for detecting abnormal sounds and danger signals" refers to technologies for identifying sounds that are unusual or indicate danger from within the ambient noise.

[0467] "Means for displaying the location of a specific sound based on map information" refers to a function for visualizing the location where the detected sound originated on a map.

[0468] The system realizing this invention rapidly detects abnormal sounds and danger signals by linking smart devices with a central processing unit, and displays their location based on map information. This system consists of smart devices (e.g., smart glasses, headsets, etc.) for collecting ambient sounds and a central server for processing the data.

[0469] Smart devices collect ambient audio data in real time using their built-in microphones and transmit it to a server using wireless communication technology. The collected audio data is digitized on the server using audio processing libraries such as Librosa, and noise is filtered by a generative AI model. This model detects abnormal sounds and danger signals, amplifies specific sounds, and identifies their location using triangulation technology. The location information is visualized and plotted on a map using a map plotting library such as Leaflet.js.

[0470] In this way, users such as security guards and rescue workers can instantly detect abnormal sounds and danger signals and accurately pinpoint their location. For example, during a nighttime patrol of a large facility, the system can detect the sound of breaking glass and display its location on a map, allowing users to respond quickly. This system effectively incorporates a generative AI model, and prompt messages such as "If an abnormal sound is detected on the premises, immediately issue an alert and display the location on the map" can be used.

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The device uses its built-in microphone to collect ambient sounds. This audio data is temporarily stored within the device.

[0474] Step 2:

[0475] The terminal transmits the collected audio data to the server using wireless communication technology. The input is audio data, and the output is data transferred to the server.

[0476] Step 3:

[0477] The server digitizes the received audio data using the Librosa library. The input is the audio data transmitted from the terminal, and the output is the audio data converted into digital format.

[0478] Step 4:

[0479] The server uses a generative AI model to filter out noise and amplify specific sounds from digitized audio data. The input is digitized audio data, and the output is filtered audio data.

[0480] Step 5:

[0481] The server uses triangulation technology to identify the sound source location of the amplified audio data. The input is filtered audio data, and the output is sound source location information.

[0482] Step 6:

[0483] The server uses Leaflet.js to plot and visualize the location of sound sources on a map. The input is the location information of the sound sources, and the output is the visualized map information.

[0484] Step 7:

[0485] Users can view map information through their device's display and respond quickly to on-site incidents based on the location of abnormal sounds or danger signals.

[0486] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0487] The system for implementing this invention integrates hardware that effectively filters noise and amplifies the voices and breathing sounds of victims, along with software equipped with an emotion engine. The aim of this system is to enable more precise and humane responses in rescue operations.

[0488] The earphone-type device worn by the user collects ambient sounds in real time and uses a generative AI model to remove unwanted noise. The filtered audio data is sent to a server, where specific sounds originating from the victim are amplified. Using the amplified audio data, the server analyzes the victim's situation and further examines it using an emotion engine. The emotion engine estimates the victim's emotional state from the tone and patterns of their voice and generates psychological support information necessary for saving lives. This allows rescue workers to understand the victim's emotional state and provide support quickly.

[0489] As a concrete example, if rescue workers use this system during post-earthquake rescue operations, voice analysis will clearly reveal cries for help, and the emotion engine will estimate that these cries are based on feelings of tension and fear. Based on this, rescue workers can flexibly adjust their approach to the victims and carry out rescue operations while calming them down.

[0490] This system also features a triangulation function that enables highly accurate location identification of disaster victims through real-time processing and digitization of audio data. Multiple terminals send data on the direction of the sound source to a server, which then calculates the location. This result is visualized on a map and provided to each rescue team member.

[0491] As a result, rescue operations can provide a new dimension of support that not only is swift but also addresses the emotions of the victims.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] When a user begins a rescue operation, each device (earphone) collects ambient sounds in real time. The built-in microphone in the device detects the sound and generates data as a digital signal.

[0495] Step 2:

[0496] The terminal compresses the collected audio data and transmits it to the server using wireless communication technology. The data is efficiently compressed and configured to arrive at the server immediately.

[0497] Step 3:

[0498] The server processes the received audio data and filters out noise components using a generative AI model. It converts the audio signal to the frequency domain, removing unwanted noise and clarifying important sounds.

[0499] Step 4:

[0500] The server amplifies specific sounds originating from disaster victims and transmits them to the terminal. These specific sounds, such as voices or breathing sounds, are amplified and returned to the user's earphones.

[0501] Step 5:

[0502] The server analyzes the amplified audio data and uses an emotion engine to analyze the tone and patterns of the voice. This allows it to estimate the emotional state of the victims.

[0503] Step 6:

[0504] Based on the emotional information generated by the emotion engine, the server provides users with appropriate information and guidance for action. It outputs psychological support information tailored to the emotional state of disaster victims.

[0505] Step 7:

[0506] The user's device receives information from the server via voice or text, which is then used in rescue operations. This information is used to facilitate communication with disaster victims and to inform rescue operation strategies.

[0507] Step 8:

[0508] The devices share detection information for audio data, and the server obtains location information from multiple devices. Triangulation technology is used to pinpoint the location of the sound source, and this information is provided to the user.

[0509] Step 9:

[0510] The server transmits data combining analysis results and location information to the user in real time, providing comprehensive support to facilitate rescue operations.

[0511] (Example 2)

[0512] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0513] In disaster areas, ambient noise makes it difficult to pinpoint the location and condition of victims. This problem reduces the efficiency of rescue operations and causes delays in saving lives. Furthermore, understanding the psychological state of victims is crucial for rescue workers to respond appropriately, but conventional techniques make it difficult to do this accurately.

[0514] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0515] In this invention, the server includes means for collecting audio data and removing scattered noise, means for processing the collected audio data and amplifying important sounds, and means for analyzing the received audio information and estimating the psychological state of individuals. This enables the rapid and accurate location and understanding of the psychological state of victims during rescue operations.

[0516] "Audio data" refers to a collection of information captured as an acoustic signal and represented in electrical or digital format.

[0517] "Noise" refers to unwanted acoustic elements that degrade the quality of the intended signal or information.

[0518] A "sound source" refers to the physical starting point or device that generates sound waves.

[0519] "Amplification" is the process of increasing the strength and magnitude of a signal to make it clearer.

[0520] "Psychological state" refers to the mental condition of an individual from the perspective of their cognitive, emotional, and behavioral responses.

[0521] "Encoding" is the process of converting analog or digital information into a specific format.

[0522] A "central control unit" refers to a central computer or server that manages information for the entire system and is responsible for data processing and issuing commands.

[0523] The system for implementing this invention is an advanced acoustic processing and analysis system that efficiently extracts and analyzes the voices of disaster victims in noisy environments. The terminal used by the user is an earphone-type device equipped with a high-sensitivity microphone that collects ambient sound data in real time. This terminal uses a generative AI model to remove noise and amplify the voices of disaster victims, for example, using "Whisper" technology.

[0524] The amplified audio data is analyzed by a server. The server further processes the audio data, picking out and emphasizing specific audio signals. Advanced algorithms are used for the analysis to identify important audio, which is then stored in a database.

[0525] The server also uses an emotion analysis engine to estimate the psychological state of victims from the tone and patterns of their voices. Software such as "EmotionXtract" is used to analyze emotional states and generate psychological support information useful for rescue operations. This allows rescue workers to respond flexibly to the psychological situation of victims.

[0526] Furthermore, this system aggregates sound source direction data from multiple terminals to a server and uses triangulation technology to pinpoint the precise location of victims. This location data is visualized on a map and provided to each rescue team member, supporting rapid and appropriate rescue operations.

[0527] As a concrete example, in rescue operations after an earthquake, rescue workers can use this system to clearly separate cries for help from other noise and determine that the emotion behind those cries is urgent. Based on this information, rescue workers can provide support while psychologically empathizing with the victims.

[0528] An example of a prompt might be: "Filter the audio collected at the scene and amplify the 'help me' cries. Then, describe the procedure for estimating the emotional state of those cries and generating necessary psychological support information." This allows for more humane and effective rescue operations.

[0529] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0530] Step 1:

[0531] The device, worn by the user as an earphone-type device, collects ambient sound using a high-sensitivity microphone. This input audio data is converted into a digital format. The converted result is output in a format suitable for information processing.

[0532] Step 2:

[0533] The device analyzes the collected digital audio data using a generating AI model and removes noise. In this process, the AI ​​model evaluates the frequency characteristics of each sound and filters out unnecessary sounds to generate clear audio. Clear audio data after filtering is output.

[0534] Step 3:

[0535] The terminal immediately sends the filtered audio data to the server. This transmission is performed using a low-latency, highly efficient communication protocol, and the output is stored in the server's receive buffer.

[0536] Step 4:

[0537] The server analyzes the received audio data and amplifies certain important sounds. In this process, the analysis algorithm selects and emphasizes sounds based on specific patterns and volume thresholds. The amplified audio is output in a format that can be used in rescue operations.

[0538] Step 5:

[0539] The server inputs the amplified audio data into an emotion analysis engine, which estimates the psychological state from the tone and patterns of the voice. The emotion engine analyzes features such as pitch, intensity, and speed of the voice and labels them with emotion categories. The generated emotion data is output and provided to the rescue team.

[0540] Step 6:

[0541] The server integrates sound source direction data received from multiple terminals and calculates the precise location of the sound source using triangulation. Each direction data is analyzed using geometric calculations to pinpoint the location of the victim. The identified location data is output and visualized on a map for rescue workers to see.

[0542] (Application Example 2)

[0543] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0544] In order to respond quickly and accurately to sudden emergencies in public transportation and large facilities, it is essential to efficiently filter important auditory information from the surrounding noise environment and analyze emotional states. However, conventional methods have been hindered by the large amount of noise, making it difficult to accurately capture urgent voices and emotional states, thus limiting the effectiveness of a rapid response.

[0545] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0546] In this invention, the server includes a device for filtering noise, a device for amplifying specific sounds, a device for analyzing audio data and reporting the situation, a device for synchronizing multiple terminals to identify the location of the sound source, software for analyzing the emotional state of the voice and generating psychological instructions, and a device for detecting events in emergencies and providing warning information. This enables the rapid collection of necessary information and appropriate security responses even in emergencies in public places.

[0547] "Device" refers to mechanical or electrical equipment designed to perform a specific function.

[0548] A "terminal" is an input / output device used for information processing and communication.

[0549] "Synchronization" refers to the process of coordinating multiple devices or systems to operate simultaneously in the same state or at the same time.

[0550] "Software" is a collection of programmed instructions that enable a computer to perform tasks and operations.

[0551] "Audio data" refers to digitally recorded audio information and is one of the data formats used for analysis and processing.

[0552] "Emotional state" refers to a person's psychological state, inferred from the tone and pattern of their voice.

[0553] "Warning information" refers to information indicating that security measures or caution are necessary in response to an emergency or unusual event.

[0554] The system required to implement this invention mainly includes the following components. First, the user wears a device that collects sound, thereby acquiring ambient sounds in real time. The device processes the sound data using a generating AI model to filter out noise and identify and amplify the desired sounds. The processed sound data is sent to a server, which uses an emotion engine to analyze the emotional state of the voice based on this data.

[0555] The server uses a Python-based speech analysis library (e.g., Librosa) and a generative AI model (e.g., an OpenAI model) to perform noise filtering and sentiment analysis on speech data. Based on the analysis results, the server provides alert information to security guards and relevant staff in public spaces, enabling a quick and appropriate response.

[0556] For example, if a sudden abnormal sound is detected on a train, the server analyzes the sound to identify emotional states such as urgency or fear. This information is immediately notified to the relevant parties, and necessary measures are taken. An example of a prompt message is, "Analyze the emotional states that may be identifiable from this audio and assess whether a rapid security response is required." Using this prompt message, a generative AI model analyzes the audio data and derives the optimal action.

[0557] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0558] Step 1:

[0559] The user wears a device that collects audio. The device acquires ambient sounds in real time and outputs the data as digital audio data. The input here is ambient sound, and the output is raw, unprocessed audio data before filtering.

[0560] Step 2:

[0561] The device processes digital audio data using a generative AI model to remove background noise. The input is digital audio data, and noise filtering is performed using prompt text. The output is clean audio data with the noise removed.

[0562] Step 3:

[0563] Clean audio data is analyzed to amplify specific sounds. The terminal uses this analysis to highlight sounds containing specific emergency or anomaly signals, generating amplified audio data. The input is noise-free audio data, and the output is audio data with specific sounds amplified.

[0564] Step 4:

[0565] The terminal sends amplified audio data to the server. Here, the input is amplified audio data, and the processed output is analyzable audio data sent to the server.

[0566] Step 5:

[0567] The server processes the amplified audio data through an emotion engine and uses a generative AI model to analyze the emotional state of the audio. The input is amplified audio data, and emotion analysis is performed using prompt text. The output is the estimated emotional state based on the analysis.

[0568] Step 6:

[0569] Based on the analysis results, the server notifies security or relevant parties of the necessary information. The input is the estimated result of the emotional state, and the output is an instruction or alarm that is sent as warning information.

[0570] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0571] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0572] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0573] [Fourth Embodiment]

[0574] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0575] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0576] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0577] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0578] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0579] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0580] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0581] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0582] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0583] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0584] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0585] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0586] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0587] The system for implementing the present invention integrates multiple earphone-type devices and a backend server system to filter noise during rescue operations and amplify specific sounds such as the voices and breathing sounds of victims for use by rescue workers. Each device collects ambient sounds in real time and transmits the data to the server via wireless communication.

[0588] The server is responsible for processing the collected audio data, effectively removing noise components using a generative AI model. During this process, time-frequency analysis techniques are used to filter and pick up faint voice signals from victims. Next, the detected specific sounds are amplified and retransmitted to earphones worn by rescue workers. This audio processing makes it possible to hear the voices of victims more clearly from beneath the rubble.

[0589] The server also has analytical capabilities, which allow it to report on the likelihood of victims and their situation based on audio data. For example, it can filter out sounds that are mistakenly identified as noise and convert sounds that appear to be human voices into text data for rescue workers.

[0590] Furthermore, this system synchronizes multiple earphones, thereby using triangulation technology to pinpoint the location of the sound source. This location information is plotted on a map, allowing rescue teams to quickly receive the precise location of victims.

[0591] As a concrete example, if rescue teams use this system on-site after a major earthquake, each team member can wear earphones and search for rubble while relying on the clear voices of victims transmitted from the server. Furthermore, based on the analyzed report data, it becomes possible to understand the situation of the victims and carry out more efficient rescue operations.

[0592] The present invention, possessing the above-described functions, has the effect of improving the success rate of life-saving operations by promptly providing important clues during rescue activities.

[0593] The following describes the processing flow.

[0594] Step 1:

[0595] When a user begins a rescue operation, each device (earphone) collects ambient sounds in real time. The microphone built into the earphone detects the sound, digitizes it, and saves it as data.

[0596] Step 2:

[0597] The terminal compresses the collected audio data and transmits it to the server using wireless communication technology. An audio codec is used to reduce data volume and enable rapid transfer.

[0598] Step 3:

[0599] The server analyzes the received audio data and applies a generative AI model to filter out ambient noise. By performing a Fourier transform and removing noise components in the frequency domain, it emphasizes important sounds.

[0600] Step 4:

[0601] The server amplifies specific sounds and transmits the amplified audio data to the terminal. It plays a particularly important role in making the voices and breathing sounds of disaster victims clearer and delivering them directly to rescue workers.

[0602] Step 5:

[0603] The server further analyzes the amplified audio data, converting human voice components and sounds that convey the situation into text, and informing the user. An AI model is used to estimate the presence and number of victims.

[0604] Step 6:

[0605] All devices worn by the user synchronize voice data detection information with each other and transmit location information to a server. Bluetooth or Wi-Fi is used to maintain synchronization between devices.

[0606] Step 7:

[0607] The server uses triangulation technology to pinpoint the location of the sound source based on the data transmitted from each terminal. It calculates the time difference and sound intensity difference of the received data and displays the estimated location of the victims on a map.

[0608] Step 8:

[0609] The server sends location information and analysis results to rescue workers' earphones, supporting rapid and efficient rescue operations. It provides necessary data in real time via voice and text information.

[0610] (Example 1)

[0611] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0612] At natural disaster and accident sites, there is a need to effectively detect faint sounds such as the voices and breathing sounds of victims and to quickly pinpoint their location. However, these specific sounds can be masked by surrounding noise, potentially significantly reducing the efficiency of rescue operations. It is necessary to solve this problem and increase the success rate of rescue operations.

[0613] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0614] In this invention, the server includes means for acquiring environmental information, means for removing noise using a generative model, and means for analyzing sound information and reporting the state of an individual. This makes it possible to effectively filter ambient noise, clearly detect the voice of a victim, and quickly pinpoint their location.

[0615] "Means for acquiring environmental information" refers to a function that collects surrounding conditions, including sound, in real time using sensors and microphones.

[0616] "Means of transmitting data to a central device via a communication network" refers to a system that transfers collected data to a central management device using wireless technologies such as Bluetooth or Wi-Fi.

[0617] "A method of removing noise using a generative model" is a process that utilizes machine learning models to effectively eliminate unwanted noise from collected audio data and extract only the important sounds.

[0618] "Means for amplifying processed audio information and retransmitting it to a receiving device" refers to a technology that amplifies a specific audio signal to an appropriate level before distributing it again to the user's device.

[0619] "A means of analyzing sound information to report the status of individuals" refers to a system that analyzes audio data to determine the presence and condition of disaster victims and reports the results to the rescue team.

[0620] "Means for synchronizing multiple receiving devices to determine the location of a sound source" refers to a method for synchronously processing audio data from multiple devices to identify the source of the sound.

[0621] A "means for visually displaying the location of a sound source" is a tool that displays the location of an identified sound source on a visual medium such as a map, and immediately provides location information to rescue teams.

[0622] This system is composed of three main components: a terminal, a server, and a user. The terminal plays a crucial role in implementing the invention. Designed as an earphone-type device, it is equipped with a high-sensitivity microphone. This microphone allows for real-time acquisition of environmental information from the rescue site.

[0623] Next, the audio data collected by the terminal is transmitted to a server via a communication network. Wireless communication technologies such as Bluetooth and Wi-Fi are used here. The server uses a generative AI model to remove noise from the received audio data. This AI model utilizes machine learning techniques, and in particular, it is responsible for the phase of extracting the necessary audio signals using time-frequency analysis.

[0624] The server also amplifies the processed audio and sends it back to the terminal. Users can then listen to this cleared audio through earphones to confirm the presence of victims. Furthermore, the server has a function to analyze the sound information, converting the audio data into text format and reporting the victim's condition to the rescue team. This information plays a crucial role in making decisions regarding rescue operations.

[0625] The rescue team, as the user, can then use this amplified and analyzed audio and location information to pinpoint the exact location of victims. To achieve this, the server synchronizes multiple receiving devices and uses triangulation technology to identify the sound source's location. The sound source's location is visually displayed and quickly communicated to the user.

[0626] As a concrete example, the prompt text to be input to the generative AI model can be written as follows: "Please tell me how to identify human voices from audio data collected at a disaster site, remove noise, and then amplify them."

[0627] This system utilizes advanced technology to quickly and accurately detect the voices of disaster victims and pinpoint their location, even in noisy environments.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1:

[0630] The device uses a microphone to acquire environmental information in real time. The input is ambient sound, which the microphone converts into digital data and outputs. This data also contains noise.

[0631] Step 2:

[0632] The terminal packets the digitized voice data and sends it to the server using Bluetooth or Wi-Fi. The input is the digital voice data obtained in step 1, and the output is data packets transmitted wirelessly.

[0633] Step 3:

[0634] The server applies a generative AI model to the received audio data to remove noise. The input is the audio data sent in step 2, and the AI ​​model uses time-frequency analysis to extract specific sounds, resulting in filtered, clean audio data as output.

[0635] Step 4:

[0636] The server amplifies the identified audio data and then retransmits it to the terminal. The input is the filtered audio data, which is the output from step 3. The server adjusts the data to a constant volume and outputs it. The output is the amplified audio signal.

[0637] Step 5:

[0638] The device provides the user with the received audio signal through earphones. The input is amplified audio data retransmitted from the server, and the output is the audio the user actually hears. In this step, the user can hear the voices of disaster victims more clearly.

[0639] Step 6:

[0640] The server analyzes the audio data, converts it to text format, and reports information about the victims to the user. The input is filtered audio data, and natural language processing technology is used to convert the audio to text and output it.

[0641] Step 7:

[0642] A server synchronizes data across multiple earphone devices and uses triangulation technology to pinpoint the location of the sound source. The input is audio information from each earphone, and the output is visually plotted location information. This information is quickly provided to the user to aid in rescue operations.

[0643] (Application Example 1)

[0644] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0645] Current emergency response systems have problems with detecting specific sounds in noisy environments and immediately pinpointing their location, which hinders a rapid response. Furthermore, abnormal sounds and danger signals are not detected in real time, leading to delays in detection and increased risk.

[0646] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0647] In this invention, the server includes means for filtering noise, means for amplifying specific sounds, means for analyzing audio data and reporting specific situations, means for synchronizing multiple information terminals to identify the location of a sound source, means for detecting abnormal sounds and danger signals, and means for displaying the location of specific sounds based on map information. This makes it possible to quickly and accurately detect abnormal sounds and danger signals, and to identify and display their locations.

[0648] "Means of filtering noise" are functions that remove unnecessary background noise and clarify important audio signals.

[0649] "Means for amplifying specific sounds" refers to techniques that increase the volume of detected specific sounds in order to make them easier to hear.

[0650] "Means of analyzing audio data to report specific situations" refers to a function that analyzes audio data and uses the obtained information to report on specific situations or events.

[0651] "A means of synchronizing multiple information terminals to pinpoint the location of a sound source" refers to a function that performs data exchange between multiple devices to accurately identify the location from which the sound was emitted.

[0652] "Means for detecting abnormal sounds and danger signals" refers to technologies for identifying sounds that are unusual or indicate danger from within the ambient noise.

[0653] "Means for displaying the location of a specific sound based on map information" refers to a function for visualizing the location where the detected sound originated on a map.

[0654] The system realizing this invention rapidly detects abnormal sounds and danger signals by linking smart devices with a central processing unit, and displays their location based on map information. This system consists of smart devices (e.g., smart glasses, headsets, etc.) for collecting ambient sounds and a central server for processing the data.

[0655] Smart devices collect ambient audio data in real time using their built-in microphones and transmit it to a server using wireless communication technology. The collected audio data is digitized on the server using audio processing libraries such as Librosa, and noise is filtered by a generative AI model. This model detects abnormal sounds and danger signals, amplifies specific sounds, and identifies their location using triangulation technology. The location information is visualized and plotted on a map using a map plotting library such as Leaflet.js.

[0656] In this way, users such as security guards and rescue workers can instantly detect abnormal sounds and danger signals and accurately pinpoint their location. For example, during a nighttime patrol of a large facility, the system can detect the sound of breaking glass and display its location on a map, allowing users to respond quickly. This system effectively incorporates a generative AI model, and prompt messages such as "If an abnormal sound is detected on the premises, immediately issue an alert and display the location on the map" can be used.

[0657] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0658] Step 1:

[0659] The device uses its built-in microphone to collect ambient sounds. This audio data is temporarily stored within the device.

[0660] Step 2:

[0661] The terminal transmits the collected audio data to the server using wireless communication technology. The input is audio data, and the output is data transferred to the server.

[0662] Step 3:

[0663] The server digitizes the received audio data using the Librosa library. The input is the audio data transmitted from the terminal, and the output is the audio data converted into digital format.

[0664] Step 4:

[0665] The server uses a generative AI model to filter out noise and amplify specific sounds from digitized audio data. The input is digitized audio data, and the output is filtered audio data.

[0666] Step 5:

[0667] The server uses triangulation technology to identify the sound source location of the amplified audio data. The input is filtered audio data, and the output is sound source location information.

[0668] Step 6:

[0669] The server uses Leaflet.js to plot and visualize the location of sound sources on a map. The input is the location information of the sound sources, and the output is the visualized map information.

[0670] Step 7:

[0671] Users can view map information through their device's display and respond quickly to on-site incidents based on the location of abnormal sounds or danger signals.

[0672] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0673] The system for implementing this invention integrates hardware that effectively filters noise and amplifies the voices and breathing sounds of victims, along with software equipped with an emotion engine. The aim of this system is to enable more precise and humane responses in rescue operations.

[0674] The earphone-type device worn by the user collects ambient sounds in real time and uses a generative AI model to remove unwanted noise. The filtered audio data is sent to a server, where specific sounds originating from the victim are amplified. Using the amplified audio data, the server analyzes the victim's situation and further examines it using an emotion engine. The emotion engine estimates the victim's emotional state from the tone and patterns of their voice and generates psychological support information necessary for saving lives. This allows rescue workers to understand the victim's emotional state and provide support quickly.

[0675] As a concrete example, if rescue workers use this system during post-earthquake rescue operations, voice analysis will clearly reveal cries for help, and the emotion engine will estimate that these cries are based on feelings of tension and fear. Based on this, rescue workers can flexibly adjust their approach to the victims and carry out rescue operations while calming them down.

[0676] This system also features a triangulation function that enables highly accurate location identification of disaster victims through real-time processing and digitization of audio data. Multiple terminals send data on the direction of the sound source to a server, which then calculates the location. This result is visualized on a map and provided to each rescue team member.

[0677] As a result, rescue operations can provide a new dimension of support that not only is swift but also addresses the emotions of the victims.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] When a user begins a rescue operation, each device (earphone) collects ambient sounds in real time. The built-in microphone in the device detects the sound and generates data as a digital signal.

[0681] Step 2:

[0682] The terminal compresses the collected audio data and transmits it to the server using wireless communication technology. The data is efficiently compressed and configured to arrive at the server immediately.

[0683] Step 3:

[0684] The server processes the received audio data and filters out noise components using a generative AI model. It converts the audio signal to the frequency domain, removing unwanted noise and clarifying important sounds.

[0685] Step 4:

[0686] The server amplifies specific sounds originating from disaster victims and transmits them to the terminal. These specific sounds, such as voices or breathing sounds, are amplified and returned to the user's earphones.

[0687] Step 5:

[0688] The server analyzes the amplified audio data and uses an emotion engine to analyze the tone and patterns of the voice. This allows it to estimate the emotional state of the victims.

[0689] Step 6:

[0690] Based on the emotional information generated by the emotion engine, the server provides users with appropriate information and guidance for action. It outputs psychological support information tailored to the emotional state of disaster victims.

[0691] Step 7:

[0692] The user's device receives information from the server via voice or text, which is then used in rescue operations. This information is used to facilitate communication with disaster victims and to inform rescue operation strategies.

[0693] Step 8:

[0694] The devices share detection information for audio data, and the server obtains location information from multiple devices. Triangulation technology is used to pinpoint the location of the sound source, and this information is provided to the user.

[0695] Step 9:

[0696] The server transmits data combining analysis results and location information to the user in real time, providing comprehensive support to facilitate rescue operations.

[0697] (Example 2)

[0698] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0699] In disaster areas, ambient noise makes it difficult to pinpoint the location and condition of victims. This problem reduces the efficiency of rescue operations and causes delays in saving lives. Furthermore, understanding the psychological state of victims is crucial for rescue workers to respond appropriately, but conventional techniques make it difficult to do this accurately.

[0700] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0701] In this invention, the server includes means for collecting audio data and removing scattered noise, means for processing the collected audio data and amplifying important sounds, and means for analyzing the received audio information and estimating the psychological state of individuals. This enables the rapid and accurate location and understanding of the psychological state of victims during rescue operations.

[0702] "Audio data" refers to a collection of information captured as an acoustic signal and represented in electrical or digital format.

[0703] "Noise" refers to unwanted acoustic elements that degrade the quality of the intended signal or information.

[0704] A "sound source" refers to the physical starting point or device that generates sound waves.

[0705] "Amplification" is the process of increasing the strength and magnitude of a signal to make it clearer.

[0706] "Psychological state" refers to the mental condition of an individual from the perspective of their cognitive, emotional, and behavioral responses.

[0707] "Encoding" is the process of converting analog or digital information into a specific format.

[0708] A "central control unit" refers to a central computer or server that manages information for the entire system and is responsible for data processing and issuing commands.

[0709] The system for implementing this invention is an advanced acoustic processing and analysis system that efficiently extracts and analyzes the voices of disaster victims in noisy environments. The terminal used by the user is an earphone-type device equipped with a high-sensitivity microphone that collects ambient sound data in real time. This terminal uses a generative AI model to remove noise and amplify the voices of disaster victims, for example, using "Whisper" technology.

[0710] The amplified audio data is analyzed by a server. The server further processes the audio data, picking out and emphasizing specific audio signals. Advanced algorithms are used for the analysis to identify important audio, which is then stored in a database.

[0711] The server also uses an emotion analysis engine to estimate the psychological state of victims from the tone and patterns of their voices. Software such as "EmotionXtract" is used to analyze emotional states and generate psychological support information useful for rescue operations. This allows rescue workers to respond flexibly to the psychological situation of victims.

[0712] Furthermore, this system aggregates sound source direction data from multiple terminals to a server and uses triangulation technology to pinpoint the precise location of victims. This location data is visualized on a map and provided to each rescue team member, supporting rapid and appropriate rescue operations.

[0713] As a concrete example, in rescue operations after an earthquake, rescue workers can use this system to clearly separate cries for help from other noise and determine that the emotion behind those cries is urgent. Based on this information, rescue workers can provide support while psychologically empathizing with the victims.

[0714] An example of a prompt might be: "Filter the audio collected at the scene and amplify the 'help me' cries. Then, describe the procedure for estimating the emotional state of those cries and generating necessary psychological support information." This allows for more humane and effective rescue operations.

[0715] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0716] Step 1:

[0717] The device, worn by the user as an earphone-type device, collects ambient sound using a high-sensitivity microphone. This input audio data is converted into a digital format. The converted result is output in a format suitable for information processing.

[0718] Step 2:

[0719] The device analyzes the collected digital audio data using a generating AI model and removes noise. In this process, the AI ​​model evaluates the frequency characteristics of each sound and filters out unnecessary sounds to generate clear audio. Clear audio data after filtering is output.

[0720] Step 3:

[0721] The terminal immediately sends the filtered audio data to the server. This transmission is performed using a low-latency, highly efficient communication protocol, and the output is stored in the server's receive buffer.

[0722] Step 4:

[0723] The server analyzes the received audio data and amplifies certain important sounds. In this process, the analysis algorithm selects and emphasizes sounds based on specific patterns and volume thresholds. The amplified audio is output in a format that can be used in rescue operations.

[0724] Step 5:

[0725] The server inputs the amplified audio data into an emotion analysis engine, which estimates the psychological state from the tone and patterns of the voice. The emotion engine analyzes features such as pitch, intensity, and speed of the voice and labels them with emotion categories. The generated emotion data is output and provided to the rescue team.

[0726] Step 6:

[0727] The server integrates sound source direction data received from multiple terminals and calculates the precise location of the sound source using triangulation. Each direction data is analyzed using geometric calculations to pinpoint the location of the victim. The identified location data is output and visualized on a map for rescue workers to see.

[0728] (Application Example 2)

[0729] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0730] In order to respond quickly and accurately to sudden emergencies in public transportation and large facilities, it is essential to efficiently filter important auditory information from the surrounding noise environment and analyze emotional states. However, conventional methods have been hindered by the large amount of noise, making it difficult to accurately capture urgent voices and emotional states, thus limiting the effectiveness of a rapid response.

[0731] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0732] In this invention, the server includes a device for filtering noise, a device for amplifying specific sounds, a device for analyzing audio data and reporting the situation, a device for synchronizing multiple terminals to identify the location of the sound source, software for analyzing the emotional state of the voice and generating psychological instructions, and a device for detecting events in emergencies and providing warning information. This enables the rapid collection of necessary information and appropriate security responses even in emergencies in public places.

[0733] "Device" refers to mechanical or electrical equipment designed to perform a specific function.

[0734] A "terminal" is an input / output device used for information processing and communication.

[0735] "Synchronization" refers to the process of coordinating multiple devices or systems to operate simultaneously in the same state or at the same time.

[0736] "Software" is a collection of programmed instructions that enable a computer to perform tasks and operations.

[0737] "Audio data" refers to digitally recorded audio information and is one of the data formats used for analysis and processing.

[0738] "Emotional state" refers to a person's psychological state, inferred from the tone and pattern of their voice.

[0739] "Warning information" refers to information indicating that security measures or caution are necessary in response to an emergency or unusual event.

[0740] The system required to implement this invention mainly includes the following components. First, the user wears a device that collects sound, thereby acquiring ambient sounds in real time. The device processes the sound data using a generating AI model to filter out noise and identify and amplify the desired sounds. The processed sound data is sent to a server, which uses an emotion engine to analyze the emotional state of the voice based on this data.

[0741] The server uses a Python-based speech analysis library (e.g., Librosa) and a generative AI model (e.g., an OpenAI model) to perform noise filtering and sentiment analysis on speech data. Based on the analysis results, the server provides alert information to security guards and relevant staff in public spaces, enabling a quick and appropriate response.

[0742] For example, if a sudden abnormal sound is detected on a train, the server analyzes the sound to identify emotional states such as urgency or fear. This information is immediately notified to the relevant parties, and necessary measures are taken. An example of a prompt message is, "Analyze the emotional states that may be identifiable from this audio and assess whether a rapid security response is required." Using this prompt message, a generative AI model analyzes the audio data and derives the optimal action.

[0743] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0744] Step 1:

[0745] The user wears a device that collects audio. The device acquires ambient sounds in real time and outputs the data as digital audio data. The input here is ambient sound, and the output is raw, unprocessed audio data before filtering.

[0746] Step 2:

[0747] The device processes digital audio data using a generative AI model to remove background noise. The input is digital audio data, and noise filtering is performed using prompt text. The output is clean audio data with the noise removed.

[0748] Step 3:

[0749] Clean audio data is analyzed to amplify specific sounds. The terminal uses this analysis to highlight sounds containing specific emergency or anomaly signals, generating amplified audio data. The input is noise-free audio data, and the output is audio data with specific sounds amplified.

[0750] Step 4:

[0751] The terminal sends the amplified audio data to the server. Here, the input is the amplified audio data, and the processed output is the analyzable audio data sent to the server.

[0752] Step 5:

[0753] The server processes the amplified audio data through an emotion engine and uses a generative AI model to analyze the emotional state of the audio. The input is amplified audio data, and emotion analysis is performed using prompt text. The output is the estimated emotional state based on the analysis.

[0754] Step 6:

[0755] Based on the analysis results, the server notifies security or relevant parties of the necessary information. The input is the estimated result of the emotional state, and the output is an instruction or alarm that is sent as warning information.

[0756] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0757] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0758] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0759] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0760] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0761] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0762] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0763] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0764] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0765] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0766] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0767] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0768] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0769] 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.

[0770] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0771] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0772] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0773] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0774] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0775] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0776] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0777] The following is further disclosed regarding the embodiments described above.

[0778] (Claim 1)

[0779] A means of filtering noise,

[0780] A means of amplifying a specific sound,

[0781] A means of analyzing audio data to report on the situation of disaster victims,

[0782] A means of synchronizing multiple devices to determine the location of the sound source,

[0783] A system that includes this.

[0784] (Claim 2)

[0785] The system according to claim 1, further comprising means for processing the generated data in real time.

[0786] (Claim 3)

[0787] The system according to claim 1, further comprising means for digitizing audio data and transmitting it to a server.

[0788] "Example 1"

[0789] (Claim 1)

[0790] Means of acquiring environmental information,

[0791] A means for transmitting acquired information to a central device via a communication network,

[0792] A method for removing noise using a generative model,

[0793] A means for amplifying processed sound information and retransmitting it to a receiving device,

[0794] A means of analyzing sound information to report the state of an individual,

[0795] A means for synchronizing multiple receiving devices to determine the location of a sound source,

[0796] A means of visually displaying the sound source location,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, further comprising means for immediately processing the generated information.

[0800] (Claim 3)

[0801] The system according to claim 1, further comprising means for quantifying sound information and transmitting it to a central device.

[0802] "Application Example 1"

[0803] (Claim 1)

[0804] A means of filtering noise,

[0805] A means of amplifying a specific sound,

[0806] A means of analyzing audio data to report specific situations,

[0807] A means of synchronizing multiple information terminals to determine the location of a sound source,

[0808] A means of detecting abnormal sounds or danger signals,

[0809] A means for displaying the location of a specific sound based on map information,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, further comprising means for processing the generated data in real time.

[0813] (Claim 3)

[0814] The system according to claim 1, further comprising means for digitizing audio data and transmitting it to a central processing unit.

[0815] "Example 2 of combining an emotion engine"

[0816] (Claim 1)

[0817] A means for collecting audio data and removing scattered noise,

[0818] A means of processing collected audio data to amplify important sounds,

[0819] A means of analyzing received audio information and estimating the psychological state of an individual,

[0820] A means for integrating directional data from multiple sound sources and calculating the location of the source,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, further comprising means for immediately processing the generated data.

[0824] (Claim 3)

[0825] The system according to claim 1, further comprising means for encoding audio information and transmitting it to a central control unit.

[0826] "Application example 2 when combining with an emotional engine"

[0827] (Claim 1)

[0828] A noise filtering device,

[0829] A device that amplifies specific sounds,

[0830] A device that analyzes audio data and reports the situation,

[0831] A device that synchronizes multiple terminals to pinpoint the location of a sound source,

[0832] Software that analyzes the emotional state of voice and generates psychological instructions,

[0833] A device that detects events during emergencies and provides warning information,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, further comprising a function for immediately processing the generated data.

[0837] (Claim 3)

[0838] The system according to claim 1, further comprising a function for digitizing audio data and transmitting it to a central processing unit. [Explanation of Symbols]

[0839] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of filtering noise, A means of amplifying a specific sound, A means of analyzing audio data to report on the situation of disaster victims, A means of synchronizing multiple devices to determine the location of the sound source, A system that includes this.

2. The system according to claim 1, further comprising means for processing the generated data in real time.

3. The system according to claim 1, further comprising means for digitizing audio data and transmitting it to a server.

Images