System

Abstract

An object of a system according to an embodiment is to enable a hearing-impaired person to visually or sensorially recognize a generation source or content of a sound.SOLUTION: A system according to an embodiment includes a sound collection unit, an analysis unit, a display unit, a camera unit, a direction estimation unit, and a vibration unit. The sound collection unit collects sound and environmental sound. The analysis unit analyzes the voice and the environmental sound collected by the voice collection unit. The display section displays the onomatopoeic sound analyzed by the analysis section. The camera unit recognizes a sound generation source. The direction estimation unit associates the sound generation source recognized by the camera unit with the generated sound. The vibration part expresses the direction of the sound generation source estimated by the direction estimation part by vibration.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem that it is difficult for hearing-impaired people to visually or sensorily recognize the source and content of a sound.

[0005] The system according to the embodiment aims to enable hearing-impaired people to visually and tactilely recognize the source and content of sounds. [Means for solving the problem]

[0006] The system according to the embodiment includes a sound collection unit, an analysis unit, a display unit, a camera unit, a direction estimation unit, and a vibration unit. The sound collection unit collects sound and environmental sound. The analysis unit analyzes the sound and environmental sound collected by the sound collection unit. The display unit displays the onomatopoeic sound analyzed by the analysis unit. The camera unit recognizes the source of the sound. The direction estimation unit associates the sound source recognized by the camera unit with the sound that is generated. The vibration unit expresses the direction of the sound source estimated by the direction estimation unit by vibration. [Effects of the Invention]

[0007] The system according to the embodiment can enable a person with hearing impairments to visually and tactilely recognize the source and content of a sound. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The sound visualization and sensory system according to the embodiment of the present invention is a system that enables hearing-impaired people to recognize sound information visually and with their senses. As a result, the sound visualization and sensory system enables hearing-impaired people to recognize sound information visually and with their senses.

[0029] A sound visualization and sensory system according to an embodiment includes a sound collection unit, an analysis unit, a display unit, a camera unit, a direction estimation unit, and a vibration unit. The sound collection unit collects sound and environmental sounds. For example, the sound collection unit collects ambient sounds using multiple microphones. The sound collection unit can also use a high-sensitivity microphone to collect environmental sounds. The sound collection unit can also focus on a specific sound source for collection. The analysis unit analyzes the sound and environmental sounds collected by the sound collection unit. For example, the analysis unit analyzes sound data using voice recognition technology. The analysis unit can also perform frequency analysis to extract sound characteristics. The analysis unit can also extract acoustic features and identify the type of sound. The display unit displays the onomatopoeic sounds analyzed by the analysis unit. For example, the display unit displays the onomatopoeic sounds as characters on the lens of the MR device. The display unit can also display onomatopoeic words corresponding to the source of the sound. The display unit can also change the display content depending on the intensity and type of sound. The camera unit recognizes the source of the sound. For example, the camera unit recognizes the source of the sound using a camera in the smart glasses. The camera unit can also identify the source of the sound using image recognition technology. The camera unit can also track the movement of the sound source. The direction estimation unit associates the sound source recognized by the camera unit with the generated sound. For example, the direction estimation unit associates sounds based on position information of the sound source. The direction estimation unit can also associate sounds according to the movement of the sound source. The direction estimation unit can also associate sounds according to the type of sound source. The vibration unit expresses the direction of the sound source estimated by the direction estimation unit using vibration. For example, the vibration unit expresses whether the direction is up, down, left, right, front, or back using vibration. The vibration unit can also express direction by changing the intensity and pattern of the vibration. The vibration unit can also express direction by combining multiple motors. As a result, the sound visualization and sensoryization system according to the embodiment enables hearing-impaired people to recognize sound information visually and sensorily.

[0030] The analysis unit may include a generation AI that analyzes audio data and generates onomatopoeic sounds. The analysis unit, for example, collects audio data and performs emotion analysis using the generation AI. For example, if a dog's bark indicates a happy emotion, it generates the onomatopoeia "woof woof." The analysis unit also collects environmental sounds and performs emotion analysis using the generation AI. For example, if the sound of rain indicates a calm emotion, it generates the onomatopoeia "drops." The analysis unit also collects human voices and performs emotion analysis using the generation AI. For example, if laughter indicates a happy emotion, it generates the onomatopoeia "ha ha ha." In this way, by converting the audio data into onomatopoeia and displaying it, sounds can be visually recognized.

[0031] When collecting voice data, the voice collection unit can simultaneously collect environmental data such as ambient temperature and humidity and reflect the data in the analysis. For example, when collecting voice data, the voice collection unit simultaneously collects ambient temperature data using a temperature sensor. For example, voice data in a cold environment is analyzed. When collecting voice data, the voice collection unit simultaneously collects ambient humidity data using a humidity sensor. For example, voice data in a high humidity environment is analyzed. When collecting voice data, the voice collection unit simultaneously collects ambient atmospheric pressure data using a barometric pressure sensor. For example, voice data at a high altitude is analyzed. This allows environmental data to be reflected in the analysis, enabling more accurate voice analysis.

[0032] The sound collection unit can use drones or robots to collect sound data and analyze a wide range of sound environments. The sound collection unit, for example, uses drones to collect wide range of sound data. For example, the sound environment of an entire city is analyzed. The sound collection unit also uses robots to collect sound data in specific areas. For example, the sound environment inside a factory is analyzed. The sound collection unit also combines drones and robots to simultaneously collect sound data from multiple areas. For example, the sound environment of an event venue is analyzed. This allows for the collection of a wider range of sound environments, allowing for the collection of a wider variety of sound data.

[0033] The sound collection unit simultaneously analyzes sounds in different frequency bands when collecting sound data, allowing for a more detailed understanding of the sound environment. For example, the sound collection unit analyzes sounds in the low frequency band when collecting sound data. For example, it analyzes precursory sounds of earthquakes. Furthermore, the sound collection unit analyzes sounds in the mid frequency band when collecting sound data. For example, it analyzes sounds of conversation. Furthermore, the sound collection unit analyzes sounds in the high frequency band when collecting sound data. For example, it analyzes birdsong. In this way, by analyzing sounds in different frequency bands, a more detailed understanding of the sound environment can be obtained.

[0034] The display unit can display the onomatopoeic sound at an optimal position based on the user's gaze tracking data. For example, the display unit displays the onomatopoeic sound at the point of the user's gaze based on the user's gaze tracking data. For example, it displays "woof woof" in the direction the gaze is facing. The display unit also dynamically displays the onomatopoeic sound in accordance with the movement of the gaze based on the gaze tracking data. For example, it updates the display position every time the gaze moves. The display unit also displays the onomatopoeic sound at the focus of the gaze based on the gaze tracking data. For example, it displays "boom" where the gaze is focused. In this way, by displaying the onomatopoeic sound at an optimal position based on the user's gaze, visual recognition is improved.

[0035] The display unit can make it possible for the user to customize the onomatopoeic sound according to their preferences. The display unit, for example, allows the user to customize the display style of the onomatopoeic sound. For example, the font or color can be changed. The display unit also allows the user to customize the display position of the onomatopoeic sound. For example, the display position can be set on the top, bottom, left, or right of the screen. The display unit also allows the user to customize the display timing of the onomatopoeic sound. For example, the delay time from when the sound is generated until it is displayed can be set. This allows the user to customize the onomatopoeic sound according to their preferences, making it possible to provide a system that is easier to use.

[0036] The display unit can use AR technology to display onomatopoeic sounds superimposed on real-world objects. For example, the display unit uses AR technology to display onomatopoeic sounds superimposed on real-world objects. For example, a "woof woof" sound is displayed near a dog. The display unit also uses AR technology to dynamically display onomatopoeic sounds. For example, a "boom" sound is displayed in the direction a car is moving. The display unit also uses AR technology to display onomatopoeic sounds in 3D space. For example, the sound of a bird is displayed in the air as a "chirp chirp." In this way, sound information can be superimposed on real-world objects using AR technology.

[0037] The display unit can automatically translate the onomatopoeic sounds into different languages ​​to accommodate international users. For example, the display unit can automatically translate the onomatopoeic sounds and display them in different languages. For example, "woof woof" is displayed in English as "Woof Woof." The display unit can also make the onomatopoeic sounds multilingual, allowing the user to select the language. For example, the display language can be selected from Japanese, English, and Chinese. The display unit can also translate the onomatopoeic sounds in real time and display them in different languages. For example, the display unit can automatically translate and display the sound the moment it is generated. This allows for automatic translation into different languages ​​to accommodate international users.

[0038] When recognizing the source of a sound, the camera unit also analyzes the movement and shape of the object, allowing for more accurate association. For example, when recognizing the source of a sound, the camera unit analyzes the movement of the object. For example, the engine sound of a moving car may be associated with a "boom." When recognizing the source of a sound, the camera unit also analyzes the shape of the object. For example, the shape of a dog may be recognized and its bark may be associated with a "woof woof." When recognizing the source of a sound, the camera unit also analyzes the color of the object. For example, the engine sound of a red car may be associated with a "boom." In this way, by analyzing the movement and shape of the object, the source of the sound can be recognized more accurately.

[0039] When recognizing the source of a sound, the camera unit can refer to past data and learn the source pattern. For example, the camera unit refers to past data when recognizing the source of a sound. For example, it may associate a previously recognized dog bark with "woof woof." In addition, the camera unit learns the source pattern when recognizing the source of a sound. For example, it may associate the engine sound of a particular car with "boom." In addition, when recognizing the source of a sound, the camera unit predicts the source pattern based on past data. For example, it may associate a particular environmental sound with "buzzing." In this way, by referring to past data and learning the source pattern, the source of the sound can be recognized more accurately.

[0040] The camera unit can use multiple cameras to integrate data from different angles when recognizing the source of a sound. For example, the camera unit uses multiple cameras to recognize the source of a sound from different angles. For example, the front and rear cameras are used to identify the source of a sound. The camera unit also integrates camera data from different angles to more accurately recognize the source of a sound. For example, left and right cameras are used to identify the source of a sound. The camera unit also uses multiple cameras to recognize the source of a sound in 3D space. For example, cameras on the top, bottom, left, and right are used to identify the source of a sound. In this way, by using multiple cameras, data from different angles can be integrated to more accurately recognize the source of a sound.

[0041] When recognizing the source of a sound, the camera unit can use drones or robots to collect data over a wide area. For example, the camera unit uses drones to recognize the source of a wide area of ​​sound. For example, it can identify the source of a sound throughout an entire city. The camera unit can also use robots to recognize the source of a sound in a specific area. For example, it can identify the source of a sound inside a factory. The camera unit can also combine drones and robots to recognize the source of sound in multiple areas simultaneously. For example, it can identify the source of a sound at an event venue. This allows the use of drones and robots to collect data over a wide area and more accurately identify the source of a sound.

[0042] The vibration unit can provide more detailed directional information by changing the intensity and pattern of vibration when sensing the direction of a sound source. For example, the vibration unit changes the intensity of vibration when sensing the direction of a sound source. For example, a strong vibration is provided for a nearby sound source. The vibration unit also changes the pattern of vibration when sensing the direction of a sound source. For example, a weak vibration is provided for a distant sound source. The vibration unit also changes the frequency of vibration when sensing the direction of a sound source. For example, a high-frequency vibration is provided for a sound source above or below. In this way, by changing the intensity and pattern of vibration, more detailed directional information can be provided.

[0043] The vibration unit can monitor the user's movements and posture when sensing the direction of the sound source, and provide an optimal vibration pattern. The vibration unit, for example, monitors the user's movements and provides an optimal vibration pattern when sensing the direction of the sound source. For example, the vibration pattern is adjusted for a user who is walking. The vibration unit can also monitor the user's posture and provide an optimal vibration pattern when sensing the direction of the sound source. For example, the vibration pattern is adjusted for a user who is sitting. The vibration unit can also monitor the user's movements and posture in real time, and provide an optimal vibration pattern when sensing the direction of the sound source. For example, the vibration pattern is adjusted for a user who is running. In this way, the optimal vibration pattern can be provided by monitoring the user's movements and posture.

[0044] When the vibration unit senses the direction of the sound source, the vibration unit can provide more detailed sensory information by using a haptic feedback device. The vibration unit senses the direction of the sound source by using, for example, a haptic feedback device. For example, a device worn on the wrist provides vibrations. The vibration unit also senses the direction of the sound source by using a haptic feedback device. For example, a device worn on the waist provides vibrations. The vibration unit also senses the direction of the sound source by using a haptic feedback device. For example, a device worn on the ankle provides vibrations. In this way, by using the haptic feedback device, more detailed sensory information can be provided.

[0045] The vibration unit can express the type and intensity of a sound by using different vibration patterns when sensing the direction of a sound source. The vibration unit, for example, expresses the type of sound by using different vibration patterns. For example, in the case of a dog barking, it provides short vibrations. The vibration unit also expresses the intensity of the sound by using different vibration patterns. For example, in the case of the sound of a car engine, it provides long vibrations. The vibration unit also expresses the type and intensity of a sound by using different vibration patterns. For example, in the case of a bird singing, it provides high-frequency vibrations. In this way, the type and intensity of a sound can be expressed by using different vibration patterns.

[0046] The analysis unit can incorporate data from different regions and cultures into the optimization of the analysis model, enabling global responsiveness. The analysis unit, for example, collects speech data from different regions and incorporates it into the analysis model. For example, it analyzes Japanese dialects and distinctive environmental sounds. The analysis unit also collects speech data from different cultures and incorporates it into the analysis model. For example, it analyzes traditional African music and environmental sounds. The analysis unit also incorporates data from different regions and cultures into the analysis model to enable global responsiveness. For example, it analyzes European urban sounds and natural sounds. In this way, incorporating data from different regions and cultures enables global responsiveness.

[0047] The analysis unit can reflect user feedback in real time in optimizing the analysis model, thereby enabling continuous improvement. The analysis unit, for example, collects user feedback in real time and reflects it in the analysis model. For example, the analysis unit collects feedback to improve the accuracy of voice recognition. The analysis unit also continuously improves the analysis model based on the user feedback. For example, the analysis unit collects feedback to improve the recognition accuracy of specific sounds. The analysis unit also reflects the user feedback collected in real time in the analysis model, thereby enabling continuous improvement. For example, the analysis unit collects feedback to improve the recognition accuracy of environmental sounds. In this way, the analysis model can be continuously improved by reflecting user feedback in real time.

[0048] The analysis unit can integrate data from different devices and platforms to optimize the analysis model and increase its versatility. The analysis unit, for example, collects data from different devices and incorporates it into the analysis model. For example, it analyzes voice data from smartphones and tablets. The analysis unit also collects data from different platforms and incorporates it into the analysis model. For example, it analyzes voice data from social media and messaging apps. The analysis unit also integrates data from different devices and platforms to increase the versatility of the analysis model. For example, it analyzes voice data from wearable devices. In this way, by integrating data from different devices and platforms, the versatility of the analysis model can be increased.

[0049] The analysis unit can formulate a step-by-step migration plan to smoothly migrate from cloud processing to an in-device self-contained system. The analysis unit, for example, formulates a plan to migrate from cloud processing to an in-device self-contained system in stages. For example, in the initial stage, some processing is performed within the device. The analysis unit also formulates a migration plan to smoothly migrate from cloud processing to an in-device self-contained system. For example, the processing capacity of the device is improved in stages. The analysis unit also conducts step-by-step tests to smoothly migrate from cloud processing to an in-device self-contained system. For example, performance evaluation is performed at each stage of the migration. In this way, by formulating a step-by-step migration plan, the migration from cloud processing to an in-device self-contained system can be smoothly performed.

[0050] The analysis unit can build a hybrid model of cloud processing and in-device self-contained processing and select the optimal processing method. The analysis unit, for example, builds a hybrid model of cloud processing and in-device self-contained processing and selects the optimal processing method. For example, the analysis unit complements cloud processing according to the processing capacity of the device. The analysis unit also uses the hybrid model to combine the advantages of cloud processing and in-device self-contained processing. For example, real-time processing is performed in-device, and large-scale analysis is performed in the cloud. The analysis unit also builds a hybrid model of cloud processing and in-device self-contained processing and selects the optimal processing method according to the user's needs. For example, if the network connection is unstable, processing is performed in-device. In this way, by building a hybrid model, the optimal processing method can be selected.

[0051] The analysis unit can utilize both cloud processing and in-device self-contained processing to meet different user needs. The analysis unit, for example, utilizes both cloud processing and in-device self-contained processing to build a system that meets different user needs. For example, advanced analysis is performed in the cloud, and basic processing is performed in the device. The analysis unit also combines the advantages of cloud processing and in-device self-contained processing to provide the optimal processing method according to the user's needs. For example, if real-time performance is required, processing is performed in the device. The analysis unit also utilizes both cloud processing and in-device self-contained processing to select the optimal processing method according to the user's usage status. For example, if the network connection is stable, cloud processing is performed. In this way, different user needs can be met by utilizing both cloud processing and in-device self-contained processing.

[0052] The analysis unit can ensure compatibility with different devices and platforms when migrating from cloud processing to an in-device self-contained system. The analysis unit ensures compatibility with different devices, for example, when migrating from cloud processing to an in-device self-contained system. For example, it realizes integration with smartphones and tablets. The analysis unit also ensures compatibility with different platforms, allowing for a smooth transition from cloud processing to an in-device self-contained system. For example, it ensures compatibility with Windows and MacOS. The analysis unit also performs tests to ensure compatibility with different devices and platforms when migrating from cloud processing to an in-device self-contained system. For example, it checks operation on each device. This ensures compatibility with different devices and platforms, allowing for a smooth transition.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] When collecting voice data, the voice collection unit can simultaneously collect environmental data such as ambient temperature and humidity and reflect the data in the analysis. For example, when collecting voice data, the voice collection unit simultaneously collects ambient temperature data using a temperature sensor. For example, voice data in a cold environment is analyzed. When collecting voice data, the voice collection unit simultaneously collects ambient humidity data using a humidity sensor. For example, voice data in a high humidity environment is analyzed. When collecting voice data, the voice collection unit simultaneously collects ambient atmospheric pressure data using a barometric pressure sensor. For example, voice data at a high altitude is analyzed. This allows environmental data to be reflected in the analysis, enabling more accurate voice analysis.

[0055] The sound collection unit can use drones or robots to collect sound data and analyze a wide range of sound environments. For example, the sound collection unit uses drones to collect wide range of sound data. For example, the sound environment of an entire city is analyzed. The sound collection unit also uses robots to collect sound data in a specific area. For example, the sound environment inside a factory is analyzed. The sound collection unit also combines drones and robots to simultaneously collect sound data from multiple areas. For example, the sound environment of an event venue is analyzed. This allows for the collection of a wider range of sound environments, allowing for the collection of a wider variety of sound data.

[0056] The sound collection unit simultaneously analyzes sounds in different frequency bands when collecting sound data, allowing for a more detailed understanding of the sound environment. For example, the sound collection unit analyzes sounds in the low frequency band when collecting sound data, such as analyzing precursory sounds of an earthquake. The sound collection unit also analyzes sounds in the mid frequency band when collecting sound data, such as analyzing sounds of conversation. The sound collection unit also analyzes sounds in the high frequency band when collecting sound data, such as analyzing birdsong. In this way, by analyzing sounds in different frequency bands, a more detailed understanding of the sound environment can be achieved.

[0057] The display unit can display the onomatopoeic sound at an optimal position based on the user's gaze tracking data. For example, the display unit displays the onomatopoeic sound at the point of the user's gaze based on the gaze tracking data. For example, it displays "woof woof" in the direction the gaze is facing. The display unit also dynamically displays the onomatopoeic sound in accordance with the movement of the gaze based on the gaze tracking data. For example, it updates the display position every time the gaze moves. The display unit also displays the onomatopoeic sound at the focus of the gaze based on the gaze tracking data. For example, it displays "boom" where the gaze is focused. In this way, by displaying the onomatopoeic sound at an optimal position based on the user's gaze, visual recognition is improved.

[0058] The display unit can customize the onomatopoeic sound according to the user's preferences. For example, the display unit allows the user to customize the display style of the onomatopoeic sound. For example, the font or color can be changed. The display unit also allows the user to customize the display position of the onomatopoeic sound. For example, the display position can be set on the top, bottom, left, or right of the screen. The display unit also allows the user to customize the display timing of the onomatopoeic sound. For example, the delay time from when the sound is generated until it is displayed can be set. This allows the user to customize the onomatopoeic sound according to their preferences, making it possible to provide a system that is easier to use.

[0059] The display unit can use AR technology to display onomatopoeic sounds superimposed on real-world objects. For example, the display unit uses AR technology to display onomatopoeic sounds superimposed on real-world objects. For example, the display unit displays "woof woof" near a dog. The display unit also uses AR technology to dynamically display onomatopoeic sounds. For example, the display unit displays "boom" in the direction a car is moving. The display unit also uses AR technology to display onomatopoeic sounds in 3D space. For example, the sound of a bird chirping is displayed in the air as "chirp chirp." In this way, sound information can be superimposed on real-world objects using AR technology.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The sound collection unit collects sounds and environmental sounds. For example, the sound collection unit collects ambient sounds using multiple microphones. The sound collection unit can also use a high-sensitivity microphone to collect environmental sounds. The sound collection unit can also focus on a specific sound source and collect sounds. Step 2: The analysis unit analyzes the voice and environmental sounds collected by the voice collection unit. For example, the analysis unit analyzes the voice data using voice recognition technology. The analysis unit can also perform frequency analysis and extract sound features. The analysis unit can also extract acoustic features and identify the type of sound. Step 3: The display unit displays the onomatopoeic sound analyzed by the analysis unit. For example, the display unit displays the onomatopoeic sound as characters on the lens of the MR device. The display unit can also display onomatopoeic words corresponding to the source of the sound. The display unit can also change the display content depending on the intensity and type of sound. Step 4: The camera unit recognizes the source of the sound. For example, the camera unit recognizes the source of the sound using the camera of the smart glasses. The camera unit can also identify the source of the sound using image recognition technology. The camera unit can also track the movement of the source of the sound. Step 5: The direction estimation unit associates the sound source recognized by the camera unit with the generated sound. For example, the direction estimation unit associates the sound based on the position information of the sound source. The direction estimation unit can also associate the sound according to the movement of the sound source. The direction estimation unit can also associate the sound according to the type of sound source. Step 6: The vibration unit uses vibration to express the direction of the sound source estimated by the direction estimation unit. For example, the vibration unit may express up, down, left, right, front, or back as vibrations. The vibration unit can also express direction by changing the strength or pattern of vibrations. The vibration unit can also express direction by combining multiple motors.

[0062] (Example 2) The sound visualization and sensory system according to the embodiment of the present invention is a system that enables hearing-impaired people to recognize sound information visually and with their senses. As a result, the sound visualization and sensory system enables hearing-impaired people to recognize sound information visually and with their senses.

[0063] A sound visualization and sensory system according to an embodiment includes a sound collection unit, an analysis unit, a display unit, a camera unit, a direction estimation unit, and a vibration unit. The sound collection unit collects sound and environmental sounds. For example, the sound collection unit collects ambient sounds using multiple microphones. The sound collection unit can also use a high-sensitivity microphone to collect environmental sounds. The sound collection unit can also focus on a specific sound source for collection. The analysis unit analyzes the sound and environmental sounds collected by the sound collection unit. For example, the analysis unit analyzes sound data using voice recognition technology. The analysis unit can also perform frequency analysis to extract sound characteristics. The analysis unit can also extract acoustic features and identify the type of sound. The display unit displays the onomatopoeic sounds analyzed by the analysis unit. For example, the display unit displays the onomatopoeic sounds as characters on the lens of the MR device. The display unit can also display onomatopoeic words corresponding to the source of the sound. The display unit can also change the display content depending on the intensity and type of sound. The camera unit recognizes the source of the sound. For example, the camera unit recognizes the source of the sound using a camera in the smart glasses. The camera unit can also identify the source of the sound using image recognition technology. The camera unit can also track the movement of the sound source. The direction estimation unit associates the sound source recognized by the camera unit with the generated sound. For example, the direction estimation unit associates sounds based on position information of the sound source. The direction estimation unit can also associate sounds according to the movement of the sound source. The direction estimation unit can also associate sounds according to the type of sound source. The vibration unit expresses the direction of the sound source estimated by the direction estimation unit using vibration. For example, the vibration unit expresses whether the direction is up, down, left, right, front, or back using vibration. The vibration unit can also express direction by changing the intensity and pattern of the vibration. The vibration unit can also express direction by combining multiple motors. As a result, the sound visualization and sensoryization system according to the embodiment enables hearing-impaired people to recognize sound information visually and sensorily.

[0064] The analysis unit may include a generation AI that analyzes audio data and generates onomatopoeic sounds. The analysis unit, for example, collects audio data and performs emotion analysis using the generation AI. For example, if a dog's bark indicates a happy emotion, it generates the onomatopoeia "woof woof." The analysis unit also collects environmental sounds and performs emotion analysis using the generation AI. For example, if the sound of rain indicates a calm emotion, it generates the onomatopoeia "drops." The analysis unit also collects human voices and performs emotion analysis using the generation AI. For example, if laughter indicates a happy emotion, it generates the onomatopoeia "ha ha ha." In this way, by converting the audio data into onomatopoeia and displaying it, sounds can be visually recognized.

[0065] When collecting voice data, the voice collection unit can simultaneously collect environmental data such as ambient temperature and humidity and reflect the data in the analysis. For example, when collecting voice data, the voice collection unit simultaneously collects ambient temperature data using a temperature sensor. For example, voice data in a cold environment is analyzed. When collecting voice data, the voice collection unit simultaneously collects ambient humidity data using a humidity sensor. For example, voice data in a high humidity environment is analyzed. When collecting voice data, the voice collection unit simultaneously collects ambient atmospheric pressure data using a barometric pressure sensor. For example, voice data at a high altitude is analyzed. This allows environmental data to be reflected in the analysis, enabling more accurate voice analysis.

[0066] The voice collection unit monitors the user's heart rate and electrodermal response when collecting voice data, and can reflect the user's emotional state in the analysis. For example, when collecting voice data, the voice collection unit simultaneously collects the user's heart rate data using a heart rate sensor. For example, voice data in a tense state is analyzed. Furthermore, when collecting voice data, the voice collection unit simultaneously collects the user's electrodermal response data using an electrodermal response sensor. For example, voice data in an excited state is analyzed. Furthermore, when collecting voice data, the voice collection unit simultaneously collects the user's respiratory data using a breathing sensor. For example, voice data in a relaxed state is analyzed. This allows the user's emotional state to be reflected in the analysis, enabling more appropriate voice analysis.

[0067] The sound collection unit can use drones or robots to collect sound data and analyze a wide range of sound environments. The sound collection unit, for example, uses drones to collect wide range of sound data. For example, the sound environment of an entire city is analyzed. The sound collection unit also uses robots to collect sound data in specific areas. For example, the sound environment inside a factory is analyzed. The sound collection unit also combines drones and robots to simultaneously collect sound data from multiple areas. For example, the sound environment of an event venue is analyzed. This allows for the collection of a wider range of sound environments, allowing for the collection of a wider variety of sound data.

[0068] The sound collection unit simultaneously analyzes sounds in different frequency bands when collecting sound data, allowing for a more detailed understanding of the sound environment. For example, the sound collection unit analyzes sounds in the low frequency band when collecting sound data. For example, it analyzes precursory sounds of earthquakes. Furthermore, the sound collection unit analyzes sounds in the mid frequency band when collecting sound data. For example, it analyzes sounds of conversation. Furthermore, the sound collection unit analyzes sounds in the high frequency band when collecting sound data. For example, it analyzes birdsong. In this way, by analyzing sounds in different frequency bands, a more detailed understanding of the sound environment can be obtained.

[0069] The analysis unit can use the emotion estimation function to analyze what emotion a user feels in response to a specific sound and reflect the result in the collection of voice data. For example, the analysis unit uses the emotion estimation function to analyze the emotion a user feels in response to a specific sound. For example, it analyzes emotions toward music. The analysis unit also uses the emotion estimation function to analyze the emotion a user feels in response to a specific environmental sound. For example, it analyzes emotions toward the sound of rain. The analysis unit also uses the emotion estimation function to analyze the emotion a user feels in response to the cry of a specific animal. For example, it analyzes emotions toward the meowing of a cat. In this way, by reflecting the user's emotions, more appropriate voice data can be collected.

[0070] The display unit can display the onomatopoeic sound at an optimal position based on the user's gaze tracking data. For example, the display unit displays the onomatopoeic sound at the point of the user's gaze based on the user's gaze tracking data. For example, it displays "woof woof" in the direction the gaze is facing. The display unit also dynamically displays the onomatopoeic sound in accordance with the movement of the gaze based on the gaze tracking data. For example, it updates the display position every time the gaze moves. The display unit also displays the onomatopoeic sound at the focus of the gaze based on the gaze tracking data. For example, it displays "boom" where the gaze is focused. In this way, by displaying the onomatopoeic sound at an optimal position based on the user's gaze, visual recognition is improved.

[0071] The display unit can make it possible for the user to customize the onomatopoeic sound according to their preferences. The display unit, for example, allows the user to customize the display style of the onomatopoeic sound. For example, the font or color can be changed. The display unit also allows the user to customize the display position of the onomatopoeic sound. For example, the display position can be set on the top, bottom, left, or right of the screen. The display unit also allows the user to customize the display timing of the onomatopoeic sound. For example, the delay time from when the sound is generated until it is displayed can be set. This allows the user to customize the onomatopoeic sound according to their preferences, making it possible to provide a system that is easier to use.

[0072] The display unit can reflect the user's emotional state when displaying the onomatopoeic sound and use a color or font that corresponds to the emotion. The display unit, for example, analyzes the user's emotional state and displays the onomatopoeic sound in a color that corresponds to the emotion. For example, a bright color is used for the emotion of joy. The display unit also analyzes the user's emotional state and displays the onomatopoeic sound in a font that corresponds to the emotion. For example, a bold font is used for the emotion of anger. The display unit also analyzes the user's emotional state and displays the onomatopoeic sound with animation that corresponds to the emotion. For example, a flickering animation is used for the emotion of surprise. In this way, visual information transmission is improved by displaying information that corresponds to the user's emotional state.

[0073] The display unit can use AR technology to display onomatopoeic sounds superimposed on real-world objects. For example, the display unit uses AR technology to display onomatopoeic sounds superimposed on real-world objects. For example, a "woof woof" sound is displayed near a dog. The display unit also uses AR technology to dynamically display onomatopoeic sounds. For example, a "boom" sound is displayed in the direction a car is moving. The display unit also uses AR technology to display onomatopoeic sounds in 3D space. For example, the sound of a bird is displayed in the air as a "chirp chirp." In this way, sound information can be superimposed on real-world objects using AR technology.

[0074] The display unit can automatically translate the onomatopoeic sounds into different languages ​​to accommodate international users. For example, the display unit can automatically translate the onomatopoeic sounds and display them in different languages. For example, "woof woof" is displayed in English as "Woof Woof." The display unit can also make the onomatopoeic sounds multilingual, allowing the user to select the language. For example, the display language can be selected from Japanese, English, and Chinese. The display unit can also translate the onomatopoeic sounds in real time and display them in different languages. For example, the display unit can automatically translate and display the sound the moment it is generated. This allows for automatic translation into different languages ​​to accommodate international users.

[0075] The display unit can use the emotion estimation function to analyze what emotion the user feels toward the onomatopoeic sound and reflect the result in the display. For example, the display unit uses the emotion estimation function to analyze the emotion the user feels toward the onomatopoeic sound. For example, the display unit analyzes the emotion toward the onomatopoeic sound. The display unit also uses the emotion estimation function to reflect the emotion the user feels toward the onomatopoeic sound in the display. For example, a positive emotion is displayed in a bright color. The display unit also uses the emotion estimation function to reflect the emotion the user feels toward the onomatopoeic sound in the display. For example, a negative emotion is displayed in a dark color. This allows the user's emotion to be reflected, thereby enabling a more appropriate display.

[0076] When recognizing the source of a sound, the camera unit also analyzes the movement and shape of the object, allowing for more accurate association. For example, when recognizing the source of a sound, the camera unit analyzes the movement of the object. For example, the engine sound of a moving car may be associated with a "boom." When recognizing the source of a sound, the camera unit also analyzes the shape of the object. For example, the shape of a dog may be recognized and its bark may be associated with a "woof woof." When recognizing the source of a sound, the camera unit also analyzes the color of the object. For example, the engine sound of a red car may be associated with a "boom." In this way, by analyzing the movement and shape of the object, the source of the sound can be recognized more accurately.

[0077] When recognizing the source of a sound, the camera unit can refer to past data and learn the source pattern. For example, the camera unit refers to past data when recognizing the source of a sound. For example, it may associate a previously recognized dog bark with "woof woof." In addition, the camera unit learns the source pattern when recognizing the source of a sound. For example, it may associate the engine sound of a particular car with "boom." In addition, when recognizing the source of a sound, the camera unit predicts the source pattern based on past data. For example, it may associate a particular environmental sound with "buzzing." In this way, by referring to past data and learning the source pattern, the source of the sound can be recognized more accurately.

[0078] The camera unit can use multiple cameras to integrate data from different angles when recognizing the source of a sound. For example, the camera unit uses multiple cameras to recognize the source of a sound from different angles. For example, the front and rear cameras are used to identify the source of a sound. The camera unit also integrates camera data from different angles to more accurately recognize the source of a sound. For example, left and right cameras are used to identify the source of a sound. The camera unit also uses multiple cameras to recognize the source of a sound in 3D space. For example, cameras on the top, bottom, left, and right are used to identify the source of a sound. In this way, by using multiple cameras, data from different angles can be integrated to more accurately recognize the source of a sound.

[0079] When recognizing the source of a sound, the camera unit can use drones or robots to collect data over a wide area. For example, the camera unit uses drones to recognize the source of a wide area of ​​sound. For example, it can identify the source of a sound throughout an entire city. The camera unit can also use robots to recognize the source of a sound in a specific area. For example, it can identify the source of a sound inside a factory. The camera unit can also combine drones and robots to recognize the source of sound in multiple areas simultaneously. For example, it can identify the source of a sound at an event venue. This allows the use of drones and robots to collect data over a wide area and more accurately identify the source of a sound.

[0080] The camera unit can use the emotion estimation function to analyze what emotion the user feels toward the source of a specific sound and reflect the result in the linking. For example, the camera unit uses the emotion estimation function to analyze the emotion the user feels toward the source of a specific sound. For example, it analyzes the emotion toward the sound of a dog barking. The camera unit also uses the emotion estimation function to reflect the emotion the user feels toward the source of a specific sound in the linking. For example, positive emotions are displayed in a bright color. The camera unit also uses the emotion estimation function to reflect the emotion the user feels toward the source of a specific sound in the linking. For example, negative emotions are displayed in a dark color. In this way, the user's emotions are reflected, allowing the source of the sound to be more appropriately recognized.

[0081] The vibration unit can provide more detailed directional information by changing the intensity and pattern of vibration when sensing the direction of a sound source. For example, the vibration unit changes the intensity of vibration when sensing the direction of a sound source. For example, a strong vibration is provided for a nearby sound source. The vibration unit also changes the pattern of vibration when sensing the direction of a sound source. For example, a weak vibration is provided for a distant sound source. The vibration unit also changes the frequency of vibration when sensing the direction of a sound source. For example, a high-frequency vibration is provided for a sound source above or below. In this way, by changing the intensity and pattern of vibration, more detailed directional information can be provided.

[0082] The vibration unit can monitor the user's movements and posture when sensing the direction of the sound source, and provide an optimal vibration pattern. The vibration unit, for example, monitors the user's movements and provides an optimal vibration pattern when sensing the direction of the sound source. For example, the vibration pattern is adjusted for a user who is walking. The vibration unit can also monitor the user's posture and provide an optimal vibration pattern when sensing the direction of the sound source. For example, the vibration pattern is adjusted for a user who is sitting. The vibration unit can also monitor the user's movements and posture in real time, and provide an optimal vibration pattern when sensing the direction of the sound source. For example, the vibration pattern is adjusted for a user who is running. In this way, the optimal vibration pattern can be provided by monitoring the user's movements and posture.

[0083] The vibration unit can reflect the user's emotional state when sensing the direction of the sound source and provide a vibration pattern according to the emotion. The vibration unit, for example, analyzes the user's emotional state and provides a vibration pattern according to the emotion when sensing the direction of the sound source. For example, if the user is in a tense state, it provides a strong vibration. The vibration unit can also analyze the user's emotional state and provide a vibration pattern according to the emotion when sensing the direction of the sound source. For example, if the user is in a relaxed state, it provides a weak vibration. The vibration unit can also analyze the user's emotional state and provide a vibration pattern according to the emotion when sensing the direction of the sound source. For example, if the user is in an excited state, it provides a high-frequency vibration. In this way, by providing a vibration pattern according to the user's emotional state, more appropriate sensory information can be provided.

[0084] When the vibration unit senses the direction of the sound source, the vibration unit can provide more detailed sensory information by using a haptic feedback device. The vibration unit senses the direction of the sound source by using, for example, a haptic feedback device. For example, a device worn on the wrist provides vibrations. The vibration unit also senses the direction of the sound source by using a haptic feedback device. For example, a device worn on the waist provides vibrations. The vibration unit also senses the direction of the sound source by using a haptic feedback device. For example, a device worn on the ankle provides vibrations. In this way, by using the haptic feedback device, more detailed sensory information can be provided.

[0085] The vibration unit can express the type and intensity of a sound by using different vibration patterns when sensing the direction of a sound source. The vibration unit, for example, expresses the type of sound by using different vibration patterns. For example, in the case of a dog barking, it provides short vibrations. The vibration unit also expresses the intensity of the sound by using different vibration patterns. For example, in the case of the sound of a car engine, it provides long vibrations. The vibration unit also expresses the type and intensity of a sound by using different vibration patterns. For example, in the case of a bird singing, it provides high-frequency vibrations. In this way, the type and intensity of a sound can be expressed by using different vibration patterns.

[0086] The vibration unit can use the emotion estimation function to analyze what emotion the user feels toward a specific sound source and reflect the result in the sensation. The vibration unit, for example, uses the emotion estimation function to analyze the emotion the user feels toward a specific sound source. For example, it analyzes the emotion toward the sound of a dog barking. The vibration unit also uses the emotion estimation function to reflect the emotion the user feels toward a specific sound source in the sensation. For example, it provides strong vibrations in the case of positive emotions. The vibration unit also uses the emotion estimation function to reflect the emotion the user feels toward a specific sound source in the sensation. For example, it provides weak vibrations in the case of negative emotions. In this way, more appropriate sensory information can be provided by reflecting the user's emotions.

[0087] The analysis unit can incorporate data from different regions and cultures into the optimization of the analysis model, enabling global responsiveness. The analysis unit, for example, collects speech data from different regions and incorporates it into the analysis model. For example, it analyzes Japanese dialects and distinctive environmental sounds. The analysis unit also collects speech data from different cultures and incorporates it into the analysis model. For example, it analyzes traditional African music and environmental sounds. The analysis unit also incorporates data from different regions and cultures into the analysis model to enable global responsiveness. For example, it analyzes European urban sounds and natural sounds. In this way, incorporating data from different regions and cultures enables global responsiveness.

[0088] The analysis unit can reflect user feedback in real time in optimizing the analysis model, thereby enabling continuous improvement. The analysis unit, for example, collects user feedback in real time and reflects it in the analysis model. For example, the analysis unit collects feedback to improve the accuracy of voice recognition. The analysis unit also continuously improves the analysis model based on the user feedback. For example, the analysis unit collects feedback to improve the recognition accuracy of specific sounds. The analysis unit also reflects the user feedback collected in real time in the analysis model, thereby enabling continuous improvement. For example, the analysis unit collects feedback to improve the recognition accuracy of environmental sounds. In this way, the analysis model can be continuously improved by reflecting user feedback in real time.

[0089] The analysis unit incorporates user emotional data into the optimization of the analysis model, and can provide analysis results according to the emotion. The analysis unit, for example, collects user emotional data and incorporates it into the analysis model. For example, it analyzes voice data that indicates positive emotions. The analysis unit also optimizes the analysis model based on the user emotional data. For example, it analyzes voice data that indicates negative emotions. The analysis unit also incorporates the user emotional data and provides analysis results according to the emotion. For example, it analyzes voice data that indicates joy. In this way, by incorporating the user emotional data, it is possible to provide analysis results according to the emotion.

[0090] The analysis unit can integrate data from different devices and platforms to optimize the analysis model and increase its versatility. The analysis unit, for example, collects data from different devices and incorporates it into the analysis model. For example, it analyzes voice data from smartphones and tablets. The analysis unit also collects data from different platforms and incorporates it into the analysis model. For example, it analyzes voice data from social media and messaging apps. The analysis unit also integrates data from different devices and platforms to increase the versatility of the analysis model. For example, it analyzes voice data from wearable devices. In this way, by integrating data from different devices and platforms, the versatility of the analysis model can be increased.

[0091] The analysis unit can use the emotion estimation function to analyze what emotions the user has toward the analysis results and reflect the results in optimization. The analysis unit, for example, uses the emotion estimation function to analyze the emotions the user has toward the analysis results. For example, it analyzes emotions toward the voice recognition results. The analysis unit also uses the emotion estimation function to reflect the emotions the user has toward the analysis results in optimization. For example, it prioritizes analysis results that indicate positive emotions. The analysis unit also uses the emotion estimation function to reflect the emotions the user has toward the analysis results in optimization. For example, it improves analysis results that indicate negative emotions. In this way, by reflecting the user's emotions, it becomes possible to optimize the analysis results.

[0092] The analysis unit can formulate a step-by-step migration plan to smoothly migrate from cloud processing to an in-device self-contained system. The analysis unit, for example, formulates a plan to migrate from cloud processing to an in-device self-contained system in stages. For example, in the initial stage, some processing is performed within the device. The analysis unit also formulates a migration plan to smoothly migrate from cloud processing to an in-device self-contained system. For example, the processing capacity of the device is improved in stages. The analysis unit also conducts step-by-step tests to smoothly migrate from cloud processing to an in-device self-contained system. For example, performance evaluation is performed at each stage of the migration. In this way, by formulating a step-by-step migration plan, the migration from cloud processing to an in-device self-contained system can be smoothly performed.

[0093] The analysis unit can build a hybrid model of cloud processing and in-device self-contained processing and select the optimal processing method. The analysis unit, for example, builds a hybrid model of cloud processing and in-device self-contained processing and selects the optimal processing method. For example, the analysis unit complements cloud processing according to the processing capacity of the device. The analysis unit also uses the hybrid model to combine the advantages of cloud processing and in-device self-contained processing. For example, real-time processing is performed in-device, and large-scale analysis is performed in the cloud. The analysis unit also builds a hybrid model of cloud processing and in-device self-contained processing and selects the optimal processing method according to the user's needs. For example, if the network connection is unstable, processing is performed in-device. In this way, by building a hybrid model, the optimal processing method can be selected.

[0094] The analysis unit can incorporate user emotional data and determine the optimal timing for transition when transitioning from cloud processing to in-device processing. For example, when transitioning from cloud processing to in-device processing, the analysis unit collects user emotional data and determines the optimal timing for transition. For example, it analyzes the user's stress level. The analysis unit also adjusts the timing of transition from cloud processing to in-device processing based on the user's emotional data. For example, it performs the transition when the user is relaxed. The analysis unit also uses the emotional data to optimize the timing of transition from cloud processing to in-device processing. For example, it performs the transition when the user's emotional state is stable. In this way, by incorporating the user's emotional data, the optimal timing for transition can be determined.

[0095] The analysis unit can utilize both cloud processing and in-device self-contained processing to meet different user needs. The analysis unit, for example, utilizes both cloud processing and in-device self-contained processing to build a system that meets different user needs. For example, advanced analysis is performed in the cloud, and basic processing is performed in the device. The analysis unit also combines the advantages of cloud processing and in-device self-contained processing to provide the optimal processing method according to the user's needs. For example, if real-time performance is required, processing is performed in the device. The analysis unit also utilizes both cloud processing and in-device self-contained processing to select the optimal processing method according to the user's usage status. For example, if the network connection is stable, cloud processing is performed. In this way, different user needs can be met by utilizing both cloud processing and in-device self-contained processing.

[0096] The analysis unit can ensure compatibility with different devices and platforms when migrating from cloud processing to an in-device self-contained system. The analysis unit ensures compatibility with different devices, for example, when migrating from cloud processing to an in-device self-contained system. For example, it realizes integration with smartphones and tablets. The analysis unit also ensures compatibility with different platforms, allowing for a smooth transition from cloud processing to an in-device self-contained system. For example, it ensures compatibility with Windows and MacOS. The analysis unit also performs tests to ensure compatibility with different devices and platforms when migrating from cloud processing to an in-device self-contained system. For example, it checks operation on each device. This ensures compatibility with different devices and platforms, allowing for a smooth transition.

[0097] The analysis unit uses the emotion estimation function to analyze how the user feels about cloud processing or in-device processing, and can reflect the results in the migration plan. The analysis unit, for example, uses the emotion estimation function to analyze how the user feels about cloud processing. For example, it analyzes the trust in cloud processing. The analysis unit also uses the emotion estimation function to analyze how the user feels about in-device processing. For example, it analyzes the sense of security about in-device processing. The analysis unit also uses the emotion estimation function to analyze how the user feels about cloud processing or in-device processing, and reflects the results in the migration plan. For example, it adjusts the migration timing based on the user's emotion data. In this way, an optimal migration plan can be formulated by reflecting the user's emotions.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] When collecting voice data, the voice collection unit can simultaneously collect environmental data such as ambient temperature and humidity and reflect the data in the analysis. For example, when collecting voice data, the voice collection unit simultaneously collects ambient temperature data using a temperature sensor. For example, voice data in a cold environment is analyzed. When collecting voice data, the voice collection unit simultaneously collects ambient humidity data using a humidity sensor. For example, voice data in a high humidity environment is analyzed. When collecting voice data, the voice collection unit simultaneously collects ambient atmospheric pressure data using a barometric pressure sensor. For example, voice data at a high altitude is analyzed. This allows environmental data to be reflected in the analysis, enabling more accurate voice analysis.

[0100] The analysis unit may include a generation AI that analyzes audio data and generates onomatopoeic sounds. For example, the analysis unit collects audio data and performs emotion analysis using the generation AI. For example, if a dog's bark indicates the emotion of joy, the onomatopoeia "woof woof" is generated. The analysis unit also collects environmental sounds and performs emotion analysis using the generation AI. For example, if the sound of rain indicates the emotion of calm, the onomatopoeia "drops" is generated. The analysis unit also collects human voices and performs emotion analysis using the generation AI. For example, if laughter indicates the emotion of enjoyment, the onomatopoeia "ha ha ha" is generated. In this way, by converting the audio data into onomatopoeia and displaying it, sounds can be visually recognized.

[0101] The voice collection unit monitors the user's heart rate and electrodermal response when collecting voice data, and can reflect the user's emotional state in the analysis. For example, when collecting voice data, the voice collection unit simultaneously collects the user's heart rate data using a heart rate sensor. For example, voice data in a tense state is analyzed. When collecting voice data, the voice collection unit simultaneously collects the user's electrodermal response data using an electrodermal response sensor. For example, voice data in an excited state is analyzed. When collecting voice data, the voice collection unit simultaneously collects the user's respiratory data using a breathing sensor. For example, voice data in a relaxed state is analyzed. This allows the user's emotional state to be reflected in the analysis, enabling more appropriate voice analysis.

[0102] The sound collection unit can use drones or robots to collect sound data and analyze a wide range of sound environments. For example, the sound collection unit uses drones to collect wide range of sound data. For example, the sound environment of an entire city is analyzed. The sound collection unit also uses robots to collect sound data in a specific area. For example, the sound environment inside a factory is analyzed. The sound collection unit also combines drones and robots to simultaneously collect sound data from multiple areas. For example, the sound environment of an event venue is analyzed. This allows for the collection of a wider range of sound environments, allowing for the collection of a wider variety of sound data.

[0103] The sound collection unit simultaneously analyzes sounds in different frequency bands when collecting sound data, allowing for a more detailed understanding of the sound environment. For example, the sound collection unit analyzes sounds in the low frequency band when collecting sound data, such as analyzing precursory sounds of an earthquake. The sound collection unit also analyzes sounds in the mid frequency band when collecting sound data, such as analyzing sounds of conversation. The sound collection unit also analyzes sounds in the high frequency band when collecting sound data, such as analyzing birdsong. In this way, by analyzing sounds in different frequency bands, a more detailed understanding of the sound environment can be achieved.

[0104] The analysis unit can use the emotion estimation function to analyze what emotion a user feels in response to a specific sound and reflect the result in the collection of voice data. For example, the analysis unit uses the emotion estimation function to analyze the emotion a user feels in response to a specific sound. For example, it analyzes emotions toward music. The analysis unit also uses the emotion estimation function to analyze the emotion a user feels in response to a specific environmental sound. For example, it analyzes emotions toward the sound of rain. The analysis unit also uses the emotion estimation function to analyze the emotion a user feels in response to the sound of a specific animal. For example, it analyzes emotions toward the sound of a cat meowing. In this way, by reflecting the user's emotions, more appropriate voice data can be collected.

[0105] The display unit can display the onomatopoeic sound at an optimal position based on the user's gaze tracking data. For example, the display unit displays the onomatopoeic sound at the point of the user's gaze based on the gaze tracking data. For example, it displays "woof woof" in the direction the gaze is facing. The display unit also dynamically displays the onomatopoeic sound in accordance with the movement of the gaze based on the gaze tracking data. For example, it updates the display position every time the gaze moves. The display unit also displays the onomatopoeic sound at the focus of the gaze based on the gaze tracking data. For example, it displays "boom" where the gaze is focused. In this way, by displaying the onomatopoeic sound at an optimal position based on the user's gaze, visual recognition is improved.

[0106] The display unit can customize the onomatopoeic sound according to the user's preferences. For example, the display unit allows the user to customize the display style of the onomatopoeic sound. For example, the font or color can be changed. The display unit also allows the user to customize the display position of the onomatopoeic sound. For example, the display position can be set on the top, bottom, left, or right of the screen. The display unit also allows the user to customize the display timing of the onomatopoeic sound. For example, the delay time from when the sound is generated until it is displayed can be set. This allows the user to customize the onomatopoeic sound according to their preferences, making it possible to provide a system that is easier to use.

[0107] The display unit can reflect the user's emotional state when displaying the onomatopoeic sound and use a color or font that corresponds to the emotion. For example, the display unit analyzes the user's emotional state and displays the onomatopoeic sound in a color that corresponds to the emotion. For example, a bright color is used for the emotion of joy. The display unit can also analyze the user's emotional state and display the onomatopoeic sound in a font that corresponds to the emotion. For example, a bold font is used for the emotion of anger. The display unit can also analyze the user's emotional state and display the onomatopoeic sound with an animation that corresponds to the emotion. For example, a flickering animation is used for the emotion of surprise. This improves visual information transmission by displaying information that corresponds to the user's emotional state.

[0108] The display unit can use AR technology to display onomatopoeic sounds superimposed on real-world objects. For example, the display unit uses AR technology to display onomatopoeic sounds superimposed on real-world objects. For example, the display unit displays "woof woof" near a dog. The display unit also uses AR technology to dynamically display onomatopoeic sounds. For example, the display unit displays "boom" in the direction a car is moving. The display unit also uses AR technology to display onomatopoeic sounds in 3D space. For example, the sound of a bird chirping is displayed in the air as "chirp chirp." In this way, sound information can be superimposed on real-world objects using AR technology.

[0109] The processing flow of the second embodiment will be briefly explained below.

[0110] Step 1: The sound collection unit collects sounds and environmental sounds. For example, the sound collection unit collects ambient sounds using multiple microphones. The sound collection unit can also use a high-sensitivity microphone to collect environmental sounds. The sound collection unit can also focus on a specific sound source and collect sounds. Step 2: The analysis unit analyzes the voice and environmental sounds collected by the voice collection unit. For example, the analysis unit analyzes the voice data using voice recognition technology. The analysis unit can also perform frequency analysis and extract sound features. The analysis unit can also extract acoustic features and identify the type of sound. Step 3: The display unit displays the onomatopoeic sound analyzed by the analysis unit. For example, the display unit displays the onomatopoeic sound as characters on the lens of the MR device. The display unit can also display onomatopoeic words corresponding to the source of the sound. The display unit can also change the display content depending on the intensity and type of sound. Step 4: The camera unit recognizes the source of the sound. For example, the camera unit recognizes the source of the sound using the camera of the smart glasses. The camera unit can also identify the source of the sound using image recognition technology. The camera unit can also track the movement of the source of the sound. Step 5: The direction estimation unit associates the sound source recognized by the camera unit with the generated sound. For example, the direction estimation unit associates the sound based on the position information of the sound source. The direction estimation unit can also associate the sound according to the movement of the sound source. The direction estimation unit can also associate the sound according to the type of sound source. Step 6: The vibration unit uses vibration to express the direction of the sound source estimated by the direction estimation unit. For example, the vibration unit may express up, down, left, right, front, or back as vibrations. The vibration unit can also express direction by changing the strength or pattern of vibrations. The vibration unit can also express direction by combining multiple motors.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0113] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0121] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] 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.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0129] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0130] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0133] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0136] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0137] 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.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0139] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0144] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0145] 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.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0147] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0148] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0150] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0151] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0152] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0153] 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.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0155] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0157] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0159] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0160] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0161] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0162] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0163] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0164] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0165] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0167] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0168] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0169] 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.

[0170] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0171] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0172] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0173] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0174] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0175] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0176] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0177] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a sound collection unit that collects sounds and environmental sounds; an analysis unit that analyzes the voice and environmental sound collected by the voice collection unit; a display unit that displays the onomatopoeic sound analyzed by the analysis unit; A camera unit that recognizes the source of the sound; a direction estimation unit that associates a sound source recognized by the camera unit with the sound being generated; a vibration unit that expresses the direction of the sound source estimated by the direction estimation unit with vibration. A system characterized by:

2. The analysis unit Includes a generative AI that analyzes voice data and generates onomatopoeic sounds 2. The system of claim 1.

3. The sound collection unit When collecting voice data, environmental data such as the surrounding temperature and humidity are also collected at the same time and reflected in the analysis.

2. The system of claim 1.

4. The sound collection unit When collecting voice data, the user's heart rate and electrodermal response are monitored to reflect their emotional state in the analysis.

2. The system of claim 1.

5. The sound collection unit Using drones and robots to collect audio data and analyze a wide range of sound environments 2. The system of claim 1.

6. The sound collection unit When collecting audio data, different frequency bands of sound are analyzed simultaneously to obtain a more detailed understanding of the sound environment.

2. The system of claim 1.

7. The analysis unit Analyze how users feel about specific sounds and reflect the results in collecting audio data 2. The system of claim 1.

8. The display unit The onomatopoeic sound is displayed in the optimal position based on the user's gaze tracking data.

2. The system of claim 1.

Images