System

Abstract

An object of a system according to an embodiment is to generate a response including bokeh of the Kansai dialect by using a generation AI and to enhance entertainment properties.SOLUTION: A system includes a voice recognition unit, a generation unit, and a voice output unit. The voice recognition unit converts the user's voice into text. The generation unit generates a response including blurring of the Kansai dialect on the basis of the text converted by the speech recognition unit. The voice output unit converts the response generated by the generation unit into voice and outputs the voice.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 not fully utilized generative AI for entertainment purposes, and there is room for improvement.

[0005] The system according to the embodiment aims to enhance entertainment value by using a generation AI to generate responses that include jokes in the Kansai dialect. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, a generation unit, and a speech output unit. The speech recognition unit converts a user's speech into text. The generation unit generates a response including a joke in Kansai dialect based on the text converted by the speech recognition unit. The speech output unit converts the response generated by the generation unit into speech and outputs the speech. [Effects of the Invention]

[0007] The system according to the embodiment uses a generation AI to generate responses that include jokes in the Kansai dialect, thereby enhancing entertainment value. [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 manzai app according to the embodiment of the present invention is a system that utilizes the random selection ability of a generation AI for entertainment purposes. This system allows the generation AI to understand Kansai dialect and deliver jokes that lighten the mood. This allows the manzai app to provide users with a fun conversational experience.

[0029] A manzai app according to an embodiment includes a speech recognition unit, a generation unit, and a speech output unit. The speech recognition unit converts a user's speech into text. For example, the speech recognition unit converts speech into text using deep learning technology. The speech recognition unit can also convert speech into text using a hidden Markov model (HMM). The speech recognition unit can also convert speech into text using a speech recognition algorithm. The generation unit generates a response including a joke in Kansai dialect based on the text converted by the speech recognition unit. For example, the generation unit generates a response including a joke in Kansai dialect using a generation AI (e.g., a text generation AI or a multimodal generation AI). The generation unit can also generate a response using a generation AI that has learned specific phrases, expressions, and grammar rules. The generation unit can also use an algorithm for generating a response including a joke in Kansai dialect. The speech output unit converts the response generated by the generation unit into speech and outputs the speech. For example, the speech output unit converts the response into speech using Text to Speech (TTS) technology. The audio output unit can also convert the response into speech using a speech synthesis algorithm. The audio output unit plays the generated speech to the user. As a result, the manzai app according to the embodiment can provide the user with a fun dialogue experience by outputting a speech response, including a joke in Kansai dialect, using the generation AI. For example, the manzai app can be used as an icebreaker during business negotiations. Furthermore, the manzai app can be used by people of all ages and genders as a conversation partner. Furthermore, the manzai app can realize more realistic dialogue by learning and reflecting models of famous people.

[0030] The speech recognition unit can learn the user's speech patterns and use an individually optimized speech recognition model. The speech recognition unit, for example, learns the user's speech patterns and uses an individually optimized speech recognition model. For example, if the user has a particular accent or dialect, the speech recognition unit learns the characteristics of the accent or dialect to improve recognition accuracy. The speech recognition unit also learns the user's speech rate and rhythm and optimizes the speech recognition model based on the learned data. For example, for a user who speaks quickly, a model that corresponds to fast speech is used. The speech recognition unit also learns the user's speech habits and characteristics and customizes the speech recognition model based on the learned data. For example, for a user who often uses specific phrases or expressions, a model that reflects those characteristics is used. This makes it possible to improve speech recognition accuracy based on the user's speech patterns.

[0031] The speech recognition unit can filter background or environmental sounds to minimize the impact of noise. For example, the speech recognition unit filters background sounds in real time during the speech recognition process to minimize the impact of noise. For example, the speech recognition unit can accurately recognize speech even in noisy environments such as cafes and train stations. The speech recognition unit also employs technology to analyze environmental sounds and extract only important speech signals. For example, wind noise and traffic noise are removed to recognize only the user's voice. The speech recognition unit also uses noise canceling technology to improve the accuracy of speech recognition. For example, background noise is canceled in real time to obtain clear speech. This minimizes the impact of noise and improves speech recognition accuracy.

[0032] The speech recognition unit can expand the speech recognition function to support multiple languages, enabling manzai dialogue in different languages. For example, the speech recognition unit expands the speech recognition function to support multiple languages, enabling manzai dialogue in different languages. For example, it supports multiple languages ​​such as Japanese, English, and French. The speech recognition unit also develops a multilingual speech recognition model to improve speech recognition accuracy in different languages. For example, it uses a model that corresponds to the pronunciation and accent of each language. The speech recognition unit also introduces technology for real-time translation of the speech recognition function to enable manzai dialogue in different languages. For example, when speaking in Japanese, text translated into English is generated. This makes it possible to realize manzai dialogue in different languages.

[0033] The voice recognition unit can analyze the user's speaking speed and rhythm and adjust the tempo of the manzai. The voice recognition unit, for example, analyzes the user's speaking speed and adjusts the tempo of the manzai based on that. For example, if the user speaks quickly, the generation AI also responds quickly. The voice recognition unit also analyzes the user's speaking rhythm and adjusts the tempo of the manzai based on that. For example, if the user speaks slowly, the generation AI also responds slowly. The voice recognition unit also analyzes the user's speaking speed and rhythm in real time and dynamically adjusts the tempo of the manzai based on that. For example, the response speed of the generation AI is adjusted to match the user's speaking. This makes it possible to adjust the tempo of the manzai based on the user's speaking speed and rhythm.

[0034] Generative AI can learn a user's dialogue history and generate more personalized responses. For example, generative AI can learn a user's past dialogue history and generate personalized responses based on that. For example, it can generate responses based on what the user has previously said. Generative AI can also analyze a user's dialogue history and generate individually optimized responses. For example, it can customize responses based on the user's preferences and interests. Generative AI can also learn a user's past dialogue history and improve the quality of responses based on that. For example, it can generate responses that reflect the user's frequently used phrases and expressions. This makes it possible to generate more personalized responses based on the user's past dialogue history.

[0035] The generation AI can analyze the user's interests and concerns in real time and provide topics that correspond to them. For example, if the user is interested in sports, the generation AI can provide topics related to sports. The generation AI can also analyze the content of the user's speech to identify their interests and concerns. For example, if the user is talking about movies, the generation AI can provide topics related to movies. The generation AI can also analyze the user's interests and concerns in real time and adjust the content of the dialogue based on that. For example, if the user is interested in music, the generation AI can provide topics related to music. This makes it possible to provide topics based on the user's interests and concerns.

[0036] The generation AI can generate specialized jokes based on the user's occupation or hobbies. For example, the generation AI generates specialized jokes based on the user's occupation. For example, it provides medical-related jokes to a user who is a doctor. The generation AI also generates specialized jokes based on the user's hobbies. For example, it provides music-related jokes to a user whose hobby is music. The generation AI also analyzes the user's occupation and hobbies in real time and generates specialized jokes based on that. For example, it provides technology-related jokes to a user who is an engineer. This makes it possible to generate specialized jokes based on the user's occupation and hobbies.

[0037] Text to Speech can add features that allow the user to customize the voice output to suit their preferences. For example, Text to Speech adds features that allow the user to customize the voice output to suit their preferences. For example, it allows the user to adjust the pitch and speed of the voice. Text to Speech also adds a feature that allows the user to select their preferred voice quality. For example, it allows the user to select a male voice, a female voice, a young voice, or an older voice. Text to Speech also provides an interface for customizing the voice output to suit the user's preferences. For example, it adds sliders that allow the user to adjust the tone and emotion of the voice. This allows the voice output to be customized to suit the user's preferences.

[0038] Text to Speech can add background sounds or sound effects to the audio output, providing a more realistic dialogue. For example, Text to Speech can add background sounds to the audio output. For example, it can play the sounds of nature or a city in the background. Text to Speech can also add sound effects to the generated audio to enhance the realism of the dialogue. For example, it can insert the sounds of laughter or applause. Text to Speech can also combine background sounds and sound effects with the audio output to provide a more realistic dialogue experience. For example, it can add sound effects appropriate to the scene. This allows background sounds and sound effects to be added to the audio output, providing a more realistic dialogue.

[0039] Text to Speech adds a function that allows the user to select different voice qualities and speaking styles, making it possible to provide audio output that suits the user's preferences. For example, Text to Speech adds a function that allows the user to select different voice qualities. For example, it makes it possible to select a low-pitched voice or a high-pitched voice. Text to Speech also adds a function that allows the user to select their preferred speaking style. For example, it makes it possible to select a voice that speaks slowly or a voice that speaks quickly. Text to Speech also provides an interface that allows the user to select different voice qualities and speaking styles. For example, it adds a slider that allows the user to adjust the tone and rhythm of the voice. This adds a function that allows the user to select different voice qualities and speaking styles, making it possible to provide audio output that suits the user's preferences.

[0040] Text to Speech translates generated speech in real time, enabling multilingual speech output. For example, Text to Speech introduces technology for translating generated speech in real time. For example, Japanese speech can be translated into English and output. Text to Speech also develops multilingual text to speech functions to enable speech output in different languages. For example, it supports multiple languages ​​such as English, French, and Chinese. Text to Speech also translates generated speech in real time, enabling dialogue in different languages. For example, if you speak in Japanese, the translated speech will be played back in English. This allows generated speech to be translated in real time, enabling multilingual speech output.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The generation unit can analyze the user's interests in real time and provide topics based on those interests. For example, if the user is interested in sports, it can provide topics related to sports. The generation unit can also analyze the content of the user's speech to identify the user's interests. For example, if the user is talking about movies, it can provide topics related to movies. Furthermore, the generation unit can analyze the user's interests in real time and adjust the content of the dialogue based on that analysis. This makes it possible to provide topics based on the user's interests.

[0043] The speech recognition unit can filter background or environmental sounds to minimize the influence of noise. For example, during the speech recognition process, background sounds can be filtered in real time to minimize the influence of noise. The speech recognition unit can also introduce technology that analyzes environmental sounds and extracts only important speech signals. Furthermore, the speech recognition unit can improve the accuracy of speech recognition by using noise canceling technology. This can minimize the influence of noise and improve the accuracy of speech recognition.

[0044] The speech recognition unit can extend the speech recognition function to support multiple languages, enabling manzai dialogue in different languages. For example, the speech recognition function can be extended to support multiple languages, enabling manzai dialogue in different languages. The speech recognition unit can also develop a multilingual speech recognition model to improve speech recognition accuracy in different languages. Furthermore, the speech recognition unit can introduce technology for translating the speech recognition function in real time to enable manzai dialogue in different languages. This allows manzai dialogue in different languages ​​to be realized.

[0045] The generation unit can generate specialized jokes based on the user's occupation or hobby. For example, specialized jokes can be generated based on the user's occupation. The generation unit can also generate specialized jokes based on the user's hobby. Furthermore, the generation unit can analyze the user's occupation or hobby in real time and generate specialized jokes based on the analysis. This makes it possible to generate specialized jokes based on the user's occupation or hobby.

[0046] Text to speech can translate generated speech in real time, enabling multilingual speech output. For example, technology can be introduced to translate generated speech in real time. Text to speech can also develop multilingual text to speech functions to enable speech output in different languages. Furthermore, text to speech can translate generated speech in real time, enabling dialogue in different languages. This allows generated speech to be translated in real time, enabling multilingual speech output.

[0047] Text to Speech can add background sounds or sound effects to the audio output to provide a more immersive dialogue. For example, background sounds can be added to the audio output. Text to Speech can also add sound effects to the generated audio to enhance the immersive dialogue. For example, Text to Speech can combine background sounds or sound effects with the audio output to provide a more realistic dialogue experience. This allows background sounds or sound effects to be added to the audio output to provide a more immersive dialogue.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The speech recognition unit converts the user's speech into text, for example, using deep learning techniques, HMM (Hidden Markov Model), or speech recognition algorithms. Step 2: The generator generates a response that includes a joke in the Kansai dialect based on the text converted by the speech recognizer. For example, it uses a generator AI (text generator AI or multimodal generator AI), a generator AI that has learned specific phrases, expressions, and grammar rules, or an algorithm for generating a response that includes a joke in the Kansai dialect. Step 3: The voice output unit converts the response generated by the generation unit into voice and outputs it. For example, the response is converted into voice using Text to Speech (TTS) technology or a voice synthesis algorithm, and the generated voice is played back to the user.

[0050] (Example 2) The manzai app according to the embodiment of the present invention is a system that utilizes the random selection ability of a generation AI for entertainment purposes. This system allows the generation AI to understand Kansai dialect and deliver jokes that lighten the mood. This allows the manzai app to provide users with a fun conversational experience.

[0051] A manzai app according to an embodiment includes a speech recognition unit, a generation unit, and a speech output unit. The speech recognition unit converts a user's speech into text. For example, the speech recognition unit converts speech into text using deep learning technology. The speech recognition unit can also convert speech into text using a hidden Markov model (HMM). The speech recognition unit can also convert speech into text using a speech recognition algorithm. The generation unit generates a response including a joke in Kansai dialect based on the text converted by the speech recognition unit. For example, the generation unit generates a response including a joke in Kansai dialect using a generation AI (e.g., a text generation AI or a multimodal generation AI). The generation unit can also generate a response using a generation AI that has learned specific phrases, expressions, and grammar rules. The generation unit can also use an algorithm for generating a response including a joke in Kansai dialect. The speech output unit converts the response generated by the generation unit into speech and outputs the speech. For example, the speech output unit converts the response into speech using Text to Speech (TTS) technology. The audio output unit can also convert the response into speech using a speech synthesis algorithm. The audio output unit plays the generated speech to the user. As a result, the manzai app according to the embodiment can provide the user with a fun dialogue experience by outputting a speech response, including a joke in Kansai dialect, using the generation AI. For example, the manzai app can be used as an icebreaker during business negotiations. Furthermore, the manzai app can be used by people of all ages and genders as a conversation partner. Furthermore, the manzai app can realize more realistic dialogue by learning and reflecting models of famous people.

[0052] The speech recognition unit can estimate the user's emotions and perform text conversion according to the emotions. For example, if the user is excited, the speech recognition unit generates text that reflects that emotion. For example, if the user excitedly says "Amazing!", the speech recognition unit converts the text to emphasize that emotion. Also, if the user is sad, the speech recognition unit generates text that reflects that emotion. For example, if the user says "Sad," the speech recognition unit converts the text to emphasize that emotion. Also, if the user is relaxed, the speech recognition unit generates text that reflects that emotion. For example, if the user says "I'm feeling relaxed today," the speech recognition unit converts the text to emphasize that emotion. In this way, by performing text conversion according to the user's emotions, more natural and emotionally rich dialogue can be achieved.

[0053] The speech recognition unit can learn the user's speech patterns and use an individually optimized speech recognition model. The speech recognition unit, for example, learns the user's speech patterns and uses an individually optimized speech recognition model. For example, if the user has a particular accent or dialect, the speech recognition unit learns the characteristics of the accent or dialect to improve recognition accuracy. The speech recognition unit also learns the user's speech rate and rhythm and optimizes the speech recognition model based on the learned data. For example, for a user who speaks quickly, a model that corresponds to fast speech is used. The speech recognition unit also learns the user's speech habits and characteristics and customizes the speech recognition model based on the learned data. For example, for a user who often uses specific phrases or expressions, a model that reflects those characteristics is used. This makes it possible to improve speech recognition accuracy based on the user's speech patterns.

[0054] The speech recognition unit can filter background or environmental sounds to minimize the impact of noise. For example, the speech recognition unit filters background sounds in real time during the speech recognition process to minimize the impact of noise. For example, the speech recognition unit can accurately recognize speech even in noisy environments such as cafes and train stations. The speech recognition unit also employs technology to analyze environmental sounds and extract only important speech signals. For example, wind noise and traffic noise are removed to recognize only the user's voice. The speech recognition unit also uses noise canceling technology to improve the accuracy of speech recognition. For example, background noise is canceled in real time to obtain clear speech. This minimizes the impact of noise and improves speech recognition accuracy.

[0055] The speech recognition unit can expand the speech recognition function to support multiple languages, enabling manzai dialogue in different languages. For example, the speech recognition unit expands the speech recognition function to support multiple languages, enabling manzai dialogue in different languages. For example, it supports multiple languages ​​such as Japanese, English, and French. The speech recognition unit also develops a multilingual speech recognition model to improve speech recognition accuracy in different languages. For example, it uses a model that corresponds to the pronunciation and accent of each language. The speech recognition unit also introduces technology for real-time translation of the speech recognition function to enable manzai dialogue in different languages. For example, when speaking in Japanese, text translated into English is generated. This makes it possible to realize manzai dialogue in different languages.

[0056] The voice recognition unit can analyze the user's speaking speed and rhythm and adjust the tempo of the manzai. The voice recognition unit, for example, analyzes the user's speaking speed and adjusts the tempo of the manzai based on that. For example, if the user speaks quickly, the generation AI also responds quickly. The voice recognition unit also analyzes the user's speaking rhythm and adjusts the tempo of the manzai based on that. For example, if the user speaks slowly, the generation AI also responds slowly. The voice recognition unit also analyzes the user's speaking speed and rhythm in real time and dynamically adjusts the tempo of the manzai based on that. For example, the response speed of the generation AI is adjusted to match the user's speaking. This makes it possible to adjust the tempo of the manzai based on the user's speaking speed and rhythm.

[0057] The speech recognition unit uses an emotion estimation function to provide a speech recognition result according to the user's emotion, thereby enabling a dialogue based on the emotion. The speech recognition unit, for example, uses the emotion estimation function to provide a speech recognition result according to the user's emotion. For example, if the user is angry, text is generated that reflects that emotion. The speech recognition unit also analyzes the user's emotion in real time and adjusts the speech recognition result based on the analysis. For example, if the user is sad, text is generated that reflects that emotion. The speech recognition unit also uses the emotion estimation function to enable a dialogue based on the user's emotion. For example, if the user is relaxed, text is generated that reflects that emotion. This enables a dialogue based on the user's emotion.

[0058] Generative AI can learn a user's dialogue history and generate more personalized responses. For example, generative AI can learn a user's past dialogue history and generate personalized responses based on that. For example, it can generate responses based on what the user has previously said. Generative AI can also analyze a user's dialogue history and generate individually optimized responses. For example, it can customize responses based on the user's preferences and interests. Generative AI can also learn a user's past dialogue history and improve the quality of responses based on that. For example, it can generate responses that reflect the user's frequently used phrases and expressions. This makes it possible to generate more personalized responses based on the user's past dialogue history.

[0059] The generation AI can analyze the content, tone, and emotions of a user's speech and generate a response based on that. For example, the generation AI can analyze the content and tone of a user's speech and generate a response based on that. For example, if a user speaks excitedly, it will generate a response that reflects that tone. The generation AI can also analyze the content and emotions of a user's speech and generate a response based on that. For example, if a user speaks sadly, it will generate a response that reflects that emotion. The generation AI can also analyze the tone and emotions of a user's speech in real time and generate a response based on that. For example, if a user speaks relaxed, it will generate a response that reflects that tone. This makes it possible to generate a response based on the content and emotions of a user's speech.

[0060] The generation AI can analyze the user's interests and concerns in real time and provide topics that correspond to them. For example, if the user is interested in sports, the generation AI can provide topics related to sports. The generation AI can also analyze the content of the user's speech to identify their interests and concerns. For example, if the user is talking about movies, the generation AI can provide topics related to movies. The generation AI can also analyze the user's interests and concerns in real time and adjust the content of the dialogue based on that. For example, if the user is interested in music, the generation AI can provide topics related to music. This makes it possible to provide topics based on the user's interests and concerns.

[0061] The generation AI can generate specialized jokes based on the user's occupation or hobbies. For example, the generation AI generates specialized jokes based on the user's occupation. For example, it provides medical-related jokes to a user who is a doctor. The generation AI also generates specialized jokes based on the user's hobbies. For example, it provides music-related jokes to a user whose hobby is music. The generation AI also analyzes the user's occupation and hobbies in real time and generates specialized jokes based on that. For example, it provides technology-related jokes to a user who is an engineer. This makes it possible to generate specialized jokes based on the user's occupation and hobbies.

[0062] The generation AI uses the emotion estimation function to generate jokes that correspond to the user's emotions, thereby enabling emotion-based dialogue. The generation AI, for example, uses the emotion estimation function to generate jokes that correspond to the user's emotions. For example, if the user is sad, it provides jokes that soothe that emotion. The generation AI also analyzes the user's emotions in real time and generates jokes based on that analysis. For example, if the user is excited, it provides jokes that enhance that emotion. The generation AI also uses the emotion estimation function to enable dialogue based on the user's emotions. For example, if the user is relaxed, it provides jokes that maintain that emotion. In this way, it is possible to generate jokes that correspond to the user's emotions and enable emotion-based dialogue.

[0063] Text to Speech can impart emotion to generated speech, enabling more natural and emotional speech output. For example, Text to Speech can impart emotion to generated speech. For example, speech with a joyful emotion can be generated. Text to Speech also introduces technology for imparting emotion to generated speech, enabling more natural speech output. For example, speech with a sad emotion can be generated. Text to Speech can also impart emotion to generated speech, enabling more emotional dialogue. For example, speech with an excited emotion can be generated. This allows emotion to be imparted to generated speech, enabling more natural and emotional speech output.

[0064] Text to Speech can add features that allow the user to customize the voice output to suit their preferences. For example, Text to Speech adds features that allow the user to customize the voice output to suit their preferences. For example, it allows the user to adjust the pitch and speed of the voice. Text to Speech also adds a feature that allows the user to select their preferred voice quality. For example, it allows the user to select a male voice, a female voice, a young voice, or an older voice. Text to Speech also provides an interface for customizing the voice output to suit the user's preferences. For example, it adds sliders that allow the user to adjust the tone and emotion of the voice. This allows the voice output to be customized to suit the user's preferences.

[0065] Text to Speech can add background sounds or sound effects to the audio output, providing a more realistic dialogue. For example, Text to Speech can add background sounds to the audio output. For example, it can play the sounds of nature or a city in the background. Text to Speech can also add sound effects to the generated audio to enhance the realism of the dialogue. For example, it can insert the sounds of laughter or applause. Text to Speech can also combine background sounds and sound effects with the audio output to provide a more realistic dialogue experience. For example, it can add sound effects appropriate to the scene. This allows background sounds and sound effects to be added to the audio output, providing a more realistic dialogue.

[0066] Text to Speech adds a function that allows the user to select different voice qualities and speaking styles, making it possible to provide audio output that suits the user's preferences. For example, Text to Speech adds a function that allows the user to select different voice qualities. For example, it makes it possible to select a low-pitched voice or a high-pitched voice. Text to Speech also adds a function that allows the user to select their preferred speaking style. For example, it makes it possible to select a voice that speaks slowly or a voice that speaks quickly. Text to Speech also provides an interface that allows the user to select different voice qualities and speaking styles. For example, it adds a slider that allows the user to adjust the tone and rhythm of the voice. This adds a function that allows the user to select different voice qualities and speaking styles, making it possible to provide audio output that suits the user's preferences.

[0067] Text to Speech translates generated speech in real time, enabling multilingual speech output. For example, Text to Speech introduces technology for translating generated speech in real time. For example, Japanese speech can be translated into English and output. Text to Speech also develops multilingual text to speech functions to enable speech output in different languages. For example, it supports multiple languages ​​such as English, French, and Chinese. Text to Speech also translates generated speech in real time, enabling dialogue in different languages. For example, if you speak in Japanese, the translated speech will be played back in English. This allows generated speech to be translated in real time, enabling multilingual speech output.

[0068] Text to Speech uses an emotion estimation function to provide voice output that corresponds to the user's emotion, thereby enabling emotion-based dialogue. Text to Speech, for example, uses the emotion estimation function to provide voice output that corresponds to the user's emotion. For example, if the user is happy, a voice that reflects that emotion is generated. Text to Speech also analyzes the user's emotion in real time and adjusts the voice output based on that analysis. For example, if the user is sad, a voice that reflects that emotion is generated. Text to Speech also uses the emotion estimation function to enable dialogue based on the user's emotion. For example, if the user is relaxed, a voice that reflects that emotion is generated. In this way, the emotion estimation function can be used to provide voice output that corresponds to the user's emotion, enabling emotion-based dialogue.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The speech recognition unit can analyze the tone and pitch of a user's voice and infer the user's emotions. For example, if the user speaks in a high tone, it can infer that the user is excited and generate text that corresponds to that emotion. Alternatively, if the user speaks in a low tone, it can infer that the user is calm and generate text that corresponds to that emotion. Furthermore, the speech recognition unit can analyze pitch fluctuations in the user's voice and detect changes in emotion in real time. This allows for more natural and emotionally rich dialogue by converting text according to the user's emotions.

[0071] The generation unit can estimate the user's emotion and adjust the content of the response based on the estimated emotion. For example, if the user is angry, the generation unit can generate a response that soothes the emotion. Also, if the user is sad, the generation unit can generate a response that comforts the emotion. Furthermore, if the user is relaxed, the generation unit can generate a response that maintains the emotion. In this way, by generating a response based on the user's emotion, it is possible to provide a more personalized interaction experience.

[0072] The audio output unit can impart emotion to the generated audio, thereby realizing a more natural and emotional audio output. For example, audio with a joyful emotion can be generated. The audio output unit can also introduce technology for imparting emotion to the generated audio, thereby realizing a more natural audio output. For example, audio with a sad emotion can be generated. The audio output unit can also impart emotion to the generated audio, thereby realizing an emotionally rich dialogue. For example, audio with an excited emotion can be generated. This allows emotion to be imparted to the generated audio, thereby realizing a more natural and emotional audio output.

[0073] The speech recognition unit can analyze the content, tone, and emotion of a user's speech and generate a response based thereon. For example, if a user speaks excitedly, a response that reflects that tone is generated. The speech recognition unit can also analyze the content, tone, and emotion of a user's speech and generate a response based thereon. For example, if a user speaks sadly, a response that reflects that emotion is generated. The speech recognition unit can also analyze the tone, tone, and emotion of a user's speech in real time and generate a response based thereon. This makes it possible to generate a response based on the content, tone, and emotion of a user's speech.

[0074] The generation unit can analyze the user's interests in real time and provide topics based on those interests. For example, if the user is interested in sports, it can provide topics related to sports. The generation unit can also analyze the content of the user's speech to identify the user's interests. For example, if the user is talking about movies, it can provide topics related to movies. Furthermore, the generation unit can analyze the user's interests in real time and adjust the content of the dialogue based on that analysis. This makes it possible to provide topics based on the user's interests.

[0075] The speech recognition unit can filter background or environmental sounds to minimize the influence of noise. For example, during the speech recognition process, background sounds can be filtered in real time to minimize the influence of noise. The speech recognition unit can also introduce technology that analyzes environmental sounds and extracts only important speech signals. Furthermore, the speech recognition unit can improve the accuracy of speech recognition by using noise canceling technology. This can minimize the influence of noise and improve the accuracy of speech recognition.

[0076] The speech recognition unit can extend the speech recognition function to support multiple languages, enabling manzai dialogue in different languages. For example, the speech recognition function can be extended to support multiple languages, enabling manzai dialogue in different languages. The speech recognition unit can also develop a multilingual speech recognition model to improve speech recognition accuracy in different languages. Furthermore, the speech recognition unit can introduce technology for translating the speech recognition function in real time to enable manzai dialogue in different languages. This allows manzai dialogue in different languages ​​to be realized.

[0077] The generation unit can generate specialized jokes based on the user's occupation or hobby. For example, specialized jokes can be generated based on the user's occupation. The generation unit can also generate specialized jokes based on the user's hobby. Furthermore, the generation unit can analyze the user's occupation or hobby in real time and generate specialized jokes based on the analysis. This makes it possible to generate specialized jokes based on the user's occupation or hobby.

[0078] Text to speech can translate generated speech in real time, enabling multilingual speech output. For example, technology can be introduced to translate generated speech in real time. Text to speech can also develop multilingual text to speech functions to enable speech output in different languages. Furthermore, text to speech can translate generated speech in real time, enabling dialogue in different languages. This allows generated speech to be translated in real time, enabling multilingual speech output.

[0079] Text to Speech can add background sounds or sound effects to the audio output to provide a more immersive dialogue. For example, background sounds can be added to the audio output. Text to Speech can also add sound effects to the generated audio to enhance the immersive dialogue. For example, Text to Speech can combine background sounds or sound effects with the audio output to provide a more realistic dialogue experience. This allows background sounds or sound effects to be added to the audio output to provide a more immersive dialogue.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The speech recognition unit converts the user's speech into text, for example, using deep learning techniques, HMM (Hidden Markov Model), or speech recognition algorithms. Step 2: The generator generates a response that includes a joke in the Kansai dialect based on the text converted by the speech recognizer. For example, it uses a generator AI (text generator AI or multimodal generator AI), a generator AI that has learned specific phrases, expressions, and grammar rules, or an algorithm for generating a response that includes a joke in the Kansai dialect. Step 3: The voice output unit converts the response generated by the generation unit into voice and outputs it. For example, the response is converted into voice using Text to Speech (TTS) technology or a voice synthesis algorithm, and the generated voice is played back to the user.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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).

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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."

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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]

[0149] 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 speech recognition unit that converts a user's speech into text; a generation unit that generates a response including a silly Kansai dialect based on the text converted by the speech recognition unit; a voice output unit that converts the response generated by the generation unit into voice and outputs the voice. A system characterized by:

2. The voice recognition unit Estimate the user's emotions and convert text according to those emotions 2. The system of claim 1.

3. The voice recognition unit Learns the user's speech patterns and uses an individually optimized speech recognition model 2. The system of claim 1.

4. The voice recognition unit Filter background or environmental sounds to minimize the impact of noise 2. The system of claim 1.

5. The voice recognition unit Expanding the voice recognition function to support multiple languages, enabling manzai dialogue in different languages 2. The system of claim 1.

Images