system

Abstract

The system according to this embodiment aims to read text aloud in a natural-sounding voice. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives text as input. The analysis unit analyzes the text input by the reception unit. The generation unit generates speech based on the text analyzed by the analysis unit. The output unit outputs the speech generated by the generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to read text in natural voice, and there is a problem that adjustments according to voice quality, accent, and emotion are insufficient.

[0005] The system according to the embodiment aims to read text in natural voice.

Means for Solving the Problems

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit inputs text. The analysis unit analyzes the text input by the reception unit. The generation unit generates voice based on the text analyzed by the analysis unit. The output unit outputs the voice generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can read text aloud in a natural-sounding voice. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI assistant narration support system using speech synthesis according to an embodiment of the present invention is a system that has the function of reading text aloud in a natural voice. In the AI ​​assistant narration support system using speech synthesis, the user inputs text, the AI ​​assistant analyzes the input text, and performs speech synthesis. At this time, the user can select from various voice qualities and accents. Appropriate inflection and tone adjustments are also made according to language and emotion. This allows the user to obtain a natural and emotionally rich voice. For example, the user inputs "Hello, it's a nice day today." This text is input to the AI ​​assistant. Next, the AI ​​assistant analyzes the input text. The AI ​​assistant understands the content of the text and prepares for speech synthesis. For example, it analyzes the grammar and meaning of the text and sets appropriate speech synthesis parameters. During speech synthesis, the user can select from various voice qualities and accents. For example, they can select a male voice, a female voice, a young voice, an older voice, or a regional accent. This allows the user to obtain a voice that suits their preferences. Furthermore, appropriate inflection and tone adjustments are also made according to language and emotion. For example, the tone and rhythm of the voice are adjusted to express emotions such as joy, sadness, and surprise. This allows users to obtain emotionally rich voices. This mechanism enables users to obtain natural and emotionally expressive voices. For instance, when a user creates a presentation narration, they can easily create a professional voice using the AI ​​assistant. It can also be used as a text-to-speech function for the visually impaired. This allows the speech synthesis narration support system AI assistant to read aloud the text entered by the user in a natural voice.

[0029] The AI ​​assistant narration support system using speech synthesis according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives text input from the user. The text input by the user includes, but is not limited to, sentences, words, and symbols. The reception unit can accept, for example, keyboard input or voice input. The reception unit can also analyze the user's input in real time and provide appropriate feedback. The analysis unit analyzes the text input by the reception unit. The analysis unit performs, for example, grammatical analysis, semantic analysis, and sentiment analysis. The analysis unit understands the content of the text and prepares it for speech synthesis. For example, the analysis unit analyzes the grammatical structure of the text and sets appropriate speech synthesis parameters. The generation unit generates speech based on the text analyzed by the analysis unit. The generation unit generates speech using, for example, a text generation AI (e.g., LLM). The generation unit can also generate speech according to the content of the text using a multimodal generation AI. The generation unit generates speech based on the voice quality and accent selected by the user. For example, the generation unit can generate male voices, female voices, young voices, elderly voices, and regional accents. The output unit outputs the voice generated by the generation unit. The output unit outputs the voice, for example, through speakers or earphones. The output unit can also be equipped with a text-to-speech function for visually impaired users. For example, the output unit can adjust the clarity of the voice and the reading speed. As a result, the speech synthesis narration support system AI assistant according to this embodiment can read aloud the text entered by the user in a natural voice.

[0030] The reception desk accepts text input from the user. This text may include, but is not limited to, sentences, words, and symbols. The reception desk can accept input via keyboard or voice. Specifically, for keyboard input, the user uses a physical or virtual keyboard. For voice input, the user inputs voice through a microphone, and speech recognition technology converts it to text. Speech recognition technology performs noise reduction and feature extraction to achieve highly accurate text conversion. The reception desk can also analyze user input in real time and provide appropriate feedback. For example, if the user's input contains typos or omissions, the reception desk automatically suggests corrections. Furthermore, the reception desk can learn the user's input history and predict future inputs, providing input completion. This allows users to input text efficiently. The reception desk responds immediately to user input, providing an interactive experience. For example, if a user inputs a question, the reception desk immediately presents relevant information to resolve the user's doubts. The reception desk can also suggest appropriate speech synthesis settings based on the user's input. This allows the reception desk to process user input efficiently and effectively, improving the overall usability of the system.

[0031] The analysis unit analyzes the text input by the reception unit. The analysis unit performs, for example, grammatical analysis, semantic analysis, and sentiment analysis. Specifically, grammatical analysis analyzes the grammatical structure of the text and identifies grammatical elements such as subject, predicate, and object. Semantic analysis understands the content of the text and extracts contextual meaning. Sentiment analysis analyzes the emotions contained in the text and classifies them into sentiment categories such as positive, negative, and neutral. Based on these analysis results, the analysis unit prepares for speech synthesis. For example, the analysis unit analyzes the grammatical structure of the text and sets appropriate speech synthesis parameters. This includes speech pitch, speed, and intonation. Furthermore, the analysis unit sets parameters to reflect appropriate emotional expressions in the speech according to the content of the text. For example, if the sentiment analysis result is positive, it sets parameters to generate a bright and cheerful voice. The analysis unit provides these analysis results to the generation unit to improve the accuracy and naturalness of speech synthesis. The analysis unit utilizes AI technology to enhance the accuracy of text analysis. For example, natural language processing (NLP) techniques are used to gain a deeper understanding of the text context and obtain more accurate analysis results. Furthermore, machine learning algorithms are used to continuously improve the analysis model and enhance analysis accuracy. This allows the analysis unit to analyze user-input text with high accuracy and prepare it optimally for speech synthesis.

[0032] The generation unit generates speech based on the text analyzed by the analysis unit. The generation unit uses, for example, text generation AI (e.g., LLM) to generate speech. Specifically, the generation unit generates natural-sounding speech based on the grammatical structure and emotional expression parameters of the text provided by the analysis unit. The text generation AI has learned from a large amount of speech data and can generate appropriate speech according to the content of the text. The generation unit can also generate speech according to the content of the text using multimodal generation AI. Multimodal generation AI utilizes not only text but also other modal information such as images and videos to generate more natural and expressive speech. The generation unit generates speech based on the voice quality and accent selected by the user. For example, the generation unit can generate male voices, female voices, young voices, older voices, and regional accents. This allows users to select a voice that suits their preferences. During the speech generation process, the generation unit adjusts parameters such as pitch, speed, and intonation to produce natural and easy-to-understand speech. Furthermore, the generation unit can output the generated speech in real time. This allows users to immediately check the generated speech and make corrections as needed. The generation unit continuously learns and improves to enhance the accuracy and naturalness of speech synthesis. For example, it can improve its generation model based on user feedback to produce higher quality speech. This allows the generation unit to read aloud text entered by the user in a natural-sounding voice.

[0033] The output unit outputs the audio generated by the generation unit. The output unit outputs the audio through, for example, speakers or headphones. Specifically, the output unit plays the generated audio through a high-quality audio device and delivers it to the user. When using speakers, the output unit adjusts the volume and sound quality to provide clear and easy-to-hear audio. When using headphones, the output unit adjusts the audio balance to fit the user's ears, providing a comfortable listening experience. The output unit can also include a text-to-speech function for visually impaired users. For example, the output unit can adjust the clarity and reading speed of the audio. When used by visually impaired users, the output unit can individually set the pitch and speed of the audio to provide audio output tailored to the user's needs. Furthermore, the output unit can transmit the generated audio to other devices and systems. For example, the generated audio can be sent to a smartphone or tablet for playback while on the go. The output unit can also record the generated audio and save it as a file for later playback. This allows users to utilize the generated audio in various ways. The output unit continuously monitors the audio output quality and makes adjustments as needed. For example, if noise occurs during audio output, the output unit automatically removes the noise, providing clear audio. This allows the output unit to output high-quality audio, providing users with a comfortable listening experience.

[0034] The generation unit has the ability to select from multiple voice qualities and accents. For example, the generation unit can generate male voices, female voices, young voices, elderly voices, and regional accents. The generation unit generates speech based on the voice qualities and accents selected by the user. For example, the generation unit can adjust the tone and rhythm of the speech based on the voice qualities and accents selected by the user. This allows the user to obtain speech tailored to their preferences. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can generate speech using a generation AI model that takes the voice qualities and accents selected by the user as input and outputs speech.

[0035] The output unit includes a text-to-speech function for visually impaired users. The output unit can, for example, adjust the clarity and reading speed of the speech. It can also adjust the tone and rhythm of the speech to make the text easier for visually impaired users to understand. For example, the output unit can adjust the volume and intonation of the speech to make the text easier for visually impaired users to understand. This allows it to be used as a text-to-speech function for visually impaired users. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can generate speech using an AI model that adjusts the tone and rhythm of speech to make the text easier for visually impaired users to understand.

[0036] The reception desk can analyze the user's past input history and suggest the optimal input method. For example, the reception desk can automatically display phrases and words that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest phrases and words that the user will use at specific times of day based on their past input history. This allows the reception desk to suggest the optimal input method based on the user's past input history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can suggest an input method using an AI model that analyzes the user's past input history and suggests the optimal input method.

[0037] The input system can suggest input options based on the user's current activities and areas of interest when text is entered. For example, if the user is at work, the input system will prioritize suggesting business-related phrases and words. It can also suggest suggestions related to a user's hobbies if the user is entering text about those hobbies. Furthermore, if the user is participating in a specific event, the input system can suggest phrases and words related to that event. This allows the system to present appropriate input options based on the user's activities and areas of interest. Some or all of the above processing in the input system may be performed using AI, for example, or not. For example, the input system can suggest input options using an AI model that takes the user's current activities and areas of interest as input and outputs suggestions.

[0038] The input field can present highly relevant input suggestions based on the user's geographical location when text is entered. For example, if the user is in a specific region, the input field can present phrases and words related to that region. Furthermore, if the user is traveling, the input field can also present suggestions related to tourist attractions or modes of transportation. Additionally, if the user is in a specific store, the input field can present phrases and words related to that store. This allows for the presentation of appropriate input suggestions based on the user's geographical location. Some or all of the above processing in the input field may be performed using AI, or not. For example, the input field can present input suggestions using an AI model that takes the user's geographical location as input and outputs highly relevant input suggestions.

[0039] The input field can analyze the user's social media activity when text is entered and suggest relevant input options. For example, the input field can suggest phrases and words related to topics the user has recently been discussing on social media. It can also suggest suggestions related to specific hashtags if the user is using them. Furthermore, if the input field belongs to a particular group or community, it can suggest phrases and words related to that group or community. This allows for the presentation of appropriate input options based on the user's social media activity. Some or all of the above processing in the input field may be performed using AI, for example, or without AI. For example, the input field can suggest input options using an AI model that takes the user's social media activity as input and outputs relevant input options.

[0040] The analysis unit can refer to past analysis data during text analysis to improve the accuracy of grammatical and semantic analysis. For example, the analysis unit can correct grammatical errors based on previously analyzed data. It can also resolve semantic ambiguities by referring to past analysis data. Furthermore, the analysis unit can select an appropriate analysis method for a specific context based on past analysis data. This improves analysis accuracy by referring to past analysis data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can take past analysis data as input and perform text analysis using an AI model that improves analysis accuracy.

[0041] The analysis unit can apply different analysis methods depending on the category of the text during text analysis. For example, in the case of business documents, the analysis unit can use analysis methods specialized in technical terms and business vocabulary. Similarly, in the case of novels and stories, the analysis unit can use analysis methods specialized in emotions and descriptions. Furthermore, in the case of scientific papers, the analysis unit can use analysis methods specialized in technical terms and structure. This enables appropriate analysis according to the category of the text. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can perform text analysis using an AI model that takes the text category as input and applies different analysis methods.

[0042] The analysis unit can determine the priority of text analysis based on the submission date of the text. For example, the analysis unit will prioritize analyzing texts with approaching deadlines. Furthermore, if the user is in a hurry, the analysis unit can perform a rapid analysis. Additionally, the analysis unit can perform a more detailed analysis on texts with ample time before the submission deadline. This allows for analysis to be performed with prioritization based on the submission date. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can perform text analysis using an AI model that takes the text submission date as input and determines the analysis priority.

[0043] The analysis unit can improve the accuracy of its analysis by referring to relevant literature and data during text analysis. For example, the analysis unit can analyze the meaning of technical terms by referring to relevant literature. The analysis unit can also supplement the content of the text based on relevant data. Furthermore, the analysis unit can improve the accuracy of its analysis by referring to relevant research results. Thus, the accuracy of the analysis is improved by referring to relevant literature and data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can take relevant literature and data as input and perform text analysis using an AI model that improves analysis accuracy.

[0044] The generation unit can generate appropriate speech by referring to the user's past speech generation history. For example, the generation unit can generate optimal speech based on the voice quality and accent previously selected by the user. The generation unit can also generate speech containing specific emotional expressions from the user's past speech generation history. Furthermore, the generation unit can analyze the user's past speech generation history and generate the most natural speech. This allows for the generation of optimal speech based on past speech generation history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that takes the user's past speech generation history as input and generates appropriate speech.

[0045] The generation unit can apply different speech generation algorithms depending on the content of the text during speech generation. For example, in the case of business documents, the generation unit may use an algorithm that generates speech in a formal tone. It may also use an algorithm that generates speech in an emotionally rich tone for novels or stories. Furthermore, for scientific papers, the generation unit may use an algorithm that generates speech in a professional tone. This enables appropriate speech generation according to the content of the text. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that takes text content as input and applies different speech generation algorithms.

[0046] The generation unit can generate appropriate speech based on the user's geographical location information during speech generation. For example, if the user is in a specific region, the generation unit can generate speech incorporating the accent of that region. Furthermore, if the user is traveling, the generation unit can generate speech containing information related to tourist destinations. Additionally, if the user is in a specific store, the generation unit can generate speech containing information related to that store. This allows for the generation of optimal speech based on the user's geographical location information. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that takes the user's geographical location information as input and generates appropriate speech.

[0047] The generation unit can improve the accuracy of speech generation by referring to relevant audio data during speech generation. For example, the generation unit can generate natural intonation based on relevant audio data. The generation unit can also generate speech that includes specific emotional expressions by referring to relevant audio data. Furthermore, the generation unit can generate speech that incorporates specific accents based on relevant audio data. This improves the accuracy of generation by referring to relevant audio data. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can take relevant audio data as input and generate speech using an AI model that improves generation accuracy.

[0048] The output unit can select the optimal output method when outputting audio by referring to the user's past output history. For example, the output unit can select the optimal output method based on the output method the user has previously selected (speaker, earphones, etc.). The output unit can also suggest an output method appropriate to a specific situation based on the user's past output history. Furthermore, the output unit can analyze the user's past output history and select the most natural audio output method. This allows the optimal output method to be selected based on past output history. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can take the user's past output history as input and output audio using an AI model that selects the optimal output method.

[0049] The output unit can optimize the output based on the user's device information when outputting audio. For example, if the user is using a smartphone, the output unit can optimize the audio to match the device's speaker characteristics. Furthermore, if the user is using a tablet, the output unit can provide audio output optimized for a larger screen. Additionally, if the user is using a smartwatch, the output unit can provide concise and easily readable audio output. This enables optimal audio output based on the user's device information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For instance, the output unit can take the user's device information as input and output audio using an AI model that optimizes the output.

[0050] The output unit can select the optimal output method when outputting audio, taking into account the user's geographical location information. For example, if the user is in a specific region, the output unit can output audio incorporating the accent of that region. Furthermore, if the user is traveling, the output unit can output audio containing information related to tourist destinations. Additionally, if the user is in a specific store, the output unit can output audio containing information related to that store. This enables optimal audio output based on the user's geographical location information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can use an AI model that takes the user's geographical location information as input and selects the optimal output method to output audio.

[0051] The output unit can analyze the user's social media activity and suggest output methods when outputting audio. For example, the output unit can output audio related to topics the user has recently been discussing on social media. Furthermore, if the user is using a specific hashtag, the output unit can also output audio containing information related to that hashtag. Additionally, if the user is a member of a specific group or community, the output unit can output audio containing information related to that group or community. This allows for the suggestion of appropriate audio output methods based on the user's social media activity. Some or all of the processing described above in the output unit may be performed using, for example, AI, or without AI. For example, the output unit can take the user's social media activity as input and output audio using an AI model that suggests output methods.

[0052] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0053] The reception desk can analyze the user's past input history and suggest the optimal input method. For example, it can automatically display phrases and words that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest phrases and words that the user will use at specific times of day based on their past input history. This allows the reception desk to suggest the optimal input method based on the user's past input history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can suggest an input method using an AI model that analyzes the user's past input history and suggests the optimal input method.

[0054] The input system can suggest input options based on the user's current activities and areas of interest when text is entered. For example, if the user is at work, it will prioritize business-related phrases and words. If the user is entering text about their hobbies, it can also suggest options related to that field. Furthermore, if the user is participating in a specific event, the input system can suggest phrases and words related to that event. This allows for the presentation of appropriate input options based on the user's activities and areas of interest. Some or all of the above processing in the input system may be performed using AI, for example, or not. For example, the input system can present input options using an AI model that takes the user's current activities and areas of interest as input and outputs input options.

[0055] The reception desk can present highly relevant input suggestions based on the user's geographical location when text is entered. For example, if the user is in a specific region, it can present phrases and words related to that region. If the user is traveling, it can also present suggestions related to tourist attractions and transportation. Furthermore, if the user is in a specific store, the reception desk can present phrases and words related to that store. This allows for the presentation of appropriate input suggestions based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can present input suggestions using an AI model that takes the user's geographical location as input and outputs highly relevant input suggestions.

[0056] The generation unit can generate appropriate speech by referring to the user's past speech generation history. For example, it can generate optimal speech based on the voice quality and accent previously selected by the user. The generation unit can also generate speech containing specific emotional expressions from the user's past speech generation history. Furthermore, the generation unit can analyze the user's past speech generation history and generate the most natural speech. This allows for the generation of optimal speech based on past speech generation history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that takes the user's past speech generation history as input and generates appropriate speech.

[0057] The output unit can optimize the output based on the user's device information when outputting audio. For example, if the user is using a smartphone, the output unit can optimize the audio to match the device's speaker characteristics. Furthermore, if the user is using a tablet, the output unit can provide audio optimized for a larger screen. Additionally, if the user is using a smartwatch, the output unit can provide concise and easily readable audio. This enables optimal audio output based on the user's device information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For instance, the output unit can take the user's device information as input and use an AI model to optimize the output before outputting audio.

[0058] The following briefly describes the processing flow for example form 1.

[0059] Step 1: The reception desk receives text input from the user. This text may include, but is not limited to, sentences, words, and symbols. The reception desk can accept input via keyboard or voice, for example. It can also analyze the user's input in real time and provide appropriate feedback. Step 2: The analysis unit analyzes the text input by the reception unit. The analysis unit performs, for example, grammatical analysis, semantic analysis, and sentiment analysis. The analysis unit understands the content of the text and prepares it for speech synthesis. For example, the analysis unit analyzes the grammatical structure of the text and sets appropriate speech synthesis parameters. Step 3: The generation unit generates speech based on the text analyzed by the analysis unit. The generation unit generates speech using, for example, a text generation AI (e.g., LLM). Alternatively, the generation unit can use a multimodal generation AI to generate speech that corresponds to the content of the text. The generation unit generates speech based on the voice quality and accent selected by the user. For example, the generation unit can generate male voices, female voices, young voices, older voices, regional accents, etc. Step 4: The output unit outputs the audio generated by the generation unit. The output unit outputs the audio through, for example, a speaker or headphones. The output unit can also be equipped with a text-to-speech function for the visually impaired. For example, the output unit can adjust the clarity of the audio and the reading speed.

[0060] (Example of form 2) An AI assistant narration support system using speech synthesis according to an embodiment of the present invention is a system that has the function of reading text aloud in a natural voice. In the AI ​​assistant narration support system using speech synthesis, the user inputs text, the AI ​​assistant analyzes the input text, and performs speech synthesis. At this time, the user can select from various voice qualities and accents. Appropriate inflection and tone adjustments are also made according to language and emotion. This allows the user to obtain a natural and emotionally rich voice. For example, the user inputs "Hello, it's a nice day today." This text is input to the AI ​​assistant. Next, the AI ​​assistant analyzes the input text. The AI ​​assistant understands the content of the text and prepares for speech synthesis. For example, it analyzes the grammar and meaning of the text and sets appropriate speech synthesis parameters. During speech synthesis, the user can select from various voice qualities and accents. For example, they can select a male voice, a female voice, a young voice, an older voice, or a regional accent. This allows the user to obtain a voice that suits their preferences. Furthermore, appropriate inflection and tone adjustments are also made according to language and emotion. For example, the tone and rhythm of the voice are adjusted to express emotions such as joy, sadness, and surprise. This allows users to obtain emotionally rich voices. This mechanism enables users to obtain natural and emotionally expressive voices. For instance, when a user creates a presentation narration, they can easily create a professional voice using the AI ​​assistant. It can also be used as a text-to-speech function for the visually impaired. This allows the speech synthesis narration support system AI assistant to read aloud the text entered by the user in a natural voice.

[0061] The AI ​​assistant narration support system using speech synthesis according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and an output unit. The reception unit receives text input from the user. The text input by the user includes, but is not limited to, sentences, words, and symbols. The reception unit can accept, for example, keyboard input or voice input. The reception unit can also analyze the user's input in real time and provide appropriate feedback. The analysis unit analyzes the text input by the reception unit. The analysis unit performs, for example, grammatical analysis, semantic analysis, and sentiment analysis. The analysis unit understands the content of the text and prepares it for speech synthesis. For example, the analysis unit analyzes the grammatical structure of the text and sets appropriate speech synthesis parameters. The generation unit generates speech based on the text analyzed by the analysis unit. The generation unit generates speech using, for example, a text generation AI (e.g., LLM). The generation unit can also generate speech according to the content of the text using a multimodal generation AI. The generation unit generates speech based on the voice quality and accent selected by the user. For example, the generation unit can generate male voices, female voices, young voices, elderly voices, and regional accents. The output unit outputs the voice generated by the generation unit. The output unit outputs the voice, for example, through speakers or earphones. The output unit can also be equipped with a text-to-speech function for visually impaired users. For example, the output unit can adjust the clarity of the voice and the reading speed. As a result, the speech synthesis narration support system AI assistant according to this embodiment can read aloud the text entered by the user in a natural voice.

[0062] The reception desk accepts text input from the user. This text may include, but is not limited to, sentences, words, and symbols. The reception desk can accept input via keyboard or voice. Specifically, for keyboard input, the user uses a physical or virtual keyboard. For voice input, the user inputs voice through a microphone, and speech recognition technology converts it to text. Speech recognition technology performs noise reduction and feature extraction to achieve highly accurate text conversion. The reception desk can also analyze user input in real time and provide appropriate feedback. For example, if the user's input contains typos or omissions, the reception desk automatically suggests corrections. Furthermore, the reception desk can learn the user's input history and predict future inputs, providing input completion. This allows users to input text efficiently. The reception desk responds immediately to user input, providing an interactive experience. For example, if a user inputs a question, the reception desk immediately presents relevant information to resolve the user's doubts. The reception desk can also suggest appropriate speech synthesis settings based on the user's input. This allows the reception desk to process user input efficiently and effectively, improving the overall usability of the system.

[0063] The analysis unit analyzes the text input by the reception unit. The analysis unit performs, for example, grammatical analysis, semantic analysis, and sentiment analysis. Specifically, grammatical analysis analyzes the grammatical structure of the text and identifies grammatical elements such as subject, predicate, and object. Semantic analysis understands the content of the text and extracts contextual meaning. Sentiment analysis analyzes the emotions contained in the text and classifies them into sentiment categories such as positive, negative, and neutral. Based on these analysis results, the analysis unit prepares for speech synthesis. For example, the analysis unit analyzes the grammatical structure of the text and sets appropriate speech synthesis parameters. This includes speech pitch, speed, and intonation. Furthermore, the analysis unit sets parameters to reflect appropriate emotional expressions in the speech according to the content of the text. For example, if the sentiment analysis result is positive, it sets parameters to generate a bright and cheerful voice. The analysis unit provides these analysis results to the generation unit to improve the accuracy and naturalness of speech synthesis. The analysis unit utilizes AI technology to enhance the accuracy of text analysis. For example, natural language processing (NLP) techniques are used to gain a deeper understanding of the text context and obtain more accurate analysis results. Furthermore, machine learning algorithms are used to continuously improve the analysis model and enhance analysis accuracy. This allows the analysis unit to analyze user-input text with high accuracy and prepare it optimally for speech synthesis.

[0064] The generation unit generates speech based on the text analyzed by the analysis unit. The generation unit uses, for example, text generation AI (e.g., LLM) to generate speech. Specifically, the generation unit generates natural-sounding speech based on the grammatical structure and emotional expression parameters of the text provided by the analysis unit. The text generation AI has learned from a large amount of speech data and can generate appropriate speech according to the content of the text. The generation unit can also generate speech according to the content of the text using multimodal generation AI. Multimodal generation AI utilizes not only text but also other modal information such as images and videos to generate more natural and expressive speech. The generation unit generates speech based on the voice quality and accent selected by the user. For example, the generation unit can generate male voices, female voices, young voices, older voices, and regional accents. This allows users to select a voice that suits their preferences. During the speech generation process, the generation unit adjusts parameters such as pitch, speed, and intonation to produce natural and easy-to-understand speech. Furthermore, the generation unit can output the generated speech in real time. This allows users to immediately check the generated speech and make corrections as needed. The generation unit continuously learns and improves to enhance the accuracy and naturalness of speech synthesis. For example, it can improve its generation model based on user feedback to produce higher quality speech. This allows the generation unit to read aloud text entered by the user in a natural-sounding voice.

[0065] The output unit outputs the audio generated by the generation unit. The output unit outputs the audio through, for example, speakers or headphones. Specifically, the output unit plays the generated audio through a high-quality audio device and delivers it to the user. When using speakers, the output unit adjusts the volume and sound quality to provide clear and easy-to-hear audio. When using headphones, the output unit adjusts the audio balance to fit the user's ears, providing a comfortable listening experience. The output unit can also include a text-to-speech function for visually impaired users. For example, the output unit can adjust the clarity and reading speed of the audio. When used by visually impaired users, the output unit can individually set the pitch and speed of the audio to provide audio output tailored to the user's needs. Furthermore, the output unit can transmit the generated audio to other devices and systems. For example, the generated audio can be sent to a smartphone or tablet for playback while on the go. The output unit can also record the generated audio and save it as a file for later playback. This allows users to utilize the generated audio in various ways. The output unit continuously monitors the audio output quality and makes adjustments as needed. For example, if noise occurs during audio output, the output unit automatically removes the noise, providing clear audio. This allows the output unit to output high-quality audio, providing users with a comfortable listening experience.

[0066] The generation unit has the ability to select from multiple voice qualities and accents. For example, the generation unit can generate male voices, female voices, young voices, elderly voices, and regional accents. The generation unit generates speech based on the voice qualities and accents selected by the user. For example, the generation unit can adjust the tone and rhythm of the speech based on the voice qualities and accents selected by the user. This allows the user to obtain speech tailored to their preferences. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can generate speech using a generation AI model that takes the voice qualities and accents selected by the user as input and outputs speech.

[0067] The generation unit has the function of adjusting intonation and tone according to language and emotion. For example, the generation unit can adjust the tone and rhythm of the voice to express emotions such as joy, sadness, or surprise. The generation unit adjusts the intonation and tone of the voice based on the language and emotion selected by the user. For example, the generation unit can adjust the pitch, volume, and rhythm of the voice based on the language and emotion selected by the user. This allows the user to obtain emotionally rich speech. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using a generative AI, for example, or without a generative AI. For example, the generation unit can generate speech using a generative AI model that takes an emotion selected by the user as input and outputs the intonation and tone of the voice.

[0068] The output unit includes a text-to-speech function for visually impaired users. The output unit can, for example, adjust the clarity and reading speed of the speech. It can also adjust the tone and rhythm of the speech to make the text easier for visually impaired users to understand. For example, the output unit can adjust the volume and intonation of the speech to make the text easier for visually impaired users to understand. This allows it to be used as a text-to-speech function for visually impaired users. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can generate speech using an AI model that adjusts the tone and rhythm of speech to make the text easier for visually impaired users to understand.

[0069] The reception desk can estimate the user's emotions and adjust the text input interface based on the estimated emotions. For example, if the user is nervous, the reception desk can provide a simple and intuitive interface to reduce the effort required for input. If the user is relaxed, the reception desk can also provide detailed input options and suggest a customizable interface. Furthermore, if the user is in a hurry, the reception desk can prioritize voice input to allow for quick text input. This allows for the provision of an interface that responds to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can provide an interface using an AI model that estimates the user's emotions and adjusts the interface based on the estimated emotions.

[0070] The reception desk can analyze the user's past input history and suggest the optimal input method. For example, the reception desk can automatically display phrases and words that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest phrases and words that the user will use at specific times of day based on their past input history. This allows the reception desk to suggest the optimal input method based on the user's past input history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can suggest an input method using an AI model that analyzes the user's past input history and suggests the optimal input method.

[0071] The input system can suggest input options based on the user's current activities and areas of interest when text is entered. For example, if the user is at work, the input system will prioritize suggesting business-related phrases and words. It can also suggest suggestions related to a user's hobbies if the user is entering text about those hobbies. Furthermore, if the user is participating in a specific event, the input system can suggest phrases and words related to that event. This allows the system to present appropriate input options based on the user's activities and areas of interest. Some or all of the above processing in the input system may be performed using AI, for example, or not. For example, the input system can suggest input options using an AI model that takes the user's current activities and areas of interest as input and outputs suggestions.

[0072] The reception desk can estimate the user's emotions and determine the priority of the text to be entered based on the estimated emotions. For example, if the user is stressed, the reception desk may suggest prioritizing the input of important text. It may also suggest prioritizing detailed information if the user is relaxed. Furthermore, if the user is in a hurry, it may suggest prioritizing short, concise text. This allows the system to determine the priority of the text to be entered according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can determine the priority of text using an AI model that estimates the user's emotions and determines the priority of text based on the estimated emotions.

[0073] The input field can present highly relevant input suggestions based on the user's geographical location when text is entered. For example, if the user is in a specific region, the input field can present phrases and words related to that region. Furthermore, if the user is traveling, the input field can also present suggestions related to tourist attractions or modes of transportation. Additionally, if the user is in a specific store, the input field can present phrases and words related to that store. This allows for the presentation of appropriate input suggestions based on the user's geographical location. Some or all of the above processing in the input field may be performed using AI, or not. For example, the input field can present input suggestions using an AI model that takes the user's geographical location as input and outputs highly relevant input suggestions.

[0074] The input field can analyze the user's social media activity when text is entered and suggest relevant input options. For example, the input field can suggest phrases and words related to topics the user has recently been discussing on social media. It can also suggest suggestions related to specific hashtags if the user is using them. Furthermore, if the input field belongs to a particular group or community, it can suggest phrases and words related to that group or community. This allows for the presentation of appropriate input options based on the user's social media activity. Some or all of the above processing in the input field may be performed using AI, for example, or without AI. For example, the input field can suggest input options using an AI model that takes the user's social media activity as input and outputs relevant input options.

[0075] The analysis unit can estimate the user's emotions and adjust the text analysis algorithm based on the estimated emotions. For example, if the user is nervous, the analysis unit can use a simple and intuitive analysis algorithm. If the user is relaxed, the analysis unit can also use an algorithm that performs a detailed analysis. Furthermore, if the user is in a hurry, the analysis unit can also use an algorithm that performs a rapid analysis. This enables text analysis that is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can perform text analysis using an AI model that estimates the user's emotions and adjusts the text analysis algorithm based on the estimated emotions.

[0076] The analysis unit can refer to past analysis data during text analysis to improve the accuracy of grammatical and semantic analysis. For example, the analysis unit can correct grammatical errors based on previously analyzed data. It can also resolve semantic ambiguities by referring to past analysis data. Furthermore, the analysis unit can select an appropriate analysis method for a specific context based on past analysis data. This improves analysis accuracy by referring to past analysis data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can take past analysis data as input and perform text analysis using an AI model that improves analysis accuracy.

[0077] The analysis unit can apply different analysis methods depending on the category of the text during text analysis. For example, in the case of business documents, the analysis unit can use analysis methods specialized in technical terms and business vocabulary. Similarly, in the case of novels and stories, the analysis unit can use analysis methods specialized in emotions and descriptions. Furthermore, in the case of scientific papers, the analysis unit can use analysis methods specialized in technical terms and structure. This enables appropriate analysis according to the category of the text. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can perform text analysis using an AI model that takes the text category as input and applies different analysis methods.

[0078] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, the analysis unit can provide a simple and highly visible display method. If the user is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a concise display method. This makes it possible to display analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can display the analysis results using an AI model that estimates the user's emotions and adjusts the display method of the analysis results based on the estimated emotions.

[0079] The analysis unit can determine the priority of text analysis based on the submission date of the text. For example, the analysis unit will prioritize analyzing texts with approaching deadlines. Furthermore, if the user is in a hurry, the analysis unit can perform a rapid analysis. Additionally, the analysis unit can perform a more detailed analysis on texts with ample time before the submission deadline. This allows for analysis to be performed with prioritization based on the submission date. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can perform text analysis using an AI model that takes the text submission date as input and determines the analysis priority.

[0080] The analysis unit can improve the accuracy of its analysis by referring to relevant literature and data during text analysis. For example, the analysis unit can analyze the meaning of technical terms by referring to relevant literature. The analysis unit can also supplement the content of the text based on relevant data. Furthermore, the analysis unit can improve the accuracy of its analysis by referring to relevant research results. Thus, the accuracy of the analysis is improved by referring to relevant literature and data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can take relevant literature and data as input and perform text analysis using an AI model that improves analysis accuracy.

[0081] The generation unit can estimate the user's emotions and adjust the speech generation parameters based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate speech in a relaxed tone. If the user is in a hurry, the generation unit can also generate speech in a quick and concise tone. Furthermore, if the user is excited, the generation unit can generate speech in an energetic tone. This enables speech generation that responds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can generate speech using an AI model that estimates the user's emotions and adjusts the speech generation parameters based on the estimated emotions.

[0082] The generation unit can generate appropriate speech by referring to the user's past speech generation history. For example, the generation unit can generate optimal speech based on the voice quality and accent previously selected by the user. The generation unit can also generate speech containing specific emotional expressions from the user's past speech generation history. Furthermore, the generation unit can analyze the user's past speech generation history and generate the most natural speech. This allows for the generation of optimal speech based on past speech generation history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that takes the user's past speech generation history as input and generates appropriate speech.

[0083] The generation unit can apply different speech generation algorithms depending on the content of the text during speech generation. For example, in the case of business documents, the generation unit may use an algorithm that generates speech in a formal tone. It may also use an algorithm that generates speech in an emotionally rich tone for novels or stories. Furthermore, for scientific papers, the generation unit may use an algorithm that generates speech in a professional tone. This enables appropriate speech generation according to the content of the text. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that takes text content as input and applies different speech generation algorithms.

[0084] The generation unit can estimate the user's emotions and adjust the tone and rhythm of the generated speech based on the estimated emotions. For example, if the user is relaxed, the generation unit will generate speech with a relaxed rhythm. If the user is in a hurry, the generation unit can also generate speech with a quick and concise rhythm. Furthermore, if the user is excited, the generation unit can generate speech with an energetic rhythm. This allows for adjustment of the tone and rhythm of speech according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that estimates the user's emotions and adjusts the tone and rhythm of speech based on the estimated emotions.

[0085] The generation unit can generate appropriate speech based on the user's geographical location information during speech generation. For example, if the user is in a specific region, the generation unit can generate speech incorporating the accent of that region. Furthermore, if the user is traveling, the generation unit can generate speech containing information related to tourist destinations. Additionally, if the user is in a specific store, the generation unit can generate speech containing information related to that store. This allows for the generation of optimal speech based on the user's geographical location information. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that takes the user's geographical location information as input and generates appropriate speech.

[0086] The generation unit can improve the accuracy of speech generation by referring to relevant audio data during speech generation. For example, the generation unit can generate natural intonation based on relevant audio data. The generation unit can also generate speech that includes specific emotional expressions by referring to relevant audio data. Furthermore, the generation unit can generate speech that incorporates specific accents based on relevant audio data. This improves the accuracy of generation by referring to relevant audio data. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can take relevant audio data as input and generate speech using an AI model that improves generation accuracy.

[0087] The output unit can estimate the user's emotions and adjust the method of voice output based on the estimated emotions. For example, if the user is nervous, the output unit can output voice in a calm tone. It can also output voice in a bright tone if the user is relaxed. Furthermore, if the user is in a hurry, the output unit can output voice in a quick and concise tone. This enables voice output that responds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI, or not. For example, the output unit can output voice using an AI model that estimates the user's emotions and adjusts the method of voice output based on the estimated emotions.

[0088] The output unit can select the optimal output method when outputting audio by referring to the user's past output history. For example, the output unit can select the optimal output method based on the output method the user has previously selected (speaker, earphones, etc.). The output unit can also suggest an output method appropriate to a specific situation based on the user's past output history. Furthermore, the output unit can analyze the user's past output history and select the most natural audio output method. This allows the optimal output method to be selected based on past output history. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can take the user's past output history as input and output audio using an AI model that selects the optimal output method.

[0089] The output unit can optimize the output based on the user's device information when outputting audio. For example, if the user is using a smartphone, the output unit can optimize the audio to match the device's speaker characteristics. Furthermore, if the user is using a tablet, the output unit can provide audio output optimized for a larger screen. Additionally, if the user is using a smartwatch, the output unit can provide concise and easily readable audio output. This enables optimal audio output based on the user's device information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For instance, the output unit can take the user's device information as input and output audio using an AI model that optimizes the output.

[0090] The output unit can estimate the user's emotions and determine the priority of audio output based on the estimated emotions. For example, if the user is stressed, the output unit may prioritize outputting important audio. If the user is relaxed, the output unit may also prioritize outputting audio containing detailed information. Furthermore, if the user is in a hurry, the output unit may prioritize outputting short, concise audio. This allows for the determination of audio output priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI, or not. For example, the output unit may output audio using an AI model that estimates the user's emotions and determines the priority of audio output based on the estimated emotions.

[0091] The output unit can select the optimal output method when outputting audio, taking into account the user's geographical location information. For example, if the user is in a specific region, the output unit can output audio incorporating the accent of that region. Furthermore, if the user is traveling, the output unit can output audio containing information related to tourist destinations. Additionally, if the user is in a specific store, the output unit can output audio containing information related to that store. This enables optimal audio output based on the user's geographical location information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can use an AI model that takes the user's geographical location information as input and selects the optimal output method to output audio.

[0092] The output unit can analyze the user's social media activity and suggest output methods when outputting audio. For example, the output unit can output audio related to topics the user has recently been discussing on social media. Furthermore, if the user is using a specific hashtag, the output unit can also output audio containing information related to that hashtag. Additionally, if the user is a member of a specific group or community, the output unit can output audio containing information related to that group or community. This allows for the suggestion of appropriate audio output methods based on the user's social media activity. Some or all of the processing described above in the output unit may be performed using, for example, AI, or without AI. For example, the output unit can take the user's social media activity as input and output audio using an AI model that suggests output methods.

[0093] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0094] The analysis unit can estimate the user's emotions and adjust the text analysis algorithm based on the estimated emotions. For example, if the user is nervous, a simple and intuitive analysis algorithm can be used. If the user is relaxed, a more detailed analysis algorithm can be used. Furthermore, if the user is in a hurry, a rapid analysis algorithm can be used. This enables text analysis that is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, or not. For example, the analysis unit can perform text analysis using an AI model that estimates the user's emotions and adjusts the text analysis algorithm based on the estimated emotions.

[0095] The generation unit can estimate the user's emotions and adjust the speech generation parameters based on the estimated emotions. For example, if the user is relaxed, it can generate speech in a relaxed tone. If the user is in a hurry, it can generate speech in a quick and concise tone. Furthermore, if the user is excited, it can generate speech in an energetic tone. This enables speech generation that responds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that estimates the user's emotions and adjusts the speech generation parameters based on the estimated emotions.

[0096] The output unit can estimate the user's emotions and adjust the method of voice output based on the estimated emotions. For example, if the user is nervous, the voice can be output in a calm tone. If the user is relaxed, the voice can be output in a bright tone. Furthermore, if the user is in a hurry, the voice can be output in a quick and concise tone. This enables voice output that is appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can output voice using an AI model that estimates the user's emotions and adjusts the method of voice output based on the estimated emotions.

[0097] The reception desk can estimate the user's emotions and adjust the text input interface based on the estimated emotions. For example, if the user is nervous, it can provide a simple and intuitive interface to reduce the effort required for input. If the user is relaxed, it can provide detailed input options and suggest a customizable interface. Furthermore, if the user is in a hurry, it can prioritize voice input to allow for quick text input. This allows for the provision of an interface that responds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can provide an interface using an AI model that estimates the user's emotions and adjusts the interface based on the estimated emotions.

[0098] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, it can provide a simple and highly visible display method. If the user is relaxed, it can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, it can provide a display method that gets straight to the point. This makes it possible to display analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can display the analysis results using an AI model that estimates the user's emotions and adjusts the display method of the analysis results based on the estimated emotions.

[0099] The reception desk can analyze the user's past input history and suggest the optimal input method. For example, it can automatically display phrases and words that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest phrases and words that the user will use at specific times of day based on their past input history. This allows the reception desk to suggest the optimal input method based on the user's past input history. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can suggest an input method using an AI model that analyzes the user's past input history and suggests the optimal input method.

[0100] The input system can suggest input options based on the user's current activities and areas of interest when text is entered. For example, if the user is at work, it will prioritize business-related phrases and words. If the user is entering text about their hobbies, it can also suggest options related to that field. Furthermore, if the user is participating in a specific event, the input system can suggest phrases and words related to that event. This allows for the presentation of appropriate input options based on the user's activities and areas of interest. Some or all of the above processing in the input system may be performed using AI, for example, or not. For example, the input system can present input options using an AI model that takes the user's current activities and areas of interest as input and outputs input options.

[0101] The reception desk can present highly relevant input suggestions based on the user's geographical location when text is entered. For example, if the user is in a specific region, it can present phrases and words related to that region. If the user is traveling, it can also present suggestions related to tourist attractions and transportation. Furthermore, if the user is in a specific store, the reception desk can present phrases and words related to that store. This allows for the presentation of appropriate input suggestions based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can present input suggestions using an AI model that takes the user's geographical location as input and outputs highly relevant input suggestions.

[0102] The generation unit can generate appropriate speech by referring to the user's past speech generation history. For example, it can generate optimal speech based on the voice quality and accent previously selected by the user. The generation unit can also generate speech containing specific emotional expressions from the user's past speech generation history. Furthermore, the generation unit can analyze the user's past speech generation history and generate the most natural speech. This allows for the generation of optimal speech based on past speech generation history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can generate speech using an AI model that takes the user's past speech generation history as input and generates appropriate speech.

[0103] The output unit can optimize the output based on the user's device information when outputting audio. For example, if the user is using a smartphone, the output unit can optimize the audio to match the device's speaker characteristics. Furthermore, if the user is using a tablet, the output unit can provide audio optimized for a larger screen. Additionally, if the user is using a smartwatch, the output unit can provide concise and easily readable audio. This enables optimal audio output based on the user's device information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For instance, the output unit can take the user's device information as input and use an AI model to optimize the output before outputting audio.

[0104] The following briefly describes the processing flow for example form 2.

[0105] Step 1: The reception desk receives text input from the user. This text may include, but is not limited to, sentences, words, and symbols. The reception desk can accept input via keyboard or voice, for example. It can also analyze the user's input in real time and provide appropriate feedback. Step 2: The analysis unit analyzes the text input by the reception unit. The analysis unit performs, for example, grammatical analysis, semantic analysis, and sentiment analysis. The analysis unit understands the content of the text and prepares it for speech synthesis. For example, the analysis unit analyzes the grammatical structure of the text and sets appropriate speech synthesis parameters. Step 3: The generation unit generates speech based on the text analyzed by the analysis unit. The generation unit generates speech using, for example, a text generation AI (e.g., LLM). Alternatively, the generation unit can use a multimodal generation AI to generate speech that corresponds to the content of the text. The generation unit generates speech based on the voice quality and accent selected by the user. For example, the generation unit can generate male voices, female voices, young voices, older voices, regional accents, etc. Step 4: The output unit outputs the audio generated by the generation unit. The output unit outputs the audio through, for example, a speaker or headphones. The output unit can also be equipped with a text-to-speech function for the visually impaired. For example, the output unit can adjust the clarity of the audio and the reading speed.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0108] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0109] For example, the reception unit is implemented by the reception device 38 of the smart device 14. For example, it can accept keyboard input or voice input. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and performs grammatical analysis, semantic analysis, sentiment analysis, etc. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates speech using text generation AI. The output unit is implemented by the output device 40 of the smart device 14 and outputs speech through a speaker or earphones. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be changed in various ways.

[0110] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0111] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0116] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0117] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0118] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0119] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0120] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0124] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0125] For example, the reception unit is implemented by the microphone 238 of the smart glasses 214. For example, it can accept keyboard input or voice input. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and performs grammatical analysis, semantic analysis, sentiment analysis, etc. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates speech using text generation AI. The output unit is implemented by the speaker 240 of the smart glasses 214 and outputs speech through speakers or earphones. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0126] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0127] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0129] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0130] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0132] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0133] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0134] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0135] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0136] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0140] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] For example, the reception unit is implemented by the microphone 238 of the headset terminal 314. For example, it can accept keyboard input or voice input. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and performs grammatical analysis, semantic analysis, sentiment analysis, etc. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates speech using text generation AI. The output unit is implemented by the speaker 240 of the headset terminal 314 and outputs speech through speakers or earphones. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0142] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0143] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0144] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0146] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0149] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0150] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] For example, the reception unit is implemented by the microphone 238 of the robot 414. For example, it can receive keyboard input or voice input. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and performs grammatical analysis, semantic analysis, sentiment analysis, etc. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates speech using text generation AI. The output unit is implemented by the speaker 240 of the robot 414 and outputs speech through speakers or earphones. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0159] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0161] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0162] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0163] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0167] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0168] 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.

[0169] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0170] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0171] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0172] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0174] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0175] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0176] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0177] (Note 1) A reception desk where you enter text, An analysis unit that analyzes the text input by the reception unit, A generation unit that generates speech based on the text analyzed by the analysis unit, The system comprises an output unit that outputs the sound generated by the generation unit. A system characterized by the following features. (Note 2) The generating unit is Features the ability to select from multiple voice qualities and accents. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is It features the ability to adjust intonation and tone according to language and emotion. The system described in Appendix 1, characterized by the features described herein. (Note 4) The output unit is, Features a text-to-speech function for the visually impaired. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is It estimates the user's emotions and adjusts the text input interface based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is It analyzes the user's past input history and suggests appropriate input methods. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When entering text, the system suggests input options based on the user's current activities and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is It estimates the user's emotions and determines the priority of the text to be entered based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When entering text, the system will suggest highly relevant input options based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When entering text, the system analyzes the user's social media activity and suggests relevant input options. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, It estimates the user's emotions and adjusts the text analysis algorithm based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During text analysis, past analysis data is referenced to improve the accuracy of grammatical and semantic analysis. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, When analyzing text, different analysis methods are applied depending on the category of the text. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During text analysis, the priority of analysis is determined based on when the text was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, When performing text analysis, referencing relevant literature and data improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is It estimates the user's emotions and adjusts the parameters of voice generation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating speech, the system refers to the user's past speech generation history to generate appropriate speech. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating speech, different speech generation algorithms are applied depending on the content of the text. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is It estimates the user's emotions and adjusts the tone and rhythm of the generated voice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating speech, the system generates appropriate speech based on the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is During speech generation, the system references relevant audio data to improve the accuracy of the generation. The system described in Appendix 1, characterized by the features described herein. (Note 23) The output unit is, It estimates the user's emotions and adjusts the voice output method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The output unit is, When outputting audio, the system selects the optimal output method by referring to the user's past output history. The system described in Appendix 1, characterized by the features described herein. (Note 25) The output unit is, When outputting audio, the output is optimized based on the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 26) The output unit is, It estimates the user's emotions and determines the priority of voice output based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The output unit is, When outputting audio, the system selects the optimal output method by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 28) The output unit is, When outputting audio, the system analyzes the user's social media activity and suggests output methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

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

Claims

1. A reception desk where you enter text, An analysis unit that analyzes the text input by the reception unit, A generation unit that generates speech based on the text analyzed by the analysis unit, The system comprises an output unit that outputs the sound generated by the generation unit. A system characterized by the following features.

2. The generating unit is Features the ability to select from multiple voice qualities and accents. The system according to feature 1.

3. The generating unit is It features the ability to adjust intonation and tone according to language and emotion. The system according to feature 1.

4. The output unit is, Features a text-to-speech function for the visually impaired. The system according to feature 1.

5. The aforementioned reception unit is It estimates the user's emotions and adjusts the text input interface based on those emotions. The system according to feature 1.

6. The aforementioned reception unit is It analyzes the user's past input history and suggests appropriate input methods. The system according to feature 1.

7. The aforementioned reception unit is When entering text, the system suggests input options based on the user's current activities and areas of interest. The system according to feature 1.

8. The aforementioned reception unit is It estimates the user's emotions and determines the priority of the text to be entered based on the estimated user emotions. The system according to feature 1.

9. The aforementioned reception unit is When entering text, the system will suggest highly relevant input options based on the user's geographical location. The system according to feature 1.

Images