System

Abstract

An object of a system according to an embodiment is to convert article content of Web media into voice and provide the voice to a user.SOLUTION: A system includes an article acquisition part, a voice generation part, and a voice provision part. The article acquisition part acquires article contents of Web media. The sound generation unit converts the article content acquired by the article acquisition unit into sound data. The sound providing unit provides the user with the sound data generated by the sound generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not adequately provided audio versions of web media article content, and there is room for improvement.

[0005] The system according to the embodiment aims to convert article content of web media into audio and provide it to users. [Means for solving the problem]

[0006] The system according to the embodiment includes an article acquisition unit, a voice generation unit, and a voice provision unit. The article acquisition unit acquires article content from web media. The voice generation unit converts the article content acquired by the article acquisition unit into voice data. The voice provision unit provides the voice data generated by the voice generation unit to a user. [Effects of the Invention]

[0007] The system according to the embodiment can convert article content of web media into audio and provide it to users. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The voice conversion system according to the embodiment of the present invention converts the article content of web media into voice using AI technology, allowing users to listen to it whenever they want with their preferred AI voice. This allows the voice conversion system to effectively utilize the user's "spare listening time."

[0029] The voice generation system according to the embodiment includes an article acquisition unit, a voice generation unit, and a voice provision unit. The article acquisition unit acquires article content from web media. For example, articles are acquired from news sites and blogs. The article acquisition unit can also automatically acquire articles using an RSS feed. For example, the RSS feed can be periodically checked to acquire new articles. The article acquisition unit can also acquire articles using an API. For example, the article acquisition unit can acquire the latest articles using a news API. The voice generation unit converts the article content acquired by the article acquisition unit into voice data. For example, the generation AI converts articles into voice data using a text generation AI (e.g., LLM). The generation AI can also convert article content into voice data using a multimodal generation AI. The generation AI also analyzes article content and generates appropriate voice data using natural language processing technology. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and voice. The generation AI uses keyword extraction technology to identify particularly important information in articles and generate voice data based on that information. The audio providing unit provides the user with the audio data generated by the audio generating unit. For example, the audio providing unit provides the audio data through a web application or a mobile application. The audio providing unit can also provide the audio data in podcast format. For example, the audio data can be distributed as a podcast so that the user can listen to it whenever they like. The audio providing unit can also provide the audio data through a smart speaker. For example, the audio data can be played using Amazon Echo or Google Home. This allows the audio system according to the embodiment to enable the user to listen to articles with their preferred AI voice whenever they like. For example, they can listen to articles while commuting or doing housework. Furthermore, by introducing this service, media companies can effectively utilize users' "spare listening time" and promote content consumption.

[0030] The speech generation unit can automatically learn technical terms and specific phrases according to the genre of the article content and generate more natural speech data. The speech generation unit, for example, analyzes the genre of the article and automatically learns technical terms and specific phrases. For example, speech that properly pronounces medical terms for medical articles and technical terms for technical articles is generated. The speech generation unit can also automatically learn technical terms and specific phrases according to the article genre and generate more natural speech. For example, speech that properly pronounces legal terms for legal articles and entertainment terms for entertainment articles is generated. The speech generation unit can also automatically learn technical terms and specific phrases according to the article genre and develop algorithms for generating more natural speech. For example, a machine learning algorithm can be used to learn technical terms and phrases according to the article genre and generate speech data based on that. This generates natural speech according to the article genre, making it possible to provide speech that is easy for users to listen to.

[0031] The speech generation unit can automatically adjust the speed and tone of the speech data according to the length and complexity of the article content to improve listenability. The speech generation unit, for example, analyzes the length of the article and automatically adjusts the speech speed. For example, a faster speed is used for long articles and a slower speed for short articles. The speech generation unit can also analyze the complexity of the article and automatically adjust the tone of the speech. For example, a clear tone is used for complex articles and a gentle tone is used for simple articles. The speech generation unit can also develop an algorithm for automatically adjusting the speech speed and tone according to the length and complexity of the article. For example, a machine learning algorithm can be used to adjust the speech speed and tone according to the length and complexity of the article, and speech data can be generated based on that. In this way, by adjusting the speech speed and tone according to the length and complexity of the article, speech that is easy for the user to listen to can be provided.

[0032] The voice generation system further includes an article summary generation unit that analyzes the content of an article and generates a summary. The article summary generation unit, for example, analyzes the content of an article and generates a summary. For example, it extracts the main points of a long article and generates a summary that allows the content to be understood in a short time. The article summary generation unit can also use natural language processing technology to analyze the content of an article, extract important information, and generate a summary. For example, it can use keyword extraction technology to pick out particularly important information from an article and generate a summary based on that information. The article summary generation unit can also use a machine learning algorithm to analyze the content of an article and train a model for generating a summary. For example, it can train on large amounts of text data to improve the accuracy of summary generation. As a result, by providing the article summary as audio data, the user can grasp the content in a short time. For example, the user can listen to the main points of an article in a short time while commuting or doing housework.

[0033] The voice generation system further includes an article-related information providing unit that analyzes the content of an article and automatically searches for related images and videos. The article-related information providing unit, for example, analyzes the content of an article and automatically searches for related images and videos. For example, it provides images and videos related to a news article. The article-related information providing unit can also use natural language processing technology to analyze the content of an article and search for related information. For example, it can use keyword extraction technology to pick out particularly important information in an article and search for related images and videos. The article-related information providing unit can also use a machine learning algorithm to analyze the content of an article and train a model for searching for related information. For example, it can train on large amounts of text data to improve the accuracy of related information searches. This allows visual information to be provided to the user by providing article-related information along with the voice data. For example, it is possible to visually check related images and videos while listening to a news article.

[0034] The audio system further includes a schedule learning unit that learns the user's schedule. The schedule learning unit, for example, learns the user's schedule and provides audio content at optimal times. For example, audio content may be automatically played during commute times or break times. The schedule learning unit can also learn the user's schedule using the user's calendar information. For example, it may link with a calendar app and provide audio content according to the schedule. The schedule learning unit can also learn the user's daily behavioral patterns and provide audio content at optimal times. For example, it may use a machine learning algorithm to analyze the user's behavioral patterns and provide audio content based on the analysis. This allows for a more efficient listening experience by providing audio content according to the user's schedule. For example, the user may listen to news articles during their commute or relaxing articles during their break.

[0035] Furthermore, the audio conversion system includes a download function unit that provides a download function to allow audio content to be listened to offline. The download function unit provides, for example, a download function to allow audio content to be listened to offline. For example, audio content can be downloaded in a Wi-Fi environment and played in an offline environment. The download function unit can also have a function to manage the download status of audio content. For example, it can display the progress of the download and notify you when it is complete. The download function unit can also have a function to set a storage period for downloaded audio content. For example, it can set the content to be automatically deleted after a certain period of time. By allowing audio content to be listened to offline, a listening experience can be provided even in places with unstable internet connections. For example, audio content can be enjoyed even in places where internet connection is difficult, such as on an airplane or subway.

[0036] The audio system further includes a device linking unit that links the audio content with other devices. The device linking unit, for example, links the audio content with a smart speaker to provide a seamless listening experience. For example, the audio content is played through a smart speaker at home. The device linking unit can also link the audio content with an in-car system. For example, audio content can be played in a car, allowing a user to listen to an article while driving. The device linking unit can also provide an API for linking the audio content with other devices. For example, the device linking unit links with a smartphone or tablet to play the audio content. This allows a seamless listening experience to be provided by linking the audio content with other devices. For example, a user can start listening to audio content through a smart speaker at home, and then continue listening on their smartphone when they are out.

[0037] The voice generation system further includes a voice preference learning unit that learns the user's voice preferences. The voice preference learning unit, for example, learns the user's voice preferences and develops an algorithm that automatically selects the optimal voice. For example, the voice preference learning unit analyzes the user's preferences based on data of previously selected voices. The voice preference learning unit can also learn the user's voice preferences using user feedback. For example, it analyzes preferences based on features of voices that the user has highly rated. The voice preference learning unit can also build a model for learning the user's voice preferences using a machine learning algorithm. For example, it can learn a large amount of voice data and develop a model that predicts the user's preferences. This makes it possible to provide a more personalized listening experience by providing a voice that matches the user's voice preferences. For example, it can automatically select the optimal voice based on the user's preferred pitch and tone.

[0038] The voice generation system further includes a custom voice generation unit that records a user's voice and generates a custom AI voice based on that voice. The custom voice generation unit provides, for example, a function that allows a user to record their own voice and generate a custom AI voice based on that voice. For example, the custom voice generation unit analyzes the characteristics of the user's voice and generates a custom AI voice. The custom voice generation unit can also develop an algorithm for generating a custom AI voice based on the user's voice. For example, the custom voice generation unit can use a machine learning algorithm to learn the characteristics of the user's voice and generate a custom AI voice based on that. The custom voice generation unit can also provide an interface for recording the user's voice. For example, the custom voice generation unit can record the user's voice using a smartphone or microphone and generate a custom AI voice based on that data. This allows for a more personalized listening experience by providing a custom AI voice based on the user's voice. For example, the custom voice generation unit can allow a user to listen to articles in their own voice.

[0039] The voice generation system further includes an interaction format generation unit that combines multiple AI voices to enable listening to an article in an interactive format. The interaction format generation unit, for example, builds a system that combines multiple AI voices to enable listening to an article in an interactive format. For example, the content of an article is explained in an interactive format by multiple characters. The interaction format generation unit can also develop an algorithm for generating an interaction format scenario. For example, a machine learning algorithm is used to generate an interaction format scenario, and audio data is generated based on the scenario. The interaction format generation unit can also provide an interface for combining multiple AI voices. For example, the voices of characters selected by the user are combined to generate an interaction format audio. This allows listening to an article in an interactive format, providing a more immersive listening experience. For example, having multiple characters explain a news article in an interactive format provides a user with an easy-to-understand and interesting listening experience.

[0040] The voice generation system further includes a background music adding unit that adds background music and sound effects to the AI ​​voice selected by the user. The background music adding unit, for example, builds a system that adds background music and sound effects to the AI ​​voice selected by the user. For example, news program-style background music is added to news articles, and calming background music is added to relaxing articles. The background music adding unit can also develop an algorithm for adding sound effects. For example, it can use a machine learning algorithm to generate sound effects based on the content of the article and add them to the audio data. The background music adding unit can also provide an interface for adding user-selected background music and sound effects to the audio data. For example, adding user-selected background music and sound effects to the audio data can provide a more immersive listening experience. By adding background music and sound effects, a more immersive listening experience can be provided. For example, adding news program-style background music when listening to a news article can provide a more realistic listening experience.

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

[0042] The voice generation system may further include a customization unit that customizes the voice tone and speed based on the user's preferences. For example, the user's preferred voice tone and speed may be set in advance, and voice data may be generated based on the settings. The customization unit may also collect user feedback and adjust the voice tone and speed based on the feedback. For example, if the user prefers a faster voice speed, the feedback may be reflected in the next voice generation. The customization unit may also analyze the user's listening history and automatically suggest the optimal voice tone and speed. This allows for a more personalized listening experience by providing voice data tailored to the user's preferences.

[0043] The speech generation unit can automatically learn technical terms and specific phrases according to the genre of the article content and generate more natural-sounding speech data. For example, speech that properly pronounces medical terms for medical articles and technical terms for technical articles is generated. The speech generation unit can also automatically learn technical terms and specific phrases according to the article genre and generate more natural-sounding speech. For example, speech that properly pronounces legal terms for legal articles and entertainment terms for entertainment articles is generated. The speech generation unit can also automatically learn technical terms and specific phrases according to the article genre and develop algorithms for generating more natural-sounding speech. For example, a machine learning algorithm can be used to learn technical terms and phrases according to the article genre and generate speech data based on that. This generates natural-sounding speech according to the article genre, making it possible to provide speech that is easy for users to listen to.

[0044] The speech generation unit can automatically adjust the speed and tone of the speech data according to the length and complexity of the article content to improve listenability. For example, a faster speed is used for long articles and a slower speed for short articles. The speech generation unit can also analyze the complexity of the article and automatically adjust the tone of the speech. For example, a clear tone is used for complex articles and a gentle tone is used for simple articles. The speech generation unit can also develop an algorithm for automatically adjusting the speed and tone of the speech according to the length and complexity of the article. For example, a machine learning algorithm can be used to adjust the speed and tone of the speech according to the length and complexity of the article, and speech data can be generated based on that. In this way, by adjusting the speed and tone of the speech according to the length and complexity of the article, it is possible to provide speech that is easy for the user to listen to.

[0045] The audio system may further include a schedule optimization unit that learns the user's schedule and provides audio content at optimal times. For example, audio content may be automatically played during commute times or break times. The schedule optimization unit may also learn the user's schedule using the user's calendar information. For example, it may link with a calendar app to provide audio content according to the schedule. The schedule optimization unit may also learn the user's daily behavioral patterns and provide audio content at optimal times. For example, it may use a machine learning algorithm to analyze the user's behavioral patterns and provide audio content based on that. This allows the audio content to be provided according to the user's schedule, providing a more efficient listening experience.

[0046] The voice conversion system may further include a voice preference optimization unit that learns a user's voice preferences and automatically selects the optimal voice. For example, the voice preference optimization unit may analyze the user's preferences based on data of previously selected voices. The voice preference optimization unit may also learn voice preferences using user feedback. For example, the voice preference optimization unit may analyze preferences based on voice features that the user has highly rated. The voice preference optimization unit may also use a machine learning algorithm to build a model for learning the user's voice preferences. For example, the voice preference optimization unit may learn a large amount of voice data and develop a model that predicts the user's preferences. This may provide a more personalized listening experience by providing a voice that matches the user's voice preferences.

[0047] The voice generation system may further include a custom voice generation unit that records a user's voice and generates a custom AI voice based on that voice. For example, the system may provide a function that allows a user to record their own voice and generate a custom AI voice based on that voice. The custom voice generation unit may also develop an algorithm for generating a custom AI voice based on the user's voice. For example, the custom voice generation unit may use a machine learning algorithm to learn the characteristics of the user's voice and generate a custom AI voice based on that. The custom voice generation unit may also provide an interface for recording the user's voice. For example, the custom voice generation unit may record the user's voice using a smartphone or microphone and generate a custom AI voice based on that data. This allows the system to provide a more personalized listening experience by providing a custom AI voice based on the user's voice.

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

[0049] Step 1: The article acquisition unit acquires article content from web media. For example, it acquires articles from news sites and blogs. The article acquisition unit can also automatically acquire articles using an RSS feed. For example, it can periodically check the RSS feed and acquire new articles. The article acquisition unit can also acquire articles using an API. For example, it can acquire the latest articles using a news API. Step 2: The speech generation unit converts the article content acquired by the article acquisition unit into speech data. For example, the generation AI uses a text generation AI (e.g., LLM) to convert the article into speech data. The generation AI can also use a multimodal generation AI to convert the article content into speech data. The generation AI also uses natural language processing technology to analyze the article content and generate appropriate speech data. For example, the text generation AI has learned from large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and speech. The generation AI uses keyword extraction technology to pick out particularly important information from the article and generate speech data based on that information. Step 3: The audio providing unit provides the user with the audio data generated by the audio generation unit. For example, the audio providing unit provides the audio data through a web application or a mobile application. The audio providing unit can also provide the audio data in podcast format. For example, the audio data can be distributed as a podcast so that the user can listen to it whenever they like. The audio providing unit can also provide the audio data through a smart speaker. For example, the audio data can be played using Amazon Echo or Google Home. This allows the audio generation system according to the embodiment to enable the user to listen to articles in their preferred AI voice whenever they like. For example, they can listen to articles while commuting or doing housework. Furthermore, by introducing this service, media companies can effectively utilize users' "spare listening time" and promote content consumption.

[0050] (Example 2) The voice conversion system according to the embodiment of the present invention converts the article content of web media into voice using AI technology, allowing users to listen to it whenever they want with their preferred AI voice. This allows the voice conversion system to effectively utilize the user's "spare listening time."

[0051] The voice generation system according to the embodiment includes an article acquisition unit, a voice generation unit, and a voice provision unit. The article acquisition unit acquires article content from web media. For example, articles are acquired from news sites and blogs. The article acquisition unit can also automatically acquire articles using an RSS feed. For example, the RSS feed can be periodically checked to acquire new articles. The article acquisition unit can also acquire articles using an API. For example, the article acquisition unit can acquire the latest articles using a news API. The voice generation unit converts the article content acquired by the article acquisition unit into voice data. For example, the generation AI converts articles into voice data using a text generation AI (e.g., LLM). The generation AI can also convert article content into voice data using a multimodal generation AI. The generation AI also analyzes article content and generates appropriate voice data using natural language processing technology. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and voice. The generation AI uses keyword extraction technology to identify particularly important information in articles and generate voice data based on that information. The audio providing unit provides the user with the audio data generated by the audio generating unit. For example, the audio providing unit provides the audio data through a web application or a mobile application. The audio providing unit can also provide the audio data in podcast format. For example, the audio data can be distributed as a podcast so that the user can listen to it whenever they like. The audio providing unit can also provide the audio data through a smart speaker. For example, the audio data can be played using Amazon Echo or Google Home. This allows the audio system according to the embodiment to enable the user to listen to articles with their preferred AI voice whenever they like. For example, they can listen to articles while commuting or doing housework. Furthermore, by introducing this service, media companies can effectively utilize users' "spare listening time" and promote content consumption.

[0052] The voice generation unit can use the emotion estimation function to generate voice data with an appropriate emotion according to the content of the article. The voice generation unit, for example, analyzes the content of the article and uses the emotion estimation function to generate voice with an appropriate emotion. For example, it generates voice with an emotional tone for an emotional article and voice with a calm tone for a news article. The voice generation unit can also use the emotion estimation function to generate emotional voice according to the content of the article. For example, it generates voice with a bright tone for an article with a joyful emotion and voice with a calm tone for an article with a sad emotion. The voice generation unit can also use the emotion estimation function to generate voice that conveys emotional empathy according to the content of the article. For example, the emotion estimation function uses text analysis technology to analyze the emotion of the article and generate voice data based on the emotion. In this way, emotional voice according to the content of the article can be generated to convey emotional empathy to the user.

[0053] The speech generation unit can automatically learn technical terms and specific phrases according to the genre of the article content and generate more natural speech data. The speech generation unit, for example, analyzes the genre of the article and automatically learns technical terms and specific phrases. For example, speech that properly pronounces medical terms for medical articles and technical terms for technical articles is generated. The speech generation unit can also automatically learn technical terms and specific phrases according to the article genre and generate more natural speech. For example, speech that properly pronounces legal terms for legal articles and entertainment terms for entertainment articles is generated. The speech generation unit can also automatically learn technical terms and specific phrases according to the article genre and develop algorithms for generating more natural speech. For example, a machine learning algorithm can be used to learn technical terms and phrases according to the article genre and generate speech data based on that. This generates natural speech according to the article genre, making it possible to provide speech that is easy for users to listen to.

[0054] The speech generation unit can automatically adjust the speed and tone of the speech data according to the length and complexity of the article content to improve listenability. The speech generation unit, for example, analyzes the length of the article and automatically adjusts the speech speed. For example, a faster speed is used for long articles and a slower speed for short articles. The speech generation unit can also analyze the complexity of the article and automatically adjust the tone of the speech. For example, a clear tone is used for complex articles and a gentle tone is used for simple articles. The speech generation unit can also develop an algorithm for automatically adjusting the speech speed and tone according to the length and complexity of the article. For example, a machine learning algorithm can be used to adjust the speech speed and tone according to the length and complexity of the article, and speech data can be generated based on that. In this way, by adjusting the speech speed and tone according to the length and complexity of the article, speech that is easy for the user to listen to can be provided.

[0055] The voice generation system further includes an article summary generation unit that analyzes the content of an article and generates a summary. The article summary generation unit, for example, analyzes the content of an article and generates a summary. For example, it extracts the main points of a long article and generates a summary that allows the content to be understood in a short time. The article summary generation unit can also use natural language processing technology to analyze the content of an article, extract important information, and generate a summary. For example, it can use keyword extraction technology to pick out particularly important information from an article and generate a summary based on that information. The article summary generation unit can also use a machine learning algorithm to analyze the content of an article and train a model for generating a summary. For example, it can train on large amounts of text data to improve the accuracy of summary generation. As a result, by providing the article summary as audio data, the user can grasp the content in a short time. For example, the user can listen to the main points of an article in a short time while commuting or doing housework.

[0056] The voice generation system further includes an article-related information providing unit that analyzes the content of an article and automatically searches for related images and videos. The article-related information providing unit, for example, analyzes the content of an article and automatically searches for related images and videos. For example, it provides images and videos related to a news article. The article-related information providing unit can also use natural language processing technology to analyze the content of an article and search for related information. For example, it can use keyword extraction technology to pick out particularly important information in an article and search for related images and videos. The article-related information providing unit can also use a machine learning algorithm to analyze the content of an article and train a model for searching for related information. For example, it can train on large amounts of text data to improve the accuracy of related information searches. This allows visual information to be provided to the user by providing article-related information along with the voice data. For example, it is possible to visually check related images and videos while listening to a news article.

[0057] The voice generation system further includes an emotional response collection unit that uses an emotion estimation function to collect a user's emotional response to the article content. The emotional response collection unit, for example, uses the emotion estimation function to collect a user's emotional response to the article content. For example, the emotional response collection unit analyzes the user's emotions after listening to the article and reflects them in the next voice generation. The emotional response collection unit may also include a sensor for collecting the user's emotional response. For example, the emotional response may be analyzed by measuring heart rate or electrodermal activity. The emotional response collection unit may also include a camera for collecting the user's emotional response. For example, facial expression recognition technology may be used to analyze the user's facial expression and collect the emotional response. This makes it possible to provide more personalized voice content by improving the next voice generation based on the user's emotional response. For example, if the user is moved by an article, the next voice generated may have an emotional tone.

[0058] The audio system further includes a schedule learning unit that learns the user's schedule. The schedule learning unit, for example, learns the user's schedule and provides audio content at optimal times. For example, audio content may be automatically played during commute times or break times. The schedule learning unit can also learn the user's schedule using the user's calendar information. For example, it may link with a calendar app and provide audio content according to the schedule. The schedule learning unit can also learn the user's daily behavioral patterns and provide audio content at optimal times. For example, it may use a machine learning algorithm to analyze the user's behavioral patterns and provide audio content based on the analysis. This allows for a more efficient listening experience by providing audio content according to the user's schedule. For example, the user may listen to news articles during their commute or relaxing articles during their break.

[0059] The voice generation system further includes an emotion estimation unit that estimates the user's current emotional state. The emotion estimation unit estimates the user's current emotional state using, for example, an emotion estimation function. For example, the emotion estimation unit estimates the user's emotional state by analyzing the user's facial expressions and voice. The emotion estimation unit can also estimate the user's emotional state using the user's biometric data. For example, the emotion estimation unit can estimate the emotional state by measuring the user's heart rate and electrodermal activity. The emotion estimation unit can also use a machine learning algorithm to learn a model for estimating the user's emotional state. For example, the emotion estimation unit can learn a large amount of emotional data to improve the accuracy of emotion estimation. This allows the system to recommend articles tailored to the user's emotional state, promoting relaxation and concentration. For example, the system can recommend articles that will help a user who is feeling stressed to relax, and articles that will improve concentration to a user who wants to concentrate.

[0060] Furthermore, the audio conversion system includes a download function unit that provides a download function to allow audio content to be listened to offline. The download function unit provides, for example, a download function to allow audio content to be listened to offline. For example, audio content can be downloaded in a Wi-Fi environment and played in an offline environment. The download function unit can also have a function to manage the download status of audio content. For example, it can display the progress of the download and notify you when it is complete. The download function unit can also have a function to set a storage period for downloaded audio content. For example, it can set the content to be automatically deleted after a certain period of time. By allowing audio content to be listened to offline, a listening experience can be provided even in places with unstable internet connections. For example, audio content can be enjoyed even in places where internet connection is difficult, such as on an airplane or subway.

[0061] The audio system further includes a device linking unit that links the audio content with other devices. The device linking unit, for example, links the audio content with a smart speaker to provide a seamless listening experience. For example, the audio content is played through a smart speaker at home. The device linking unit can also link the audio content with an in-car system. For example, audio content can be played in a car, allowing a user to listen to an article while driving. The device linking unit can also provide an API for linking the audio content with other devices. For example, the device linking unit links with a smartphone or tablet to play the audio content. This allows a seamless listening experience to be provided by linking the audio content with other devices. For example, a user can start listening to audio content through a smart speaker at home, and then continue listening on their smartphone when they are out.

[0062] The voice generation system further includes an emotion estimation unit that estimates the user's emotional state. The emotion estimation unit estimates the user's emotional state using, for example, an emotion estimation function. For example, the emotion estimation unit estimates the user's emotional state by analyzing the user's facial expressions and voice. The emotion estimation unit can also estimate the user's emotional state using the user's biometric data. For example, the emotion estimation unit can estimate the emotional state by measuring the user's heart rate and electrodermal activity. The emotion estimation unit can also learn a model for estimating the user's emotional state using a machine learning algorithm. For example, the emotion estimation unit can learn a large amount of emotion data to improve the accuracy of emotion estimation. This makes it possible to maximize the relaxing effect by providing audio content during the user's most relaxing time. For example, the user's emotion data is analyzed and audio content is played during the user's most relaxing time.

[0063] The voice generation system further includes a voice preference learning unit that learns the user's voice preferences. The voice preference learning unit, for example, learns the user's voice preferences and develops an algorithm that automatically selects the optimal voice. For example, the voice preference learning unit analyzes the user's preferences based on data of previously selected voices. The voice preference learning unit can also learn the user's voice preferences using user feedback. For example, it analyzes preferences based on features of voices that the user has highly rated. The voice preference learning unit can also build a model for learning the user's voice preferences using a machine learning algorithm. For example, it can learn a large amount of voice data and develop a model that predicts the user's preferences. This makes it possible to provide a more personalized listening experience by providing a voice that matches the user's voice preferences. For example, it can automatically select the optimal voice based on the user's preferred pitch and tone.

[0064] The voice generation system further includes a custom voice generation unit that records a user's voice and generates a custom AI voice based on that voice. The custom voice generation unit provides, for example, a function that allows a user to record their own voice and generate a custom AI voice based on that voice. For example, the custom voice generation unit analyzes the characteristics of the user's voice and generates a custom AI voice. The custom voice generation unit can also develop an algorithm for generating a custom AI voice based on the user's voice. For example, the custom voice generation unit can use a machine learning algorithm to learn the characteristics of the user's voice and generate a custom AI voice based on that. The custom voice generation unit can also provide an interface for recording the user's voice. For example, the custom voice generation unit can record the user's voice using a smartphone or microphone and generate a custom AI voice based on that data. This allows for a more personalized listening experience by providing a custom AI voice based on the user's voice. For example, the custom voice generation unit can allow a user to listen to articles in their own voice.

[0065] The voice generation system further includes an emotion estimation unit that estimates the user's emotional state. The emotion estimation unit estimates the user's emotional state using, for example, an emotion estimation function. For example, the emotion estimation unit estimates the user's emotional state by analyzing the user's facial expressions and voice. The emotion estimation unit can also estimate the user's emotional state using biometric data of the user. For example, the emotion estimation unit can estimate the emotional state by measuring the user's heart rate and electrodermal activity. The emotion estimation unit can also use a machine learning algorithm to learn a model for estimating the user's emotional state. For example, the emotion estimation unit can learn a large amount of emotional data to improve the accuracy of emotion estimation. This makes it possible to provide a more personalized listening experience by providing an audio tone that matches the user's emotional state. For example, a gentle tone is used when the user is relaxed, and a clear tone is used when the user is focused.

[0066] The voice generation system further includes an interaction format generation unit that combines multiple AI voices to enable listening to an article in an interactive format. The interaction format generation unit, for example, builds a system that combines multiple AI voices to enable listening to an article in an interactive format. For example, the content of an article is explained in an interactive format by multiple characters. The interaction format generation unit can also develop an algorithm for generating an interaction format scenario. For example, a machine learning algorithm is used to generate an interaction format scenario, and audio data is generated based on the scenario. The interaction format generation unit can also provide an interface for combining multiple AI voices. For example, the voices of characters selected by the user are combined to generate an interaction format audio. This allows listening to an article in an interactive format, providing a more immersive listening experience. For example, having multiple characters explain a news article in an interactive format provides a user with an easy-to-understand and interesting listening experience.

[0067] The voice generation system further includes a background music adding unit that adds background music and sound effects to the AI ​​voice selected by the user. The background music adding unit, for example, builds a system that adds background music and sound effects to the AI ​​voice selected by the user. For example, news program-style background music is added to news articles, and calming background music is added to relaxing articles. The background music adding unit can also develop an algorithm for adding sound effects. For example, it can use a machine learning algorithm to generate sound effects based on the content of the article and add them to the audio data. The background music adding unit can also provide an interface for adding user-selected background music and sound effects to the audio data. For example, adding user-selected background music and sound effects to the audio data can provide a more immersive listening experience. By adding background music and sound effects, a more immersive listening experience can be provided. For example, adding news program-style background music when listening to a news article can provide a more realistic listening experience.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The voice generation system may further include a customization unit that customizes the voice tone and speed based on the user's preferences. For example, the user's preferred voice tone and speed may be set in advance, and voice data may be generated based on the settings. The customization unit may also collect user feedback and adjust the voice tone and speed based on the feedback. For example, if the user prefers a faster voice speed, the feedback may be reflected in the next voice generation. The customization unit may also analyze the user's listening history and automatically suggest the optimal voice tone and speed. This allows for a more personalized listening experience by providing voice data tailored to the user's preferences.

[0070] The voice generation unit can use the emotion estimation function to generate voice data with an appropriate emotion according to the content of the article. For example, it generates an emotional tone of voice for an emotional article and a calm tone of voice for a news article. The voice generation unit can also use the emotion estimation function to generate emotional voice according to the content of the article. For example, it generates a bright tone of voice for an article with a joyful emotion and a calm tone of voice for an article with a sad emotion. The voice generation unit can also use the emotion estimation function to generate voice that imparts emotional empathy according to the content of the article. For example, the emotion estimation function uses text analysis technology to analyze the emotion of the article and generate voice data based on the emotion. In this way, it is possible to impart emotional empathy to the user by generating emotional voice according to the content of the article.

[0071] The speech generation unit can automatically learn technical terms and specific phrases according to the genre of the article content and generate more natural-sounding speech data. For example, speech that properly pronounces medical terms for medical articles and technical terms for technical articles is generated. The speech generation unit can also automatically learn technical terms and specific phrases according to the article genre and generate more natural-sounding speech. For example, speech that properly pronounces legal terms for legal articles and entertainment terms for entertainment articles is generated. The speech generation unit can also automatically learn technical terms and specific phrases according to the article genre and develop algorithms for generating more natural-sounding speech. For example, a machine learning algorithm can be used to learn technical terms and phrases according to the article genre and generate speech data based on that. This generates natural-sounding speech according to the article genre, making it possible to provide speech that is easy for users to listen to.

[0072] The speech generation unit can automatically adjust the speed and tone of the speech data according to the length and complexity of the article content to improve listenability. For example, a faster speed is used for long articles and a slower speed for short articles. The speech generation unit can also analyze the complexity of the article and automatically adjust the tone of the speech. For example, a clear tone is used for complex articles and a gentle tone is used for simple articles. The speech generation unit can also develop an algorithm for automatically adjusting the speed and tone of the speech according to the length and complexity of the article. For example, a machine learning algorithm can be used to adjust the speed and tone of the speech according to the length and complexity of the article, and speech data can be generated based on that. In this way, by adjusting the speed and tone of the speech according to the length and complexity of the article, it is possible to provide speech that is easy for the user to listen to.

[0073] The voice generation system may further include an emotion adaptation unit that estimates the user's emotional state and selects audio content based on the estimated emotion. For example, if the user feels like relaxing, it provides relaxing audio content. The emotion adaptation unit may also analyze the user's emotional state in real time and automatically switch audio content based on the analysis. For example, if the user feels stressed, it provides audio content that alleviates stress. The emotion adaptation unit may also accumulate the user's emotional data and analyze long-term emotional trends. This allows for a more personalized listening experience by providing audio content tailored to the user's emotional state.

[0074] The audio system may further include a schedule optimization unit that learns the user's schedule and provides audio content at optimal times. For example, audio content may be automatically played during commute times or break times. The schedule optimization unit may also learn the user's schedule using the user's calendar information. For example, it may link with a calendar app to provide audio content according to the schedule. The schedule optimization unit may also learn the user's daily behavioral patterns and provide audio content at optimal times. For example, it may use a machine learning algorithm to analyze the user's behavioral patterns and provide audio content based on that. This allows the audio content to be provided according to the user's schedule, providing a more efficient listening experience.

[0075] The voice generation system may further include an emotional response optimization unit that collects the user's emotional responses and optimizes the voice content based on the data. For example, the emotional responses of the user after listening to an article may be analyzed and reflected in the next voice generation. The emotional response optimization unit may also include a sensor for collecting the user's emotional responses. For example, the emotional response may be analyzed by measuring heart rate or electrodermal activity. The emotional response optimization unit may also include a camera for collecting the user's emotional responses. For example, facial expression recognition technology may be used to analyze the user's facial expressions and collect the emotional responses. This allows the next voice generation to be improved based on the user's emotional responses, thereby providing more personalized voice content.

[0076] The voice conversion system may further include a voice preference optimization unit that learns a user's voice preferences and automatically selects the optimal voice. For example, the voice preference optimization unit may analyze the user's preferences based on data of previously selected voices. The voice preference optimization unit may also learn voice preferences using user feedback. For example, the voice preference optimization unit may analyze preferences based on voice features that the user has highly rated. The voice preference optimization unit may also use a machine learning algorithm to build a model for learning the user's voice preferences. For example, the voice preference optimization unit may learn a large amount of voice data and develop a model that predicts the user's preferences. This may provide a more personalized listening experience by providing a voice that matches the user's voice preferences.

[0077] The voice generation system may further include an emotional tone adjustment unit that estimates the user's emotional state and adjusts the voice tone based on the estimated emotional state. For example, a gentle tone may be used when the user is relaxed, and a clear tone may be used when the user is focused. The emotional tone adjustment unit may also analyze the user's emotional state in real time and automatically switch the voice tone based on the analysis. For example, if the user is feeling stressed, a tone that reduces stress may be used. The emotional tone adjustment unit may also accumulate the user's emotional data and analyze long-term emotional trends. This allows the user to provide a more personalized listening experience by providing a voice tone that matches the user's emotional state.

[0078] The voice generation system may further include a custom voice generation unit that records a user's voice and generates a custom AI voice based on that voice. For example, the system may provide a function that allows a user to record their own voice and generate a custom AI voice based on that voice. The custom voice generation unit may also develop an algorithm for generating a custom AI voice based on the user's voice. For example, the custom voice generation unit may use a machine learning algorithm to learn the characteristics of the user's voice and generate a custom AI voice based on that. The custom voice generation unit may also provide an interface for recording the user's voice. For example, the custom voice generation unit may record the user's voice using a smartphone or microphone and generate a custom AI voice based on that data. This allows the system to provide a more personalized listening experience by providing a custom AI voice based on the user's voice.

[0079] The processing flow of the second embodiment will be briefly explained below.

[0080] Step 1: The article acquisition unit acquires article content from web media. For example, it acquires articles from news sites and blogs. The article acquisition unit can also automatically acquire articles using an RSS feed. For example, it can periodically check the RSS feed and acquire new articles. The article acquisition unit can also acquire articles using an API. For example, it can acquire the latest articles using a news API. Step 2: The speech generation unit converts the article content acquired by the article acquisition unit into speech data. For example, the generation AI uses a text generation AI (e.g., LLM) to convert the article into speech data. The generation AI can also use a multimodal generation AI to convert the article content into speech data. The generation AI also uses natural language processing technology to analyze the article content and generate appropriate speech data. For example, the text generation AI has learned from large amounts of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, including not only text but also images and speech. The generation AI uses keyword extraction technology to pick out particularly important information from the article and generate speech data based on that information. Step 3: The audio providing unit provides the user with the audio data generated by the audio generation unit. For example, the audio providing unit provides the audio data through a web application or a mobile application. The audio providing unit can also provide the audio data in podcast format. For example, the audio data can be distributed as a podcast so that the user can listen to it whenever they like. The audio providing unit can also provide the audio data through a smart speaker. For example, the audio data can be played using Amazon Echo or Google Home. This allows the audio generation system according to the embodiment to enable the user to listen to articles in their preferred AI voice whenever they like. For example, they can listen to articles while commuting or doing housework. Furthermore, by introducing this service, media companies can effectively utilize users' "spare listening time" and promote content consumption.

[0081] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0082] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0083] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0084] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0085] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0086] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0087] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0088] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0089] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0090] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0091] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0092] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0093] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0094] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0095] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0096] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0097] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0098] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0099] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0100] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0101] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0102] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0103] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0104] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0105] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0106] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0107] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0108] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0109] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0110] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0111] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0113] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0114] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0115] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0117] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

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

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

[0121] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0122] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0125] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0130] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0131] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0132] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0133] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0134] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0135] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0136] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0137] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0138] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0139] 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.

[0140] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0141] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0142] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0143] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0144] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0145] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0146] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0147] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0148] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an article acquisition unit that acquires article content from web media; a voice generating unit that converts the article content acquired by the article acquiring unit into voice data; a voice providing unit that provides the voice data generated by the voice generating unit to a user. A system characterized by:

2. an article summary generation unit that analyzes the content of an article and generates a summary; the speech providing unit providing the summary generated by the article summary generating unit as speech data.

2. The system of claim 1.

3. a schedule learning unit that learns a user's schedule; the audio providing unit automatically providing audio content at optimal timing based on the schedule learned by the schedule learning unit.

2. The system of claim 1.

4. a voice preference learning unit that learns a user's voice preference; the voice generation unit develops an algorithm to automatically select an optimal voice based on the preferences learned by the voice preference learning unit.

2. The system of claim 1.

5. The voice generation unit Generate voice data with appropriate emotions according to the content of the article.

2. The system of claim 1.

Images