system

Abstract

The system according to this embodiment aims to automatically organize and summarize voice-input messages, convert them into natural-sounding speech, and save them. [Solution] The system according to the embodiment comprises a reception unit, a summarization unit, a conversion unit, and a storage unit. The reception unit receives voice input. The summarization unit analyzes the voice data received by the reception unit and extracts and summarizes the important points. The conversion unit converts the summarized message created by the summarization unit into natural-sounding voice. The storage unit saves the voice generated by the conversion unit as an answering machine message.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to appropriately summarize an answering machine message and difficult to convey the main points.

[0005] The system according to the embodiment aims to automatically organize and summarize a voice-input message, convert it into natural voice, and save it.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a summarization unit, a conversion unit, and a storage unit. The reception unit receives voice input. The summarization unit analyzes the voice data received by the reception unit and extracts and summarizes the important points. The conversion unit converts the summarized message created by the summarization unit into natural-sounding voice. The storage unit saves the voice generated by the conversion unit as an answering machine message. [Effects of the Invention]

[0007] The system according to this embodiment can automatically organize and summarize voice-input messages, convert them into natural-sounding speech, and save them. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The answering machine support system according to an embodiment of the present invention is a system in which the user inputs the content they want to convey via voice, and a generating AI automatically organizes and summarizes it to create a concise message. The answering machine support system takes the content the user wants to convey via voice input, and the generating AI automatically organizes and summarizes it to create a concise message. It also has a function to convert the organized message into natural-sounding speech and save it as an answering machine message. This supports users who are not comfortable with answering machines, from organizing the message to converting it to speech and sending it. For example, the user inputs the content they want to convey via voice input. At this time, the user can speak freely in their own words. For example, they might input something like, "The meeting time has been changed, so please change it to 3pm." This voice data is input to the generating AI. Next, the generating AI analyzes the input voice data and extracts and summarizes the important points. The generating AI identifies keywords and important phrases from the voice data and creates a concise message. For example, a summarized message such as "The meeting time has been changed to 3pm" is generated. The generated summarized message is converted into natural-sounding speech by the generating AI. The AI-generating system customizes the tone, speaking speed, and emotional expression of the voice to produce audio that reflects the nuances the user wants to convey. For example, it can generate an audio message in a calm tone saying, "The meeting time has been changed to 3 PM." Finally, the generated audio is saved as an answering machine message. This allows the recipient to receive a concise and easy-to-understand message. For example, when the recipient plays the answering machine message, they will hear a voice message saying, "The meeting time has been changed to 3 PM." This system allows users to summarize what they want to convey concisely and express the appropriate tone and emotion. In addition, because recipients receive easy-to-understand messages, communication efficiency is improved. For example, in a business setting, important information can be conveyed concisely, leading to increased work efficiency. In this way, the answering machine support system can summarize what the user wants to convey concisely and save it as an answering machine message in a natural voice.

[0029] The answering machine support system according to this embodiment comprises a reception unit, a summarization unit, a conversion unit, and a storage unit. The reception unit receives voice input. The reception unit can receive voice input using, for example, a microphone. The reception unit can also receive voice input using specific speech recognition technology. Furthermore, the reception unit can perform noise reduction and preprocessing of the voice data. For example, the reception unit can remove noise from the voice data using filtering technology. The reception unit can also remove noise from the voice data using a noise-canceling algorithm. Furthermore, the reception unit can normalize the voice data and adjust the sampling rate. For example, the reception unit normalizes the voice data to make the volume constant. The reception unit also adjusts the sampling rate of the voice data to convert it into a format that is easy to analyze. The summarization unit uses a generation AI to analyze the voice data received by the reception unit and extract and summarize important points. The summarization unit uses, for example, natural language processing technology to identify keywords and important phrases from the voice data and create a concise message. For example, the summarization unit uses morphological analysis to analyze the voice data and extract keywords. The summarization unit can also analyze the sentence structure of the audio data using grammatical analysis and identify important phrases. Furthermore, the summarization unit can analyze the meaning of the audio data using semantic analysis and extract important information. The conversion unit uses generative AI to convert the summarized message created by the summarization unit into natural-sounding speech. The conversion unit can, for example, use speech synthesis technology to customize the tone, speaking speed, and emotional expression to generate natural-sounding speech. For example, the conversion unit can convert the summarized message into speech using text-to-speech (TTS) technology. The conversion unit can also generate more natural-sounding speech using deep learning-based speech synthesis technology. Furthermore, the conversion unit can generate speech that reflects the user's nuances by customizing the tone, speaking speed, and emotional expression. For example, the conversion unit can adjust the pitch to enrich emotional expression. The conversion unit can also change the speaking speed by adjusting the number of syllables per second. The storage unit saves the speech generated by the conversion unit as an answering machine message.The storage unit, for example, compresses and encodes audio data and saves it in an appropriate format. For instance, the storage unit compresses audio data using a compression algorithm. The storage unit can also encode audio data by specifying an encoding format. Furthermore, the storage unit can save audio data in formats such as MP3, WAV, and AAC. As a result, the answering machine support system according to this embodiment can concisely summarize what the user wants to convey and save it as an answering machine message in a natural voice.

[0030] The reception unit accepts voice input. For example, it can accept voice input using a microphone. Specifically, by using a high-sensitivity microphone, it can accurately capture voices from a distance or quiet voices. The reception unit can also accept voice input using specific speech recognition technologies. For example, by using a deep learning-based speech recognition model, high-precision speech recognition is possible even in noisy environments. Furthermore, the reception unit can perform noise reduction and preprocessing of the audio data. For example, the reception unit can remove noise from the audio data using filtering techniques. Specifically, it can remove noise in a specific frequency band using a bandpass filter. The reception unit can also remove noise from the audio data using noise cancellation algorithms. For example, it can cancel background noise in real time using active noise cancellation technology. Furthermore, the reception unit can normalize the audio data and adjust the sampling rate. For example, the reception unit normalizes the audio data to make the volume constant. Specifically, it adjusts the overall volume based on the peak volume of the audio data. The reception unit can also adjust the sampling rate of the audio data to convert it into a format that is easy to analyze. For example, downsampling a 44.1kHz sampling rate to 16kHz can reduce the amount of data while maintaining analysis accuracy. This allows the receiving unit to accept high-precision audio input under diverse environments and conditions and convert it into a format suitable for subsequent processing.

[0031] The summarization unit uses generative AI to analyze audio data received by the reception unit, extracting and summarizing key points. For example, the summarization unit uses natural language processing techniques to identify keywords and important phrases from the audio data and create a concise message. Specifically, it analyzes the audio data using morphological analysis to extract keywords. For instance, it converts the audio data to text and inputs that text into a morphological analysis engine to extract important words such as nouns and verbs. The summarization unit can also analyze the sentence structure of the audio data using grammatical analysis to identify important phrases. For example, it uses dependency structure analysis to clarify relationships between subjects, predicates, and objects, and identify phrases containing important information. Furthermore, the summarization unit can analyze the meaning of the audio data using semantic analysis to extract important information. For example, it constructs a semantic network and analyzes the semantic relationships between words and phrases within the audio data to extract important information. This allows the summarization unit to quickly and accurately extract key points from audio data and generate concise and easy-to-understand messages. Additionally, the summarization unit can use generative AI to reconstruct the extracted information into natural-sounding sentences. For example, the generation AI generates grammatically correct sentences based on extracted keywords and phrases, and arranges them in a format that is easy for the user to understand. This allows the summarization unit to efficiently analyze the audio data and concisely summarize important information.

[0032] The conversion unit uses a generation AI to convert the summary message created by the summarization unit into natural-sounding speech. The conversion unit can, for example, use speech synthesis technology to customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. Specifically, it uses text-to-speech (TTS) technology to convert the summary message into speech. For example, it inputs the summary message into a TTS engine and generates a speech waveform. The conversion unit can also generate more natural-sounding speech using deep learning-based speech synthesis technology. For example, using advanced speech synthesis models such as WaveNet or Tacotron can generate natural-sounding speech that closely resembles a human voice. Furthermore, the conversion unit can customize voice tone, speaking speed, and emotional expression to generate speech that reflects the user's nuances. For example, the conversion unit adjusts pitch to enrich emotional expression. Specifically, it adjusts the pitch of the speech waveform to express emotions such as joy and sadness. The conversion unit can also change the speaking speed by adjusting the number of syllables per second. For example, it can increase the speaking speed when the speaker is in a hurry and decrease it when they are calm, generating speech appropriate to the situation. This allows the conversion unit to transform summary messages into natural and easy-to-understand speech, providing them in a format that is easy for users to comprehend. Furthermore, the conversion unit can provide the generated speech in multiple languages. For example, by generating speech in the user's language, such as English, Japanese, and Chinese, it can accommodate a global user base. This enables the conversion unit to transform summary messages into natural-sounding speech in multiple languages, catering to a wide range of users.

[0033] The storage unit saves the audio generated by the conversion unit as an answering machine message. The storage unit compresses and encodes the audio data and saves it in an appropriate format. Specifically, it compresses the audio data using a compression algorithm. For example, using compression formats such as MP3 or AAC reduces the data size while maintaining sound quality. The storage unit can also encode the audio data by specifying an encoding format. For example, saving in WAV format preserves uncompressed, high-quality audio data. Furthermore, the storage unit can save audio data in formats such as MP3, WAV, and AAC. This allows users to select the optimal format according to their playback environment. The storage unit can also manage metadata for the audio data. For example, adding metadata such as the creation date and time, caller information, and summary content makes later searching and management easier. This allows the storage unit to efficiently manage the generated audio data and quickly provide necessary information. Furthermore, the storage unit can also save audio data using cloud storage. For example, uploading audio data to a cloud server and making it accessible via the internet allows users to play the audio data from anywhere. This allows the storage unit to safely and efficiently store the generated audio data, enabling it to provide a highly convenient service to users.

[0034] The receiving unit can perform noise reduction and preprocessing of audio data. For example, the receiving unit can remove noise from audio data using filtering techniques. For example, the receiving unit can also remove noise from audio data using noise-canceling algorithms. The receiving unit can also normalize audio data and adjust the sampling rate. For example, the receiving unit normalizes the audio data to make the volume constant. The receiving unit also adjusts the sampling rate of the audio data to convert it into a format that is easy to analyze. This can improve the quality of the audio data. Some or all of the above processing in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input audio data into AI and have the AI ​​perform noise reduction and preprocessing.

[0035] The summarization unit can use natural language processing techniques to identify keywords and important phrases from audio data and create concise messages. For example, the summarization unit can analyze audio data using morphological analysis and extract keywords. For example, the summarization unit can also analyze the sentence structure of audio data using grammatical analysis and identify important phrases. Furthermore, the summarization unit can analyze the meaning of audio data using semantic analysis and extract important information. This allows it to extract important information from audio data and generate concise messages. Some or all of the above processing in the summarization unit is performed using a generative AI. For example, the summarization unit can input audio data into the generative AI and have the generative AI perform the identification of keywords and important phrases and the creation of concise messages.

[0036] The conversion unit can use speech synthesis technology to customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. For example, the conversion unit can convert a summary message into speech using text-to-speech (TTS) technology. For example, the conversion unit can also generate more natural-sounding speech using deep learning-based speech synthesis technology. Furthermore, by customizing voice tone, speaking speed, and emotional expression, the conversion unit generates speech that reflects the user's nuances. For example, the conversion unit can adjust pitch to enrich emotional expression. It can also change the speaking speed by adjusting the number of syllables per second. This allows for the generation of natural-sounding speech that reflects the user's nuances. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input a summary message into the generation AI and have the generation AI generate speech with customized voice tone, speaking speed, and emotional expression.

[0037] The storage unit can compress and encode audio data and save it in an appropriate format. For example, the storage unit can compress audio data using a compression algorithm. For example, the storage unit can also encode audio data by specifying an encoding format. Furthermore, the storage unit can save audio data in formats such as MP3, WAV, and AAC. This allows for efficient storage of audio data. Some or all of the above-described processes in the storage unit may be performed using AI or not. For example, the storage unit can input audio data into AI and have the AI ​​perform compression and encoding.

[0038] The reception unit can analyze the user's past voice input history to select the optimal pre-processing method when performing noise reduction or pre-processing of audio data. For example, the reception unit can analyze the noise pattern of audio data previously recorded by the user and apply the optimal noise reduction filter. For example, the reception unit can also perform pre-processing that emphasizes a specific frequency band based on the user's past voice input history. Furthermore, the reception unit can perform optimal volume adjustment based on the user's past voice data. In this way, the quality of the audio data can be improved by performing optimal pre-processing based on past voice input history. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input past voice input history into AI and have the AI ​​select the optimal pre-processing method.

[0039] The reception unit can analyze the user's current ambient noise in real time during voice input to improve the accuracy of noise reduction. For example, when a user is using voice input in a cafe, the reception unit can analyze ambient noise in real time and perform noise reduction. For example, when a user is using voice input in a car, the reception unit can analyze engine noise in real time and perform noise reduction. Furthermore, when a user is using voice input outdoors, the reception unit can analyze wind noise in real time and perform noise reduction. This allows for improved noise reduction accuracy by analyzing ambient noise in real time. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the current ambient noise into the AI ​​and have the AI ​​perform the noise reduction accuracy improvement.

[0040] The reception unit can prioritize processing highly relevant voice data based on the user's geographical location information when voice input is received. For example, if the user is in a specific region, the reception unit will prioritize processing voice data related to that region. For example, if the user is traveling, the reception unit can also prioritize processing voice data related to the travel destination. Furthermore, if the user is at home, the reception unit can prioritize processing voice data related to home. This allows for the priority processing of highly relevant voice data based on geographical location information. Some or all of the above processing in the reception unit may be performed using AI, or it may be performed without AI. For example, the reception unit can input geographical location information into AI and have the AI ​​select and process highly relevant voice data.

[0041] The reception unit can analyze the user's social media activity during voice input and prioritize processing relevant audio data. For example, if the user posts about a specific topic on social media, the reception unit will prioritize processing audio data related to that topic. For example, if the reception unit participates in a specific event on social media, it can also prioritize processing audio data related to that event. Furthermore, if the reception unit uses a specific hashtag on social media, it can prioritize processing audio data related to that hashtag. This allows for the priority processing of relevant audio data based on social media activity. Some or all of the processing described above in the reception unit may be performed using AI or not. For example, the reception unit can input social media activity data into AI and have the AI ​​select and process relevant audio data.

[0042] The summarization unit uses natural language processing technology to identify keywords and important phrases from audio data and create concise messages. It can improve the accuracy of summaries by referencing the user's past message history. For example, the summarization unit improves summarization accuracy based on keywords the user has used in the past. It can also identify important phrases from the user's past message history and incorporate them into the summary. Furthermore, the summarization unit can analyze the user's past message history and select the optimal summarization method. This allows for improved summarization accuracy based on past message history. Some or all of the above processing in the summarization unit is performed using a generative AI. For example, the summarization unit can input past message history into the generative AI and have the generative AI perform the summarization accuracy improvement.

[0043] The summarization unit can adjust the level of detail in the summary by considering the context of the audio data during summary generation. For example, if the context of the audio data is complex, the summarization unit will generate a detailed summary. For example, if the context of the audio data is simple, the summarization unit can also generate a concise summary. Furthermore, the summarization unit can dynamically adjust the level of detail in the summary according to the context of the audio data. This allows for the generation of a summary with a level of detail appropriate to the context of the audio data. Some or all of the above processing in the summarization unit is performed using a generation AI. For example, the summarization unit can input contextual information of the audio data into the generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0044] The summarization unit can determine the priority of summaries based on when the audio data was submitted. For example, if the audio data was recently submitted, the summarization unit will prioritize the generation of the summary. For example, if the audio data is old, the summarization unit can generate the summary with the normal priority. The summarization unit can also dynamically adjust the priority of summaries according to when the audio data was submitted. This allows for the generation of summaries with a priority corresponding to the submission date. Some or all of the above processing in the summarization unit is performed using a generation AI. For example, the summarization unit can input the audio data submission date information into the generation AI and have the generation AI determine the priority of summaries.

[0045] The summarization unit can adjust the order of summaries based on the relevance of the audio data during summary generation. For example, the summarization unit will prioritize summarizing audio data that contains important content. For example, the summarization unit can also generate summaries in the normal order if the audio data contains less relevant content. Furthermore, the summarization unit can dynamically adjust the order of summaries according to the relevance of the audio data. This allows for the generation of summaries in an order that reflects their relevance. Some or all of the above processing in the summarization unit is performed using a generation AI. For example, the summarization unit can input relevance information of the audio data into the generation AI and have the generation AI perform the adjustment of the summary order.

[0046] The conversion unit uses speech synthesis technology to customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. It can also refer to the user's past speech synthesis history to generate the optimal speech. For example, the conversion unit generates the optimal speech based on the voice tone the user has used in the past. For example, the conversion unit can select the optimal speaking speed from the user's past speech synthesis history. Furthermore, the conversion unit can analyze the user's past speech synthesis history and select the optimal emotional expression. This allows the conversion unit to generate the optimal speech based on past speech synthesis history. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input past speech synthesis history into the generation AI and have the generation AI perform the generation of the optimal speech.

[0047] The conversion unit can adjust the level of detail of the speech during speech synthesis, taking into account the context of the speech data. For example, if the context of the speech data is complex, the conversion unit can generate detailed speech. For example, if the context of the speech data is simple, the conversion unit can also generate concise speech. Furthermore, the conversion unit can dynamically adjust the level of detail of the speech according to the context of the speech data. This allows for the generation of speech with a level of detail appropriate to the context of the speech data. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input contextual information of the speech data into the generation AI and have the generation AI perform the adjustment of the level of detail of the speech.

[0048] The conversion unit can determine the priority of speech synthesis based on the submission date of the audio data during speech synthesis. For example, if the audio data has been recently submitted, the conversion unit will prioritize generating speech from that data. For example, if the audio data is old, the conversion unit can generate speech with the normal priority. The conversion unit can also dynamically adjust the speech synthesis priority according to the submission date of the audio data. This allows for the generation of speech with a priority corresponding to the submission date. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input the submission date information of the audio data into the generation AI and have the generation AI determine the priority of speech synthesis.

[0049] The conversion unit can adjust the order of speech synthesis based on the relevance of the audio data during speech synthesis. For example, the conversion unit will prioritize generating speech if the audio data contains important content. For example, the conversion unit can also generate speech in the normal order if the audio data contains less relevant content. Furthermore, the conversion unit can dynamically adjust the order of speech synthesis according to the relevance of the audio data. This allows for the generation of speech in an order that reflects its relevance. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input information about the relevance of the audio data into the generation AI and have the generation AI adjust the order of speech synthesis.

[0050] The storage unit can select the optimal storage method by referring to the user's past storage history when compressing or encoding audio data. For example, the storage unit can select the optimal compression method based on the compression format the user has used in the past. For example, the storage unit can also select the optimal encoding method from the user's past storage history. Furthermore, the storage unit can analyze the user's past storage history and select the optimal storage format. This allows the storage unit to select the optimal storage method based on past storage history. Some or all of the above processing in the storage unit may be performed using AI, or it may be performed without AI. For example, the storage unit can input past storage history into AI and have the AI ​​select the optimal storage method.

[0051] The storage unit can adjust the level of detail of the audio data when saving it, taking into account the context of the audio data. For example, if the context of the audio data is complex, the storage unit will save it in a detailed format. For example, if the context of the audio data is simple, the storage unit can also save it in a concise format. Furthermore, the storage unit can dynamically adjust the level of detail of the audio data according to the context of the audio data. This allows the audio data to be saved with a level of detail appropriate to its context. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input contextual information of the audio data into the AI ​​and have the AI ​​perform the adjustment of the level of detail of the audio data.

[0052] The storage unit can determine the priority of saving audio data based on when the audio data was submitted. For example, if the audio data was recently submitted, the storage unit will prioritize saving it. For example, if the audio data is old, the storage unit may save it with the normal priority. The storage unit can also dynamically adjust the saving priority according to when the audio data was submitted. This allows the audio data to be saved with priority according to the submission date. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input the audio data submission date information into the AI ​​and have the AI ​​perform the determination of the saving priority.

[0053] The storage unit can adjust the order in which audio data is saved based on its relevance. For example, if the audio data contains important content, the storage unit will save it preferentially. For example, if the audio data contains less relevant content, the storage unit may save it in the normal order. The storage unit can also dynamically adjust the order in which audio data is saved according to its relevance. This allows the audio data to be saved in an order that is appropriate to its relevance. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input information about the relevance of the audio data into the AI ​​and have the AI ​​perform the adjustment of the saving order.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The reception unit can analyze the user's past voice input history and select the optimal pre-processing method when the user submits voice input. For example, it can analyze the noise pattern of previously recorded voice data and apply the most suitable noise reduction filter. It can also perform pre-processing to emphasize specific frequency bands based on the user's past voice input history. Furthermore, it can perform optimal volume adjustment based on the user's past voice data. In this way, the quality of the voice data can be improved by performing optimal pre-processing based on past voice input history.

[0056] The conversion unit uses speech synthesis technology to customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. It can also refer to the user's past speech synthesis history to generate the optimal speech. For example, it can generate the optimal speech based on the voice tone the user has used in the past. Furthermore, it can select the optimal speaking speed from the user's past speech synthesis history. It can also analyze the user's past speech synthesis history to select the optimal emotional expression. This allows for the generation of optimal speech based on past speech synthesis history.

[0057] The storage unit can adjust the level of detail when saving audio data, taking into account the context of the audio data. For example, if the context of the audio data is complex, it can be saved in a detailed format. Conversely, if the context of the audio data is simple, it can be saved in a concise format. Furthermore, the level of detail can be dynamically adjusted according to the context of the audio data. This allows for saving audio data with a level of detail appropriate to its context.

[0058] The summarization unit can adjust the level of detail in the summary during generation, taking into account the context of the audio data. For example, if the context of the audio data is complex, a detailed summary can be generated. Conversely, if the context of the audio data is simple, a concise summary can be generated. Furthermore, the level of detail in the summary can be dynamically adjusted according to the context of the audio data. This allows for the generation of summaries with a level of detail appropriate to the context of the audio data.

[0059] The storage unit can determine the storage priority of audio data based on when the audio data was submitted. For example, if the audio data was recently submitted, it can be saved with priority. If the audio data is old, it can be saved with the normal priority. Furthermore, the storage priority can be dynamically adjusted according to when the audio data was submitted. This allows audio data to be saved with priority according to the submission date.

[0060] The reception system can prioritize processing highly relevant voice data based on the user's geographical location during voice input. For example, if the user is in a specific region, it can prioritize processing voice data related to that region. Similarly, if the user is traveling, it can prioritize processing voice data related to their travel destination. Furthermore, if the user is at home, it can prioritize processing voice data related to their home. This allows for the prioritization of highly relevant voice data based on geographical location information.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The reception unit receives voice input. For example, it can receive voice input using a microphone. It can also receive voice input using specific speech recognition technology. Furthermore, the reception unit can denoise and preprocess the voice data. For example, it can remove noise from the voice data using filtering technology or noise-canceling algorithms. It can also normalize the voice data and adjust the sampling rate. Step 2: The summarization unit uses generation AI to analyze the audio data received by the reception unit and extract and summarize the key points. For example, it uses natural language processing technology to identify keywords and important phrases from the audio data and create a concise message. It also uses morphological analysis, grammatical analysis, and semantic analysis to analyze the audio data and extract important information. Step 3: The conversion unit uses generation AI to convert the summary message created by the summarization unit into natural-sounding speech. For example, speech synthesis technology can be used to customize the tone of voice, speaking speed, and emotional expression to generate natural-sounding speech. Text-to-speech (TTS) technology and deep learning-based speech synthesis technology can be used to generate even more natural-sounding speech. By customizing the tone of voice, speaking speed, and emotional expression, speech that reflects the user's nuances can be generated. Step 4: The storage unit saves the audio generated by the conversion unit as an answering machine message. For example, it compresses and encodes the audio data and saves it in an appropriate format. It can compress the audio data using a compression algorithm and encode the audio data by specifying an encoding format. The audio data can be saved in formats such as MP3, WAV, and AAC.

[0063] (Example of form 2) The answering machine support system according to an embodiment of the present invention is a system in which the user inputs the content they want to convey via voice, and a generating AI automatically organizes and summarizes it to create a concise message. The answering machine support system takes the content the user wants to convey via voice input, and the generating AI automatically organizes and summarizes it to create a concise message. It also has a function to convert the organized message into natural-sounding speech and save it as an answering machine message. This supports users who are not comfortable with answering machines, from organizing the message to converting it to speech and sending it. For example, the user inputs the content they want to convey via voice input. At this time, the user can speak freely in their own words. For example, they might input something like, "The meeting time has been changed, so please change it to 3pm." This voice data is input to the generating AI. Next, the generating AI analyzes the input voice data and extracts and summarizes the important points. The generating AI identifies keywords and important phrases from the voice data and creates a concise message. For example, a summarized message such as "The meeting time has been changed to 3pm" is generated. The generated summarized message is converted into natural-sounding speech by the generating AI. The AI-generating system customizes the tone, speaking speed, and emotional expression of the voice to produce audio that reflects the nuances the user wants to convey. For example, it can generate an audio message in a calm tone saying, "The meeting time has been changed to 3 PM." Finally, the generated audio is saved as an answering machine message. This allows the recipient to receive a concise and easy-to-understand message. For example, when the recipient plays the answering machine message, they will hear a voice message saying, "The meeting time has been changed to 3 PM." This system allows users to summarize what they want to convey concisely and express the appropriate tone and emotion. In addition, because recipients receive easy-to-understand messages, communication efficiency is improved. For example, in a business setting, important information can be conveyed concisely, leading to increased work efficiency. In this way, the answering machine support system can summarize what the user wants to convey concisely and save it as an answering machine message in a natural voice.

[0064] The answering machine support system according to this embodiment comprises a reception unit, a summarization unit, a conversion unit, and a storage unit. The reception unit receives voice input. The reception unit can receive voice input using, for example, a microphone. The reception unit can also receive voice input using specific speech recognition technology. Furthermore, the reception unit can perform noise reduction and preprocessing of the voice data. For example, the reception unit can remove noise from the voice data using filtering technology. The reception unit can also remove noise from the voice data using a noise-canceling algorithm. Furthermore, the reception unit can normalize the voice data and adjust the sampling rate. For example, the reception unit normalizes the voice data to make the volume constant. The reception unit also adjusts the sampling rate of the voice data to convert it into a format that is easy to analyze. The summarization unit uses a generation AI to analyze the voice data received by the reception unit and extract and summarize important points. The summarization unit uses, for example, natural language processing technology to identify keywords and important phrases from the voice data and create a concise message. For example, the summarization unit uses morphological analysis to analyze the voice data and extract keywords. The summarization unit can also analyze the sentence structure of the audio data using grammatical analysis and identify important phrases. Furthermore, the summarization unit can analyze the meaning of the audio data using semantic analysis and extract important information. The conversion unit uses generative AI to convert the summarized message created by the summarization unit into natural-sounding speech. The conversion unit can, for example, use speech synthesis technology to customize the tone, speaking speed, and emotional expression to generate natural-sounding speech. For example, the conversion unit can convert the summarized message into speech using text-to-speech (TTS) technology. The conversion unit can also generate more natural-sounding speech using deep learning-based speech synthesis technology. Furthermore, the conversion unit can generate speech that reflects the user's nuances by customizing the tone, speaking speed, and emotional expression. For example, the conversion unit can adjust the pitch to enrich emotional expression. The conversion unit can also change the speaking speed by adjusting the number of syllables per second. The storage unit saves the speech generated by the conversion unit as an answering machine message.The storage unit, for example, compresses and encodes audio data and saves it in an appropriate format. For instance, the storage unit compresses audio data using a compression algorithm. The storage unit can also encode audio data by specifying an encoding format. Furthermore, the storage unit can save audio data in formats such as MP3, WAV, and AAC. As a result, the answering machine support system according to this embodiment can concisely summarize what the user wants to convey and save it as an answering machine message in a natural voice.

[0065] The reception unit accepts voice input. For example, it can accept voice input using a microphone. Specifically, by using a high-sensitivity microphone, it can accurately capture voices from a distance or quiet voices. The reception unit can also accept voice input using specific speech recognition technologies. For example, by using a deep learning-based speech recognition model, high-precision speech recognition is possible even in noisy environments. Furthermore, the reception unit can perform noise reduction and preprocessing of the audio data. For example, the reception unit can remove noise from the audio data using filtering techniques. Specifically, it can remove noise in a specific frequency band using a bandpass filter. The reception unit can also remove noise from the audio data using noise cancellation algorithms. For example, it can cancel background noise in real time using active noise cancellation technology. Furthermore, the reception unit can normalize the audio data and adjust the sampling rate. For example, the reception unit normalizes the audio data to make the volume constant. Specifically, it adjusts the overall volume based on the peak volume of the audio data. The reception unit can also adjust the sampling rate of the audio data to convert it into a format that is easy to analyze. For example, downsampling a 44.1kHz sampling rate to 16kHz can reduce the amount of data while maintaining analysis accuracy. This allows the receiving unit to accept high-precision audio input under diverse environments and conditions and convert it into a format suitable for subsequent processing.

[0066] The summarization unit uses generative AI to analyze audio data received by the reception unit, extracting and summarizing key points. For example, the summarization unit uses natural language processing techniques to identify keywords and important phrases from the audio data and create a concise message. Specifically, it analyzes the audio data using morphological analysis to extract keywords. For instance, it converts the audio data to text and inputs that text into a morphological analysis engine to extract important words such as nouns and verbs. The summarization unit can also analyze the sentence structure of the audio data using grammatical analysis to identify important phrases. For example, it uses dependency structure analysis to clarify relationships between subjects, predicates, and objects, and identify phrases containing important information. Furthermore, the summarization unit can analyze the meaning of the audio data using semantic analysis to extract important information. For example, it constructs a semantic network and analyzes the semantic relationships between words and phrases within the audio data to extract important information. This allows the summarization unit to quickly and accurately extract key points from audio data and generate concise and easy-to-understand messages. Additionally, the summarization unit can use generative AI to reconstruct the extracted information into natural-sounding sentences. For example, the generation AI generates grammatically correct sentences based on extracted keywords and phrases, and arranges them in a format that is easy for the user to understand. This allows the summarization unit to efficiently analyze the audio data and concisely summarize important information.

[0067] The conversion unit uses a generation AI to convert the summary message created by the summarization unit into natural-sounding speech. The conversion unit can, for example, use speech synthesis technology to customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. Specifically, it uses text-to-speech (TTS) technology to convert the summary message into speech. For example, it inputs the summary message into a TTS engine and generates a speech waveform. The conversion unit can also generate more natural-sounding speech using deep learning-based speech synthesis technology. For example, using advanced speech synthesis models such as WaveNet or Tacotron can generate natural-sounding speech that closely resembles a human voice. Furthermore, the conversion unit can customize voice tone, speaking speed, and emotional expression to generate speech that reflects the user's nuances. For example, the conversion unit adjusts pitch to enrich emotional expression. Specifically, it adjusts the pitch of the speech waveform to express emotions such as joy and sadness. The conversion unit can also change the speaking speed by adjusting the number of syllables per second. For example, it can increase the speaking speed when the speaker is in a hurry and decrease it when they are calm, generating speech appropriate to the situation. This allows the conversion unit to transform summary messages into natural and easy-to-understand speech, providing them in a format that is easy for users to comprehend. Furthermore, the conversion unit can provide the generated speech in multiple languages. For example, by generating speech in the user's language, such as English, Japanese, and Chinese, it can accommodate a global user base. This enables the conversion unit to transform summary messages into natural-sounding speech in multiple languages, catering to a wide range of users.

[0068] The storage unit saves the audio generated by the conversion unit as an answering machine message. The storage unit compresses and encodes the audio data and saves it in an appropriate format. Specifically, it compresses the audio data using a compression algorithm. For example, using compression formats such as MP3 or AAC reduces the data size while maintaining sound quality. The storage unit can also encode the audio data by specifying an encoding format. For example, saving in WAV format preserves uncompressed, high-quality audio data. Furthermore, the storage unit can save audio data in formats such as MP3, WAV, and AAC. This allows users to select the optimal format according to their playback environment. The storage unit can also manage metadata for the audio data. For example, adding metadata such as the creation date and time, caller information, and summary content makes later searching and management easier. This allows the storage unit to efficiently manage the generated audio data and quickly provide necessary information. Furthermore, the storage unit can also save audio data using cloud storage. For example, uploading audio data to a cloud server and making it accessible via the internet allows users to play the audio data from anywhere. This allows the storage unit to safely and efficiently store the generated audio data, enabling it to provide a highly convenient service to users.

[0069] The receiving unit can perform noise reduction and preprocessing of audio data. For example, the receiving unit can remove noise from audio data using filtering techniques. For example, the receiving unit can also remove noise from audio data using noise-canceling algorithms. The receiving unit can also normalize audio data and adjust the sampling rate. For example, the receiving unit normalizes the audio data to make the volume constant. The receiving unit also adjusts the sampling rate of the audio data to convert it into a format that is easy to analyze. This can improve the quality of the audio data. Some or all of the above processing in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input audio data into AI and have the AI ​​perform noise reduction and preprocessing.

[0070] The summarization unit can use natural language processing techniques to identify keywords and important phrases from audio data and create concise messages. For example, the summarization unit can analyze audio data using morphological analysis and extract keywords. For example, the summarization unit can also analyze the sentence structure of audio data using grammatical analysis and identify important phrases. Furthermore, the summarization unit can analyze the meaning of audio data using semantic analysis and extract important information. This allows it to extract important information from audio data and generate concise messages. Some or all of the above processing in the summarization unit is performed using a generative AI. For example, the summarization unit can input audio data into the generative AI and have the generative AI perform the identification of keywords and important phrases and the creation of concise messages.

[0071] The conversion unit can use speech synthesis technology to customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. For example, the conversion unit can convert a summary message into speech using text-to-speech (TTS) technology. For example, the conversion unit can also generate more natural-sounding speech using deep learning-based speech synthesis technology. Furthermore, by customizing voice tone, speaking speed, and emotional expression, the conversion unit generates speech that reflects the user's nuances. For example, the conversion unit can adjust pitch to enrich emotional expression. It can also change the speaking speed by adjusting the number of syllables per second. This allows for the generation of natural-sounding speech that reflects the user's nuances. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input a summary message into the generation AI and have the generation AI generate speech with customized voice tone, speaking speed, and emotional expression.

[0072] The storage unit can compress and encode audio data and save it in an appropriate format. For example, the storage unit can compress audio data using a compression algorithm. For example, the storage unit can also encode audio data by specifying an encoding format. Furthermore, the storage unit can save audio data in formats such as MP3, WAV, and AAC. This allows for efficient storage of audio data. Some or all of the above-described processes in the storage unit may be performed using AI or not. For example, the storage unit can input audio data into AI and have the AI ​​perform compression and encoding.

[0073] The reception unit can estimate the user's emotions and adjust the timing of voice input acceptance based on the estimated emotions. For example, if the user is nervous, the reception unit will wait until the user is relaxed before accepting voice input. For example, if the user is in a hurry, the reception unit can accept voice input immediately. Alternatively, if the user is calm, the reception unit can accept voice input at a natural timing. This allows for voice input to be accepted at an appropriate time according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input user emotion data into an AI and have the AI ​​perform emotion estimation and adjustment of acceptance timing.

[0074] The reception unit can analyze the user's past voice input history to select the optimal pre-processing method when performing noise reduction or pre-processing of audio data. For example, the reception unit can analyze the noise pattern of audio data previously recorded by the user and apply the optimal noise reduction filter. For example, the reception unit can also perform pre-processing that emphasizes a specific frequency band based on the user's past voice input history. Furthermore, the reception unit can perform optimal volume adjustment based on the user's past voice data. In this way, the quality of the audio data can be improved by performing optimal pre-processing based on past voice input history. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input past voice input history into AI and have the AI ​​select the optimal pre-processing method.

[0075] The reception unit can analyze the user's current ambient noise in real time during voice input to improve the accuracy of noise reduction. For example, when a user is using voice input in a cafe, the reception unit can analyze ambient noise in real time and perform noise reduction. For example, when a user is using voice input in a car, the reception unit can analyze engine noise in real time and perform noise reduction. Furthermore, when a user is using voice input outdoors, the reception unit can analyze wind noise in real time and perform noise reduction. This allows for improved noise reduction accuracy by analyzing ambient noise in real time. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the current ambient noise into the AI ​​and have the AI ​​perform the noise reduction accuracy improvement.

[0076] The reception unit can estimate the user's emotions and determine the priority of voice input based on the estimated emotions. For example, if the user is nervous, the reception unit may prioritize voice input over other inputs. For example, if the user is relaxed, the reception unit may accept voice input with normal priority. Also, if the user is in a hurry, the reception unit may accept voice input with the highest priority. This allows for voice input to be accepted with priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input user emotion data into an AI and have the AI ​​perform emotion estimation and priority determination.

[0077] The reception unit can prioritize processing highly relevant voice data based on the user's geographical location information when voice input is received. For example, if the user is in a specific region, the reception unit will prioritize processing voice data related to that region. For example, if the user is traveling, the reception unit can also prioritize processing voice data related to the travel destination. Furthermore, if the user is at home, the reception unit can prioritize processing voice data related to home. This allows for the priority processing of highly relevant voice data based on geographical location information. Some or all of the above processing in the reception unit may be performed using AI, or it may be performed without AI. For example, the reception unit can input geographical location information into AI and have the AI ​​select and process highly relevant voice data.

[0078] The reception unit can analyze the user's social media activity during voice input and prioritize processing relevant audio data. For example, if the user posts about a specific topic on social media, the reception unit will prioritize processing audio data related to that topic. For example, if the reception unit participates in a specific event on social media, it can also prioritize processing audio data related to that event. Furthermore, if the reception unit uses a specific hashtag on social media, it can prioritize processing audio data related to that hashtag. This allows for the priority processing of relevant audio data based on social media activity. Some or all of the processing described above in the reception unit may be performed using AI or not. For example, the reception unit can input social media activity data into AI and have the AI ​​select and process relevant audio data.

[0079] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the user is stressed, the summarization unit can generate a concise and to-the-point summary. For example, if the user is relaxed, the summarization unit can also generate a summary that includes detailed information. Furthermore, if the user is in a hurry, the summarization unit can generate a summary quickly. This allows for the generation of summaries with expressions that are appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the summarization unit are performed using generative AI. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI adjust the way the summary is presented.

[0080] The summarization unit uses natural language processing technology to identify keywords and important phrases from audio data and create concise messages. It can improve the accuracy of summaries by referencing the user's past message history. For example, the summarization unit improves summarization accuracy based on keywords the user has used in the past. It can also identify important phrases from the user's past message history and incorporate them into the summary. Furthermore, the summarization unit can analyze the user's past message history and select the optimal summarization method. This allows for improved summarization accuracy based on past message history. Some or all of the above processing in the summarization unit is performed using a generative AI. For example, the summarization unit can input past message history into the generative AI and have the generative AI perform the summarization accuracy improvement.

[0081] The summarization unit can adjust the level of detail in the summary by considering the context of the audio data during summary generation. For example, if the context of the audio data is complex, the summarization unit will generate a detailed summary. For example, if the context of the audio data is simple, the summarization unit can also generate a concise summary. Furthermore, the summarization unit can dynamically adjust the level of detail in the summary according to the context of the audio data. This allows for the generation of a summary with a level of detail appropriate to the context of the audio data. Some or all of the above processing in the summarization unit is performed using a generation AI. For example, the summarization unit can input contextual information of the audio data into the generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0082] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated emotions. For example, if the user is stressed, the summarization unit can generate a short, concise summary. For example, if the user is relaxed, the summarization unit can generate a longer summary containing more detailed information. Furthermore, if the user is in a hurry, the summarization unit can generate a summary quickly. This allows for the generation of summaries of appropriate length based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the summarization unit are performed using generative AI. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI adjust the length of the summary.

[0083] The summarization unit can determine the priority of summaries based on when the audio data was submitted. For example, if the audio data was recently submitted, the summarization unit will prioritize the generation of the summary. For example, if the audio data is old, the summarization unit can generate the summary with the normal priority. The summarization unit can also dynamically adjust the priority of summaries according to when the audio data was submitted. This allows for the generation of summaries with a priority corresponding to the submission date. Some or all of the above processing in the summarization unit is performed using a generation AI. For example, the summarization unit can input the audio data submission date information into the generation AI and have the generation AI determine the priority of summaries.

[0084] The summarization unit can adjust the order of summaries based on the relevance of the audio data during summary generation. For example, the summarization unit will prioritize summarizing audio data that contains important content. For example, the summarization unit can also generate summaries in the normal order if the audio data contains less relevant content. Furthermore, the summarization unit can dynamically adjust the order of summaries according to the relevance of the audio data. This allows for the generation of summaries in an order that reflects their relevance. Some or all of the above processing in the summarization unit is performed using a generation AI. For example, the summarization unit can input relevance information of the audio data into the generation AI and have the generation AI perform the adjustment of the summary order.

[0085] The conversion unit can estimate the user's emotions and adjust the speech synthesis expression based on the estimated emotions. For example, if the user is nervous, the conversion unit can generate speech in a calm tone. For example, if the user is relaxed, the conversion unit can also generate speech in a bright tone. Furthermore, if the user is in a hurry, the conversion unit can generate speech quickly and concisely. This allows for the generation of speech in an expression that matches the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the conversion unit is performed using the generative AI. For example, the conversion unit can input user emotion data into the generative AI and have the generative AI adjust the speech synthesis expression.

[0086] The conversion unit uses speech synthesis technology to customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. It can also refer to the user's past speech synthesis history to generate the optimal speech. For example, the conversion unit generates the optimal speech based on the voice tone the user has used in the past. For example, the conversion unit can select the optimal speaking speed from the user's past speech synthesis history. Furthermore, the conversion unit can analyze the user's past speech synthesis history and select the optimal emotional expression. This allows the conversion unit to generate the optimal speech based on past speech synthesis history. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input past speech synthesis history into the generation AI and have the generation AI perform the generation of the optimal speech.

[0087] The conversion unit can adjust the level of detail of the speech during speech synthesis, taking into account the context of the speech data. For example, if the context of the speech data is complex, the conversion unit can generate detailed speech. For example, if the context of the speech data is simple, the conversion unit can also generate concise speech. Furthermore, the conversion unit can dynamically adjust the level of detail of the speech according to the context of the speech data. This allows for the generation of speech with a level of detail appropriate to the context of the speech data. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input contextual information of the speech data into the generation AI and have the generation AI perform the adjustment of the level of detail of the speech.

[0088] The conversion unit can estimate the user's emotions and adjust the length of the synthesized speech based on the estimated emotions. For example, if the user is nervous, the conversion unit can generate a short, concise speech. For example, if the user is relaxed, the conversion unit can also generate a longer speech containing more detailed information. Furthermore, if the user is in a hurry, the conversion unit can generate speech quickly. This allows for the generation of speech of a length appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the conversion unit is performed using the generative AI. For example, the conversion unit can input user emotion data into the generative AI and have the generative AI adjust the length of the synthesized speech.

[0089] The conversion unit can determine the priority of speech synthesis based on the submission date of the audio data during speech synthesis. For example, if the audio data has been recently submitted, the conversion unit will prioritize generating speech from that data. For example, if the audio data is old, the conversion unit can generate speech with the normal priority. The conversion unit can also dynamically adjust the speech synthesis priority according to the submission date of the audio data. This allows for the generation of speech with a priority corresponding to the submission date. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input the submission date information of the audio data into the generation AI and have the generation AI determine the priority of speech synthesis.

[0090] The conversion unit can adjust the order of speech synthesis based on the relevance of the audio data during speech synthesis. For example, the conversion unit will prioritize generating speech if the audio data contains important content. For example, the conversion unit can also generate speech in the normal order if the audio data contains less relevant content. Furthermore, the conversion unit can dynamically adjust the order of speech synthesis according to the relevance of the audio data. This allows for the generation of speech in an order that reflects its relevance. Some or all of the above processing in the conversion unit is performed using a generation AI. For example, the conversion unit can input information about the relevance of the audio data into the generation AI and have the generation AI adjust the order of speech synthesis.

[0091] The storage unit can estimate the user's emotions and adjust the method of saving the audio data based on the estimated emotions. For example, if the user is nervous, the storage unit can save the audio data in a concise format. For example, if the user is relaxed, the storage unit can also save the audio data in a detailed format. Furthermore, if the user is in a hurry, the storage unit can save the audio data quickly. This allows the audio data to be saved in a way that suits the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input the user's emotion data into an AI and have the AI ​​adjust the saving method.

[0092] The storage unit can select the optimal storage method by referring to the user's past storage history when compressing or encoding audio data. For example, the storage unit can select the optimal compression method based on the compression format the user has used in the past. For example, the storage unit can also select the optimal encoding method from the user's past storage history. Furthermore, the storage unit can analyze the user's past storage history and select the optimal storage format. This allows the storage unit to select the optimal storage method based on past storage history. Some or all of the above processing in the storage unit may be performed using AI, or it may be performed without AI. For example, the storage unit can input past storage history into AI and have the AI ​​select the optimal storage method.

[0093] The storage unit can adjust the level of detail of the audio data when saving it, taking into account the context of the audio data. For example, if the context of the audio data is complex, the storage unit will save it in a detailed format. For example, if the context of the audio data is simple, the storage unit can also save it in a concise format. Furthermore, the storage unit can dynamically adjust the level of detail of the audio data according to the context of the audio data. This allows the audio data to be saved with a level of detail appropriate to its context. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input contextual information of the audio data into the AI ​​and have the AI ​​perform the adjustment of the level of detail of the audio data.

[0094] The storage unit can estimate the user's emotions and determine the priority for saving audio data based on the estimated emotions. For example, if the user is nervous, the storage unit will save the audio data with priority over other data. For example, if the user is relaxed, the storage unit may save the audio data with normal priority. Also, if the user is in a hurry, the storage unit may save the audio data with the highest priority. This allows for saving audio data with priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input the user's emotion data into an AI and have the AI ​​determine the saving priority.

[0095] The storage unit can determine the priority of saving audio data based on when the audio data was submitted. For example, if the audio data was recently submitted, the storage unit will prioritize saving it. For example, if the audio data is old, the storage unit may save it with the normal priority. The storage unit can also dynamically adjust the saving priority according to when the audio data was submitted. This allows the audio data to be saved with priority according to the submission date. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input the audio data submission date information into the AI ​​and have the AI ​​perform the determination of the saving priority.

[0096] The storage unit can adjust the order in which audio data is saved based on its relevance. For example, if the audio data contains important content, the storage unit will save it preferentially. For example, if the audio data contains less relevant content, the storage unit may save it in the normal order. The storage unit can also dynamically adjust the order in which audio data is saved according to its relevance. This allows the audio data to be saved in an order that is appropriate to its relevance. Some or all of the above processing in the storage unit may be performed using AI or not. For example, the storage unit can input information about the relevance of the audio data into the AI ​​and have the AI ​​perform the adjustment of the saving order.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The reception unit can analyze the user's past voice input history and select the optimal pre-processing method when the user submits voice input. For example, it can analyze the noise pattern of previously recorded voice data and apply the most suitable noise reduction filter. It can also perform pre-processing to emphasize specific frequency bands based on the user's past voice input history. Furthermore, it can perform optimal volume adjustment based on the user's past voice data. In this way, the quality of the voice data can be improved by performing optimal pre-processing based on past voice input history.

[0099] The summarization function can estimate the user's emotions and adjust the way the summary is presented based on those emotions. For example, if the user is stressed, it can generate a concise and to-the-point summary. If the user is relaxed, it can generate a summary that includes detailed information. Furthermore, if the user is in a hurry, it can generate a summary quickly. This allows for the generation of summaries using expressions that are appropriate to the user's emotions.

[0100] The conversion unit uses speech synthesis technology to customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. It can also refer to the user's past speech synthesis history to generate the optimal speech. For example, it can generate the optimal speech based on the voice tone the user has used in the past. Furthermore, it can select the optimal speaking speed from the user's past speech synthesis history. It can also analyze the user's past speech synthesis history to select the optimal emotional expression. This allows for the generation of optimal speech based on past speech synthesis history.

[0101] The storage unit can adjust the level of detail when saving audio data, taking into account the context of the audio data. For example, if the context of the audio data is complex, it can be saved in a detailed format. Conversely, if the context of the audio data is simple, it can be saved in a concise format. Furthermore, the level of detail can be dynamically adjusted according to the context of the audio data. This allows for saving audio data with a level of detail appropriate to its context.

[0102] The reception system can estimate the user's emotions and adjust the timing of voice input acceptance based on those estimates. For example, if the user is nervous, it can wait until the user is relaxed before accepting voice input. If the user is in a hurry, it can accept voice input immediately. Furthermore, if the user is calm, it can accept voice input at a natural timing. This allows for voice input to be accepted at the appropriate time according to the user's emotions.

[0103] The summarization unit can adjust the level of detail in the summary during generation, taking into account the context of the audio data. For example, if the context of the audio data is complex, a detailed summary can be generated. Conversely, if the context of the audio data is simple, a concise summary can be generated. Furthermore, the level of detail in the summary can be dynamically adjusted according to the context of the audio data. This allows for the generation of summaries with a level of detail appropriate to the context of the audio data.

[0104] The conversion unit can estimate the user's emotions and adjust the speech synthesis expression based on the estimated emotions. For example, if the user is nervous, it can generate speech in a calm tone. If the user is relaxed, it can generate speech in a bright tone. Furthermore, if the user is in a hurry, it can generate speech quickly and concisely. This allows for the generation of speech in an expression that matches the user's emotions.

[0105] The storage unit can determine the storage priority of audio data based on when the audio data was submitted. For example, if the audio data was recently submitted, it can be saved with priority. If the audio data is old, it can be saved with the normal priority. Furthermore, the storage priority can be dynamically adjusted according to when the audio data was submitted. This allows audio data to be saved with priority according to the submission date.

[0106] The reception system can prioritize processing highly relevant voice data based on the user's geographical location during voice input. For example, if the user is in a specific region, it can prioritize processing voice data related to that region. Similarly, if the user is traveling, it can prioritize processing voice data related to their travel destination. Furthermore, if the user is at home, it can prioritize processing voice data related to their home. This allows for the prioritization of highly relevant voice data based on geographical location information.

[0107] The storage unit can estimate the user's emotions and determine the priority for saving audio data based on the estimated emotions. For example, if the user is nervous, the audio data can be saved with priority over other data. If the user is relaxed, the audio data can be saved with the normal priority. Furthermore, if the user is in a hurry, the audio data can be saved with the highest priority. This allows for the saving of audio data with priorities that correspond to the user's emotions.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The reception unit receives voice input. For example, it can receive voice input using a microphone. It can also receive voice input using specific speech recognition technology. Furthermore, the reception unit can denoise and preprocess the voice data. For example, it can remove noise from the voice data using filtering technology or noise-canceling algorithms. It can also normalize the voice data and adjust the sampling rate. Step 2: The summarization unit uses generation AI to analyze the audio data received by the reception unit and extract and summarize the key points. For example, it uses natural language processing technology to identify keywords and important phrases from the audio data and create a concise message. It also uses morphological analysis, grammatical analysis, and semantic analysis to analyze the audio data and extract important information. Step 3: The conversion unit uses generation AI to convert the summary message created by the summarization unit into natural-sounding speech. For example, speech synthesis technology can be used to customize the tone of voice, speaking speed, and emotional expression to generate natural-sounding speech. Text-to-speech (TTS) technology and deep learning-based speech synthesis technology can be used to generate even more natural-sounding speech. By customizing the tone of voice, speaking speed, and emotional expression, speech that reflects the user's nuances can be generated. Step 4: The storage unit saves the audio generated by the conversion unit as an answering machine message. For example, it compresses and encodes the audio data and saves it in an appropriate format. It can compress the audio data using a compression algorithm and encode the audio data by specifying an encoding format. The audio data can be saved in formats such as MP3, WAV, and AAC.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements described above, including the reception unit, summarization unit, conversion unit, and storage unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 38B of the smart device 14 and performs noise reduction and preprocessing by the control unit 46A. The summarization unit is implemented in the specific processing unit 290 of the data processing unit 12, which analyzes the voice data using a generation AI and extracts and summarizes the important points. The conversion unit is implemented in the specific processing unit 290 of the data processing unit 12, which converts the summarized message into natural-sounding voice using a generation AI. The storage unit stores the voice data in the storage 50 of the smart device 14, for example. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

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

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

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

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

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

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

[0125] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

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

[0127] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

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

[0129] Each of the multiple elements described above, including the reception unit, summarization unit, conversion unit, and storage unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the smart glasses 214 and performs noise reduction and preprocessing by the control unit 46A. The summarization unit is implemented in the specific processing unit 290 of the data processing unit 12, which analyzes the voice data using a generation AI and extracts and summarizes the important points. The conversion unit is implemented in the specific processing unit 290 of the data processing unit 12, which converts the summarized message into natural-sounding voice using a generation AI. The storage unit stores the voice data in the storage 50 of the smart glasses 214, for example. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the reception unit, summarization unit, conversion unit, and storage unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the headset terminal 314 and performs noise reduction and preprocessing by the control unit 46A. The summarization unit is implemented in the specific processing unit 290 of the data processing unit 12, which analyzes the voice data using a generation AI and extracts and summarizes the important points. The conversion unit is implemented in the specific processing unit 290 of the data processing unit 12, which converts the summarized message into natural-sounding voice using a generation AI. The storage unit stores the voice data in the storage 50 of the headset terminal 314, for example. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the reception unit, summarization unit, conversion unit, and storage unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives voice input using the microphone 238 of the robot 414 and performs noise reduction and preprocessing by the control unit 46A. The summarization unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which analyzes the voice data using a generation AI and extracts and summarizes the important points. The conversion unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, which converts the summarized message into natural-sounding voice using a generation AI. The storage unit stores the voice data in, for example, the storage 50 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0163] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] 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.

[0173] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) A reception desk that accepts voice input, The summarization unit analyzes the audio data received by the reception unit and extracts and summarizes the important points, A conversion unit that converts the summary message created by the summarization unit into natural speech, The system includes a storage unit that stores the audio generated by the conversion unit as an answering machine message. A system characterized by the following features. (Note 2) The aforementioned reception unit is Noise reduction and preprocessing of audio data The system described in Appendix 1, characterized by the features described herein. (Note 3) The summary section above is, Using natural language processing techniques, keywords and important phrases are identified from audio data to create concise messages. The system described in Appendix 1, characterized by the features described herein. (Note 4) The conversion unit is Using speech synthesis technology, we customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned storage unit is Compress and encode audio data and save it in an appropriate format. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When performing noise reduction or preprocessing on audio data, the system analyzes the user's past voice input history to select the optimal preprocessing method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is During voice input, the system analyzes the user's current ambient noise in real time to improve the accuracy of noise reduction. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is It estimates the user's emotions and determines the priority of voice input based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is During voice input, the system prioritizes processing of highly relevant voice data based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is During voice input, the system analyzes the user's social media activity and prioritizes processing relevant voice data. The system described in Appendix 1, characterized by the features described herein. (Note 12) The summary section above is, It estimates the user's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The summary section above is, When using natural language processing techniques to identify keywords and important phrases from audio data and create concise messages, the accuracy of the summaries is improved by referencing the user's past message history. The system described in Appendix 1, characterized by the features described herein. (Note 14) The summary section above is, When generating a summary, the level of detail in the summary is adjusted by considering the context of the audio data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The summary section above is, It estimates the user's sentiment and adjusts the length of the summary based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The summary section above is, When generating summaries, the priority of summaries is determined based on when the audio data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The summary section above is, During summary generation, the order of summaries is adjusted based on the relevance of the audio data. The system described in Appendix 1, characterized by the features described herein. (Note 18) The conversion unit is It estimates the user's emotions and adjusts the speech synthesis expression based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The conversion unit is Using speech synthesis technology, the system customizes voice tone, speaking speed, and emotional expression to generate natural-sounding speech, referencing the user's past speech synthesis history to produce the optimal voice. The system described in Appendix 1, characterized by the features described herein. (Note 20) The conversion unit is During speech synthesis, the level of detail of the speech is adjusted considering the context of the speech data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The conversion unit is It estimates the user's emotions and adjusts the length of the synthesized speech based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The conversion unit is During speech synthesis, the priority of speech synthesis is determined based on the timing of audio data submission. The system described in Appendix 1, characterized by the features described herein. (Note 23) The conversion unit is During speech synthesis, the order of speech synthesis is adjusted based on the relationships between the speech data. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned storage unit is The system estimates the user's emotions and adjusts how audio data is stored based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned storage unit is When compressing or encoding audio data, the system selects the optimal storage method by referring to the user's past saving history. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned storage unit is When saving audio data, the level of detail saved is adjusted considering the context of the audio data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned storage unit is The system estimates the user's emotions and determines the priority for saving audio data based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned storage unit is When saving audio data, the saving priority is determined based on when the audio data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned storage unit is When saving audio data, the saving order is adjusted based on the relationships between the audio data. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that accepts voice input, The summarization unit analyzes the audio data received by the reception unit and extracts and summarizes the important points, A conversion unit that converts the summary message created by the summarization unit into natural speech, The system includes a storage unit that stores the audio generated by the conversion unit as an answering machine message. A system characterized by the following features.

2. The aforementioned reception unit is Noise reduction and preprocessing of audio data The system according to feature 1.

3. The summary section above is, Using natural language processing techniques, keywords and important phrases are identified from audio data to create concise messages. The system according to feature 1.

4. The conversion unit is Using speech synthesis technology, we customize voice tone, speaking speed, and emotional expression to generate natural-sounding speech. The system according to feature 1.

5. The aforementioned storage unit is Compress and encode audio data and save it in an appropriate format. The system according to feature 1.

6. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. The system according to feature 1.

7. The aforementioned reception unit is When performing noise reduction or preprocessing on audio data, the system analyzes the user's past voice input history to select the optimal preprocessing method. The system according to feature 1.

8. The aforementioned reception unit is During voice input, the system analyzes the user's current ambient noise in real time to improve the accuracy of noise reduction. The system according to feature 1.

9. The aforementioned reception unit is It estimates the user's emotions and determines the priority of voice input based on the estimated emotions. The system according to feature 1.

10. The aforementioned reception unit is During voice input, the system prioritizes processing of highly relevant voice data based on the user's geographical location. The system according to feature 1.

Images