System

Abstract

An object of a system according to an embodiment is to analyze a voice input and convert the voice input into a natural and beautiful sentence.SOLUTION: A system includes a speech analysis part, an unnecessary part removal part, a punctuation insertion part, a grammar correction part, an expression conversion part, and a style correction part. The voice analysis unit analyzes a voice input. The unnecessary portion removal unit removes an unnecessary portion from the voice input analyzed by the voice analysis unit. The punctuation insertion unit inserts a punctuation mark into the speech input removed by the unnecessary portion removal unit. The grammar correction unit corrects grammar of the speech input including the punctuation inserted by the punctuation insertion unit. An expression conversion part converts the expression of the voice input including the grammar corrected by the grammar correction part. The style correction part corrects the style of the voice input including the expression converted by the expression conversion part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have difficulty generating natural and beautiful sentences from speech input, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze voice input and convert it into natural and beautiful sentences. [Means for solving the problem]

[0006] A system according to an embodiment includes a speech analysis unit, an unnecessary portion removal unit, a punctuation insertion unit, a grammar correction unit, an expression conversion unit, and a style correction unit. The speech analysis unit analyzes a speech input. The unnecessary portion removal unit removes unnecessary portions from the speech input analyzed by the speech analysis unit. The punctuation insertion unit inserts punctuation into the speech input removed by the unnecessary portion removal unit. The grammar correction unit corrects the grammar of the speech input including the punctuation inserted by the punctuation insertion unit. The expression conversion unit converts the expression of the speech input including the grammar corrected by the grammar correction unit. The style correction unit corrects the style of the speech input including the expression converted by the expression conversion unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze voice input and convert it into natural and beautiful sentences. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The assistant tool according to the embodiment of the present invention is a system that converts speech input into natural Japanese using the power of AI and outputs it as beautiful sentences in real time. This allows the assistant tool to generate beautiful sentences in real time through speech input.

[0029] The assistant tool according to the embodiment includes a speech analysis unit, an unnecessary part removal unit, a punctuation insertion unit, a grammar correction unit, an expression conversion unit, and a style correction unit. The speech analysis unit analyzes speech input. For example, the speech analysis unit analyzes speech data spoken by a user in real time. The speech analysis unit can also analyze recorded speech files. The speech analysis unit can also analyze real-time input from a microphone. The unnecessary part removal unit removes unnecessary parts from the speech input analyzed by the speech analysis unit. For example, the unnecessary part removal unit removes silent parts such as "uh-huh" and repetitive words. The unnecessary part removal unit can also remove meaningless speech. The unnecessary part removal unit can also estimate the speaker's emotions using a generation AI and remove unnecessary parts according to the emotion. The punctuation insertion unit inserts punctuation into the speech input removed by the unnecessary part removal unit. For example, the punctuation insertion unit inserts periods and commas in appropriate positions. The punctuation insertion unit can also insert exclamation marks and question marks. The punctuation insertion unit can also analyze context and automatically insert not only appropriate punctuation but also appropriate line breaks. The grammar correction unit corrects the grammar of the speech input including the punctuation inserted by the punctuation insertion unit. For example, the grammar correction unit corrects subject-predicate agreement. The grammar correction unit can also correct tense agreement. The grammar correction unit can also estimate the speaker's emotions using generative AI and correct grammar and expressions according to the emotions. The expression conversion unit converts the expressions of the speech input including the grammar corrected by the grammar correction unit. For example, the expression conversion unit converts to formal expressions. The expression conversion unit can also convert to concise expressions. The expression conversion unit can also learn the speaker's past speech data and reflect that person's unique phrasing and style. The style correction unit corrects the style of the speech input including the expressions converted by the expression conversion unit. For example, the style correction unit corrects to a casual style. The style correction unit can also correct the writing style to a more formal one.The style correction unit can also use a generative AI to estimate the speaker's emotions and correct the writing style according to the emotions.As a result, the assistant tool according to the embodiment can generate beautiful sentences in real time by analyzing the voice input, removing unnecessary parts, inserting punctuation, correcting grammar, converting expressions, and correcting writing style. For example, it can be used in a variety of situations, such as creating meeting minutes or writing blog articles.

[0030] The unnecessary part removal unit can analyze background sounds of voice input and automatically remove specific noises. For example, when voice input is performed, the generation AI analyzes background sounds and automatically removes keyboard keystroke sounds. For example, if a user is typing while speaking, the keystroke sounds are filtered to output clear voice. This removes background noise, enabling clear voice input.

[0031] The unnecessary part removal unit can analyze the speaker's speaking speed and rhythm and generate sentences at a natural tempo. For example, if a speaker speaks quickly, the generation AI inserts appropriate pauses to generate sentences at a natural tempo. Specifically, if a fast-speaking speaker says, "The weather is nice today. How about tomorrow?", the AI ​​outputs "The weather is nice today. How about tomorrow?" This makes it possible to generate sentences at a natural tempo based on the speaking speed and rhythm.

[0032] The voice analysis unit can link the analysis results of the voice input with other devices and provide feedback in real time. For example, the voice analysis unit can link the analysis results of the voice input with a smartwatch and provide feedback in real time. For example, when a user speaks into a smartwatch, the generation AI displays the analysis results on the smartwatch screen. This allows the analysis results of the voice input to be linked with other devices and provide feedback in real time.

[0033] The unnecessary part removal unit can be provided with a multilingual support function that simultaneously analyzes voice inputs in different languages ​​and removes unnecessary parts. The unnecessary part removal unit adds a multilingual support function that simultaneously analyzes voice inputs in different languages ​​and removes unnecessary parts, for example. For example, voice inputs in English and Japanese are simultaneously analyzed, and unnecessary parts are removed and output. This makes it possible to simultaneously analyze voice inputs in different languages ​​and remove unnecessary parts.

[0034] The punctuation insertion unit can analyze the context and automatically insert not only appropriate punctuation marks but also appropriate line break positions. For example, the punctuation insertion unit analyzes the context and automatically inserts not only appropriate punctuation marks but also appropriate line break positions. For example, it breaks long sentences at appropriate positions to make them easier to read. Specifically, it breaks the sentence "The weather is nice today. What about tomorrow?" and outputs it. This allows appropriate punctuation marks and line break positions to be automatically inserted based on the context.

[0035] The punctuation mark insertion unit can analyze the rhythm and intonation of a speaker's speech and insert punctuation marks based on the results. For example, the punctuation mark insertion unit can analyze the rhythm of a speaker's speech and insert punctuation marks based on the results. For example, the punctuation mark insertion unit can insert punctuation marks when the speaker takes a breath. Specifically, the unit can output "The weather is nice today." This allows punctuation marks to be inserted based on the rhythm and intonation of speech.

[0036] The punctuation insertion unit can work with other text generation tools to instantly reflect the results of punctuation insertion. For example, the punctuation insertion unit can work with an email creation tool to instantly reflect the results of punctuation insertion. For example, the punctuation inserted by the generation AI can be reflected in the email body. Specifically, the email body can reflect something like, "The weather is nice today. How about tomorrow?" This allows the results of punctuation insertion to be instantly reflected in work with other text generation tools.

[0037] The punctuation mark insertion unit can accommodate the punctuation rules of different languages ​​and have a multilingual automatic punctuation mark insertion function. For example, the punctuation mark insertion unit accommodates the punctuation rules of different languages ​​and adds a multilingual automatic punctuation mark insertion function. For example, it inserts appropriate punctuation marks into English sentences. Specifically, it outputs "Today is a good day." This allows for compatibility with the punctuation rules of different languages ​​and automatic punctuation mark insertion in multiple languages.

[0038] The grammar correction unit learns the speaker's past speech data and can reflect that person's unique phrasing and style. For example, the generation AI learns the speaker's frequently used phrases and reflects them in the sentence. Specifically, it corrects "I went to the movies yesterday" to "Yesterday, I went to the movies." This allows the unit to learn the speaker's past speech data and reflect that person's unique phrasing and style.

[0039] The grammar correction unit generates more natural sentences by deeply analyzing the context and automatically completing related information. For example, if a speaker says, "I went to the movies yesterday," the generation AI will output the completion as, "I went to the movies yesterday. It was very interesting." This allows for a deep analysis of the context and automatic completion of related information, resulting in the generation of more natural sentences.

[0040] The grammar correction unit can work with other text generation tools to instantly reflect the results of grammar and expression corrections. For example, the grammar correction unit can work with a blog creation tool to instantly reflect the results of grammar and expression corrections. For example, the sentence corrected by the generation AI can be reflected in a blog post. Specifically, the blog post can reflect "Yesterday, I went to the movies." This allows the results of grammar and expression corrections to be instantly reflected in collaboration with other text generation tools.

[0041] The grammar correction unit can accommodate the grammar rules of different languages ​​and have a function for correcting grammar and expressions in multiple languages. For example, the grammar correction unit can accommodate the grammar rules of different languages ​​and add a function for correcting grammar and expressions in multiple languages. For example, it can perform appropriate grammar correction on an English sentence. Specifically, it can output "I went to see a movie yesterday." This makes it possible to accommodate the grammar rules of different languages ​​and correct grammar and expressions in multiple languages.

[0042] The style correction unit can learn the speaker's past correction history and reflect style correction patterns specific to that person. For example, the style correction unit learns the speaker's past correction history and reflects style correction patterns specific to that person. For example, the generation AI learns the style that the speaker often uses and reflects it in the sentence. Specifically, it corrects "Yesterday, I went to see a movie" to "Yesterday, I watched a movie." This allows the unit to learn the speaker's past correction history and reflect style correction patterns specific to that person.

[0043] The style correction unit performs a deep analysis of the context and automatically completes related information, thereby enabling more natural style correction. For example, if a speaker says, "Yesterday, I went to the movies," the generation AI will complete and output "Yesterday, I went to the movies. It was very interesting." This allows for a deep analysis of the context and automatically completes related information, enabling more natural style correction.

[0044] The style correction unit can work with other text generation tools to instantly reflect the results of style correction. The style correction unit can work with, for example, a report creation tool to instantly reflect the results of style correction. For example, the sentence corrected by the generation AI is reflected in the body of the report. Specifically, "Yesterday, I went to the movies." is reflected in the body of the report. This allows the results of style correction to be reflected instantly in work with other text generation tools.

[0045] The style correction unit can accommodate the style rules of different languages ​​and have a style correction function in multiple languages. For example, the style correction unit accommodates the style rules of different languages ​​and adds a style correction function in multiple languages. For example, it performs appropriate style correction on English sentences. Specifically, it outputs "I went to see a movie yesterday." This makes it possible to accommodate the style rules of different languages ​​and perform style correction in multiple languages.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The assistant tool can analyze the content of the user's speech and automatically search for and provide related information. For example, if a user says, "What's the weather like tomorrow?", the generation AI can automatically search for and provide the weather forecast. Also, if a user says, "What time is the next meeting?", it can search for and provide calendar information. This makes it possible to automatically provide related information based on the content of the user's speech.

[0048] The assistant tool can analyze the content of the user's utterance and generate sentences in an appropriate style. For example, if the user is having a casual conversation, the generation AI can generate sentences in a casual style. Conversely, if the user is having a formal conversation, it can also generate sentences in a formal style. This makes it possible to generate sentences in an appropriate style based on the content of the user's utterance.

[0049] The assistant tool can analyze the user's speech and provide appropriate background information. For example, if a user says, "Tell me about this project," the generative AI can provide an overview of the project. Or, if a user says, "Tell me about this person," it can provide a profile of that person. This makes it possible to provide appropriate background information based on the user's speech.

[0050] The assistant tool can analyze the user's speech and suggest appropriate actions. For example, if the user says, "I'm tired," the generation AI can suggest, "Let's take a short break." Or, if the user says, "I'm hungry," it can suggest, "Let's search for a nearby restaurant." This makes it possible to suggest appropriate actions based on the user's speech.

[0051] The assistant tool can analyze the user's speech and set appropriate reminders. For example, if the user says, "Don't forget about tomorrow's meeting," the generative AI can set a reminder. Also, if the user says, "Tell me when to take my medicine," it can remind the user to take their medicine. This makes it possible to set appropriate reminders based on the user's speech.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The voice analysis unit analyzes the voice input. For example, it analyzes the voice data spoken by the user in real time. It can also analyze recorded voice files and real-time input from a microphone. Step 2: The unnecessary part removal unit removes unnecessary parts from the voice input analyzed by the voice analysis unit. For example, it removes silent parts such as "uh-huh," repeated words, and meaningless sounds. It can also use generative AI to estimate the speaker's emotions and remove unnecessary parts according to their emotions. Step 3: The punctuation inserter inserts punctuation marks into the speech input that has been removed by the garbage collector. For example, it inserts periods, commas, exclamation marks, and question marks in the appropriate positions. It can also analyze the context and automatically insert appropriate line breaks. Step 4: The grammar correction unit corrects the grammar of the speech input, including the punctuation inserted by the punctuation insertion unit. For example, it corrects subject-predicate agreement and tense agreement. It can also use generation AI to estimate the speaker's emotions and correct grammar and expressions accordingly. Step 5: The expression conversion unit converts the speech input, including the grammar corrected by the grammar correction unit. For example, it converts it into a more formal or concise expression. It can also learn from the speaker's past speech data and reflect that person's unique phrasing and style. Step 6: The style correction unit corrects the style of the speech input, including the expressions converted by the expression conversion unit. For example, it may correct the style to a more casual or formal style. It can also use generation AI to estimate the speaker's emotions and correct the style accordingly.

[0054] (Example 2) The assistant tool according to the embodiment of the present invention is a system that converts speech input into natural Japanese using the power of AI and outputs it as beautiful sentences in real time. This allows the assistant tool to generate beautiful sentences in real time through speech input.

[0055] The assistant tool according to the embodiment includes a speech analysis unit, an unnecessary part removal unit, a punctuation insertion unit, a grammar correction unit, an expression conversion unit, and a style correction unit. The speech analysis unit analyzes speech input. For example, the speech analysis unit analyzes speech data spoken by a user in real time. The speech analysis unit can also analyze recorded speech files. The speech analysis unit can also analyze real-time input from a microphone. The unnecessary part removal unit removes unnecessary parts from the speech input analyzed by the speech analysis unit. For example, the unnecessary part removal unit removes silent parts such as "uh-huh" and repetitive words. The unnecessary part removal unit can also remove meaningless speech. The unnecessary part removal unit can also estimate the speaker's emotions using a generation AI and remove unnecessary parts according to the emotion. The punctuation insertion unit inserts punctuation into the speech input removed by the unnecessary part removal unit. For example, the punctuation insertion unit inserts periods and commas in appropriate positions. The punctuation insertion unit can also insert exclamation marks and question marks. The punctuation insertion unit can also analyze context and automatically insert not only appropriate punctuation but also appropriate line breaks. The grammar correction unit corrects the grammar of the speech input including the punctuation inserted by the punctuation insertion unit. For example, the grammar correction unit corrects subject-predicate agreement. The grammar correction unit can also correct tense agreement. The grammar correction unit can also estimate the speaker's emotions using generative AI and correct grammar and expressions according to the emotions. The expression conversion unit converts the expressions of the speech input including the grammar corrected by the grammar correction unit. For example, the expression conversion unit converts to formal expressions. The expression conversion unit can also convert to concise expressions. The expression conversion unit can also learn the speaker's past speech data and reflect that person's unique phrasing and style. The style correction unit corrects the style of the speech input including the expressions converted by the expression conversion unit. For example, the style correction unit corrects to a casual style. The style correction unit can also correct the writing style to a more formal one.The style correction unit can also use a generative AI to estimate the speaker's emotions and correct the writing style according to the emotions.As a result, the assistant tool according to the embodiment can generate beautiful sentences in real time by analyzing the voice input, removing unnecessary parts, inserting punctuation, correcting grammar, converting expressions, and correcting writing style. For example, it can be used in a variety of situations, such as creating meeting minutes or writing blog articles.

[0056] The unnecessary part removal unit uses the generation AI to estimate the speaker's emotions and can remove unnecessary parts according to their emotions. For example, when a voice is input, the generation AI analyzes the speaker's emotions in real time, and if the speaker is nervous, it will prioritize removing unnecessary parts such as "umm" and "hmm." For example, it can analyze the voice of a speaker who is nervous during a presentation and automatically remove unnecessary interjections. This makes it possible to remove unnecessary parts according to the speaker's emotions.

[0057] The unnecessary part removal unit can analyze background sounds of voice input and automatically remove specific noises. For example, when voice input is performed, the generation AI analyzes background sounds and automatically removes keyboard keystroke sounds. For example, if a user is typing while speaking, the keystroke sounds are filtered to output clear voice. This removes background noise, enabling clear voice input.

[0058] The unnecessary part removal unit can analyze the speaker's speaking speed and rhythm and generate sentences at a natural tempo. For example, if a speaker speaks quickly, the generation AI inserts appropriate pauses to generate sentences at a natural tempo. Specifically, if a fast-speaking speaker says, "The weather is nice today. How about tomorrow?", the AI ​​outputs "The weather is nice today. How about tomorrow?" This makes it possible to generate sentences at a natural tempo based on the speaking speed and rhythm.

[0059] The voice analysis unit can link the analysis results of the voice input with other devices and provide feedback in real time. For example, the voice analysis unit can link the analysis results of the voice input with a smartwatch and provide feedback in real time. For example, when a user speaks into a smartwatch, the generation AI displays the analysis results on the smartwatch screen. This allows the analysis results of the voice input to be linked with other devices and provide feedback in real time.

[0060] The unnecessary part removal unit can be provided with a multilingual support function that simultaneously analyzes voice inputs in different languages ​​and removes unnecessary parts. The unnecessary part removal unit adds a multilingual support function that simultaneously analyzes voice inputs in different languages ​​and removes unnecessary parts, for example. For example, voice inputs in English and Japanese are simultaneously analyzed, and unnecessary parts are removed and output. This makes it possible to simultaneously analyze voice inputs in different languages ​​and remove unnecessary parts.

[0061] The unnecessary part removal unit uses the emotion estimation function to provide feedback in real time according to the speaker's emotion, making it possible to elicit positive emotions. The unnecessary part removal unit, for example, uses the emotion estimation function to provide feedback in real time according to the speaker's emotion. For example, if the speaker is nervous, the generation AI provides feedback to help them relax. Specifically, it provides voice feedback saying, "Please speak in a relaxed manner." This makes it possible to provide feedback in accordance with the speaker's emotion and elicit positive emotions.

[0062] The punctuation insertion unit can use the generation AI to estimate the speaker's emotions and insert punctuation marks according to the emotions. For example, if the speaker is excited, the generation AI will use exclamation marks frequently. Specifically, it will output "The weather is nice today!" This makes it possible to insert punctuation marks according to the speaker's emotions.

[0063] The punctuation insertion unit can analyze the context and automatically insert not only appropriate punctuation marks but also appropriate line break positions. For example, the punctuation insertion unit analyzes the context and automatically inserts not only appropriate punctuation marks but also appropriate line break positions. For example, it breaks long sentences at appropriate positions to make them easier to read. Specifically, it breaks the sentence "The weather is nice today. What about tomorrow?" and outputs it. This allows appropriate punctuation marks and line break positions to be automatically inserted based on the context.

[0064] The punctuation mark insertion unit can analyze the rhythm and intonation of a speaker's speech and insert punctuation marks based on the results. For example, the punctuation mark insertion unit can analyze the rhythm of a speaker's speech and insert punctuation marks based on the results. For example, the punctuation mark insertion unit can insert punctuation marks when the speaker takes a breath. Specifically, the unit can output "The weather is nice today." This allows punctuation marks to be inserted based on the rhythm and intonation of speech.

[0065] The punctuation insertion unit can work with other text generation tools to instantly reflect the results of punctuation insertion. For example, the punctuation insertion unit can work with an email creation tool to instantly reflect the results of punctuation insertion. For example, the punctuation inserted by the generation AI can be reflected in the email body. Specifically, the email body can reflect something like, "The weather is nice today. How about tomorrow?" This allows the results of punctuation insertion to be instantly reflected in work with other text generation tools.

[0066] The punctuation mark insertion unit can accommodate the punctuation rules of different languages ​​and have a multilingual automatic punctuation mark insertion function. For example, the punctuation mark insertion unit accommodates the punctuation rules of different languages ​​and adds a multilingual automatic punctuation mark insertion function. For example, it inserts appropriate punctuation marks into English sentences. Specifically, it outputs "Today is a good day." This allows for compatibility with the punctuation rules of different languages ​​and automatic punctuation mark insertion in multiple languages.

[0067] The punctuation insertion unit can use the emotion estimation function to suggest a punctuation style that corresponds to the speaker's emotion. For example, if the speaker is excited, the generation AI will use exclamation marks frequently. Specifically, it will output "The weather is nice today!" This allows it to suggest a punctuation style that corresponds to the speaker's emotion.

[0068] The grammar correction unit can estimate the speaker's emotions using the generation AI and modify grammar and expressions accordingly. For example, if the speaker is sad, the generation AI will use softer expressions. Specifically, it will modify "I went to the movies yesterday" to "Yesterday, I went to the movies." This makes it possible to modify grammar and expressions according to the speaker's emotions.

[0069] The grammar correction unit learns the speaker's past speech data and can reflect that person's unique phrasing and style. For example, the generation AI learns the speaker's frequently used phrases and reflects them in the sentence. Specifically, it corrects "I went to the movies yesterday" to "Yesterday, I went to the movies." This allows the unit to learn the speaker's past speech data and reflect that person's unique phrasing and style.

[0070] The grammar correction unit generates more natural sentences by deeply analyzing the context and automatically completing related information. For example, if a speaker says, "I went to the movies yesterday," the generation AI will output the completion as, "I went to the movies yesterday. It was very interesting." This allows for a deep analysis of the context and automatic completion of related information, resulting in the generation of more natural sentences.

[0071] The grammar correction unit can work with other text generation tools to instantly reflect the results of grammar and expression corrections. For example, the grammar correction unit can work with a blog creation tool to instantly reflect the results of grammar and expression corrections. For example, the sentence corrected by the generation AI can be reflected in a blog post. Specifically, the blog post can reflect "Yesterday, I went to the movies." This allows the results of grammar and expression corrections to be instantly reflected in collaboration with other text generation tools.

[0072] The grammar correction unit can accommodate the grammar rules of different languages ​​and have a function for correcting grammar and expressions in multiple languages. For example, the grammar correction unit can accommodate the grammar rules of different languages ​​and add a function for correcting grammar and expressions in multiple languages. For example, it can perform appropriate grammar correction on an English sentence. Specifically, it can output "I went to see a movie yesterday." This makes it possible to accommodate the grammar rules of different languages ​​and correct grammar and expressions in multiple languages.

[0073] The grammar correction unit can use the emotion estimation function to suggest grammar and expression styles that correspond to the speaker's emotions. For example, if the speaker is nervous, the generation AI will suggest polite phrases. Specifically, it will correct "Yesterday, I went to see a movie" to "Yesterday, I watched a movie." This makes it possible to suggest grammar and expression styles that correspond to the speaker's emotions.

[0074] The style correction unit can estimate the speaker's emotions using the generation AI and correct the style according to the emotions. For example, if the speaker is happy, the generation AI will change the style to a brighter one. Specifically, it will correct "Yesterday, I went to the movies" to "Yesterday, I enjoyed the movie." This makes it possible to correct the style according to the speaker's emotions.

[0075] The style correction unit can learn the speaker's past correction history and reflect style correction patterns specific to that person. For example, the style correction unit learns the speaker's past correction history and reflects style correction patterns specific to that person. For example, the generation AI learns the style that the speaker often uses and reflects it in the sentence. Specifically, it corrects "Yesterday, I went to see a movie" to "Yesterday, I watched a movie." This allows the unit to learn the speaker's past correction history and reflect style correction patterns specific to that person.

[0076] The style correction unit performs a deep analysis of the context and automatically completes related information, thereby enabling more natural style correction. For example, if a speaker says, "Yesterday, I went to the movies," the generation AI will complete and output "Yesterday, I went to the movies. It was very interesting." This allows for a deep analysis of the context and automatically completes related information, enabling more natural style correction.

[0077] The style correction unit can work with other text generation tools to instantly reflect the results of style correction. The style correction unit can work with, for example, a report creation tool to instantly reflect the results of style correction. For example, the sentence corrected by the generation AI is reflected in the body of the report. Specifically, "Yesterday, I went to the movies." is reflected in the body of the report. This allows the results of style correction to be reflected instantly in work with other text generation tools.

[0078] The style correction unit can accommodate the style rules of different languages ​​and have a style correction function in multiple languages. For example, the style correction unit accommodates the style rules of different languages ​​and adds a style correction function in multiple languages. For example, it performs appropriate style correction on English sentences. Specifically, it outputs "I went to see a movie yesterday." This makes it possible to accommodate the style rules of different languages ​​and perform style correction in multiple languages.

[0079] The style correction unit can use the emotion estimation function to suggest a style of writing that matches the emotion of the speaker. For example, if the speaker is nervous, the generation AI suggests a formal style of writing. Specifically, it corrects "Yesterday, I went to the movies" to "Yesterday, I watched a movie." This makes it possible to suggest a style of writing that matches the emotion of the speaker.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] The assistant tool can analyze the user's tone of voice and provide appropriate feedback. For example, if the user is tired, the generative AI can suggest, "Please take a short break." If the user is excited, the AI ​​can also provide feedback such as, "Please speak calmly." This makes it possible to provide appropriate feedback based on the user's tone of voice.

[0082] The assistant tool can analyze the content of the user's speech and automatically search for and provide related information. For example, if a user says, "What's the weather like tomorrow?", the generation AI can automatically search for and provide the weather forecast. Also, if a user says, "What time is the next meeting?", it can search for and provide calendar information. This makes it possible to automatically provide related information based on the content of the user's speech.

[0083] The assistant tool can analyze the user's speaking speed and provide feedback at an appropriate speed. For example, if the user is speaking too quickly, the generation AI can suggest, "Please speak a little more slowly." Also, if the user is speaking too slowly, the AI ​​can provide feedback such as, "Please speak a little faster." This makes it possible to provide appropriate feedback based on the user's speaking speed.

[0084] The assistant tool can analyze the content of the user's utterance and generate sentences in an appropriate style. For example, if the user is having a casual conversation, the generation AI can generate sentences in a casual style. Conversely, if the user is having a formal conversation, it can also generate sentences in a formal style. This makes it possible to generate sentences in an appropriate style based on the content of the user's utterance.

[0085] The assistant tool can analyze the content of the user's speech and provide feedback at the appropriate time. For example, if the user asks a question, the generative AI can provide an immediate answer. Also, if the user has been talking for a long time, it can suggest, "Let's take a short break." This makes it possible to provide feedback at the appropriate time based on the content of the user's speech.

[0086] The assistant tool can analyze the user's speech and provide appropriate background information. For example, if a user says, "Tell me about this project," the generative AI can provide an overview of the project. Or, if a user says, "Tell me about this person," it can provide a profile of that person. This makes it possible to provide appropriate background information based on the user's speech.

[0087] The assistant tool can estimate the user's emotions and play music that corresponds to the emotion. For example, if the user wants to relax, the AI ​​generator will play relaxing music. If the user wants to concentrate, it can also play music that helps improve concentration. This makes it possible to provide music that corresponds to the user's emotions.

[0088] The assistant tool can analyze the user's speech and suggest appropriate actions. For example, if the user says, "I'm tired," the generation AI can suggest, "Let's take a short break." Or, if the user says, "I'm hungry," it can suggest, "Let's search for a nearby restaurant." This makes it possible to suggest appropriate actions based on the user's speech.

[0089] The assistant tool can analyze the user's speech and set appropriate reminders. For example, if the user says, "Don't forget about tomorrow's meeting," the generative AI can set a reminder. Also, if the user says, "Tell me when to take my medicine," it can remind the user to take their medicine. This makes it possible to set appropriate reminders based on the user's speech.

[0090] The assistant tool can estimate the user's emotions and send messages according to their emotions. For example, if the user is sad, the generation AI can send a message saying "Cheer up." If the user is happy, it can also send a message saying "Congratulations." This makes it possible to provide messages according to the user's emotions.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The voice analysis unit analyzes the voice input. For example, it analyzes the voice data spoken by the user in real time. It can also analyze recorded voice files and real-time input from a microphone. Step 2: The unnecessary part removal unit removes unnecessary parts from the voice input analyzed by the voice analysis unit. For example, it removes silent parts such as "uh-huh," repeated words, and meaningless sounds. It can also use generative AI to estimate the speaker's emotions and remove unnecessary parts according to their emotions. Step 3: The punctuation inserter inserts punctuation marks into the speech input that has been removed by the garbage collector. For example, it inserts periods, commas, exclamation marks, and question marks in the appropriate positions. It can also analyze the context and automatically insert appropriate line breaks. Step 4: The grammar correction unit corrects the grammar of the speech input, including the punctuation inserted by the punctuation insertion unit. For example, it corrects subject-predicate agreement and tense agreement. It can also use generation AI to estimate the speaker's emotions and correct grammar and expressions accordingly. Step 5: The expression conversion unit converts the speech input, including the grammar corrected by the grammar correction unit. For example, it converts it into a more formal or concise expression. It can also learn from the speaker's past speech data and reflect that person's unique phrasing and style. Step 6: The style correction unit corrects the style of the speech input, including the expressions converted by the expression conversion unit. For example, it may correct the style to a more casual or formal style. It can also use generation AI to estimate the speaker's emotions and correct the style accordingly.

[0093] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0094] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0095] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0096] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0097] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0098] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0099] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0100] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0101] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0102] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0103] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0104] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0105] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0106] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0107] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0109] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0111] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0112] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0121] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0127] 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.

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

[0129] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0134] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0137] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0143] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0144] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0145] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0146] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0147] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0148] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0149] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0150] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0151] 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.

[0152] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0153] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0154] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0155] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0156] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0157] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0158] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0159] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0160] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a voice analysis unit that analyzes voice input; an unnecessary portion removal unit that removes unnecessary portions from the voice input analyzed by the voice analysis unit; a punctuation insertion unit that inserts punctuation into the speech input removed by the unnecessary portion removal unit; a grammar correction unit that corrects the grammar of the speech input including the punctuation marks inserted by the punctuation mark insertion unit; an expression conversion unit that converts an expression of the speech input including the grammar corrected by the grammar correction unit; a style correction unit that corrects the style of the speech input including the expression converted by the expression conversion unit. system.

2. The voice analysis unit The analysis results of the voice input are linked to other devices to provide real-time feedback.

2. The system of claim 1.

3. The unnecessary part removal unit Equipped with a multilingual function that simultaneously analyzes voice input in different languages ​​and removes unnecessary parts 2. The system of claim 1.

4. The punctuation insertion unit Analyzes the context and automatically inserts appropriate punctuation as well as line breaks 2. The system of claim 1.

5. The grammar correction unit Generative AI estimates the speaker's emotions and modifies grammar and expressions according to those emotions.

2. The system of claim 1.

6. The style correction unit Generative AI estimates the speaker's emotions and modifies the writing style accordingly 2. The system of claim 1.

7. The unnecessary part removal unit The speaker's emotions are estimated using generative AI, and unnecessary parts are removed according to those emotions.

2. The system of claim 1.

8. The punctuation insertion unit The speaker's emotions are estimated using generative AI, and punctuation is inserted according to the emotions.

2. The system of claim 1.

Images