System

Abstract

An object of a system according to an embodiment is to analyze voice in real time and propose an appropriate comment or keyword.SOLUTION: A system according to an embodiment includes a voice analysis unit, a context understanding unit, and a comment suggestion unit. The voice analysis unit analyzes the voice from the microphone in real time. The context understanding unit understands a context based on the voice data analyzed by the voice analysis unit. The comment proposing unit proposes an appropriate comment or keyword based on the context understood by the context understanding unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that it is difficult to analyze speech in real time and suggest appropriate comments and keywords.

[0005] The system according to the embodiment aims to analyze speech in real time and suggest appropriate comments and keywords. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice analysis unit, a context understanding unit, and a comment suggestion unit. The voice analysis unit analyzes voice from a microphone in real time. The context understanding unit understands the context based on the voice data analyzed by the voice analysis unit. The comment suggestion unit suggests appropriate comments and keywords based on the context understood by the context understanding unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze voice in real time and suggest appropriate comments and keywords. [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 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 AI ​​speech supporter according to an embodiment of the present invention is a system that analyzes audio from a microphone in real time, and uses a generation AI to suggest appropriate comments and keywords based on the context. This allows the AI ​​speech supporter to resolve situations where a person is suddenly asked to speak, thereby enabling smooth communication.

[0029] The AI ​​speech supporter according to the embodiment includes a voice analysis unit, a context understanding unit, and a comment suggestion unit. The voice analysis unit analyzes voice from a microphone in real time. For example, the voice analysis unit converts voice into text using a voice recognition algorithm. The voice analysis unit can also clean the voice data using noise reduction technology. The voice analysis unit can also analyze the frequency characteristics of the voice and extract speaker characteristics. For example, the voice analysis unit converts voice into text with high accuracy using a voice recognition algorithm. The noise reduction technology effectively removes background noise and provides clear voice data. Analyzing the frequency characteristics of the voice can grasp the speaker's voice characteristics in detail. The context understanding unit understands the context based on the voice data analyzed by the voice analysis unit. For example, the context understanding unit analyzes the flow of the conversation using natural language processing technology. The context understanding unit can also understand the intention of the utterance using a semantic analysis algorithm. The context understanding unit can also extract the theme or topic of the conversation. For example, the natural language processing technology analyzes the context of the conversation and understands the intention of the utterance. The semantic analysis algorithm analyzes the content of utterances in detail and generates appropriate responses. Extracting themes and topics of the conversation makes it easier to understand the flow of the conversation. The comment suggestion unit suggests appropriate comments and keywords based on the context understood by the context understanding unit. For example, the comment suggestion unit suggests important keywords using keyword extraction technology. The comment suggestion unit can also suggest comments based on appropriate comment selection criteria. The comment suggestion unit can also suggest comments in real time that match the flow of the conversation. For example, keyword extraction technology extracts important keywords in a conversation and generates appropriate comments. Comments that match the flow of the conversation are suggested based on appropriate comment selection criteria. Suggesting comments in real time that match the flow of the conversation supports smooth communication. As a result, the AI ​​speech supporter according to the embodiment can resolve situations where a person is suddenly asked to speak and can achieve smooth communication.For example, when participants are asked to speak during an online meeting, the AI ​​can suggest appropriate comments and keywords, allowing them to speak with confidence. In the future, it is expected that the AI ​​will also support speech in a variety of situations, such as weddings, funerals, and social gatherings.

[0030] The audio analysis unit can analyze background sounds and environmental sounds included in the audio data and determine the appropriate timing to speak. The audio analysis unit, for example, analyzes background sounds and environmental sounds included in the audio data and determines the appropriate timing to speak. For example, it can encourage a participant to speak at a time when there is less noise in the conference room. The audio analysis unit can also detect specific sounds and determine the timing to speak based on those sounds. For example, it can detect when other participants have finished speaking during a conference and encourage a participant to speak at that time. The audio analysis unit can also analyze the noise level of the audio data and encourage a participant to speak at a time when there is less noise. For example, it can detect when there is less external noise during a conference and encourage a participant to speak at that time. In this way, it is possible to determine the appropriate timing to speak by analyzing background sounds and environmental sounds.

[0031] The speech analysis unit can translate speech in different languages ​​in real time to support speech at international conferences. The speech analysis unit can, for example, use speech analysis technology to translate speech in different languages ​​in real time to support speech at international conferences. For example, it performs real-time translation from English to Japanese. The speech analysis unit can also analyze speech in different languages ​​and display the translation results as text data. For example, it can translate English speech spoken during a conference into Japanese and display the translation as text. The speech analysis unit can also analyze speech in different languages ​​and output the translation results as speech data. For example, it can translate English speech spoken during a conference into Japanese and output the translation as Japanese speech. This makes it possible to support speech at international conferences by translating speech in different languages ​​in real time.

[0032] The voice analysis unit can automatically summarize what is said based on the voice analysis results and generate meeting minutes. The voice analysis unit, for example, automatically summarizes what is said based on the voice analysis results and generates meeting minutes. For example, it extracts important points and generates a summary. The voice analysis unit can also analyze what is said and save the summary as text data. For example, it can summarize what is said during a meeting in real time and save it as text data. The voice analysis unit can also automatically generate meeting minutes based on the summary. For example, it can summarize what is said during a meeting and organize it as minutes. In this way, it is possible to automatically summarize what is said and generate meeting minutes.

[0033] The context understanding unit can analyze the flow of conversation and suggest consistent comments by referring to past utterances. The context understanding unit, for example, analyzes the flow of conversation and suggests consistent comments by referring to past utterances. For example, it suggests comments based on utterances made in a previous meeting. The context understanding unit can also analyze the flow of conversation and search past utterances to suggest appropriate comments. For example, it searches past utterance histories and suggests related comments. The context understanding unit can also analyze the flow of conversation and suggest comments that maintain the consistency of the conversation based on past utterances. For example, it suggests comments related to the agenda of the previous meeting. In this way, it is possible to suggest consistent comments by referring to past utterances.

[0034] The context understanding unit can obtain the latest news and data related to the topic of the conversation in real time and suggest comments based on it. The context understanding unit, for example, obtains the latest news and data related to the topic of the conversation in real time and suggests comments based on it. For example, it generates comments based on data on the latest market trends. The context understanding unit can also obtain the latest news using a news API and suggest comments based on it. For example, it obtains the latest economic news using a news API and suggests related comments. The context understanding unit can also obtain the latest data using database access and suggest comments based on it. For example, it obtains the latest statistical data from a database and suggests comments based on it. This makes it possible to suggest comments based on the latest news and data.

[0035] The context understanding unit can use context analysis technology to suggest appropriate questions and comments during lessons in educational settings. The context understanding unit can, for example, use context analysis technology to suggest appropriate questions and comments during lessons in educational settings. For example, it suggests questions in line with the progress of the lesson. The context understanding unit can also analyze the content of the lesson and suggest questions to check comprehension. For example, it suggests questions to check comprehension based on the content of the lesson. The context understanding unit can also analyze the progress of the lesson and suggest advanced questions. For example, it suggests questions related to advanced content in line with the progress of the lesson. This makes it possible to suggest appropriate questions and comments during lessons in educational settings.

[0036] The comment suggestion unit can apply the context-based comment suggestion function to a customer support chatbot to enhance customer service. The comment suggestion unit can, for example, apply the context-based comment suggestion function to a customer support chatbot to enhance customer service. For example, it can suggest appropriate answers to customer questions. The comment suggestion unit can also refer to the customer's past inquiry history and suggest comments based on that. For example, it can suggest relevant answers based on the content of past inquiries. The comment suggestion unit can also analyze the customer's emotional state and suggest comments accordingly. For example, if a customer is dissatisfied, it can suggest an apologetic comment. By applying this to a customer support chatbot, customer service can be enhanced.

[0037] The context understanding unit can analyze the content of statements made during a meeting in real time, understand the speaker's intention, and suggest appropriate follow-up questions. The context understanding unit, for example, analyzes the content of statements made during a meeting in real time, understands the speaker's intention, and suggests appropriate follow-up questions. For example, if a speaker is talking about the progress of a project, it suggests questions about the next step. The context understanding unit can also analyze the content of statements and suggest questions to confirm additional information or to dig deeper. For example, if a speaker is proposing a new idea, it suggests follow-up questions to learn more about the details. The context understanding unit can also understand the speaker's intention and suggest follow-up questions that match the flow of the conversation. For example, if a speaker points out a problem, it suggests questions about the solution. This makes it possible to understand the speaker's intention and suggest appropriate follow-up questions.

[0038] The context understanding unit can analyze the progress of a meeting and make suggestions to support time management and the progress of agenda items. The context understanding unit, for example, analyzes the progress of a meeting in real time and makes suggestions to support time management and the progress of agenda items. For example, it may suggest moving on to the next agenda item if the meeting is likely to go over the scheduled time. The context understanding unit can also analyze the progress of a meeting and make suggestions to adjust the priority of agenda items. For example, it may suggest taking up important agenda items first. The context understanding unit can also analyze the progress of a meeting and make suggestions to optimize time allocation. For example, it may make suggestions to adjust the time allocation for each agenda item. In this way, the progress of a meeting can be analyzed and suggestions to support time management and the progress of agenda items can be made.

[0039] The voice analysis unit can automatically record the content of statements made in online conferences and build a database that can be searched later. The voice analysis unit, for example, automatically records the content of statements made in online conferences and builds a database that can be searched later. For example, the content of statements can be saved as text data, enabling keyword searches. The voice analysis unit can also analyze the content of statements, extract important points, and save them in a database. For example, the content of statements made during a conference can be analyzed in real time, extract important points, and save them in a database. The voice analysis unit can also build a database based on the content of statements and save them in a format that can be referenced later. For example, the content of statements made during a conference can be saved as text data, building a database that can be searched later. In this way, the content of statements made in online conferences can be automatically recorded and a database that can be searched later can be built.

[0040] The speech analysis unit can translate statements made during a meeting in real time to support communication between participants who speak different languages. The speech analysis unit, for example, translates statements made during a meeting in real time to support communication between participants who speak different languages. For example, it performs real-time translation from English to Japanese. The speech analysis unit can also analyze the content of statements and display the translation results as text data. For example, it can translate English speech made during a meeting into Japanese and display it as text. The speech analysis unit can also analyze the content of statements and output the translation results as audio data. For example, it can translate English speech made during a meeting into Japanese and output it as Japanese audio. This makes it possible to translate statements made during a meeting in real time to support communication between participants who speak different languages.

[0041] The context understanding unit can analyze the content of utterances made at ceremonial occasions and social gatherings, and suggest appropriate comments based on cultural background and manners. The context understanding unit can, for example, analyze the content of utterances made at ceremonial occasions and social gatherings, and suggest appropriate comments based on cultural background and manners. For example, it can suggest comments that are suitable for a speech at a wedding. The context understanding unit can also analyze the content of utterances and suggest comments that are based on cultural background. For example, it can suggest comments that are suitable for a eulogy at a funeral. The context understanding unit can also analyze the content of utterances and suggest comments that are based on manners. For example, it can suggest comments that are suitable for a self-introduction at a social gathering. In this way, it is possible to analyze the content of utterances made at ceremonial occasions and social gatherings, and suggest appropriate comments based on cultural background and manners.

[0042] The context understanding unit can analyze comments made at large-scale events in real time, understand the speaker's intention, and provide appropriate follow-up. For example, the context understanding unit can analyze comments made at large-scale events in real time, understand the speaker's intention, and provide appropriate follow-up. For example, if the speaker is proposing a new idea, the unit can follow up on the details. The context understanding unit can also analyze the content of comments to confirm additional information or ask probing questions. For example, if the speaker points out a problem, the unit can follow up on the solution. The context understanding unit can also understand the speaker's intention and provide follow-up according to the flow of the conversation. For example, if the speaker is talking about the progress of a project, the unit can follow up on the next step. This makes it possible to analyze comments made at large-scale events in real time, understand the speaker's intention, and provide appropriate follow-up.

[0043] The voice analysis unit can automatically record what is said at ceremonial occasions and social gatherings, and build a database that can be referenced later. The voice analysis unit can automatically record what is said at ceremonial occasions and social gatherings, and build a database that can be referenced later. For example, a speech at a wedding can be saved as text data and made searchable later. The voice analysis unit can also analyze what is said, extract important points, and save them in a database. For example, a eulogy at a funeral can be analyzed in real time, extract important points, and save them in a database. The voice analysis unit can also build a database based on what is said, and save them in a format that can be referenced later. For example, a self-introduction at a social gathering can be saved as text data, and a database that can be searched later can be built. In this way, what is said at ceremonial occasions and social gatherings can be automatically recorded, and a database that can be referenced later can be built.

[0044] The voice analysis unit can translate comments made during an event in real time to support communication between participants who speak different languages. The voice analysis unit, for example, translates comments made during an event in real time to support communication between participants who speak different languages. For example, it performs real-time translation from English to Japanese. The voice analysis unit can also analyze the content of comments and display the translation results as text data. For example, it can translate English speech made during an event into Japanese and display it as text. The voice analysis unit can also analyze the content of comments and output the translation results as voice data. For example, it can translate English speech made during an event into Japanese and output it as Japanese speech. This allows for real-time translation of comments made during an event to support communication between participants who speak different languages.

[0045] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0046] The audio analysis unit can analyze background and environmental sounds contained in the audio data to determine the appropriate timing to speak. For example, it can encourage a participant to speak at a time when there is less noise in the conference room. The audio analysis unit can also detect specific sounds and determine the timing to speak based on those sounds. For example, it can detect when other participants have finished speaking during a conference and encourage a participant to speak at that time. The audio analysis unit can also analyze the noise level of the audio data and encourage a participant to speak at a time when there is less noise. For example, it can detect when there is less external noise during a conference and encourage a participant to speak at that time. In this way, the appropriate timing to speak can be determined by analyzing background and environmental sounds.

[0047] The speech analysis unit can translate speech in different languages ​​in real time to support speech at international conferences. For example, speech analysis technology can be used to translate speech in different languages ​​in real time to support speech at international conferences. For example, real-time translation from English to Japanese is performed. The speech analysis unit can also analyze speech in different languages ​​and display the translation results as text data. For example, English speech spoken during a conference can be translated into Japanese and displayed as text. The speech analysis unit can also analyze speech in different languages ​​and output the translation results as speech data. For example, English speech spoken during a conference can be translated into Japanese and output as Japanese speech. This makes it possible to support speech at international conferences by translating speech in different languages ​​in real time.

[0048] The voice analysis unit can automatically summarize what is said based on the voice analysis results and generate meeting minutes. For example, the voice analysis unit can automatically summarize what is said based on the voice analysis results and generate meeting minutes. For example, it can extract important points and generate a summary. The voice analysis unit can also analyze what is said and save the summary as text data. For example, it can summarize what is said during a meeting in real time and save it as text data. The voice analysis unit can also automatically generate meeting minutes based on the summary. For example, it can summarize what is said during a meeting and organize it as minutes. In this way, it is possible to automatically summarize what is said and generate meeting minutes.

[0049] The context understanding unit can analyze the flow of conversation and suggest consistent comments by referring to past utterances. For example, the context understanding unit can analyze the flow of conversation and suggest consistent comments by referring to past utterances. For example, it can suggest comments based on utterances made in a previous meeting. The context understanding unit can also analyze the flow of conversation and search past utterances to suggest appropriate comments. For example, it can search past utterance histories to suggest related comments. The context understanding unit can also analyze the flow of conversation and suggest comments that maintain the consistency of the conversation based on past utterances. For example, it can suggest comments related to the agenda of the previous meeting. This makes it possible to suggest consistent comments by referring to past utterances.

[0050] The context understanding unit can obtain the latest news and data related to the conversation topic in real time and suggest comments based on it. For example, the context understanding unit can obtain the latest news and data related to the conversation topic in real time and suggest comments based on it. For example, the context understanding unit can generate comments based on data on the latest market trends. The context understanding unit can also obtain the latest news using a news API and suggest comments based on it. For example, the context understanding unit can obtain the latest economic news using a news API and suggest related comments. The context understanding unit can also obtain the latest data using database access and suggest comments based on it. For example, the context understanding unit can obtain the latest statistical data from a database and suggest comments based on it. This makes it possible to suggest comments based on the latest news and data.

[0051] The context understanding unit can use context analysis technology to suggest appropriate questions and comments during lessons in educational settings. For example, the context analysis technology can be used to suggest appropriate questions and comments during lessons in educational settings. For example, questions can be suggested in line with the progress of the lesson. The context understanding unit can also analyze the content of the lesson and suggest questions to check comprehension. For example, questions can be suggested to check comprehension based on the content of the lesson. The context understanding unit can also analyze the progress of the lesson and suggest advanced questions. For example, questions related to advanced content can be suggested in line with the progress of the lesson. This makes it possible to suggest appropriate questions and comments during lessons in educational settings.

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

[0053] Step 1: The voice analyzer analyzes the audio from the microphone in real time. For example, the voice analyzer can use a voice recognition algorithm to convert the audio into text. It can also clean the audio data using noise reduction technology and analyze the frequency characteristics of the audio to extract speaker characteristics. Step 2: The context understanding unit understands the context based on the speech data analyzed by the speech analysis unit. For example, it uses natural language processing technology to analyze the flow of the conversation and uses semantic analysis algorithms to understand the intent of what is being said. It can also extract themes and topics of the conversation. Step 3: The comment suggestion unit suggests appropriate comments and keywords based on the context understood by the context understanding unit. For example, it uses keyword extraction technology to suggest important keywords and suggests comments based on appropriate comment selection criteria. It can also suggest comments in real time based on the flow of the conversation.

[0054] (Example 2) The AI ​​speech supporter according to an embodiment of the present invention is a system that analyzes audio from a microphone in real time, and uses a generation AI to suggest appropriate comments and keywords based on the context. This allows the AI ​​speech supporter to resolve situations where a person is suddenly asked to speak, thereby enabling smooth communication.

[0055] The AI ​​speech supporter according to the embodiment includes a voice analysis unit, a context understanding unit, and a comment suggestion unit. The voice analysis unit analyzes voice from a microphone in real time. For example, the voice analysis unit converts voice into text using a voice recognition algorithm. The voice analysis unit can also clean the voice data using noise reduction technology. The voice analysis unit can also analyze the frequency characteristics of the voice and extract speaker characteristics. For example, the voice analysis unit converts voice into text with high accuracy using a voice recognition algorithm. The noise reduction technology effectively removes background noise and provides clear voice data. Analyzing the frequency characteristics of the voice can grasp the speaker's voice characteristics in detail. The context understanding unit understands the context based on the voice data analyzed by the voice analysis unit. For example, the context understanding unit analyzes the flow of the conversation using natural language processing technology. The context understanding unit can also understand the intention of the utterance using a semantic analysis algorithm. The context understanding unit can also extract the theme or topic of the conversation. For example, the natural language processing technology analyzes the context of the conversation and understands the intention of the utterance. The semantic analysis algorithm analyzes the content of utterances in detail and generates appropriate responses. Extracting themes and topics of the conversation makes it easier to understand the flow of the conversation. The comment suggestion unit suggests appropriate comments and keywords based on the context understood by the context understanding unit. For example, the comment suggestion unit suggests important keywords using keyword extraction technology. The comment suggestion unit can also suggest comments based on appropriate comment selection criteria. The comment suggestion unit can also suggest comments in real time that match the flow of the conversation. For example, keyword extraction technology extracts important keywords in a conversation and generates appropriate comments. Comments that match the flow of the conversation are suggested based on appropriate comment selection criteria. Suggesting comments in real time that match the flow of the conversation supports smooth communication. As a result, the AI ​​speech supporter according to the embodiment can resolve situations where a person is suddenly asked to speak and can achieve smooth communication.For example, when participants are asked to speak during an online meeting, the AI ​​can suggest appropriate comments and keywords, allowing them to speak with confidence. In the future, it is expected that the AI ​​will also support speech in a variety of situations, such as weddings, funerals, and social gatherings.

[0056] The voice analysis unit can analyze the tone and speed of a speaker's voice to estimate the speaker's emotions, such as nervousness or impatience, and suggest appropriate comments to the comment suggestion unit. The voice analysis unit, for example, analyzes the speaker's tone and speed in real time to estimate emotions, such as nervousness or impatience. For example, if the speaker's voice tone is high and the speed is fast, it can determine that the speaker is nervous and suggest a comment encouraging the speaker to relax. The voice analysis unit can also analyze changes in voice tone and speed to monitor changes in the speaker's emotions in real time. For example, if the voice tone suddenly changes, it can determine that the speaker is surprised and suggest a comment encouraging the speaker to relax. The voice analysis unit can also analyze patterns in voice tone and speed to grasp the speaker's emotional tendencies. For example, if the voice tone is low and the speed is slow, it can determine that the speaker is calm and suggest a positive comment. In this way, appropriate comments can be suggested according to the speaker's emotions, thereby alleviating tension and impatience.

[0057] The audio analysis unit can analyze background sounds and environmental sounds included in the audio data and determine the appropriate timing to speak. The audio analysis unit, for example, analyzes background sounds and environmental sounds included in the audio data and determines the appropriate timing to speak. For example, it can encourage a participant to speak at a time when there is less noise in the conference room. The audio analysis unit can also detect specific sounds and determine the timing to speak based on those sounds. For example, it can detect when other participants have finished speaking during a conference and encourage a participant to speak at that time. The audio analysis unit can also analyze the noise level of the audio data and encourage a participant to speak at a time when there is less noise. For example, it can detect when there is less external noise during a conference and encourage a participant to speak at that time. In this way, it is possible to determine the appropriate timing to speak by analyzing background sounds and environmental sounds.

[0058] The voice analysis unit can use the emotion estimation function to analyze the speaker's emotional state in real time and suggest comments that will elicit positive emotions from the speaker. The voice analysis unit, for example, can use the emotion estimation function to analyze the speaker's emotional state in real time and suggest comments that will elicit positive emotions. For example, if the speaker is nervous, it can suggest comments that encourage the speaker to relax. The voice analysis unit can also use the emotion estimation function to monitor changes in the speaker's emotions in real time and suggest positive comments at the appropriate time. For example, it can suggest encouraging comments when the speaker begins to calm down. The voice analysis unit can also use the emotion estimation function to grasp the speaker's emotional tendencies and suggest comments that will elicit long-term positive emotions. For example, it can continuously suggest positive comments so that the speaker can speak with confidence. In this way, by suggesting comments that elicit positive emotions from the speaker, the speaker can speak more smoothly.

[0059] The speech analysis unit can translate speech in different languages ​​in real time to support speech at international conferences. The speech analysis unit can, for example, use speech analysis technology to translate speech in different languages ​​in real time to support speech at international conferences. For example, it performs real-time translation from English to Japanese. The speech analysis unit can also analyze speech in different languages ​​and display the translation results as text data. For example, it can translate English speech spoken during a conference into Japanese and display the translation as text. The speech analysis unit can also analyze speech in different languages ​​and output the translation results as speech data. For example, it can translate English speech spoken during a conference into Japanese and output the translation as Japanese speech. This makes it possible to support speech at international conferences by translating speech in different languages ​​in real time.

[0060] The voice analysis unit can automatically summarize what is said based on the voice analysis results and generate meeting minutes. The voice analysis unit, for example, automatically summarizes what is said based on the voice analysis results and generates meeting minutes. For example, it extracts important points and generates a summary. The voice analysis unit can also analyze what is said and save the summary as text data. For example, it can summarize what is said during a meeting in real time and save it as text data. The voice analysis unit can also automatically generate meeting minutes based on the summary. For example, it can summarize what is said during a meeting and organize it as minutes. In this way, it is possible to automatically summarize what is said and generate meeting minutes.

[0061] The voice analysis unit can use the emotion estimation function to analyze the emotional state of all conference participants and make suggestions to optimize the progress of the conference. The voice analysis unit, for example, uses the emotion estimation function to analyze the emotional state of all conference participants and make suggestions to optimize the progress of the conference. For example, if a participant is tired, it suggests taking a break. The voice analysis unit can also use the emotion estimation function to monitor changes in the emotions of conference participants in real time and make suggestions to adjust the progress at an appropriate time. For example, if a participant is losing concentration, it makes a suggestion to change the agenda. The voice analysis unit can also use the emotion estimation function to grasp the emotional trends of conference participants and make suggestions to optimize the long-term progress plan. For example, it makes a suggestion to bring up important agenda items when participants are relaxed. In this way, the emotional state of all conference participants can be analyzed and suggestions to optimize the progress of the conference can be made.

[0062] The context understanding unit can analyze the flow of conversation and suggest consistent comments by referring to past utterances. The context understanding unit, for example, analyzes the flow of conversation and suggests consistent comments by referring to past utterances. For example, it suggests comments based on utterances made in a previous meeting. The context understanding unit can also analyze the flow of conversation and search past utterances to suggest appropriate comments. For example, it searches past utterance histories and suggests related comments. The context understanding unit can also analyze the flow of conversation and suggest comments that maintain the consistency of the conversation based on past utterances. For example, it suggests comments related to the agenda of the previous meeting. In this way, it is possible to suggest consistent comments by referring to past utterances.

[0063] The context understanding unit can obtain the latest news and data related to the topic of the conversation in real time and suggest comments based on it. The context understanding unit, for example, obtains the latest news and data related to the topic of the conversation in real time and suggests comments based on it. For example, it generates comments based on data on the latest market trends. The context understanding unit can also obtain the latest news using a news API and suggest comments based on it. For example, it obtains the latest economic news using a news API and suggests related comments. The context understanding unit can also obtain the latest data using database access and suggest comments based on it. For example, it obtains the latest statistical data from a database and suggests comments based on it. This makes it possible to suggest comments based on the latest news and data.

[0064] The emotion estimation function can analyze the atmosphere of a conversation and suggest comments that include appropriate humor or empathy. The emotion estimation function, for example, analyzes the atmosphere of a conversation and suggests comments that include appropriate humor or empathy. For example, if the conversation is tense, it will suggest comments that include humor. The emotion estimation function can also analyze the atmosphere of a conversation and suggest comments that show empathy. For example, if the speaker is sad, it will suggest comments that show empathy. The emotion estimation function can also analyze the atmosphere of a conversation and suggest comments that include humor or empathy at the appropriate time. For example, it will suggest comments that include humor when the conversation becomes relaxed. In this way, it is possible to suggest comments that include humor or empathy that are appropriate for the atmosphere of the conversation.

[0065] The context understanding unit can use context analysis technology to suggest appropriate questions and comments during lessons in educational settings. The context understanding unit can, for example, use context analysis technology to suggest appropriate questions and comments during lessons in educational settings. For example, it suggests questions in line with the progress of the lesson. The context understanding unit can also analyze the content of the lesson and suggest questions to check comprehension. For example, it suggests questions to check comprehension based on the content of the lesson. The context understanding unit can also analyze the progress of the lesson and suggest advanced questions. For example, it suggests questions related to advanced content in line with the progress of the lesson. This makes it possible to suggest appropriate questions and comments during lessons in educational settings.

[0066] The comment suggestion unit can apply the context-based comment suggestion function to a customer support chatbot to enhance customer service. The comment suggestion unit can, for example, apply the context-based comment suggestion function to a customer support chatbot to enhance customer service. For example, it can suggest appropriate answers to customer questions. The comment suggestion unit can also refer to the customer's past inquiry history and suggest comments based on that. For example, it can suggest relevant answers based on the content of past inquiries. The comment suggestion unit can also analyze the customer's emotional state and suggest comments accordingly. For example, if a customer is dissatisfied, it can suggest an apologetic comment. By applying this to a customer support chatbot, customer service can be enhanced.

[0067] The emotion estimation function can suggest personalized comments according to the user's emotions. For example, the emotion estimation function can suggest personalized comments according to the user's emotions. For example, if the user is feeling down, it can suggest encouraging comments. The emotion estimation function can also monitor changes in the user's emotions in real time and suggest personalized comments at the appropriate time. For example, it can suggest positive comments when the user is relaxed. The emotion estimation function can also grasp the user's emotional trends and suggest long-term personalized comments. For example, it can continuously suggest encouraging comments to help the user act with confidence. This makes it possible to suggest personalized comments according to the user's emotions.

[0068] The context understanding unit can analyze the content of statements made during a meeting in real time, understand the speaker's intention, and suggest appropriate follow-up questions. The context understanding unit, for example, analyzes the content of statements made during a meeting in real time, understands the speaker's intention, and suggests appropriate follow-up questions. For example, if a speaker is talking about the progress of a project, it suggests questions about the next step. The context understanding unit can also analyze the content of statements and suggest questions to confirm additional information or to dig deeper. For example, if a speaker is proposing a new idea, it suggests follow-up questions to learn more about the details. The context understanding unit can also understand the speaker's intention and suggest follow-up questions that match the flow of the conversation. For example, if a speaker points out a problem, it suggests questions about the solution. This makes it possible to understand the speaker's intention and suggest appropriate follow-up questions.

[0069] The context understanding unit can analyze the progress of a meeting and make suggestions to support time management and the progress of agenda items. The context understanding unit, for example, analyzes the progress of a meeting in real time and makes suggestions to support time management and the progress of agenda items. For example, it may suggest moving on to the next agenda item if the meeting is likely to go over the scheduled time. The context understanding unit can also analyze the progress of a meeting and make suggestions to adjust the priority of agenda items. For example, it may suggest taking up important agenda items first. The context understanding unit can also analyze the progress of a meeting and make suggestions to optimize time allocation. For example, it may make suggestions to adjust the time allocation for each agenda item. In this way, the progress of a meeting can be analyzed and suggestions to support time management and the progress of agenda items can be made.

[0070] The emotion estimation function can monitor the emotional state of meeting participants and suggest comments that will ease tension. For example, the emotion estimation function can monitor the emotional state of meeting participants and suggest comments that will ease tension. For example, if a participant is nervous, it can suggest comments that encourage them to relax. The emotion estimation function can also monitor changes in the emotions of meeting participants in real time and suggest comments that will ease tension at the appropriate time. For example, it can suggest comments that encourage participants to relax when they are feeling nervous. The emotion estimation function can also grasp the emotional trends of meeting participants and suggest comments that will ease tension over the long term. For example, it can continuously suggest comments that encourage participants to relax so that they can speak with confidence. This makes it possible to monitor the emotional state of meeting participants and suggest comments that will ease tension.

[0071] The voice analysis unit can automatically record the content of statements made in online conferences and build a database that can be searched later. The voice analysis unit, for example, automatically records the content of statements made in online conferences and builds a database that can be searched later. For example, the content of statements can be saved as text data, enabling keyword searches. The voice analysis unit can also analyze the content of statements, extract important points, and save them in a database. For example, the content of statements made during a conference can be analyzed in real time, extract important points, and save them in a database. The voice analysis unit can also build a database based on the content of statements and save them in a format that can be referenced later. For example, the content of statements made during a conference can be saved as text data, building a database that can be searched later. In this way, the content of statements made in online conferences can be automatically recorded and a database that can be searched later can be built.

[0072] The speech analysis unit can translate statements made during a meeting in real time to support communication between participants who speak different languages. The speech analysis unit, for example, translates statements made during a meeting in real time to support communication between participants who speak different languages. For example, it performs real-time translation from English to Japanese. The speech analysis unit can also analyze the content of statements and display the translation results as text data. For example, it can translate English speech made during a meeting into Japanese and display it as text. The speech analysis unit can also analyze the content of statements and output the translation results as audio data. For example, it can translate English speech made during a meeting into Japanese and output it as Japanese audio. This makes it possible to translate statements made during a meeting in real time to support communication between participants who speak different languages.

[0073] The emotion estimation function can analyze the atmosphere of a meeting and suggest breaks at the appropriate time. The emotion estimation function can, for example, analyze the atmosphere of a meeting and suggest breaks at the appropriate time. For example, if participants are tired, it will suggest a break. The emotion estimation function can also analyze the atmosphere of a meeting, monitor changes in participants' emotions in real time, and suggest breaks at the appropriate time. For example, it will suggest a break if participants are losing concentration. The emotion estimation function can also analyze the atmosphere of a meeting, grasp participants' emotional trends, and suggest long-term break plans. For example, it will suggest a break when participants are relaxed. This makes it possible to analyze the atmosphere of a meeting and suggest breaks at the appropriate time.

[0074] The context understanding unit can analyze the content of utterances made at ceremonial occasions and social gatherings, and suggest appropriate comments based on cultural background and manners. The context understanding unit can, for example, analyze the content of utterances made at ceremonial occasions and social gatherings, and suggest appropriate comments based on cultural background and manners. For example, it can suggest comments that are suitable for a speech at a wedding. The context understanding unit can also analyze the content of utterances and suggest comments that are based on cultural background. For example, it can suggest comments that are suitable for a eulogy at a funeral. The context understanding unit can also analyze the content of utterances and suggest comments that are based on manners. For example, it can suggest comments that are suitable for a self-introduction at a social gathering. In this way, it is possible to analyze the content of utterances made at ceremonial occasions and social gatherings, and suggest appropriate comments based on cultural background and manners.

[0075] The context understanding unit can analyze comments made at large-scale events in real time, understand the speaker's intention, and provide appropriate follow-up. For example, the context understanding unit can analyze comments made at large-scale events in real time, understand the speaker's intention, and provide appropriate follow-up. For example, if the speaker is proposing a new idea, the unit can follow up on the details. The context understanding unit can also analyze the content of comments to confirm additional information or ask probing questions. For example, if the speaker points out a problem, the unit can follow up on the solution. The context understanding unit can also understand the speaker's intention and provide follow-up according to the flow of the conversation. For example, if the speaker is talking about the progress of a project, the unit can follow up on the next step. This makes it possible to analyze comments made at large-scale events in real time, understand the speaker's intention, and provide appropriate follow-up.

[0076] The emotion estimation function can analyze the emotional state of event participants and suggest comments that will create a positive atmosphere. For example, if a participant is nervous, the emotion estimation function can suggest comments that encourage them to relax. The emotion estimation function can also monitor changes in participants' emotions in real time and suggest positive comments at the appropriate time. For example, it can suggest encouraging comments when a participant is relaxed. The emotion estimation function can also grasp participants' emotional trends and suggest comments that will create a long-term positive atmosphere. For example, it can continuously suggest positive comments to help participants act with confidence. This makes it possible to analyze the emotional state of event participants and suggest comments that will create a positive atmosphere.

[0077] The voice analysis unit can automatically record what is said at ceremonial occasions and social gatherings, and build a database that can be referenced later. The voice analysis unit can automatically record what is said at ceremonial occasions and social gatherings, and build a database that can be referenced later. For example, a speech at a wedding can be saved as text data and made searchable later. The voice analysis unit can also analyze what is said, extract important points, and save them in a database. For example, a eulogy at a funeral can be analyzed in real time, extract important points, and save them in a database. The voice analysis unit can also build a database based on what is said, and save them in a format that can be referenced later. For example, a self-introduction at a social gathering can be saved as text data, and a database that can be searched later can be built. In this way, what is said at ceremonial occasions and social gatherings can be automatically recorded, and a database that can be referenced later can be built.

[0078] The voice analysis unit can translate comments made during an event in real time to support communication between participants who speak different languages. The voice analysis unit, for example, translates comments made during an event in real time to support communication between participants who speak different languages. For example, it performs real-time translation from English to Japanese. The voice analysis unit can also analyze the content of comments and display the translation results as text data. For example, it can translate English speech made during an event into Japanese and display it as text. The voice analysis unit can also analyze the content of comments and output the translation results as voice data. For example, it can translate English speech made during an event into Japanese and output it as Japanese speech. This allows for real-time translation of comments made during an event to support communication between participants who speak different languages.

[0079] The emotion estimation function can analyze the atmosphere of an event and suggest speeches and activities at the appropriate timing. The emotion estimation function can, for example, analyze the atmosphere of an event and suggest speeches and activities at the appropriate timing. For example, it can suggest a speech when participants are relaxed. The emotion estimation function can also analyze the atmosphere of an event, monitor changes in participants' emotions in real time, and suggest speeches and activities at the appropriate timing. For example, it can suggest an activity when participants are concentrating. The emotion estimation function can also analyze the atmosphere of an event, grasp participants' emotional trends, and suggest long-term speech and activity plans. For example, it can suggest an activity when participants are enjoying themselves. This makes it possible to analyze the atmosphere of an event and suggest speeches and activities at the appropriate timing.

[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 voice analysis unit analyzes the tone and speed of the speaker's voice to estimate the speaker's emotions, such as nervousness or impatience, and can suggest appropriate comments to the comment suggestion unit. For example, if the voice tone is high and the speed is fast, it can determine that the speaker is nervous and suggest comments encouraging them to relax. The voice analysis unit can also analyze changes in voice tone and speed to monitor changes in the speaker's emotions in real time. For example, if the voice tone changes suddenly, it can determine that the speaker is surprised and suggest reassuring comments. The voice analysis unit can also analyze patterns in voice tone and speed to grasp the speaker's emotional tendencies. For example, if the voice tone is low and the speed is slow, it can determine that the speaker is calm and suggest positive comments. This allows the system to suggest appropriate comments according to the speaker's emotions, thereby reducing tension and impatience.

[0082] The audio analysis unit can analyze background and environmental sounds contained in the audio data to determine the appropriate timing to speak. For example, it can encourage a participant to speak at a time when there is less noise in the conference room. The audio analysis unit can also detect specific sounds and determine the timing to speak based on those sounds. For example, it can detect when other participants have finished speaking during a conference and encourage a participant to speak at that time. The audio analysis unit can also analyze the noise level of the audio data and encourage a participant to speak at a time when there is less noise. For example, it can detect when there is less external noise during a conference and encourage a participant to speak at that time. In this way, the appropriate timing to speak can be determined by analyzing background and environmental sounds.

[0083] The voice analysis unit can use the emotion estimation function to analyze the speaker's emotional state in real time and suggest comments that will elicit positive emotions from the speaker. For example, if the speaker is nervous, it can suggest comments that encourage them to relax. The voice analysis unit can also use the emotion estimation function to monitor the speaker's emotional changes in real time and suggest positive comments at the appropriate time. For example, it can suggest encouraging comments when the speaker begins to calm down. The voice analysis unit can also use the emotion estimation function to grasp the speaker's emotional tendencies and suggest comments that will elicit long-term positive emotions. For example, it can continuously suggest positive comments so that the speaker can speak with confidence. In this way, suggesting comments that will elicit positive emotions from the speaker allows for smoother speech.

[0084] The speech analysis unit can translate speech in different languages ​​in real time to support speech at international conferences. For example, speech analysis technology can be used to translate speech in different languages ​​in real time to support speech at international conferences. For example, real-time translation from English to Japanese is performed. The speech analysis unit can also analyze speech in different languages ​​and display the translation results as text data. For example, English speech spoken during a conference can be translated into Japanese and displayed as text. The speech analysis unit can also analyze speech in different languages ​​and output the translation results as speech data. For example, English speech spoken during a conference can be translated into Japanese and output as Japanese speech. This makes it possible to support speech at international conferences by translating speech in different languages ​​in real time.

[0085] The voice analysis unit can automatically summarize what is said based on the voice analysis results and generate meeting minutes. For example, the voice analysis unit can automatically summarize what is said based on the voice analysis results and generate meeting minutes. For example, it can extract important points and generate a summary. The voice analysis unit can also analyze what is said and save the summary as text data. For example, it can summarize what is said during a meeting in real time and save it as text data. The voice analysis unit can also automatically generate meeting minutes based on the summary. For example, it can summarize what is said during a meeting and organize it as minutes. In this way, it is possible to automatically summarize what is said and generate meeting minutes.

[0086] The voice analysis unit can use the emotion estimation function to analyze the emotional state of all meeting participants and make suggestions to optimize the progress of the meeting. For example, the emotion estimation function can be used to analyze the emotional state of all meeting participants and make suggestions to optimize the progress of the meeting. For example, if a participant is tired, the voice analysis unit can also use the emotion estimation function to monitor changes in the emotions of meeting participants in real time and make suggestions to adjust the progress at the appropriate time. For example, if a participant is losing concentration, the voice analysis unit can make suggestions to change the agenda. The voice analysis unit can also use the emotion estimation function to grasp the emotional trends of meeting participants and make suggestions to optimize the long-term progress plan. For example, the voice analysis unit can make a suggestion to bring up important agenda items when participants are relaxed. In this way, the emotional state of all meeting participants can be analyzed and suggestions to optimize the progress of the meeting can be made.

[0087] The context understanding unit can analyze the flow of conversation and suggest consistent comments by referring to past utterances. For example, the context understanding unit can analyze the flow of conversation and suggest consistent comments by referring to past utterances. For example, it can suggest comments based on utterances made in a previous meeting. The context understanding unit can also analyze the flow of conversation and search past utterances to suggest appropriate comments. For example, it can search past utterance histories to suggest related comments. The context understanding unit can also analyze the flow of conversation and suggest comments that maintain the consistency of the conversation based on past utterances. For example, it can suggest comments related to the agenda of the previous meeting. This makes it possible to suggest consistent comments by referring to past utterances.

[0088] The context understanding unit can obtain the latest news and data related to the conversation topic in real time and suggest comments based on it. For example, the context understanding unit can obtain the latest news and data related to the conversation topic in real time and suggest comments based on it. For example, the context understanding unit can generate comments based on data on the latest market trends. The context understanding unit can also obtain the latest news using a news API and suggest comments based on it. For example, the context understanding unit can obtain the latest economic news using a news API and suggest related comments. The context understanding unit can also obtain the latest data using database access and suggest comments based on it. For example, the context understanding unit can obtain the latest statistical data from a database and suggest comments based on it. This makes it possible to suggest comments based on the latest news and data.

[0089] The emotion estimation function can analyze the atmosphere of a conversation and suggest comments that include appropriate humor or empathy. For example, it can analyze the atmosphere of a conversation and suggest comments that include appropriate humor or empathy. For example, if the conversation is tense, it can suggest comments that include humor. The emotion estimation function can also analyze the atmosphere of a conversation and suggest comments that show empathy. For example, if the speaker is sad, it can suggest comments that show empathy. The emotion estimation function can also analyze the atmosphere of a conversation and suggest comments that include humor or empathy at the appropriate time. For example, it can suggest comments that include humor when the conversation becomes relaxed. This makes it possible to suggest comments that include humor or empathy that are appropriate for the atmosphere of the conversation.

[0090] The context understanding unit can use context analysis technology to suggest appropriate questions and comments during lessons in educational settings. For example, the context analysis technology can be used to suggest appropriate questions and comments during lessons in educational settings. For example, questions can be suggested in line with the progress of the lesson. The context understanding unit can also analyze the content of the lesson and suggest questions to check comprehension. For example, questions can be suggested to check comprehension based on the content of the lesson. The context understanding unit can also analyze the progress of the lesson and suggest advanced questions. For example, questions related to advanced content can be suggested in line with the progress of the lesson. This makes it possible to suggest appropriate questions and comments during lessons in educational settings.

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

[0092] Step 1: The voice analyzer analyzes the audio from the microphone in real time. For example, the voice analyzer can use a voice recognition algorithm to convert the audio into text. It can also clean the audio data using noise reduction technology and analyze the frequency characteristics of the audio to extract speaker characteristics. Step 2: The context understanding unit understands the context based on the speech data analyzed by the speech analysis unit. For example, it uses natural language processing technology to analyze the flow of the conversation and uses semantic analysis algorithms to understand the intent of what is being said. It can also extract themes and topics of the conversation. Step 3: The comment suggestion unit suggests appropriate comments and keywords based on the context understood by the context understanding unit. For example, it uses keyword extraction technology to suggest important keywords and suggests comments based on appropriate comment selection criteria. It can also suggest comments in real time based on the flow of the conversation.

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

[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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, 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 processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and 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 the voice from the microphone in real time, a context understanding unit that understands a context based on the voice data analyzed by the voice analysis unit; a comment suggestion unit that suggests appropriate comments and keywords based on the context understood by the context understanding unit. A system characterized by:

2. The voice analysis unit Translating the speech in different languages ​​in real time to support speeches at international conferences 2. The system of claim 1.

3. The context understanding unit Analyze the flow of conversation and suggest consistent comments by referring to previous comments 2. The system of claim 1.

4. The context understanding unit Analyzes what is being said in a meeting in real time, understands the speaker's intent, and suggests appropriate follow-up questions 2. The system of claim 1.

5. The context understanding unit Analyzes comments made at ceremonial occasions and social gatherings, and suggests appropriate comments based on cultural background and etiquette.

2. The system of claim 1.

6. The voice analysis unit Analyzing the tone and speed of the speaker's voice, estimating the speaker's feelings such as nervousness or impatience, and suggesting appropriate comments to the comment suggestion unit 2. The system of claim 1.

Images