system

Abstract

The system according to this embodiment aims to facilitate one-on-one conversations and improve relationships. [Solution] The system according to the embodiment comprises a recording unit, a text conversion unit, an analysis unit, and a speaking unit. The recording unit records the conversation. The text conversion unit converts the conversation recorded by the recording unit into text. The analysis unit analyzes the content converted into text by the text conversion unit and infers emotions. The speaking unit makes appropriate statements based on the emotions inferred by the analysis unit.

Description

Technical Field

Background Art

Prior Art Documents

Patent Documents

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0009] In the prior art, it is difficult to make appropriate utterances in a one-on-one conversation, which may prevent the improvement of the relationship.

[0010] The system according to an embodiment aims to smooth one-on-one conversations and improve the relationship.

Means for Solving the Problems

[0011]

[0012] The system according to an embodiment includes a recording unit, a text conversion unit, an analysis unit, and a speaking unit. The recording unit records conversations. The text conversion unit converts the conversations recorded by the recording unit into text. The analysis unit analyzes the content converted into text by the text conversion unit and estimates emotions. The speaking unit makes appropriate utterances based on the emotions estimated by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can facilitate one-on-one conversations and improve relationships. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​speaker system according to an embodiment of the present invention is specialized in supporting one-on-one conversations, facilitating smooth interactions between two people and helping to improve their relationship. The AI ​​speaker system constantly records and transcribes the conversation between the two people. Next, it analyzes the transcribed content using natural language processing (NLP) and sentiment analysis to infer the feelings and emotions of the people. For example, in conversations between parents and children or husbands and wives, if the AI ​​speaker system detects anger or frustration, it will make statements that encourage calm dialogue. Conversely, if it senses joy or happiness, it will respond in a way that further strengthens those positive emotions. This facilitates communication within the family and improves relationships. For example, it can resolve problems such as parents and children frequently losing conversation or husbands and wives asking one-sided questions, creating a better atmosphere within the family. Furthermore, the presence of the AI ​​speaker system provides awareness to both parties before emotions escalate, supporting smooth daily communication. In this way, the AI ​​speaker system can support one-on-one conversations, facilitating smooth interactions between two people and helping to improve their relationship.

[0029] The AI ​​speaker system according to this embodiment comprises a recording unit, a text conversion unit, an analysis unit, and a speech unit. The recording unit records conversations. The recording unit can, for example, always record conversations between parents and children or between spouses. The recording unit records the content of conversations in detail so that they can be analyzed later. For example, the recording unit records conversations in various everyday situations, such as conversations between parents and children or between spouses. The text conversion unit converts the conversations recorded by the recording unit into text. The text conversion unit converts conversations into text using, for example, speech recognition technology. The text conversion unit converts the content of conversations into text in detail so that they can be analyzed later. For example, the text conversion unit converts conversations in various everyday situations, such as conversations between parents and children or between spouses. The analysis unit analyzes the content converted into text by the text conversion unit and infers emotions. The analysis unit analyzes the content of conversations using, for example, natural language processing (NLP) and sentiment analysis. The analysis unit determines the fluctuations in speech during the conversation and grasps changes in negative and positive emotions in real time. For example, if the analysis unit senses that a child is angry during a conversation with their parent, it will make a statement to encourage calmer dialogue. The speaking unit will then make an appropriate statement based on the emotion inferred by the analysis unit. For example, if the speaking unit senses that a child is angry during a conversation with their parent, it might say, "Hey, you're getting a little too angry!" to prevent the emotion from spreading. Conversely, if the speaking unit senses that a child is having fun during a conversation with their parent, it might say, "You both seem to be having fun today, did something good happen?" to reinforce the positive emotion. In this way, the AI ​​speaker system according to this embodiment can support one-on-one conversations, facilitate smoother interactions between two people, and help improve their relationship.

[0030] The recording unit records conversations. For example, it can continuously record conversations between parents and children or between spouses. The recording unit meticulously records the content of conversations so that they can be analyzed later. Specifically, the recording unit uses a high-sensitivity microphone to clearly capture ambient sounds. This minimizes background noise and distractions, allowing for accurate recording of conversation content. Furthermore, the recording unit is equipped with an algorithm to compress and efficiently store audio data. This saves storage space even when recording long conversations. The recording unit also has a function to automatically detect the start and end of conversations and record only the necessary parts. For example, it automatically starts recording when a conversation between parents and children begins and stops recording when the conversation ends. This allows for efficient storage of conversation content without recording unnecessary data. In addition, the recording unit can record multiple conversations simultaneously, allowing for centralized management of conversations taking place in multiple locations within the home. In this way, the recording unit comprehensively supports communication within the home and provides a foundation for later analysis and transcription.

[0031] The text conversion unit converts conversations recorded by the recording unit into text. The text conversion unit uses, for example, speech recognition technology to convert conversations into text. Specifically, the text conversion unit is equipped with a high-precision speech recognition engine that can handle various accents and speaking styles. This allows for accurate transcription of conversations between parents and children or spouses. The text conversion unit analyzes audio data in real time and instantly converts it into text. For example, a conversation between parents and children can be transcribed simultaneously as it progresses, making it easy to search and analyze later. Furthermore, the text conversion unit has a function to learn the characteristics of the user's voice to improve the accuracy of speech recognition. This improves recognition accuracy with each use, enabling more accurate transcription. The text conversion unit also understands the context of the conversation and inserts appropriate punctuation and line breaks to generate easy-to-read text. This makes the transcribed conversation easier to understand when reviewed later. The text conversion unit supports multiple languages ​​and can accurately transcribe conversations in different languages. This allows for effective use in international households and multilingual environments.

[0032] The analysis unit analyzes the text generated by the text generation unit and infers emotions. For example, the analysis unit uses natural language processing (NLP) and sentiment analysis to analyze the content of conversations. Specifically, the analysis unit receives text data as input and analyzes the context, word choice, and expression. This allows it to evaluate changes and intensity of emotions within a conversation. For example, if a child says "I've had enough!" in a conversation with their parent, the analysis unit recognizes this statement as a negative emotion and infers that the child is feeling anger or frustration. Using sentiment analysis algorithms, the analysis unit can classify emotions into positive, negative, and neutral, and even identify more specific types of emotions (joy, sadness, anger, surprise, etc.). This allows for a detailed understanding of emotional fluctuations within a conversation. Furthermore, the analysis unit can learn specific patterns and trends based on past conversation data and predict future emotional changes. For example, it can analyze past data to determine what emotions are likely to arise in specific situations or on specific topics, and build a predictive model. This allows the analysis unit to not only perform real-time sentiment analysis but also grasp long-term emotional trends, enabling more effective dialogue support.

[0033] The speaking unit makes appropriate statements based on the emotions inferred by the analysis unit. For example, if a child is angry during a parent-child conversation, the speaking unit might say, "Hey, you're getting a little too angry!" to prevent the emotion from spreading. Specifically, the speaking unit has an algorithm to generate appropriate statements based on the emotion information provided by the analysis unit. The speaking unit selects the appropriate tone and wording depending on the type and intensity of the emotion. For example, if a child is angry, the speaking unit might say in a calm and composed tone, "What's wrong? Did something happen?" to soothe the child's emotions. If a child is happy, the speaking unit might say in a bright and cheerful tone, "That's wonderful! Tell me more!" to reinforce the positive emotion. The speaking unit can also monitor the user's reaction in real time and adjust its statements as needed. For example, if a child shows further anger in response to a statement, the speaking unit will try a different approach. Furthermore, the speaking unit can learn the most effective speaking patterns for a particular user based on past conversation data and make individually customized statements. This allows the speaking unit to empathize with the user's emotions and support the improvement of relationships through appropriate dialogue.

[0034] It is equipped with an emotion recognition unit that grasps emotional changes in real time. The emotion recognition unit can grasp emotional changes in real time. For example, the emotion recognition unit can determine the fluctuations in speech during a conversation and grasp negative and positive emotional changes in real time. For example, if a child is feeling angry during a conversation with a parent, the emotion recognition unit can sense that emotion and make statements that encourage calm dialogue. Conversely, if a child is feeling happy during a conversation with a parent, the emotion recognition unit can sense that emotion and make statements that reinforce positive emotions. This allows for more appropriate responses by grasping emotional changes in real time. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without using AI.

[0035] It is equipped with a positive response unit that enhances positive emotions. The positive response unit can enhance positive emotions. For example, in a conversation between a parent and child, if the child is feeling happy, the positive response unit will make a statement such as, "You both seem to be having fun today, did something good happen?" to enhance the positive emotion. For example, in a conversation between a married couple, if both are feeling happy, the positive response unit will make a statement that further enhances that feeling. For example, in a conversation between friends, if both are feeling happy, the positive response unit will make a statement that further enhances that feeling. In this way, the quality of the conversation can be improved by enhancing positive emotions. Some or all of the processing described above in the positive response unit may be performed using AI, for example, or without using AI.

[0036] It is equipped with a negative response unit that suppresses negative emotions. The negative response unit can suppress negative emotions. For example, if a child is feeling angry during a conversation with their parent, the negative response unit might say, "Hey, you're getting a little too angry!" to prevent the emotion from spreading. For example, if a couple is feeling irritated during a conversation, the negative response unit might make a statement to suppress that emotion. For example, if two friends are feeling angry during a conversation, the negative response unit might make a statement to suppress that emotion. By suppressing negative emotions, the quality of the conversation can be improved. Some or all of the processing described above in the negative response unit may be performed using AI, for example, or without using AI.

[0037] The recording unit can continuously record conversations between parents and children, or between spouses. The recording unit continuously records conversations in various everyday situations, such as conversations between parents and children or between spouses. The recording unit meticulously records the content of conversations so that they can be analyzed later. For example, the recording unit records conversations in various everyday situations, such as conversations between parents and children or between spouses. By continuously recording conversations between parents and children or between spouses, it is possible to improve relationships. Some or all of the above-described processing in the recording unit may be performed using AI, for example, or without AI.

[0038] The speaking unit can make statements that give both parties awareness before emotions escalate. For example, if a child is angry in a conversation with their parent, the speaking unit might say, "Hey, you're getting a little too angry!" to prevent the emotion from spreading. For example, if a spouse is feeling irritated in a conversation, the speaking unit might make statements to calm those emotions. For example, if two friends are feeling angry in a conversation, the speaking unit might make statements to calm those emotions. This improves the quality of the dialogue by giving awareness before emotions escalate. Some or all of the processing described above in the speaking unit may be performed using AI, for example, or not using AI.

[0039] The recording unit can prioritize recording specific keywords or phrases when recording a conversation. For example, if the user utters keywords such as "important" or "important," the recording unit will prioritize recording those parts. For example, if the user mentions a specific name or place, the recording unit will record that part in detail. For example, if the recording unit uses emotional words (e.g., "anger," "joy"), the recording unit will focus on recording those parts. By prioritizing the recording of specific keywords or phrases, important information will not be missed. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI.

[0040] The recording unit simultaneously records background and ambient sounds from conversations, which can then be used for later analysis. For example, the recording unit can record background sounds during a conversation (e.g., television sounds, car sounds) to understand the context of the conversation. For example, the recording unit can record ambient sounds from the location where the conversation took place (e.g., café sounds, office sounds) and use them for analysis. For example, the recording unit can record noise during a conversation (e.g., wind sounds, background noise) and filter and analyze it later. By recording background and ambient sounds, the context of the conversation can be understood more accurately. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI.

[0041] The recording unit can record conversations while taking the user's geographical location into consideration. For example, if the user is in a specific location (e.g., home, office), the recording unit will prioritize recording conversations at that location. For example, if the user is on the move, the recording unit will record conversations at their destination. For example, if the user is attending a specific event (e.g., a meeting, party), the recording unit will record conversations during that event. This makes it possible to record conversations according to location by taking geographical location information into consideration. Some or all of the above processing in the recording unit may be performed using AI, for example, or without using AI.

[0042] The recording unit can analyze a user's social media activity and record relevant conversations. For example, the recording unit can record conversations related to topics mentioned by the user on social media. For example, the recording unit can prioritize recording conversations with people the user follows on social media. For example, the recording unit can record conversations related to groups or events the user participates in on social media. This allows for efficient recording of relevant conversations by analyzing social media activity. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI.

[0043] The transcription unit can adjust the level of detail in the transcription based on the importance of the conversation. For example, the transcription unit transcribes important conversations in detail, recording even the smallest details. For example, the transcription unit transcribes general conversations in a simplified manner, recording only the main points. For example, the transcription unit transcribes short conversations concisely and long conversations in detail. This allows important information to be recorded in detail by adjusting the level of detail in the transcription based on the importance of the conversation. Some or all of the above processing in the transcription unit may be performed using AI, for example, or without using AI.

[0044] The text conversion unit can apply different text conversion algorithms depending on the category of the conversation. For example, the text conversion unit may apply a text conversion algorithm that includes technical terms to business conversations. For example, the text conversion unit may apply a concise and easy-to-understand text conversion algorithm to everyday conversations. For example, the text conversion unit may apply an algorithm that reflects emotions to emotional conversations. By applying a text conversion algorithm according to the category of the conversation, more appropriate text conversion becomes possible. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without using AI.

[0045] The text conversion unit can perform text conversion while considering the attribute information of the speakers in the conversation. For example, if the speaker is an expert, the text conversion unit will include technical terms. For example, if the speaker is a child, the text conversion unit will produce concise and easy-to-understand text. For example, if the speaker is emotional, the text conversion unit will produce text that reflects the emotion. This makes it possible to produce more appropriate text by considering the attribute information of the speakers. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without using AI.

[0046] The transcription unit can improve the accuracy of transcription by referring to relevant literature for the conversation. For example, the transcription unit can refer to relevant literature for technical terms mentioned in the conversation and accurately transcribe them. For example, the transcription unit can refer to relevant literature for historical facts mentioned in the conversation and accurately transcribe them. For example, the transcription unit can refer to relevant literature for names of people and places mentioned in the conversation and accurately transcribe them. In this way, the accuracy of transcription is improved by referring to relevant literature. Some or all of the above processing in the transcription unit may be performed using AI, for example, or without using AI.

[0047] The analysis unit can improve the accuracy of its analysis by considering the relationships between conversations. For example, the analysis unit performs analysis by considering the context of statements in a conversation. For example, the analysis unit performs analysis by considering the relationships between speakers in a conversation. For example, the analysis unit performs analysis by considering the context of statements in a conversation. As a result, the accuracy of the analysis is improved by considering the relationships between conversations. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0048] The analysis unit can perform analysis while considering the attribute information of the speakers in the conversation. For example, if the speaker is an expert, the analysis unit will perform analysis based on their expert knowledge. For example, if the speaker is a child, the analysis unit will perform a concise and easy-to-understand analysis. For example, if the speaker is emotional, the analysis unit will perform an analysis that reflects their emotions. By considering the attribute information of the speakers, a more appropriate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0049] The analysis unit can perform analysis while considering the geographical distribution of conversations. For example, the analysis unit can perform analysis based on geographical information of the location where the conversation took place. For example, the analysis unit can perform analysis based on place names mentioned in the conversation. For example, the analysis unit can display the analysis results while considering the geographical distribution of conversations. This makes it possible to perform more accurate analysis by considering geographical distribution. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0050] The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the conversation. For example, the analysis unit can refer to relevant literature to accurately analyze technical terms mentioned in the conversation. For example, the analysis unit can refer to relevant literature to accurately analyze historical facts mentioned in the conversation. For example, the analysis unit can refer to relevant literature to accurately analyze names of people and places mentioned in the conversation. In this way, the accuracy of the analysis is improved by referring to relevant literature. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0051] The speaking unit can adjust the level of detail in its statements based on the importance of the conversation. For example, it might make detailed statements in important conversations, explaining every detail. For example, it might make concise statements in general conversations, conveying only the main points. For example, it might make concise statements in short conversations and detailed statements in long conversations. This allows important information to be conveyed in detail by adjusting the level of detail in statements based on the importance of the conversation. Some or all of the above processing in the speaking unit may be performed using AI, for example, or not using AI.

[0052] The speech function can apply different speech algorithms depending on the category of the conversation. For example, the speech function might apply a speech algorithm that includes technical terms to business conversations. For example, the speech function might apply a speech algorithm that is concise and easy to understand to everyday conversations. For example, the speech function might apply a speech algorithm that reflects emotions to emotional conversations. By applying speech algorithms according to the category of the conversation, more appropriate responses become possible. Some or all of the processing described above in the speech function may be performed using AI, for example, or without using AI.

[0053] The speaking unit can make statements while considering the attribute information of the speaker in the conversation. For example, if the speaker is an expert, the speaking unit will make statements that include technical terms. For example, if the speaker is a child, the speaking unit will make statements that are concise and easy to understand. For example, if the speaker is emotional, the speaking unit will make statements that reflect that emotion. This allows for more appropriate responses by considering the attribute information of the speaker. Some or all of the above processing in the speaking unit may be performed using AI, for example, or not using AI.

[0054] The speaking unit can improve the accuracy of its statements by referring to relevant literature in the conversation. For example, the speaking unit can refer to relevant literature for technical terms mentioned in the conversation and pronounce them accurately. For example, the speaking unit can refer to relevant literature for historical facts mentioned in the conversation and pronounce them accurately. For example, the speaking unit can refer to relevant literature for names of people and places mentioned in the conversation and pronounce them accurately. In this way, the accuracy of the statements is improved by referring to relevant literature. Some or all of the above processing in the speaking unit may be performed using AI, for example, or without using AI.

[0055] The emotion recognition unit can improve the accuracy of emotion recognition by considering the interrelationships in the conversation. For example, the emotion recognition unit performs emotion recognition by considering the context of statements made in the conversation. For example, the emotion recognition unit performs emotion recognition by considering the relationship between speakers in the conversation. For example, the emotion recognition unit performs emotion recognition by considering the context of statements made in the conversation. As a result, the accuracy of emotion recognition is improved by considering the interrelationships in the conversation. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without using AI.

[0056] The emotion recognition unit can perform emotion recognition while considering the geographical distribution of the conversation. For example, the emotion recognition unit can perform emotion recognition based on geographical information of the location where the conversation took place. For example, the emotion recognition unit can perform emotion recognition based on place names mentioned in the conversation. For example, the emotion recognition unit can perform emotion recognition while considering the geographical distribution of the conversation. This makes it possible to perform emotion recognition more accurately by considering the geographical distribution. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without using AI.

[0057] The positive response unit can improve the accuracy of positive responses by considering the relationships within the conversation. For example, the positive response unit considers the context of statements in the conversation when making a positive response. For example, the positive response unit considers the relationship between speakers in the conversation when making a positive response. For example, the positive response unit considers the context of statements in the conversation when making a positive response. As a result, the accuracy of positive responses is improved by considering the relationships within the conversation. Some or all of the above processing in the positive response unit may be performed using AI, for example, or without using AI.

[0058] The positive response unit can make positive responses while considering the geographical distribution of the conversation. For example, the positive response unit can make positive responses based on geographical information of the location where the conversation took place. For example, the positive response unit can make positive responses based on place names mentioned in the conversation. For example, the positive response unit can make positive responses while considering the geographical distribution of the conversation. This makes it possible to make more accurate positive responses by considering the geographical distribution. Some or all of the above processing in the positive response unit may be performed using AI, for example, or without using AI.

[0059] The negative response unit can improve the accuracy of its negative responses by considering the relationships within the conversation. For example, the negative response unit considers the context of statements in the conversation when making a negative response. For example, the negative response unit considers the relationship between speakers in the conversation when making a negative response. For example, the negative response unit considers the context of statements in the conversation when making a negative response. This improves the accuracy of negative responses by considering the relationships within the conversation. Some or all of the above processing in the negative response unit may be performed using AI, for example, or without using AI.

[0060] The negative response unit can perform negative responses while considering the geographical distribution of the conversation. For example, the negative response unit can perform negative responses based on geographical information of the location where the conversation took place. For example, the negative response unit can perform negative responses based on place names mentioned in the conversation. For example, the negative response unit can perform negative responses while considering the geographical distribution of the conversation. This makes it possible to perform more accurate negative responses by considering the geographical distribution. Some or all of the above processing in the negative response unit may be performed using AI, for example, or without using AI.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] AI speaker systems can analyze a user's purchase history and estimate their interests. For example, if a user frequently purchases products from a particular brand, the system can engage them by discussing topics related to that brand. Similarly, if a user purchases products from a specific category, the system can attract their interest by providing information related to that category. Furthermore, it can improve user satisfaction by offering advice and usage instructions related to recently purchased items. This enables more personalized conversations by providing appropriate responses based on the user's purchase history.

[0063] The AI ​​speaker system can analyze the user's calendar information and provide appropriate responses based on the user's schedule. For example, if the user has a busy schedule, it can provide short, to-the-point responses. If the user has relaxed time, it can provide responses that include detailed explanations. Furthermore, if the user is attending a specific event, it can engage the user's interest by providing information related to that event. This enables more personalized conversations by providing appropriate responses based on the user's calendar information.

[0064] AI speaker systems can analyze a user's geographical location and provide appropriate responses based on their current location. For example, if a user is at home, the system can offer remarks to encourage relaxation within the home. If a user is in the office, it can provide work-related information to improve their productivity. Furthermore, if a user is traveling, it can enhance their travel experience by providing relevant tourist information and restaurant recommendations. This enables more personalized conversations by providing appropriate responses based on the user's geographical location.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The recording unit records conversations. For example, it continuously records conversations between parents and children or husbands and wives, and records the content of the conversations in detail so that they can be analyzed later. Step 2: The text conversion unit converts the conversation recorded by the recording unit into text. For example, speech recognition technology is used to transcribe the conversation in detail so that it can be analyzed later. Step 3: The analysis unit analyzes the content transcribed by the text conversion unit and infers emotions. For example, it uses natural language processing (NLP) and sentiment analysis to analyze the content of the conversation, determine the fluctuations in speech, and grasp changes in negative and positive emotions in real time. Step 4: The speaking unit makes appropriate statements based on the emotions inferred by the analysis unit. For example, if a child is angry during a conversation with their parent, the speaking unit might say, "Hey, you're being a little too angry!" to prevent the emotion from spreading. If the child is happy, the speaking unit might say, "You both seem to be having fun today, did something good happen?" to reinforce the positive emotion.

[0067] (Example of form 2) The AI ​​speaker system according to an embodiment of the present invention is specialized in supporting one-on-one conversations, facilitating smooth interactions between two people and helping to improve their relationship. The AI ​​speaker system constantly records and transcribes the conversation between the two people. Next, it analyzes the transcribed content using natural language processing (NLP) and sentiment analysis to infer the feelings and emotions of the people. For example, in conversations between parents and children or husbands and wives, if the AI ​​speaker system detects anger or frustration, it will make statements that encourage calm dialogue. Conversely, if it senses joy or happiness, it will respond in a way that further strengthens those positive emotions. This facilitates communication within the family and improves relationships. For example, it can resolve problems such as parents and children frequently losing conversation or husbands and wives asking one-sided questions, creating a better atmosphere within the family. Furthermore, the presence of the AI ​​speaker system provides awareness to both parties before emotions escalate, supporting smooth daily communication. In this way, the AI ​​speaker system can support one-on-one conversations, facilitating smooth interactions between two people and helping to improve their relationship.

[0068] The AI ​​speaker system according to this embodiment comprises a recording unit, a text conversion unit, an analysis unit, and a speech unit. The recording unit records conversations. The recording unit can, for example, always record conversations between parents and children or between spouses. The recording unit records the content of conversations in detail so that they can be analyzed later. For example, the recording unit records conversations in various everyday situations, such as conversations between parents and children or between spouses. The text conversion unit converts the conversations recorded by the recording unit into text. The text conversion unit converts conversations into text using, for example, speech recognition technology. The text conversion unit converts the content of conversations into text in detail so that they can be analyzed later. For example, the text conversion unit converts conversations in various everyday situations, such as conversations between parents and children or between spouses. The analysis unit analyzes the content converted into text by the text conversion unit and infers emotions. The analysis unit analyzes the content of conversations using, for example, natural language processing (NLP) and sentiment analysis. The analysis unit determines the fluctuations in speech during the conversation and grasps changes in negative and positive emotions in real time. For example, if the analysis unit senses that a child is angry during a conversation with their parent, it will make a statement to encourage calmer dialogue. The speaking unit will then make an appropriate statement based on the emotion inferred by the analysis unit. For example, if the speaking unit senses that a child is angry during a conversation with their parent, it might say, "Hey, you're getting a little too angry!" to prevent the emotion from spreading. Conversely, if the speaking unit senses that a child is having fun during a conversation with their parent, it might say, "You both seem to be having fun today, did something good happen?" to reinforce the positive emotion. In this way, the AI ​​speaker system according to this embodiment can support one-on-one conversations, facilitate smoother interactions between two people, and help improve their relationship.

[0069] The recording unit records conversations. For example, it can continuously record conversations between parents and children or between spouses. The recording unit meticulously records the content of conversations so that they can be analyzed later. Specifically, the recording unit uses a high-sensitivity microphone to clearly capture ambient sounds. This minimizes background noise and distractions, allowing for accurate recording of conversation content. Furthermore, the recording unit is equipped with an algorithm to compress and efficiently store audio data. This saves storage space even when recording long conversations. The recording unit also has a function to automatically detect the start and end of conversations and record only the necessary parts. For example, it automatically starts recording when a conversation between parents and children begins and stops recording when the conversation ends. This allows for efficient storage of conversation content without recording unnecessary data. In addition, the recording unit can record multiple conversations simultaneously, allowing for centralized management of conversations taking place in multiple locations within the home. In this way, the recording unit comprehensively supports communication within the home and provides a foundation for later analysis and transcription.

[0070] The text conversion unit converts conversations recorded by the recording unit into text. The text conversion unit uses, for example, speech recognition technology to convert conversations into text. Specifically, the text conversion unit is equipped with a high-precision speech recognition engine that can handle various accents and speaking styles. This allows for accurate transcription of conversations between parents and children or spouses. The text conversion unit analyzes audio data in real time and instantly converts it into text. For example, a conversation between parents and children can be transcribed simultaneously as it progresses, making it easy to search and analyze later. Furthermore, the text conversion unit has a function to learn the characteristics of the user's voice to improve the accuracy of speech recognition. This improves recognition accuracy with each use, enabling more accurate transcription. The text conversion unit also understands the context of the conversation and inserts appropriate punctuation and line breaks to generate easy-to-read text. This makes the transcribed conversation easier to understand when reviewed later. The text conversion unit supports multiple languages ​​and can accurately transcribe conversations in different languages. This allows for effective use in international households and multilingual environments.

[0071] The analysis unit analyzes the text generated by the text generation unit and infers emotions. For example, the analysis unit uses natural language processing (NLP) and sentiment analysis to analyze the content of conversations. Specifically, the analysis unit receives text data as input and analyzes the context, word choice, and expression. This allows it to evaluate changes and intensity of emotions within a conversation. For example, if a child says "I've had enough!" in a conversation with their parent, the analysis unit recognizes this statement as a negative emotion and infers that the child is feeling anger or frustration. Using sentiment analysis algorithms, the analysis unit can classify emotions into positive, negative, and neutral, and even identify more specific types of emotions (joy, sadness, anger, surprise, etc.). This allows for a detailed understanding of emotional fluctuations within a conversation. Furthermore, the analysis unit can learn specific patterns and trends based on past conversation data and predict future emotional changes. For example, it can analyze past data to determine what emotions are likely to arise in specific situations or on specific topics, and build a predictive model. This allows the analysis unit to not only perform real-time sentiment analysis but also grasp long-term emotional trends, enabling more effective dialogue support.

[0072] The speaking unit makes appropriate statements based on the emotions inferred by the analysis unit. For example, if a child is angry during a parent-child conversation, the speaking unit might say, "Hey, you're getting a little too angry!" to prevent the emotion from spreading. Specifically, the speaking unit has an algorithm to generate appropriate statements based on the emotion information provided by the analysis unit. The speaking unit selects the appropriate tone and wording depending on the type and intensity of the emotion. For example, if a child is angry, the speaking unit might say in a calm and composed tone, "What's wrong? Did something happen?" to soothe the child's emotions. If a child is happy, the speaking unit might say in a bright and cheerful tone, "That's wonderful! Tell me more!" to reinforce the positive emotion. The speaking unit can also monitor the user's reaction in real time and adjust its statements as needed. For example, if a child shows further anger in response to a statement, the speaking unit will try a different approach. Furthermore, the speaking unit can learn the most effective speaking patterns for a particular user based on past conversation data and make individually customized statements. This allows the speaking unit to empathize with the user's emotions and support the improvement of relationships through appropriate dialogue.

[0073] It is equipped with an emotion recognition unit that grasps emotional changes in real time. The emotion recognition unit can grasp emotional changes in real time. For example, the emotion recognition unit can determine the fluctuations in speech during a conversation and grasp negative and positive emotional changes in real time. For example, if a child is feeling angry during a conversation with a parent, the emotion recognition unit can sense that emotion and make statements that encourage calm dialogue. Conversely, if a child is feeling happy during a conversation with a parent, the emotion recognition unit can sense that emotion and make statements that reinforce positive emotions. This allows for more appropriate responses by grasping emotional changes in real time. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without using AI.

[0074] It is equipped with a positive response unit that enhances positive emotions. The positive response unit can enhance positive emotions. For example, in a conversation between a parent and child, if the child is feeling happy, the positive response unit will make a statement such as, "You both seem to be having fun today, did something good happen?" to enhance the positive emotion. For example, in a conversation between a married couple, if both are feeling happy, the positive response unit will make a statement that further enhances that feeling. For example, in a conversation between friends, if both are feeling happy, the positive response unit will make a statement that further enhances that feeling. In this way, the quality of the conversation can be improved by enhancing positive emotions. Some or all of the processing described above in the positive response unit may be performed using AI, for example, or without using AI.

[0075] It is equipped with a negative response unit that suppresses negative emotions. The negative response unit can suppress negative emotions. For example, if a child is feeling angry during a conversation with their parent, the negative response unit might say, "Hey, you're getting a little too angry!" to prevent the emotion from spreading. For example, if a couple is feeling irritated during a conversation, the negative response unit might make a statement to suppress that emotion. For example, if two friends are feeling angry during a conversation, the negative response unit might make a statement to suppress that emotion. By suppressing negative emotions, the quality of the conversation can be improved. Some or all of the processing described above in the negative response unit may be performed using AI, for example, or without using AI.

[0076] The recording unit can continuously record conversations between parents and children, or between spouses. The recording unit continuously records conversations in various everyday situations, such as conversations between parents and children or between spouses. The recording unit meticulously records the content of conversations so that they can be analyzed later. For example, the recording unit records conversations in various everyday situations, such as conversations between parents and children or between spouses. By continuously recording conversations between parents and children or between spouses, it is possible to improve relationships. Some or all of the above-described processing in the recording unit may be performed using AI, for example, or without AI.

[0077] The speaking unit can make statements that give both parties awareness before emotions escalate. For example, if a child is angry in a conversation with their parent, the speaking unit might say, "Hey, you're getting a little too angry!" to prevent the emotion from spreading. For example, if a spouse is feeling irritated in a conversation, the speaking unit might make statements to calm those emotions. For example, if two friends are feeling angry in a conversation, the speaking unit might make statements to calm those emotions. This improves the quality of the dialogue by giving awareness before emotions escalate. Some or all of the processing described above in the speaking unit may be performed using AI, for example, or not using AI.

[0078] The recording unit can estimate the user's emotions and adjust the timing of conversation recording based on the estimated emotions. For example, if the user is stressed, the recording unit will record the conversation frequently to collect detailed data. For example, if the user is relaxed, the recording unit will record the conversation at intervals, recording only the important parts. For example, if the user is in a hurry, the recording unit will prioritize recording important conversations in a short amount of time. This allows for more appropriate data collection by adjusting the recording timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI.

[0079] The recording unit can prioritize recording specific keywords or phrases when recording a conversation. For example, if the user utters keywords such as "important" or "important," the recording unit will prioritize recording those parts. For example, if the user mentions a specific name or place, the recording unit will record that part in detail. For example, if the recording unit uses emotional words (e.g., "anger," "joy"), the recording unit will focus on recording those parts. By prioritizing the recording of specific keywords or phrases, important information will not be missed. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI.

[0080] The recording unit simultaneously records background and ambient sounds from conversations, which can then be used for later analysis. For example, the recording unit can record background sounds during a conversation (e.g., television sounds, car sounds) to understand the context of the conversation. For example, the recording unit can record ambient sounds from the location where the conversation took place (e.g., café sounds, office sounds) and use them for analysis. For example, the recording unit can record noise during a conversation (e.g., wind sounds, background noise) and filter and analyze it later. By recording background and ambient sounds, the context of the conversation can be understood more accurately. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI.

[0081] The recording unit can estimate the user's emotions and determine the priority of conversations to record based on the estimated emotions. For example, if the user is angry, the recording unit will prioritize recording that conversation. For example, if the user is happy, the recording unit will record that conversation in detail. For example, if the user is sad, the recording unit will focus on recording that conversation. This allows important conversations to be recorded preferentially by prioritizing them based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI, for example, or not using AI.

[0082] The recording unit can record conversations while taking the user's geographical location into consideration. For example, if the user is in a specific location (e.g., home, office), the recording unit will prioritize recording conversations at that location. For example, if the user is on the move, the recording unit will record conversations at their destination. For example, if the user is attending a specific event (e.g., a meeting, party), the recording unit will record conversations during that event. This makes it possible to record conversations according to location by taking geographical location information into consideration. Some or all of the above processing in the recording unit may be performed using AI, for example, or without using AI.

[0083] The recording unit can analyze a user's social media activity and record relevant conversations. For example, the recording unit can record conversations related to topics mentioned by the user on social media. For example, the recording unit can prioritize recording conversations with people the user follows on social media. For example, the recording unit can record conversations related to groups or events the user participates in on social media. This allows for efficient recording of relevant conversations by analyzing social media activity. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI.

[0084] The text generation unit can estimate the user's emotions and adjust the textual expression based on the estimated emotions. For example, if the user is angry, the text generation unit will use restrained expression. For example, if the user is happy, the text generation unit will use emphatic expression. For example, if the user is sad, the text generation unit will use mellow expression. By adjusting the textual expression based on the user's emotions, more appropriate text generation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the text generation unit may be performed using AI, for example, or without AI.

[0085] The transcription unit can adjust the level of detail in the transcription based on the importance of the conversation. For example, the transcription unit transcribes important conversations in detail, recording even the smallest details. For example, the transcription unit transcribes general conversations in a simplified manner, recording only the main points. For example, the transcription unit transcribes short conversations concisely and long conversations in detail. This allows important information to be recorded in detail by adjusting the level of detail in the transcription based on the importance of the conversation. Some or all of the above processing in the transcription unit may be performed using AI, for example, or without using AI.

[0086] The text conversion unit can apply different text conversion algorithms depending on the category of the conversation. For example, the text conversion unit may apply a text conversion algorithm that includes technical terms to business conversations. For example, the text conversion unit may apply a concise and easy-to-understand text conversion algorithm to everyday conversations. For example, the text conversion unit may apply an algorithm that reflects emotions to emotional conversations. By applying a text conversion algorithm according to the category of the conversation, more appropriate text conversion becomes possible. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without using AI.

[0087] The text generation unit can estimate the user's emotions and adjust the length of the text based on the estimated emotions. For example, if the user is in a hurry, the text generation unit will produce a short, concise text. For example, if the user is relaxed, the text generation unit will produce a longer text that includes detailed explanations. For example, if the user is excited, the text generation unit will produce text that emphasizes emotions. By adjusting the length of the text based on the user's emotions, more appropriate text generation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the text generation unit may be performed using AI, for example, or without AI.

[0088] The text conversion unit can perform text conversion while considering the attribute information of the speakers in the conversation. For example, if the speaker is an expert, the text conversion unit will include technical terms. For example, if the speaker is a child, the text conversion unit will produce concise and easy-to-understand text. For example, if the speaker is emotional, the text conversion unit will produce text that reflects the emotion. This makes it possible to produce more appropriate text by considering the attribute information of the speakers. Some or all of the above processing in the text conversion unit may be performed using AI, for example, or without using AI.

[0089] The transcription unit can improve the accuracy of transcription by referring to relevant literature for the conversation. For example, the transcription unit can refer to relevant literature for technical terms mentioned in the conversation and accurately transcribe them. For example, the transcription unit can refer to relevant literature for historical facts mentioned in the conversation and accurately transcribe them. For example, the transcription unit can refer to relevant literature for names of people and places mentioned in the conversation and accurately transcribe them. In this way, the accuracy of transcription is improved by referring to relevant literature. Some or all of the above processing in the transcription unit may be performed using AI, for example, or without using AI.

[0090] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. For example, if the user is angry, the analysis unit will perform an analysis that suppresses those emotions. For example, if the user is happy, the analysis unit will perform an analysis that emphasizes those emotions. For example, if the user is sad, the analysis unit will perform an analysis that mitigates those emotions. By adjusting the analysis criteria based on the user's emotions, a more appropriate analysis becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI.

[0091] The analysis unit can improve the accuracy of its analysis by considering the relationships between conversations. For example, the analysis unit performs analysis by considering the context of statements in a conversation. For example, the analysis unit performs analysis by considering the relationships between speakers in a conversation. For example, the analysis unit performs analysis by considering the context of statements in a conversation. As a result, the accuracy of the analysis is improved by considering the relationships between conversations. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0092] The analysis unit can perform analysis while considering the attribute information of the speakers in the conversation. For example, if the speaker is an expert, the analysis unit will perform analysis based on their expert knowledge. For example, if the speaker is a child, the analysis unit will perform a concise and easy-to-understand analysis. For example, if the speaker is emotional, the analysis unit will perform an analysis that reflects their emotions. By considering the attribute information of the speakers, a more appropriate analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0093] The analysis unit can estimate the user's emotions and adjust the display order of the analysis results based on the estimated user emotions. For example, if the user is angry, the analysis unit will prioritize displaying analysis results that suppress emotions. For example, if the user is happy, the analysis unit will prioritize displaying analysis results that emphasize emotions. For example, if the user is sad, the analysis unit will prioritize displaying analysis results that mitigate emotions. By adjusting the display order of analysis results based on the user's emotions, it becomes possible to provide more appropriate information. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0094] The analysis unit can perform analysis while considering the geographical distribution of conversations. For example, the analysis unit can perform analysis based on geographical information of the location where the conversation took place. For example, the analysis unit can perform analysis based on place names mentioned in the conversation. For example, the analysis unit can display the analysis results while considering the geographical distribution of conversations. This makes it possible to perform more accurate analysis by considering geographical distribution. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0095] The analysis unit can improve the accuracy of its analysis by referring to relevant literature related to the conversation. For example, the analysis unit can refer to relevant literature to accurately analyze technical terms mentioned in the conversation. For example, the analysis unit can refer to relevant literature to accurately analyze historical facts mentioned in the conversation. For example, the analysis unit can refer to relevant literature to accurately analyze names of people and places mentioned in the conversation. In this way, the accuracy of the analysis is improved by referring to relevant literature. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0096] The speaking unit can estimate the user's emotions and adjust the way it expresses itself based on those emotions. For example, if the user is angry, the speaking unit will express itself calmly. For example, if the user is happy, the speaking unit will express itself cheerfully. For example, if the user is sad, the speaking unit will express itself gently. By adjusting the way it expresses itself based on the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speaking unit may be performed using AI, for example, or without AI.

[0097] The speaking unit can adjust the level of detail in its statements based on the importance of the conversation. For example, it might make detailed statements in important conversations, explaining every detail. For example, it might make concise statements in general conversations, conveying only the main points. For example, it might make concise statements in short conversations and detailed statements in long conversations. This allows important information to be conveyed in detail by adjusting the level of detail in statements based on the importance of the conversation. Some or all of the above processing in the speaking unit may be performed using AI, for example, or not using AI.

[0098] The speech function can apply different speech algorithms depending on the category of the conversation. For example, the speech function might apply a speech algorithm that includes technical terms to business conversations. For example, the speech function might apply a speech algorithm that is concise and easy to understand to everyday conversations. For example, the speech function might apply a speech algorithm that reflects emotions to emotional conversations. By applying speech algorithms according to the category of the conversation, more appropriate responses become possible. Some or all of the processing described above in the speech function may be performed using AI, for example, or without using AI.

[0099] The speaking unit can estimate the user's emotions and adjust the length of its utterances based on the estimated emotions. For example, if the user is in a hurry, the speaking unit will make short, to-the-point utterances. If the user is relaxed, the speaking unit will make longer utterances that include detailed explanations. If the user is excited, the speaking unit will make utterances that emphasize emotions. By adjusting the length of utterances based on the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speaking unit may be performed using AI, for example, or not using AI.

[0100] The speaking unit can make statements while considering the attribute information of the speaker in the conversation. For example, if the speaker is an expert, the speaking unit will make statements that include technical terms. For example, if the speaker is a child, the speaking unit will make statements that are concise and easy to understand. For example, if the speaker is emotional, the speaking unit will make statements that reflect that emotion. This allows for more appropriate responses by considering the attribute information of the speaker. Some or all of the above processing in the speaking unit may be performed using AI, for example, or not using AI.

[0101] The speaking unit can improve the accuracy of its statements by referring to relevant literature in the conversation. For example, the speaking unit can refer to relevant literature for technical terms mentioned in the conversation and pronounce them accurately. For example, the speaking unit can refer to relevant literature for historical facts mentioned in the conversation and pronounce them accurately. For example, the speaking unit can refer to relevant literature for names of people and places mentioned in the conversation and pronounce them accurately. In this way, the accuracy of the statements is improved by referring to relevant literature. Some or all of the above processing in the speaking unit may be performed using AI, for example, or without using AI.

[0102] The emotion recognition unit can estimate the user's emotions and adjust its emotion recognition method based on the estimated user emotions. For example, if the user is angry, the emotion recognition unit will recognize the emotions in a way that suppresses them. For example, if the user is happy, the emotion recognition unit will recognize the emotions in a way that emphasizes them. For example, if the user is sad, the emotion recognition unit will recognize the emotions in a way that mitigates them. By adjusting the emotion recognition method based on the user's emotions, more appropriate emotion recognition becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without AI.

[0103] The emotion recognition unit can improve the accuracy of emotion recognition by considering the interrelationships in the conversation. For example, the emotion recognition unit performs emotion recognition by considering the context of statements made in the conversation. For example, the emotion recognition unit performs emotion recognition by considering the relationship between speakers in the conversation. For example, the emotion recognition unit performs emotion recognition by considering the context of statements made in the conversation. As a result, the accuracy of emotion recognition is improved by considering the interrelationships in the conversation. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without using AI.

[0104] The emotion recognition unit can estimate the user's emotions and determine the priority of emotion recognition based on the estimated user emotions. For example, if the user is feeling angry, the emotion recognition unit will prioritize recognizing that emotion. For example, if the user is feeling happy, the emotion recognition unit will prioritize recognizing that emotion. For example, if the user is feeling sad, the emotion recognition unit will prioritize recognizing that emotion. In this way, by determining the priority of emotion recognition based on the user's emotions, important emotions can be prioritized. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without using AI.

[0105] The emotion recognition unit can perform emotion recognition while considering the geographical distribution of the conversation. For example, the emotion recognition unit can perform emotion recognition based on geographical information of the location where the conversation took place. For example, the emotion recognition unit can perform emotion recognition based on place names mentioned in the conversation. For example, the emotion recognition unit can perform emotion recognition while considering the geographical distribution of the conversation. This makes it possible to perform emotion recognition more accurately by considering the geographical distribution. Some or all of the above processing in the emotion recognition unit may be performed using AI, for example, or without using AI.

[0106] The positive response unit can estimate the user's emotions and adjust its positive response method based on the estimated emotions. For example, if the user is feeling happy, the positive response unit will provide a positive response that emphasizes that emotion. For example, if the user is relaxed, the positive response unit will provide a positive response that softens the emotion. For example, if the user is excited, the positive response unit will provide a positive response that emphasizes the emotion. By adjusting the positive response method based on the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the positive response unit may be performed using AI, for example, or without using AI.

[0107] The positive response unit can improve the accuracy of positive responses by considering the relationships within the conversation. For example, the positive response unit considers the context of statements in the conversation when making a positive response. For example, the positive response unit considers the relationship between speakers in the conversation when making a positive response. For example, the positive response unit considers the context of statements in the conversation when making a positive response. As a result, the accuracy of positive responses is improved by considering the relationships within the conversation. Some or all of the above processing in the positive response unit may be performed using AI, for example, or without using AI.

[0108] The positive response unit can estimate the user's emotions and determine the priority of positive responses based on the estimated user emotions. For example, if the user is feeling happy, the positive response unit will prioritize responding to that emotion. For example, if the user is relaxed, the positive response unit will prioritize responding to that emotion. For example, if the user is excited, the positive response unit will prioritize responding to that emotion. In this way, by determining the priority of positive responses based on the user's emotions, important emotions can be responded to preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the positive response unit may be performed using AI, for example, or without using AI.

[0109] The positive response unit can make positive responses while considering the geographical distribution of the conversation. For example, the positive response unit can make positive responses based on geographical information of the location where the conversation took place. For example, the positive response unit can make positive responses based on place names mentioned in the conversation. For example, the positive response unit can make positive responses while considering the geographical distribution of the conversation. This makes it possible to make more accurate positive responses by considering the geographical distribution. Some or all of the above processing in the positive response unit may be performed using AI, for example, or without using AI.

[0110] The negative response unit can estimate the user's emotions and adjust its negative response method based on the estimated emotions. For example, if the user is angry, the negative response unit will provide a negative response that alleviates that emotion. For example, if the user is sad, the negative response unit will provide a negative response that alleviates that emotion. For example, if the user is stressed, the negative response unit will provide a negative response that alleviates that emotion. By adjusting the negative response method based on the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the negative response unit may be performed using AI, for example, or without AI.

[0111] The negative response unit can improve the accuracy of its negative responses by considering the relationships within the conversation. For example, the negative response unit considers the context of statements in the conversation when making a negative response. For example, the negative response unit considers the relationship between speakers in the conversation when making a negative response. For example, the negative response unit considers the context of statements in the conversation when making a negative response. This improves the accuracy of negative responses by considering the relationships within the conversation. Some or all of the above processing in the negative response unit may be performed using AI, for example, or without using AI.

[0112] The negative response unit can estimate the user's emotions and determine the priority of negative responses based on the estimated user emotions. For example, if the user is angry, the negative response unit will prioritize responding to that emotion. For example, if the user is sad, the negative response unit will prioritize responding to that emotion. For example, if the user is stressed, the negative response unit will prioritize responding to that emotion. In this way, by determining the priority of negative responses based on the user's emotions, important emotions can be prioritized. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the negative response unit may be performed using AI, for example, or without using AI.

[0113] The negative response unit can perform negative responses while considering the geographical distribution of the conversation. For example, the negative response unit can perform negative responses based on geographical information of the location where the conversation took place. For example, the negative response unit can perform negative responses based on place names mentioned in the conversation. For example, the negative response unit can perform negative responses while considering the geographical distribution of the conversation. This makes it possible to perform more accurate negative responses by considering the geographical distribution. Some or all of the above processing in the negative response unit may be performed using AI, for example, or without using AI.

[0114] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0115] AI speaker systems can analyze the tone and speed of a user's voice to estimate their emotions. For example, if a user speaks quickly, the system can estimate that the user is feeling tense or anxious and offer relaxing remarks. Conversely, if a user speaks slowly, the system can estimate that the user is relaxed and offer calm responses. Furthermore, if the user's voice has a high tone, the system can estimate that the user is excited and offer remarks to alleviate that excitement. By providing appropriate responses based on the user's voice tone and speed, more natural conversations become possible.

[0116] AI speaker systems can analyze a user's facial expressions and estimate their emotions. For example, if a user is smiling, the system can estimate that they are feeling happy and provide a positive response. If a user is frowning, the system can estimate that they are feeling confused or anxious and offer reassuring remarks. Furthermore, if a user is wide-eyed, the system can estimate that they are feeling surprised and offer reassuring remarks. This allows for more emotionally resonant conversations by providing appropriate responses based on the user's facial expressions.

[0117] AI speaker systems can analyze user gestures and estimate their emotions. For example, if a user is waving their hands, the system can estimate anger or frustration and offer calming remarks. If a user is crossing their arms, the system can estimate defensiveness and offer reassuring remarks. Furthermore, if a user is holding their hands outstretched, the system can estimate openness and offer positive responses. This allows for more natural conversations by providing appropriate responses based on the user's gestures.

[0118] AI speaker systems can analyze a user's past conversation history and estimate their emotions. For example, if a user has felt anger over a particular topic in the past, the system can respond carefully when that topic comes up again. Similarly, if a user has felt joy over a specific topic in the past, the system can promote positive conversation by actively bringing up that topic. Furthermore, if a user has felt sadness over a particular topic in the past, the system can avoid negative emotions by avoiding that topic. This allows for more personalized conversations by providing appropriate responses based on the user's past conversation history.

[0119] AI speaker systems can analyze a user's social media activity and estimate their emotions. For example, if a user makes positive posts on social media, the system can estimate that they are feeling happy and respond positively. Conversely, if a user makes negative posts, the system can estimate that they are feeling sad or angry and offer comforting remarks. Furthermore, if a user has participated in a specific event, the system can engage their interest by bringing up topics related to that event. This allows for more personalized conversations by providing appropriate responses based on the user's social media activity.

[0120] AI speaker systems can analyze a user's health data and estimate their emotions. For example, if a user's heart rate is elevated, the system can estimate they are feeling stressed or excited and offer suggestions to help them relax. Similarly, if a user's sleep data indicates insufficient sleep, the system can estimate they are feeling tired or irritable and offer suggestions to rest. Furthermore, if a user's exercise data shows increased activity, the system can estimate they are feeling energetic and offer positive responses. This allows for more health-conscious conversations by providing appropriate responses based on the user's health data.

[0121] AI speaker systems can analyze a user's music playback history and estimate their emotions. For example, if a user is playing upbeat music, the system can estimate that they are feeling excited or happy and provide a positive response. If a user is playing slow-tempo music, the system can estimate that they are feeling relaxed or calm and provide a gentle response. Furthermore, if a user is playing sad music, the system can estimate that they are feeling sad and offer comforting remarks. This allows for more emotionally resonant conversations by providing appropriate responses based on the user's music playback history.

[0122] AI speaker systems can analyze a user's purchase history and estimate their interests. For example, if a user frequently purchases products from a particular brand, the system can engage them by discussing topics related to that brand. Similarly, if a user purchases products from a specific category, the system can attract their interest by providing information related to that category. Furthermore, it can improve user satisfaction by offering advice and usage instructions related to recently purchased items. This enables more personalized conversations by providing appropriate responses based on the user's purchase history.

[0123] The AI ​​speaker system can analyze the user's calendar information and provide appropriate responses based on the user's schedule. For example, if the user has a busy schedule, it can provide short, to-the-point responses. If the user has relaxed time, it can provide responses that include detailed explanations. Furthermore, if the user is attending a specific event, it can engage the user's interest by providing information related to that event. This enables more personalized conversations by providing appropriate responses based on the user's calendar information.

[0124] AI speaker systems can analyze a user's geographical location and provide appropriate responses based on their current location. For example, if a user is at home, the system can offer remarks to encourage relaxation within the home. If a user is in the office, it can provide work-related information to improve their productivity. Furthermore, if a user is traveling, it can enhance their travel experience by providing relevant tourist information and restaurant recommendations. This enables more personalized conversations by providing appropriate responses based on the user's geographical location.

[0125] The following briefly describes the processing flow for example form 2.

[0126] Step 1: The recording unit records conversations. For example, it continuously records conversations between parents and children or husbands and wives, and records the content of the conversations in detail so that they can be analyzed later. Step 2: The text conversion unit converts the conversation recorded by the recording unit into text. For example, speech recognition technology is used to transcribe the conversation in detail so that it can be analyzed later. Step 3: The analysis unit analyzes the content transcribed by the text conversion unit and infers emotions. For example, it uses natural language processing (NLP) and sentiment analysis to analyze the content of the conversation, determine the fluctuations in speech, and grasp changes in negative and positive emotions in real time. Step 4: The speaking unit makes appropriate statements based on the emotions inferred by the analysis unit. For example, if a child is angry during a conversation with their parent, the speaking unit might say, "Hey, you're being a little too angry!" to prevent the emotion from spreading. If the child is happy, the speaking unit might say, "You both seem to be having fun today, did something good happen?" to reinforce the positive emotion.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0129] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the recording unit, text conversion unit, analysis unit, speech unit, emotion recognition unit, positive response unit, and negative response unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the recording unit records the conversation using the microphone 38B of the smart device 14. The text conversion unit converts the speech into text using the processor 46 of the smart device 14. The analysis unit analyzes the texted content using the identification processing unit 290 of the data processing unit 12 and infers the emotion. The speech unit makes appropriate statements using the speaker 40B of the smart device 14. The emotion recognition unit grasps changes in emotion in real time using the identification processing unit 290 of the data processing unit 12. The positive response unit makes statements that reinforce positive emotions using the control unit 46A of the smart device 14. The negative response unit makes statements that suppress negative emotions using the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0131] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0132] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the recording unit, text conversion unit, analysis unit, speech unit, emotion recognition unit, positive response unit, and negative response unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the recording unit records the conversation using the microphone 238 of the smart glasses 214. The text conversion unit converts the speech into text using the processor 46 of the smart glasses 214. The analysis unit analyzes the texted content using the identification processing unit 290 of the data processing unit 12 and infers the emotion. The speech unit makes appropriate statements using the speaker 240 of the smart glasses 214. The emotion recognition unit grasps changes in emotion in real time using the identification processing unit 290 of the data processing unit 12. The positive response unit makes statements that reinforce positive emotions using the control unit 46A of the smart glasses 214. The negative response unit makes statements that suppress negative emotions using the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0147] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0148] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0157] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

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

[0159] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0161] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the recording unit, text conversion unit, analysis unit, speech unit, emotion recognition unit, positive response unit, and negative response unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the recording unit records the conversation using the microphone 238 of the headset terminal 314. The text conversion unit converts the speech into text using the processor 46 of the headset terminal 314. The analysis unit analyzes the texted content using the identification processing unit 290 of the data processing unit 12 and infers the emotion. The speech unit makes appropriate statements using the speaker 240 of the headset terminal 314. The emotion recognition unit grasps changes in emotion in real time using the identification processing unit 290 of the data processing unit 12. The positive response unit makes statements that reinforce positive emotions using the control unit 46A of the headset terminal 314. The negative response unit makes statements that suppress negative emotions using the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0163] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0164] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0165] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0166] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0167] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0169] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0170] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0171] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0172] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0173] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0174] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0175] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0176] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0177] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0178] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0179] Each of the multiple elements described above, including the recording unit, text conversion unit, analysis unit, speech unit, emotion recognition unit, positive response unit, and negative response unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the recording unit records the conversation using the microphone 238 of the robot 414. The text conversion unit converts the speech into text using the processor 46 of the robot 414. The analysis unit analyzes the texted content using the identification processing unit 290 of the data processing unit 12 and infers the emotion. The speech unit makes appropriate statements using the speaker 240 of the robot 414. The emotion recognition unit grasps changes in emotion in real time using the identification processing unit 290 of the data processing unit 12. The positive response unit makes statements that reinforce positive emotions using the control unit 46A of the robot 414. The negative response unit makes statements that suppress negative emotions using the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0180] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0181] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0182] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0183] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0184] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0185] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0186] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0187] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0188] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0189] 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.

[0190] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0191] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0192] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0193] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0194] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0195] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0196] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0197] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0198] (Note 1) A recording unit for recording conversations, A text conversion unit that converts the conversation recorded by the recording unit into text, An analysis unit analyzes the content converted into text by the text conversion unit and infers emotions, A speaking unit that makes appropriate statements based on the emotions inferred by the analysis unit, Equipped with A system characterized by the following features. (Note 2) It is equipped with an emotion recognition unit that grasps changes in emotions in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) Equipped with a positive response section that enhances positive emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) It is equipped with a negative response unit that suppresses negative emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned recording unit is Always record conversations between parents and children, or between spouses. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned statement is, Make statements that give both parties a sense of awareness before emotions escalate. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned recording unit is It estimates the user's emotions and adjusts the timing of conversation recording based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned recording unit is When recording conversations, prioritize recording specific keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned recording unit is The system also records background noise and ambient sounds from conversations and uses them for later analysis. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned recording unit is It estimates the user's emotions and determines the priority of conversations to record based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned recording unit is Record conversations while taking the user's geographical location into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned recording unit is Analyze users' social media activity and record relevant conversations. The system described in Appendix 1, characterized by the features described herein. (Note 13) The text conversion unit, It estimates the user's emotions and adjusts the textual expression based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The text conversion unit, Adjust the level of detail in the text based on the importance of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The text conversion unit, Apply different text transcription algorithms depending on the category of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The text conversion unit, It estimates the user's emotions and adjusts the length of the text based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The text conversion unit, The text is converted to a document while taking into account the attribute information of the speakers in the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 18) The text conversion unit, Improve the accuracy of text transcription by referring to relevant literature for the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, We estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, Improve the accuracy of the analysis by considering the interrelationships in the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, The analysis takes into account the attribute information of the speakers in the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, It estimates the user's emotions and adjusts the display order of the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit, The analysis will take into account the geographical distribution of the conversations. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit, Referencing relevant literature on the conversation will improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned statement is, It estimates the user's emotions and adjusts the way the message is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned statement is, Adjust the level of detail in statements based on their importance in the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned statement is, Apply different speech algorithms depending on the category of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned statement is, It estimates the user's emotions and adjusts the length of their comments based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned statement is, When making a statement, take into account the attribute information of the speaker in the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned statement is, Referencing relevant literature on conversations improves the accuracy of statements. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned emotion recognition unit, It estimates the user's emotions and adjusts the method of understanding those emotions based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned emotion recognition unit, When assessing emotions, consider the interpersonal relationships in the conversation to improve the accuracy of emotional assessment. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned emotion recognition unit, It estimates the user's emotions and determines the priority of emotion recognition based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned emotion recognition unit, When assessing emotions, consider the geographical distribution of conversations. The system described in Appendix 2, characterized by the features described herein. (Note 35) The positive response unit is It estimates the user's emotions and adjusts the method of positive response based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 36) The positive response unit is When giving a positive response, improve the accuracy of the positive response by considering the reciprocal relationship of the conversation. The system described in Appendix 3, characterized by the features described herein. (Note 37) The positive response unit is It estimates the user's emotions and prioritizes positive responses based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The positive response unit is When giving a positive response, consider the geographical distribution of the conversation when making a positive response. The system described in Appendix 3, characterized by the features described herein. (Note 39) The negative response unit is It estimates the user's emotions and adjusts the method of negative responses based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 40) The negative response unit is When responding negatively, improve the accuracy of the negative response by considering the context of the conversation. The system described in Appendix 4, characterized by the features described herein. (Note 41) The negative response unit is It estimates the user's emotions and prioritizes negative responses based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The negative response unit is When responding negatively, consider the geographical distribution of the conversation when making your negative response. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A recording unit for recording conversations, A text conversion unit that converts the conversation recorded by the recording unit into text, An analysis unit analyzes the content converted into text by the text conversion unit and infers emotions, A speaking unit that makes appropriate statements based on the emotions inferred by the analysis unit, Equipped with A system characterized by the following features.

2. It is equipped with an emotion recognition unit that grasps changes in emotions in real time. The system according to feature 1.

3. Equipped with a positive response section that enhances positive emotions. The system according to feature 1.

4. It is equipped with a negative response unit that suppresses negative emotions. The system according to feature 1.

5. The aforementioned recording unit is Always record conversations between parents and children, or between spouses. The system according to feature 1.

6. The aforementioned statement is, Make statements that give both parties a sense of awareness before emotions escalate. The system according to feature 1.

7. The aforementioned recording unit is It estimates the user's emotions and adjusts the timing of conversation recording based on the estimated emotions. The system according to feature 1.

8. The aforementioned recording unit is When recording conversations, prioritize recording specific keywords or phrases. The system according to feature 1.

9. The aforementioned recording unit is The system also records background noise and ambient sounds from conversations and uses them for later analysis. The system according to feature 1.

10. The aforementioned recording unit is It estimates the user's emotions and determines the priority of conversations to record based on the estimated user emotions. The system according to feature 1.

Images