system

Abstract

The system according to this embodiment aims to automatically classify speakers based on conversation logs and provide the most appropriate topic. [Solution] The system according to the embodiment comprises an acquisition unit, a classification unit, a provision unit, and an analysis unit. The acquisition unit acquires conversation logs. The classification unit automatically classifies speakers based on the conversation logs acquired by the acquisition unit. The provision unit provides the most suitable topic based on the information of the speakers classified by the classification unit. The analysis unit analyzes the other party's reaction to the topic provided by the provision unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to provide an optimal topic based on the content of the conversation and the information of the speaker, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically classify speakers based on conversation logs and provide an optimal topic.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, a classification unit, a provision unit, and an analysis unit. The acquisition unit acquires conversation logs. The classification unit automatically classifies speakers based on the conversation logs acquired by the acquisition unit. The provision unit provides the most suitable topic based on the information of the speakers classified by the classification unit. The analysis unit analyzes the other party's reaction to the topic provided by the provision unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically classify speakers based on conversation logs and provide the most appropriate topic. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The conversation support system according to an embodiment of the present invention is a system that acquires conversation logs for each meeting and each person involved, and automatically classifies them by observing the changes in the frequency of the speaker's voice. The conversation support system provides the most suitable topic to the agent, taking into account previous conversation logs, the latest news, and the user's own situation. By analyzing the other party's reaction through image recognition, it is also possible to suggest topics similar to those that the user previously enjoyed. For example, the conversation support system acquires conversation logs for each meeting and each person involved. For example, it records the content of conversations at the beginning of a meeting or when meeting with a colleague. These conversation logs are saved for later reference. Next, the conversation support system automatically classifies the conversations by observing the changes in the frequency of the speaker's voice. Using speech recognition AI, it analyzes the characteristics of the speaker's voice and identifies the speaker. For example, if the frequency of speaker A's voice has a specific pattern, speaker A is identified based on that pattern. Furthermore, the conversation support system provides the most suitable topic to the agent, taking into account previous conversation logs, the latest news, and the user's own situation. For example, based on previous conversation logs, it identifies topics that speaker A is interested in and provides the latest news related to those topics. Furthermore, the system selects appropriate topics by considering speaker A's current situation (e.g., work progress or personal interests). By analyzing the other person's reactions through image recognition, it can also suggest topics similar to those the other person enjoyed in the past. For example, if the other person smiles, the system determines that the topic is favorable to them and offers a similar topic in the next conversation. This mechanism eliminates the problem of struggling to find icebreaker topics in meetings or conversations with colleagues, and prevents awkward situations caused by a lack of small talk topics. By providing optimal topics, the agent facilitates smoother conversations and boosts work motivation. This enables the conversation support system to acquire conversation logs, classify speakers, provide optimal topics, and analyze the other person's reactions.

[0029] The conversation support system according to this embodiment comprises an acquisition unit, a classification unit, a provision unit, and an analysis unit. The acquisition unit acquires conversation logs. Conversation logs include, but are not limited to, audio data, text data, and conversation metadata. The acquisition unit acquires conversation logs for each meeting or person, for example. For example, it records the content of conversations at the beginning of a meeting or when meeting with colleagues. These conversation logs are saved for later reference. The classification unit automatically classifies speakers based on the conversation logs acquired by the acquisition unit. The classification unit automatically classifies speakers by, for example, looking at the changes in the frequency of the speaker's voice. For example, it uses speech recognition AI to analyze the characteristics of the speaker's voice and identify the speaker. For example, if the frequency of speaker A's voice has a specific pattern, it identifies speaker A based on that pattern. The provision unit provides the most suitable topic based on the speaker information classified by the classification unit. The provision unit provides the most suitable topic based on, for example, previous conversation logs, the latest news, and its own situation. For example, based on previous conversation logs, the system identifies topics that speaker A is interested in and provides the latest news related to those topics. It also selects appropriate topics considering speaker A's current situation (e.g., work progress or personal interests). The analysis unit analyzes the other party's reaction to the topics provided by the provision unit. The analysis unit analyzes the other party's reaction using, for example, image recognition, and feeds back information to the provision unit to provide topics similar to those that the other party enjoyed in the past. For example, if the other party smiles, the system determines that the topic is favorable to them and provides a similar topic in the next conversation. This enables the conversation support system to acquire conversation logs, classify speakers, provide optimal topics, and analyze the other party's reactions.

[0030] The acquisition unit acquires conversation logs. These conversation logs include, but are not limited to, audio data, text data, and conversation metadata. For example, the unit acquires conversation logs for each meeting or individual. For instance, it records the content of conversations at the beginning of a meeting or when meeting with colleagues. These conversation logs are saved for later reference. Specifically, the acquisition unit has a function to automatically start recording at the beginning of a conversation and stop recording when the conversation ends. Audio data is collected in high quality through a microphone, and clear audio data is obtained using noise reduction technology. Text data is obtained by transcribing the audio data in real time using speech recognition technology, and the content of the conversation is saved in text format. Conversation metadata includes information such as the date, time, location, and participants of the conversation; this information is important for understanding the context of the conversation. The acquisition unit centrally manages this data and stores it in a database for easy searching and referencing later. Furthermore, the acquisition unit ensures data security by encrypting data and controlling access for privacy protection. This allows the acquisition unit to efficiently acquire detailed records of conversations and provide the data necessary for subsequent processing.

[0031] The classification unit automatically classifies speakers based on conversation logs acquired by the acquisition unit. For example, the classification unit automatically classifies speakers by looking at the changes in the frequency of their voices. Specifically, it uses speech recognition AI to analyze the characteristics of speakers' voices and identify them. For example, if the frequency of speaker A's voice has a specific pattern, it identifies speaker A based on that pattern. The speech recognition AI uses deep learning technology to learn from large amounts of speech data and can identify speaker characteristics with high accuracy. Furthermore, the classification unit also analyzes the content of the speaker's speech and characteristics of their speaking style (e.g., speaking speed, intonation, accent, etc.) to help identify speakers. As a result, the classification unit can accurately identify each speaker even in conversations with multiple speakers and classify the conversation logs by speaker. The classification unit also saves the speaker identification results in a database for later reference. This allows the classification unit to organize the conversation content by speaker and provide the information necessary for subsequent processing.

[0032] The service provider provides the most suitable topics based on speaker information classified by the classification unit. For example, the service provider provides the most suitable topics based on past conversation logs, the latest news, and the speaker's own situation. Specifically, the service provider analyzes past conversation logs to identify topics that speaker A is interested in. For example, it extracts hobbies and interests that speaker A has frequently discussed in the past and provides the latest news and information related to those topics. The service provider also selects appropriate topics considering speaker A's current situation (for example, work progress and personal interests). This includes referring to speaker A's schedule and recent activity history to provide highly relevant topics. Furthermore, the service provider uses AI to select topics and provide the most interesting topics for speaker A. The AI ​​analyzes conversation logs using natural language processing technology to understand speaker A's interests and concerns. This allows the service provider to provide the most suitable topics for speaker A and improve the quality of the conversation.

[0033] The analysis department analyzes the other party's reactions to topics provided by the content provider department. For example, the analysis department analyzes the other party's reactions using image recognition and provides feedback to the content provider department to help them provide topics similar to those the other party previously enjoyed. Specifically, the analysis department uses a camera to analyze the other party's facial expressions and gestures in real time to determine their emotional state. For example, if the other party smiles, the analysis department determines that the topic is favorable to them and provides a similar topic in the next conversation. Conversely, if the other party shows no interest or displays an unpleasant expression, the analysis department provides feedback to avoid that topic. Furthermore, the analysis department analyzes audio data to detect changes in the other party's tone of voice and speaking style. This allows for a more accurate understanding of the other party's emotions and level of interest. The analysis department provides this information back to the content provider department, helping them to provide more appropriate topics in the next conversation. In this way, the analysis department can improve the quality of conversations and facilitate smoother communication with the other party.

[0034] The acquisition unit can acquire conversation logs for each meeting and each person involved. For example, the acquisition unit records the content of conversations at the beginning of a meeting or when meeting with colleagues. These conversation logs are saved for later reference. The acquisition unit can, for example, record the content of a meeting as audio data and convert it to text data. The acquisition unit can also record conversation metadata (e.g., date and time of the conversation, location, participants, etc.). This allows for detailed conversation recording by acquiring conversation logs for each meeting and each person involved. Conversation logs include, but are not limited to, audio data, text data, and conversation metadata. Some or all of the processing described above in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can record the content of a conversation as audio data, input it into a generating AI, and have the generating AI perform the conversion from audio data to text data.

[0035] The classification unit can automatically classify speakers by observing the frequency changes of their voices. For example, the classification unit uses speech recognition AI to analyze the characteristics of a speaker's voice and identify the speaker. For example, if speaker A's voice frequency has a specific pattern, speaker A can be identified based on that pattern. The classification unit can also estimate a speaker's emotional state by observing the frequency changes of their voices. For example, if the frequency of a speaker's voice increases, it can be estimated that the speaker is excited. This makes it possible to identify speakers by automatically classifying them based on the frequency changes of their voices. The frequency changes of a voice include, but are not limited to, the frequency range and the pattern of changes. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input the frequency change data of speakers' voices into a generating AI and have the generating AI perform speaker identification.

[0036] The service provider can provide the most suitable topics based on previous conversation logs, the latest news, and the user's own situation. For example, based on previous conversation logs, the service provider can identify topics that speaker A is interested in and provide the latest news related to those topics. The service provider can also select appropriate topics by considering speaker A's current situation (e.g., work progress or personal interests). For example, the service provider can provide news articles related to topics that speaker A has recently become interested in. The service provider can also select appropriate topics by considering speaker A's current emotional state. For example, if speaker A is relaxed, it can provide light topics, and if speaker A is tense, it can provide topics to help them relax. This allows the conversation to proceed smoothly by providing the most suitable topics based on previous conversation logs, the latest news, and the user's own situation. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can input previous conversation logs, the latest news, and its own situation data into a generating AI and have the generating AI select the most suitable topics.

[0037] The analysis unit can analyze the other party's reactions using image recognition and feed that information back to the supply unit to provide topics similar to those the other party enjoyed in the past. For example, if the other party smiles, the analysis unit will determine that the topic is favorable to them and provide a similar topic in the next conversation. The analysis unit can also analyze reactions by analyzing not only the other party's facial expressions but also their gestures and changes in posture. For example, if the other party nods, the analysis unit will determine that they are interested in the topic and provide a related topic in the next conversation. This improves the quality of conversation by analyzing the other party's reactions and providing topics similar to those the other party enjoyed in the past. Image recognition includes, but is not limited to, the algorithms used and the objects to be recognized. Some or all of the processing described above in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the other party's reaction data into a generating AI and have the generating AI perform the reaction analysis.

[0038] The acquisition unit can automatically evaluate importance based on the content of conversations and prioritize the acquisition of important conversations. For example, if a specific keyword appears in a conversation, the acquisition unit will prioritize the acquisition of that conversation. The acquisition unit can also analyze the tone and emphasized parts of a conversation and prioritize the acquisition of important conversations. Furthermore, the acquisition unit can also consider the length and frequency of conversations and prioritize the acquisition of important conversations. This ensures that important information is not missed by evaluating importance based on the content of conversations and prioritizing the acquisition of important conversations. Importance includes, but is not limited to, the content of the conversation and the attributes of the speakers. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input conversation content data into a generating AI and have the generating AI perform the importance evaluation.

[0039] The acquisition unit can analyze background and ambient sounds in a conversation and remove noise to obtain a clear log. For example, the acquisition unit can filter background sounds during a conversation and remove noise. The acquisition unit can also analyze ambient sounds and highlight important parts of the conversation. Furthermore, the acquisition unit can use noise cancellation technology when recording a conversation to obtain a clear log. This allows for the acquisition of a clear conversation log by analyzing background and ambient sounds and removing noise. Background and ambient sounds include, but are not limited to, speech filtering technology and noise reduction algorithms. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input conversation background sound data into a generating AI and have the generating AI perform noise reduction.

[0040] The acquisition unit can prioritize the acquisition of highly relevant logs by considering the location and time of the conversation. For example, the acquisition unit can prioritize the acquisition of highly relevant logs based on the location where the conversation took place. It can also prioritize the acquisition of highly relevant logs based on the time of the conversation. Furthermore, the acquisition unit can analyze the relationship between the content of the conversation and the location and time of the conversation and determine the priority. This allows for the efficient acquisition of important conversation logs by prioritizing the acquisition of highly relevant logs by considering the location and time of the conversation. Location and time of the conversation include, but are not limited to, the method of identifying the location and the division of the time of the conversation. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the conversation location and time of the conversation data into a generating AI and have the generating AI prioritize highly relevant logs.

[0041] The acquisition unit can acquire logs while considering the attribute information of the conversation participants. For example, the acquisition unit can acquire logs based on the occupation or position of the conversation participants. The acquisition unit can also acquire logs while considering the past statements of the conversation participants. Furthermore, the acquisition unit can acquire logs based on the interests or areas of expertise of the conversation participants. This allows for the efficient acquisition of important conversation logs by considering the attribute information of the conversation participants. Participant attribute information includes, but is not limited to, age, gender, and occupation. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input the attribute information data of the conversation participants into a generating AI and have the generating AI perform log acquisition.

[0042] The classification unit can improve classification accuracy by analyzing the characteristics of the speaker's speech, in addition to the changes in the frequency of the speaker's voice. For example, the classification unit can improve classification accuracy by analyzing the speaker's speaking speed. It can also improve classification accuracy by analyzing the speaker's intonation. Furthermore, it can also improve classification accuracy by analyzing the rhythm of the speaker's speech. In this way, classification accuracy is improved by analyzing the characteristics of the speaker's speech. These characteristics of speech include, but are not limited to, speaking speed, intonation, and rhythm. Some or all of the above processing in the classification unit may be performed using, for example, AI, or not using AI. For example, the classification unit can input speaker speech characteristic data into a generating AI and have the generating AI perform the improvement of classification accuracy.

[0043] The classification unit can identify speakers by referring to past conversation logs when classifying speakers. For example, the classification unit can identify speakers by referring to past conversation logs. The classification unit can also identify speakers by analyzing patterns in past conversation logs. Furthermore, the classification unit can identify speakers by considering the frequency and content of past conversation logs. This makes speaker identification easier by referring to past conversation logs. Past conversation logs include, but are not limited to, the retention period and search methods. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input past conversation log data into a generating AI and have the generating AI perform speaker identification.

[0044] The classification unit can classify speakers while considering their geographical accent and dialect. For example, the classification unit can analyze and classify speakers based on their geographical accent. It can also analyze and classify speakers based on their dialect. Furthermore, the classification unit can classify speakers while considering their geographical background. This improves classification accuracy by considering speakers' geographical accent and dialect. Geographical accent and dialect include, but are not limited to, regional characteristics and dialect types. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input speakers' geographical accent and dialect data into a generating AI and have the generating AI perform the classification.

[0045] The classification unit can classify speakers based on their occupation or field of expertise. For example, the classification unit can analyze and classify the speaker's occupation. It can also analyze and classify the speaker's field of expertise. Furthermore, the classification unit can adjust the classification criteria based on the speaker's occupation or field of expertise. This improves classification accuracy by classifying based on the speaker's occupation or field of expertise. Occupation and field of expertise include, but are not limited to, the type of occupation and the scope of expertise. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input speaker occupation and field of expertise data into a generating AI and have the generating AI perform the classification.

[0046] The content provider can select the most suitable topic by considering the speaker's past statements and interests when selecting a topic to offer. For example, the content provider can analyze the speaker's past statements and select the most suitable topic. The content provider can also select the most suitable topic by considering the speaker's interests. Furthermore, the content provider can combine the speaker's past statements and interests to select the most suitable topic. This allows the content provider to offer the most suitable topic by considering the speaker's past statements and interests. Past statements and interests include, but are not limited to, the method of recording statements and the method of identifying interests. Some or all of the above processing in the content provider may be performed using AI, for example, or without AI. For example, the content provider can input the speaker's past statements and interest data into a generating AI and have the generating AI select the most suitable topic.

[0047] The content provider can select topics by considering current social trends and news when selecting topics to offer. For example, the content provider can analyze current social trends and select the most suitable topic. It can also select the most suitable topic by considering the latest news. Furthermore, it can combine social trends and news to select the most suitable topic. This allows for the provision of appropriate topics by considering current social trends and news. Social trends and news include, but are not limited to, news sources and methods for identifying trends. Some or all of the above processing in the content provider may be performed using AI, for example, or without AI. For example, the content provider can input social trend and news data into a generating AI and have the generating AI perform topic selection.

[0048] The content provider can select topics to offer by considering the speaker's geographical background and culture. For example, the content provider can analyze the speaker's geographical background and select the most appropriate topic. It can also select the most appropriate topic by considering the speaker's culture. Furthermore, it can combine the speaker's geographical background and culture to select the most appropriate topic. This allows for the provision of appropriate topics by considering the speaker's geographical background and culture. Geographical background and culture include, but are not limited to, regional cultures and methods for identifying backgrounds. Some or all of the above processing in the content provider may be performed using AI, for example, or without AI. For example, the content provider can input the speaker's geographical background and cultural data into a generating AI and have the generating AI perform topic selection.

[0049] The content provider can select topics related to the speaker's occupation or field of expertise when selecting topics to offer. For example, the content provider can analyze the speaker's occupation and select the most suitable topic. It can also select the most suitable topic by considering the speaker's field of expertise. Furthermore, it can combine topics related to the speaker's occupation and field of expertise to select the most suitable topic. This allows for the provision of more interesting topics by offering topics related to the speaker's occupation and field of expertise. Occupation and field of expertise include, but are not limited to, the type of occupation and the scope of expertise. Some or all of the processing described above in the content provider may be performed using AI, for example, or without AI. For example, the content provider can input the speaker's occupation and field of expertise data into a generating AI and have the generating AI perform topic selection.

[0050] The analysis unit can improve accuracy by analyzing not only facial expressions but also gestures and changes in posture when analyzing the other party's reaction. For example, the analysis unit can analyze the other party's gestures to improve the accuracy of the reaction. The analysis unit can also analyze changes in the other party's posture to improve the accuracy of the reaction. Furthermore, the analysis unit can comprehensively analyze the other party's facial expressions, gestures, and changes in posture to improve the accuracy of the reaction. This improves the accuracy of reaction analysis by analyzing not only facial expressions but also gestures and changes in posture. Changes in gestures and posture include, but are not limited to, the type of movement and patterns of change. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the other party's gestures and changes in posture into a generating AI and have the generating AI perform the reaction analysis.

[0051] The analysis unit can improve the accuracy of its analysis of the other party's reaction by referring to past reaction data. For example, the analysis unit can refer to past reaction data to analyze the current reaction. The analysis unit can also analyze patterns in past reaction data to predict the current reaction. Furthermore, the analysis unit can compare past reaction data with the current reaction to improve the accuracy of its analysis. This improves the accuracy of the analysis of the current reaction by referring to past reaction data. Past reaction data includes, but is not limited to, the retention period and search method. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input past reaction data into a generating AI and have the generating AI perform the reaction analysis.

[0052] The analysis unit can perform its analysis by considering the time and location of the reaction when analyzing the other party's reaction. For example, the analysis unit can perform its analysis by considering the time of day when the reaction occurred. It can also perform its analysis by considering the location when the reaction occurred. Furthermore, the analysis unit can perform its analysis by combining the time and location of the reaction. This improves the accuracy of the analysis by considering the time and location of the reaction. The time and location include, but are not limited to, time zone divisions and methods for identifying locations. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input reaction time and location data into a generating AI and have the generating AI perform the analysis.

[0053] The analysis unit can perform its analysis by considering the cultural elements underlying the reaction when analyzing the other party's reaction. For example, the analysis unit can analyze the cultural elements underlying the reaction. The analysis unit can also perform its analysis by considering the cultural background of the reaction. Furthermore, the analysis unit can combine the cultural elements and background of the reaction in its analysis. This improves the accuracy of the analysis by considering the cultural elements underlying the reaction. Cultural elements include, but are not limited to, the type of culture and the method of identifying the elements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input cultural element data of the reaction into a generating AI and have the generating AI perform the analysis.

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

[0055] The conversation support system can refer to a user's past conversation history and prioritize providing topics the user has previously shown interest in. For example, if a user has shown interest in a particular topic in a previous conversation, it can provide the latest information related to that topic. Similarly, if a user has previously shown interest in a particular news story, it can provide the latest events related to that news story. Furthermore, it can provide information related to hobbies and interests the user has previously discussed. This allows the system to leverage the user's past conversation history to provide a more personalized conversation experience. The system stores the user's conversation history in a database and references it as needed. Natural language processing techniques can be used to analyze the conversation history.

[0056] The conversation support system can understand the user's current activity status and provide topics appropriate to that situation. For example, if the user is working, it can provide work-related topics. If the user is on a break, it can provide relaxing topics. Furthermore, if the user is exercising, it can provide exercise-related topics. This allows the system to provide appropriate topics according to the user's current activity status. The system acquires the user's activity status from sensors and user input data, and analyzes the activity status. Based on the analysis results, it selects appropriate topics and provides them to the user.

[0057] The conversation support system can analyze a user's past conversation history to identify topics the user wants to avoid and prevent them from discussing those topics. For example, if a user has previously reacted negatively to a particular topic, the system can avoid that topic. Similarly, if a user has previously reacted negatively to a particular news story, the system can avoid topics related to that news story. Furthermore, it can avoid topics that a user has previously stated they do not want to discuss. This allows the system to leverage the user's past conversation history to avoid topics they wish to avoid. The system stores the user's conversation history in a database and references it as needed. Natural language processing techniques can be used to analyze the conversation history.

[0058] The conversation support system can understand the user's current environment and provide topics appropriate to that environment. For example, if the user is in a quiet place, it can provide topics suitable for a quiet environment. If the user is in a noisy place, it can provide topics suitable for a noisy environment. Furthermore, if the user is outdoors, it can provide topics suitable for an outdoor environment. In this way, it can provide appropriate topics according to the user's current environment. The system acquires user environment data from sensors and user input data and analyzes the environment. Based on the analysis results, it selects appropriate topics and provides them to the user.

[0059] A conversation support system can analyze a user's past conversation history to identify topics of particular interest and provide information related to those topics. For example, if a user has frequently discussed a particular hobby in the past, the system can provide the latest information related to that hobby. Similarly, if a user has shown interest in a particular news story in the past, the system can provide the latest events related to that news. Furthermore, if a user has shown interest in a particular field in the past, the system can provide information related to that field. This allows the system to leverage the user's past conversation history to provide more personalized information. The system stores the user's conversation history in a database and references it as needed. Natural language processing techniques can be used to analyze the conversation history.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The acquisition unit acquires the conversation log. The conversation log includes audio data, text data, and conversation metadata. The acquisition unit acquires the conversation log for each meeting and person, for example, recording the content of conversations at the beginning of a meeting or when meeting with colleagues. This conversation log is saved for later reference. Step 2: The classification unit automatically classifies speakers based on the conversation logs acquired by the acquisition unit. The classification unit automatically classifies speakers by observing the frequency changes of their voices, and identifies speakers by analyzing the characteristics of their voices using speech recognition AI. For example, if the frequency of speaker A's voice has a specific pattern, speaker A is identified based on that pattern. Step 3: The provider unit provides the most suitable topic based on the speaker information classified by the classification unit. The provider unit provides the most suitable topic based on previous conversation logs, the latest news, and its own situation. For example, based on previous conversation logs, it identifies topics that speaker A is interested in and provides the latest news related to those topics. It also selects appropriate topics by considering speaker A's current situation (e.g., work progress or personal interests). Step 4: The analysis unit analyzes the other party's reaction to the topic provided by the provision unit. The analysis unit analyzes the other party's reaction using image recognition and feeds back information to the provision unit to provide topics similar to those the other party enjoyed in the past. For example, if the other party smiles, the analysis unit determines that the topic is favorable to the other party and provides a similar topic in the next conversation.

[0062] (Example of form 2) The conversation support system according to an embodiment of the present invention is a system that acquires conversation logs for each meeting and each person involved, and automatically classifies them by observing the changes in the frequency of the speaker's voice. The conversation support system provides the most suitable topic to the agent, taking into account previous conversation logs, the latest news, and the user's own situation. By analyzing the other party's reaction through image recognition, it is also possible to suggest topics similar to those that the user previously enjoyed. For example, the conversation support system acquires conversation logs for each meeting and each person involved. For example, it records the content of conversations at the beginning of a meeting or when meeting with a colleague. These conversation logs are saved for later reference. Next, the conversation support system automatically classifies the conversations by observing the changes in the frequency of the speaker's voice. Using speech recognition AI, it analyzes the characteristics of the speaker's voice and identifies the speaker. For example, if the frequency of speaker A's voice has a specific pattern, speaker A is identified based on that pattern. Furthermore, the conversation support system provides the most suitable topic to the agent, taking into account previous conversation logs, the latest news, and the user's own situation. For example, based on previous conversation logs, it identifies topics that speaker A is interested in and provides the latest news related to those topics. Furthermore, the system selects appropriate topics by considering speaker A's current situation (e.g., work progress or personal interests). By analyzing the other person's reactions through image recognition, it can also suggest topics similar to those the other person enjoyed in the past. For example, if the other person smiles, the system determines that the topic is favorable to them and offers a similar topic in the next conversation. This mechanism eliminates the problem of struggling to find icebreaker topics in meetings or conversations with colleagues, and prevents awkward situations caused by a lack of small talk topics. By providing optimal topics, the agent facilitates smoother conversations and boosts work motivation. This enables the conversation support system to acquire conversation logs, classify speakers, provide optimal topics, and analyze the other person's reactions.

[0063] The conversation support system according to this embodiment comprises an acquisition unit, a classification unit, a provision unit, and an analysis unit. The acquisition unit acquires conversation logs. Conversation logs include, but are not limited to, audio data, text data, and conversation metadata. The acquisition unit acquires conversation logs for each meeting or person, for example. For example, it records the content of conversations at the beginning of a meeting or when meeting with colleagues. These conversation logs are saved for later reference. The classification unit automatically classifies speakers based on the conversation logs acquired by the acquisition unit. The classification unit automatically classifies speakers by, for example, looking at the changes in the frequency of the speaker's voice. For example, it uses speech recognition AI to analyze the characteristics of the speaker's voice and identify the speaker. For example, if the frequency of speaker A's voice has a specific pattern, it identifies speaker A based on that pattern. The provision unit provides the most suitable topic based on the speaker information classified by the classification unit. The provision unit provides the most suitable topic based on, for example, previous conversation logs, the latest news, and its own situation. For example, based on previous conversation logs, the system identifies topics that speaker A is interested in and provides the latest news related to those topics. It also selects appropriate topics considering speaker A's current situation (e.g., work progress or personal interests). The analysis unit analyzes the other party's reaction to the topics provided by the provision unit. The analysis unit analyzes the other party's reaction using, for example, image recognition, and feeds back information to the provision unit to provide topics similar to those that the other party enjoyed in the past. For example, if the other party smiles, the system determines that the topic is favorable to them and provides a similar topic in the next conversation. This enables the conversation support system to acquire conversation logs, classify speakers, provide optimal topics, and analyze the other party's reactions.

[0064] The acquisition unit acquires conversation logs. These conversation logs include, but are not limited to, audio data, text data, and conversation metadata. For example, the unit acquires conversation logs for each meeting or individual. For instance, it records the content of conversations at the beginning of a meeting or when meeting with colleagues. These conversation logs are saved for later reference. Specifically, the acquisition unit has a function to automatically start recording at the beginning of a conversation and stop recording when the conversation ends. Audio data is collected in high quality through a microphone, and clear audio data is obtained using noise reduction technology. Text data is obtained by transcribing the audio data in real time using speech recognition technology, and the content of the conversation is saved in text format. Conversation metadata includes information such as the date, time, location, and participants of the conversation; this information is important for understanding the context of the conversation. The acquisition unit centrally manages this data and stores it in a database for easy searching and referencing later. Furthermore, the acquisition unit ensures data security by encrypting data and controlling access for privacy protection. This allows the acquisition unit to efficiently acquire detailed records of conversations and provide the data necessary for subsequent processing.

[0065] The classification unit automatically classifies speakers based on conversation logs acquired by the acquisition unit. For example, the classification unit automatically classifies speakers by looking at the changes in the frequency of their voices. Specifically, it uses speech recognition AI to analyze the characteristics of speakers' voices and identify them. For example, if the frequency of speaker A's voice has a specific pattern, it identifies speaker A based on that pattern. The speech recognition AI uses deep learning technology to learn from large amounts of speech data and can identify speaker characteristics with high accuracy. Furthermore, the classification unit also analyzes the content of the speaker's speech and characteristics of their speaking style (e.g., speaking speed, intonation, accent, etc.) to help identify speakers. As a result, the classification unit can accurately identify each speaker even in conversations with multiple speakers and classify the conversation logs by speaker. The classification unit also saves the speaker identification results in a database for later reference. This allows the classification unit to organize the conversation content by speaker and provide the information necessary for subsequent processing.

[0066] The service provider provides the most suitable topics based on speaker information classified by the classification unit. For example, the service provider provides the most suitable topics based on past conversation logs, the latest news, and the speaker's own situation. Specifically, the service provider analyzes past conversation logs to identify topics that speaker A is interested in. For example, it extracts hobbies and interests that speaker A has frequently discussed in the past and provides the latest news and information related to those topics. The service provider also selects appropriate topics considering speaker A's current situation (for example, work progress and personal interests). This includes referring to speaker A's schedule and recent activity history to provide highly relevant topics. Furthermore, the service provider uses AI to select topics and provide the most interesting topics for speaker A. The AI ​​analyzes conversation logs using natural language processing technology to understand speaker A's interests and concerns. This allows the service provider to provide the most suitable topics for speaker A and improve the quality of the conversation.

[0067] The analysis department analyzes the other party's reactions to topics provided by the content provider department. For example, the analysis department analyzes the other party's reactions using image recognition and provides feedback to the content provider department to help them provide topics similar to those the other party previously enjoyed. Specifically, the analysis department uses a camera to analyze the other party's facial expressions and gestures in real time to determine their emotional state. For example, if the other party smiles, the analysis department determines that the topic is favorable to them and provides a similar topic in the next conversation. Conversely, if the other party shows no interest or displays an unpleasant expression, the analysis department provides feedback to avoid that topic. Furthermore, the analysis department analyzes audio data to detect changes in the other party's tone of voice and speaking style. This allows for a more accurate understanding of the other party's emotions and level of interest. The analysis department provides this information back to the content provider department, helping them to provide more appropriate topics in the next conversation. In this way, the analysis department can improve the quality of conversations and facilitate smoother communication with the other party.

[0068] The acquisition unit can acquire conversation logs for each meeting and each person involved. For example, the acquisition unit records the content of conversations at the beginning of a meeting or when meeting with colleagues. These conversation logs are saved for later reference. The acquisition unit can, for example, record the content of a meeting as audio data and convert it to text data. The acquisition unit can also record conversation metadata (e.g., date and time of the conversation, location, participants, etc.). This allows for detailed conversation recording by acquiring conversation logs for each meeting and each person involved. Conversation logs include, but are not limited to, audio data, text data, and conversation metadata. Some or all of the processing described above in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can record the content of a conversation as audio data, input it into a generating AI, and have the generating AI perform the conversion from audio data to text data.

[0069] The classification unit can automatically classify speakers by observing the frequency changes of their voices. For example, the classification unit uses speech recognition AI to analyze the characteristics of a speaker's voice and identify the speaker. For example, if speaker A's voice frequency has a specific pattern, speaker A can be identified based on that pattern. The classification unit can also estimate a speaker's emotional state by observing the frequency changes of their voices. For example, if the frequency of a speaker's voice increases, it can be estimated that the speaker is excited. This makes it possible to identify speakers by automatically classifying them based on the frequency changes of their voices. The frequency changes of a voice include, but are not limited to, the frequency range and the pattern of changes. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input the frequency change data of speakers' voices into a generating AI and have the generating AI perform speaker identification.

[0070] The service provider can provide the most suitable topics based on previous conversation logs, the latest news, and the user's own situation. For example, based on previous conversation logs, the service provider can identify topics that speaker A is interested in and provide the latest news related to those topics. The service provider can also select appropriate topics by considering speaker A's current situation (e.g., work progress or personal interests). For example, the service provider can provide news articles related to topics that speaker A has recently become interested in. The service provider can also select appropriate topics by considering speaker A's current emotional state. For example, if speaker A is relaxed, it can provide light topics, and if speaker A is tense, it can provide topics to help them relax. This allows the conversation to proceed smoothly by providing the most suitable topics based on previous conversation logs, the latest news, and the user's own situation. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can input previous conversation logs, the latest news, and its own situation data into a generating AI and have the generating AI select the most suitable topics.

[0071] The analysis unit can analyze the other party's reactions using image recognition and feed that information back to the supply unit to provide topics similar to those the other party enjoyed in the past. For example, if the other party smiles, the analysis unit will determine that the topic is favorable to them and provide a similar topic in the next conversation. The analysis unit can also analyze reactions by analyzing not only the other party's facial expressions but also their gestures and changes in posture. For example, if the other party nods, the analysis unit will determine that they are interested in the topic and provide a related topic in the next conversation. This improves the quality of conversation by analyzing the other party's reactions and providing topics similar to those the other party enjoyed in the past. Image recognition includes, but is not limited to, the algorithms used and the objects to be recognized. Some or all of the processing described above in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the other party's reaction data into a generating AI and have the generating AI perform the reaction analysis.

[0072] The acquisition unit can estimate the user's emotions and adjust the timing of conversation log acquisition based on the estimated user emotions. For example, if the user is relaxed, the acquisition unit can acquire the conversation log at the start of the conversation. If the user is tense, the acquisition unit can also acquire the conversation log in the middle of the conversation. Furthermore, if the user is excited, the acquisition unit can also acquire the conversation log at the end of the conversation. By adjusting the timing of conversation log acquisition based on the user's emotions, the conversation log can be acquired at the appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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 acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the user's emotion data into the generative AI and have the generative AI perform emotion estimation.

[0073] The acquisition unit can automatically evaluate importance based on the content of conversations and prioritize the acquisition of important conversations. For example, if a specific keyword appears in a conversation, the acquisition unit will prioritize the acquisition of that conversation. The acquisition unit can also analyze the tone and emphasized parts of a conversation and prioritize the acquisition of important conversations. Furthermore, the acquisition unit can also consider the length and frequency of conversations and prioritize the acquisition of important conversations. This ensures that important information is not missed by evaluating importance based on the content of conversations and prioritizing the acquisition of important conversations. Importance includes, but is not limited to, the content of the conversation and the attributes of the speakers. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input conversation content data into a generating AI and have the generating AI perform the importance evaluation.

[0074] The acquisition unit can analyze background and ambient sounds in a conversation and remove noise to obtain a clear log. For example, the acquisition unit can filter background sounds during a conversation and remove noise. The acquisition unit can also analyze ambient sounds and highlight important parts of the conversation. Furthermore, the acquisition unit can use noise cancellation technology when recording a conversation to obtain a clear log. This allows for the acquisition of a clear conversation log by analyzing background and ambient sounds and removing noise. Background and ambient sounds include, but are not limited to, speech filtering technology and noise reduction algorithms. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input conversation background sound data into a generating AI and have the generating AI perform noise reduction.

[0075] The acquisition unit can estimate the user's emotions and determine the priority of conversation logs to acquire based on the estimated user emotions. For example, if the user is relaxed, the acquisition unit will prioritize acquiring conversation logs of high importance. Conversely, if the user is tense, the acquisition unit can also prioritize acquiring conversation logs of low importance. Furthermore, if the user is excited, the acquisition unit can determine priorities based on the content of the conversation. This allows for the priority acquisition of important conversation logs by prioritizing them based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI, or not. For example, the acquisition unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0076] The acquisition unit can prioritize the acquisition of highly relevant logs by considering the location and time of the conversation. For example, the acquisition unit can prioritize the acquisition of highly relevant logs based on the location where the conversation took place. It can also prioritize the acquisition of highly relevant logs based on the time of the conversation. Furthermore, the acquisition unit can analyze the relationship between the content of the conversation and the location and time of the conversation and determine the priority. This allows for the efficient acquisition of important conversation logs by prioritizing the acquisition of highly relevant logs by considering the location and time of the conversation. Location and time of the conversation include, but are not limited to, the method of identifying the location and the division of the time of the conversation. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the conversation location and time of the conversation data into a generating AI and have the generating AI prioritize highly relevant logs.

[0077] The acquisition unit can acquire logs while considering the attribute information of the conversation participants. For example, the acquisition unit can acquire logs based on the occupation or position of the conversation participants. The acquisition unit can also acquire logs while considering the past statements of the conversation participants. Furthermore, the acquisition unit can acquire logs based on the interests or areas of expertise of the conversation participants. This allows for the efficient acquisition of important conversation logs by considering the attribute information of the conversation participants. Participant attribute information includes, but is not limited to, age, gender, and occupation. Some or all of the above processing in the acquisition unit may be performed using, for example, AI, or not using AI. For example, the acquisition unit can input the attribute information data of the conversation participants into a generating AI and have the generating AI perform log acquisition.

[0078] The classification unit can estimate the user's emotions and adjust the speaker classification criteria based on the estimated user emotions. For example, if the user is relaxed, the classification unit can use detailed classification criteria. If the user is tense, the classification unit can also use simplified classification criteria. Furthermore, if the user is excited, the classification unit can adjust the classification criteria according to the change in emotions. This allows for more accurate speaker classification by adjusting the speaker classification criteria 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 classification unit may be performed using AI, or not using AI. For example, the classification unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0079] The classification unit can improve classification accuracy by analyzing the characteristics of the speaker's speech, in addition to the changes in the frequency of the speaker's voice. For example, the classification unit can improve classification accuracy by analyzing the speaker's speaking speed. It can also improve classification accuracy by analyzing the speaker's intonation. Furthermore, it can also improve classification accuracy by analyzing the rhythm of the speaker's speech. In this way, classification accuracy is improved by analyzing the characteristics of the speaker's speech. These characteristics of speech include, but are not limited to, speaking speed, intonation, and rhythm. Some or all of the above processing in the classification unit may be performed using, for example, AI, or not using AI. For example, the classification unit can input speaker speech characteristic data into a generating AI and have the generating AI perform the improvement of classification accuracy.

[0080] The classification unit can identify speakers by referring to past conversation logs when classifying speakers. For example, the classification unit can identify speakers by referring to past conversation logs. The classification unit can also identify speakers by analyzing patterns in past conversation logs. Furthermore, the classification unit can identify speakers by considering the frequency and content of past conversation logs. This makes speaker identification easier by referring to past conversation logs. Past conversation logs include, but are not limited to, the retention period and search methods. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input past conversation log data into a generating AI and have the generating AI perform speaker identification.

[0081] The classification unit can estimate the user's emotions and adjust the order in which the speaker classification results are displayed based on the estimated user emotions. For example, if the user is relaxed, the classification unit can display detailed classification results. If the user is tense, the classification unit can also display simplified classification results. Furthermore, if the user is excited, the classification unit can adjust the order in which the classification results are displayed according to the change in emotions. This allows for a user-friendly display by adjusting the order in which the speaker classification results are displayed 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 classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0082] The classification unit can classify speakers while considering their geographical accent and dialect. For example, the classification unit can analyze and classify speakers based on their geographical accent. It can also analyze and classify speakers based on their dialect. Furthermore, the classification unit can classify speakers while considering their geographical background. This improves classification accuracy by considering speakers' geographical accent and dialect. Geographical accent and dialect include, but are not limited to, regional characteristics and dialect types. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input speakers' geographical accent and dialect data into a generating AI and have the generating AI perform the classification.

[0083] The classification unit can classify speakers based on their occupation or field of expertise. For example, the classification unit can analyze and classify the speaker's occupation. It can also analyze and classify the speaker's field of expertise. Furthermore, the classification unit can adjust the classification criteria based on the speaker's occupation or field of expertise. This improves classification accuracy by classifying based on the speaker's occupation or field of expertise. Occupation and field of expertise include, but are not limited to, the type of occupation and the scope of expertise. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input speaker occupation and field of expertise data into a generating AI and have the generating AI perform the classification.

[0084] The service provider can estimate the user's emotions and adjust the way the topics are presented based on the estimated emotions. For example, if the user is relaxed, the service provider will use a softer style of expression. If the user is tense, the service provider may use a concise and clear style of expression. Furthermore, if the user is excited, the service provider may use an emotionally charged style of expression. By adjusting the way topics are presented based on the user's emotions, it becomes possible to provide more appropriate topics. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0085] The content provider can select the most suitable topic by considering the speaker's past statements and interests when selecting a topic to offer. For example, the content provider can analyze the speaker's past statements and select the most suitable topic. The content provider can also select the most suitable topic by considering the speaker's interests. Furthermore, the content provider can combine the speaker's past statements and interests to select the most suitable topic. This allows the content provider to offer the most suitable topic by considering the speaker's past statements and interests. Past statements and interests include, but are not limited to, the method of recording statements and the method of identifying interests. Some or all of the above processing in the content provider may be performed using AI, for example, or without AI. For example, the content provider can input the speaker's past statements and interest data into a generating AI and have the generating AI select the most suitable topic.

[0086] The content provider can select topics by considering current social trends and news when selecting topics to offer. For example, the content provider can analyze current social trends and select the most suitable topic. It can also select the most suitable topic by considering the latest news. Furthermore, it can combine social trends and news to select the most suitable topic. This allows for the provision of appropriate topics by considering current social trends and news. Social trends and news include, but are not limited to, news sources and methods for identifying trends. Some or all of the above processing in the content provider may be performed using AI, for example, or without AI. For example, the content provider can input social trend and news data into a generating AI and have the generating AI perform topic selection.

[0087] The service provider can estimate the user's emotions and determine the priority of topics to offer based on the estimated emotions. For example, if the user is relaxed, the service provider will prioritize high-importance topics. If the user is stressed, the service provider can also prioritize low-importance topics. Furthermore, if the user is excited, the service provider can determine the priority of topics according to the change in emotions. This allows for the provision of more appropriate topics by prioritizing topics 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 service provider may be performed using AI, or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0088] The content provider can select topics to offer by considering the speaker's geographical background and culture. For example, the content provider can analyze the speaker's geographical background and select the most appropriate topic. It can also select the most appropriate topic by considering the speaker's culture. Furthermore, it can combine the speaker's geographical background and culture to select the most appropriate topic. This allows for the provision of appropriate topics by considering the speaker's geographical background and culture. Geographical background and culture include, but are not limited to, regional cultures and methods for identifying backgrounds. Some or all of the above processing in the content provider may be performed using AI, for example, or without AI. For example, the content provider can input the speaker's geographical background and cultural data into a generating AI and have the generating AI perform topic selection.

[0089] The content provider can select topics related to the speaker's occupation or field of expertise when selecting topics to offer. For example, the content provider can analyze the speaker's occupation and select the most suitable topic. It can also select the most suitable topic by considering the speaker's field of expertise. Furthermore, it can combine topics related to the speaker's occupation and field of expertise to select the most suitable topic. This allows for the provision of more interesting topics by offering topics related to the speaker's occupation and field of expertise. Occupation and field of expertise include, but are not limited to, the type of occupation and the scope of expertise. Some or all of the processing described above in the content provider may be performed using AI, for example, or without AI. For example, the content provider can input the speaker's occupation and field of expertise data into a generating AI and have the generating AI perform topic selection.

[0090] The analysis unit can estimate the user's emotions and adjust the analysis criteria for the other party's reaction based on the estimated user emotions. For example, if the user is relaxed, the analysis unit can use detailed analysis criteria. If the user is tense, the analysis unit can also use simplified analysis criteria. Furthermore, if the user is excited, the analysis unit can adjust the analysis criteria according to the change in emotions. This allows for more accurate analysis by adjusting the analysis criteria for the other party's reaction 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 analysis unit may be performed using AI or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0091] The analysis unit can improve accuracy by analyzing not only facial expressions but also gestures and changes in posture when analyzing the other party's reaction. For example, the analysis unit can analyze the other party's gestures to improve the accuracy of the reaction. The analysis unit can also analyze changes in the other party's posture to improve the accuracy of the reaction. Furthermore, the analysis unit can comprehensively analyze the other party's facial expressions, gestures, and changes in posture to improve the accuracy of the reaction. This improves the accuracy of reaction analysis by analyzing not only facial expressions but also gestures and changes in posture. Changes in gestures and posture include, but are not limited to, the type of movement and patterns of change. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on the other party's gestures and changes in posture into a generating AI and have the generating AI perform the reaction analysis.

[0092] The analysis unit can improve the accuracy of its analysis of the other party's reaction by referring to past reaction data. For example, the analysis unit can refer to past reaction data to analyze the current reaction. The analysis unit can also analyze patterns in past reaction data to predict the current reaction. Furthermore, the analysis unit can compare past reaction data with the current reaction to improve the accuracy of its analysis. This improves the accuracy of the analysis of the current reaction by referring to past reaction data. Past reaction data includes, but is not limited to, the retention period and search method. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input past reaction data into a generating AI and have the generating AI perform the reaction analysis.

[0093] The analysis unit can estimate the user's emotions and adjust how the other party's reactions are displayed based on the estimated emotions. For example, if the user is relaxed, the analysis unit can provide a detailed reaction display. If the user is tense, the analysis unit can also provide a simplified reaction display. Furthermore, if the user is excited, the analysis unit can adjust how the reaction display is displayed according to the change in emotions. This allows for more appropriate displays by adjusting how the other party's reactions are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's emotion data into a generative AI and have the generative AI perform emotion estimation.

[0094] The analysis unit can perform its analysis by considering the time and location of the reaction when analyzing the other party's reaction. For example, the analysis unit can perform its analysis by considering the time of day when the reaction occurred. It can also perform its analysis by considering the location when the reaction occurred. Furthermore, the analysis unit can perform its analysis by combining the time and location of the reaction. This improves the accuracy of the analysis by considering the time and location of the reaction. The time and location include, but are not limited to, time zone divisions and methods for identifying locations. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input reaction time and location data into a generating AI and have the generating AI perform the analysis.

[0095] The analysis unit can perform its analysis by considering the cultural elements underlying the reaction when analyzing the other party's reaction. For example, the analysis unit can analyze the cultural elements underlying the reaction. The analysis unit can also perform its analysis by considering the cultural background of the reaction. Furthermore, the analysis unit can combine the cultural elements and background of the reaction in its analysis. This improves the accuracy of the analysis by considering the cultural elements underlying the reaction. Cultural elements include, but are not limited to, the type of culture and the method of identifying the elements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input cultural element data of the reaction into a generating AI and have the generating AI perform the analysis.

[0096] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0097] A conversation support system can estimate a user's emotions and adjust the conversation based on those emotions. For example, if a user is nervous, the system can offer topics to help them relax. If a user is excited, the system can offer topics to maintain that excitement. Furthermore, if a user is sad, the system can offer comforting topics. This enables the conversation to proceed appropriately according to the user's emotions. Emotion estimation is performed, for example, by analyzing changes in voice tone and facial expressions. The system collects user emotion data and estimates emotions using an emotion engine. By adjusting the conversation based on the estimated emotions, a more comfortable conversational experience can be provided to the user.

[0098] The conversation support system can refer to a user's past conversation history and prioritize providing topics the user has previously shown interest in. For example, if a user has shown interest in a particular topic in a previous conversation, it can provide the latest information related to that topic. Similarly, if a user has previously shown interest in a particular news story, it can provide the latest events related to that news story. Furthermore, it can provide information related to hobbies and interests the user has previously discussed. This allows the system to leverage the user's past conversation history to provide a more personalized conversation experience. The system stores the user's conversation history in a database and references it as needed. Natural language processing techniques can be used to analyze the conversation history.

[0099] The conversation support system can understand the user's current activity status and provide topics appropriate to that situation. For example, if the user is working, it can provide work-related topics. If the user is on a break, it can provide relaxing topics. Furthermore, if the user is exercising, it can provide exercise-related topics. This allows the system to provide appropriate topics according to the user's current activity status. The system acquires the user's activity status from sensors and user input data, and analyzes the activity status. Based on the analysis results, it selects appropriate topics and provides them to the user.

[0100] A conversation support system can estimate a user's emotions and adjust the conversation pace based on those emotions. For example, if the user is relaxed, the conversation can proceed at a slow pace. If the user is excited, the conversation can proceed at a faster pace. Furthermore, if the user is tired, the conversation pace can be slowed down to help the user relax. This allows the system to provide an appropriate conversation pace according to the user's emotions. Emotion estimation is performed by analyzing changes in voice tone and facial expressions. The system collects user emotion data and estimates emotions using an emotion engine. By adjusting the conversation pace based on the estimated emotions, a more comfortable conversation experience can be provided to the user.

[0101] A conversation support system can estimate a user's emotions and adjust the conversation content based on those emotions. For example, if a user is sad, it can offer topics to comfort them. If a user is angry, it can offer topics to help them calm down. Furthermore, if a user is happy, it can offer topics to share that happiness. This allows the system to provide appropriate conversation content tailored to the user's emotions. Emotion estimation is performed by analyzing changes in voice tone and facial expressions. The system collects user emotion data and estimates emotions using an emotion engine. By adjusting the conversation content based on the estimated emotions, the system can provide a more comfortable conversation experience for the user.

[0102] The conversation support system can analyze a user's past conversation history to identify topics the user wants to avoid and prevent them from discussing those topics. For example, if a user has previously reacted negatively to a particular topic, the system can avoid that topic. Similarly, if a user has previously reacted negatively to a particular news story, the system can avoid topics related to that news story. Furthermore, it can avoid topics that a user has previously stated they do not want to discuss. This allows the system to leverage the user's past conversation history to avoid topics they wish to avoid. The system stores the user's conversation history in a database and references it as needed. Natural language processing techniques can be used to analyze the conversation history.

[0103] The conversation support system can understand the user's current environment and provide topics appropriate to that environment. For example, if the user is in a quiet place, it can provide topics suitable for a quiet environment. If the user is in a noisy place, it can provide topics suitable for a noisy environment. Furthermore, if the user is outdoors, it can provide topics suitable for an outdoor environment. In this way, it can provide appropriate topics according to the user's current environment. The system acquires user environment data from sensors and user input data and analyzes the environment. Based on the analysis results, it selects appropriate topics and provides them to the user.

[0104] The conversation support system can estimate the user's emotions and adjust the timing of the conversation's end based on those emotions. For example, if the user is tired, the conversation can be ended earlier. Conversely, if the user is enjoying the conversation, it can be continued. Furthermore, if the user is in a hurry, the conversation can be shortened. This allows the system to provide an appropriate conversation ending time that matches the user's emotions. Emotion estimation is performed by analyzing changes in voice tone and facial expressions. The system collects user emotion data and estimates emotions using an emotion engine. By adjusting the conversation ending time based on the estimated emotions, a more comfortable conversation experience can be provided to the user.

[0105] A conversation support system can analyze a user's past conversation history to identify topics of particular interest and provide information related to those topics. For example, if a user has frequently discussed a particular hobby in the past, the system can provide the latest information related to that hobby. Similarly, if a user has shown interest in a particular news story in the past, the system can provide the latest events related to that news. Furthermore, if a user has shown interest in a particular field in the past, the system can provide information related to that field. This allows the system to leverage the user's past conversation history to provide more personalized information. The system stores the user's conversation history in a database and references it as needed. Natural language processing techniques can be used to analyze the conversation history.

[0106] A conversation support system can estimate a user's emotions and adjust the conversation format based on those emotions. For example, if the user is relaxed, the conversation can proceed in a casual format. If the user is nervous, it can proceed in a formal format. Furthermore, if the user is excited, it can proceed in an interactive format. This allows the system to provide an appropriate conversation format according to the user's emotions. Emotion estimation is performed by analyzing changes in voice tone and facial expressions. The system collects user emotion data and estimates emotions using an emotion engine. By adjusting the conversation format based on the estimated emotions, a more comfortable conversation experience can be provided to the user.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The acquisition unit acquires the conversation log. The conversation log includes audio data, text data, and conversation metadata. The acquisition unit acquires the conversation log for each meeting and person, for example, recording the content of conversations at the beginning of a meeting or when meeting with colleagues. This conversation log is saved for later reference. Step 2: The classification unit automatically classifies speakers based on the conversation logs acquired by the acquisition unit. The classification unit automatically classifies speakers by observing the frequency changes of their voices, and identifies speakers by analyzing the characteristics of their voices using speech recognition AI. For example, if the frequency of speaker A's voice has a specific pattern, speaker A is identified based on that pattern. Step 3: The provider unit provides the most suitable topic based on the speaker information classified by the classification unit. The provider unit provides the most suitable topic based on previous conversation logs, the latest news, and its own situation. For example, based on previous conversation logs, it identifies topics that speaker A is interested in and provides the latest news related to those topics. It also selects appropriate topics by considering speaker A's current situation (e.g., work progress or personal interests). Step 4: The analysis unit analyzes the other party's reaction to the topic provided by the provision unit. The analysis unit analyzes the other party's reaction using image recognition and feeds back information to the provision unit to provide topics similar to those the other party enjoyed in the past. For example, if the other party smiles, the analysis unit determines that the topic is favorable to the other party and provides a similar topic in the next conversation.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] Each of the multiple elements described above, including the acquisition unit, classification unit, provision unit, and analysis unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the acquisition unit acquires conversation logs using the camera 42 and microphone 38B of the smart device 14 and records the content of the conversation with the control unit 46A. The classification unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, which analyzes the characteristics of the speaker's voice using speech recognition AI and identifies the speaker. The provision unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, which provides the most appropriate topic based on previous conversation logs, the latest news, and the user's own situation. The analysis unit analyzes the other party's reaction using the camera 42 of the smart device 14 and feeds back information to the provision unit via the control unit 46A to provide topics similar to those the user previously enjoyed. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the acquisition unit, classification unit, provision unit, and analysis unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit acquires conversation logs using the camera 42 and microphone 238 of the smart glasses 214 and records the content of the conversation using the control unit 46A. The classification unit is implemented in the identification processing unit 290 of the data processing unit 12 and identifies the speaker by analyzing the characteristics of the speaker's voice using speech recognition AI. The provision unit is implemented in the identification processing unit 290 of the data processing unit 12 and provides the most appropriate topic based on previous conversation logs, the latest news, and the user's own situation. The analysis unit analyzes the other party's reaction using the camera 42 of the smart glasses 214 and feeds back information to the provision unit via the control unit 46A to provide a topic similar to one the user previously enjoyed. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the acquisition unit, classification unit, provision unit, and analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit acquires conversation logs using the camera 42 and microphone 238 of the headset terminal 314 and records the content of the conversation using the control unit 46A. The classification unit is implemented in the identification processing unit 290 of the data processing unit 12 and identifies the speaker by analyzing the characteristics of the speaker's voice using speech recognition AI. The provision unit is implemented in the identification processing unit 290 of the data processing unit 12 and provides the most appropriate topic based on previous conversation logs, the latest news, and the user's own situation. The analysis unit analyzes the other party's reaction using the camera 42 of the headset terminal 314 and feeds back information to the provision unit via the control unit 46A to provide a topic similar to one the user previously enjoyed. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0145] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the acquisition unit, classification unit, provision unit, and analysis unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit acquires conversation logs using the camera 42 and microphone 238 of the robot 414 and records the content of the conversation using the control unit 46A. The classification unit is implemented in the identification processing unit 290 of the data processing unit 12 and identifies the speaker by analyzing the characteristics of the speaker's voice using speech recognition AI. The provision unit is implemented in the identification processing unit 290 of the data processing unit 12 and provides the most appropriate topic based on previous conversation logs, the latest news, and its own situation. The analysis unit analyzes the other party's reaction using the camera 42 of the robot 414 and feeds back information to the provision unit via the control unit 46A to provide a topic similar to one that was previously well-received. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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."

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] (Note 1) The unit that retrieves the conversation log, A classification unit that automatically classifies speakers based on the conversation log acquired by the acquisition unit, A providing unit that provides the most suitable topic based on the speaker information classified by the classification unit, The system includes an analysis unit that analyzes the other party's reaction to the topic provided by the aforementioned provision unit. A system characterized by the following features. (Note 2) The acquisition unit is, Obtain conversation logs for each meeting and each person involved. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned classification unit is Automatically classifies by observing the changes in the frequency of the speaker's voice. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, Based on previous conversation logs, the latest news, and your own situation, we will provide the most suitable topics. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit is By using image recognition to analyze the other party's reaction, information is fed back to the service department to provide topics similar to those the other party previously enjoyed. The system described in Appendix 1, characterized by the features described herein. (Note 6) The acquisition unit is, The system estimates the user's emotions and adjusts the timing of conversation log acquisition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, The system automatically evaluates the importance of conversations based on their content and prioritizes retrieving important conversations. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, It analyzes background and ambient sounds in conversations, removes noise, and obtains clear logs. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, It estimates the user's emotions and determines the priority of conversation logs to retrieve based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, Prioritize retrieving relevant logs by considering the location and time of the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, Logs are retrieved while considering the attribute information of the conversation participants. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned classification unit is It estimates the user's emotions and adjusts the speaker classification criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned classification unit is In addition to analyzing the frequency changes of the speaker's voice, we analyze the characteristics of the speaker's speaking style to improve classification accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned classification unit is When classifying speakers, the system identifies them by referring to past conversation logs. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned classification unit is It estimates the user's emotions and adjusts the order in which speaker classification results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned classification unit is When classifying speakers, their geographical accent and dialect should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned classification unit is When classifying speakers, the classification is based on the speaker's occupation or field of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned supply unit is, It estimates the user's emotions and adjusts the way topics are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, When selecting topics to offer, the most suitable topics are chosen by considering the speaker's past statements and interests. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When selecting topics to offer, we consider current social trends and news. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of topics to provide based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, When selecting topics to present, we take into consideration the speaker's geographical background and culture. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When selecting topics to be presented, choose topics related to the speaker's occupation or area of ​​expertise. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit is It estimates the user's emotions and adjusts the analysis criteria for the other party's reaction based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit is When analyzing the other person's reaction, we improve accuracy by analyzing not only facial expressions but also gestures and changes in posture. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned analysis unit is When analyzing the other party's reaction, refer to past reaction data to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the other party's reactions are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned analysis unit is When analyzing the other party's reaction, consider the time and location of the reaction. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned analysis unit is When analyzing someone's reaction, consider the cultural factors behind that reaction. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0181] 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. The unit that retrieves the conversation log, A classification unit that automatically classifies speakers based on the conversation log acquired by the acquisition unit, A providing unit that provides the most suitable topic based on the speaker information classified by the classification unit, The system includes an analysis unit that analyzes the other party's reaction to the topic provided by the aforementioned provision unit. A system characterized by the following features.

2. The acquisition unit is, Obtain conversation logs for each meeting and each person involved. The system according to feature 1.

3. The aforementioned classification unit is Automatically classifies by observing the changes in the frequency of the speaker's voice. The system according to feature 1.

4. The aforementioned supply unit is, Based on previous conversation logs, the latest news, and your own situation, we will provide the most suitable topics. The system according to feature 1.

5. The aforementioned analysis unit is By using image recognition to analyze the other party's reaction, information is fed back to the service department to provide topics similar to those the other party previously enjoyed. The system according to feature 1.

6. The acquisition unit is, The system estimates the user's emotions and adjusts the timing of conversation log acquisition based on the estimated emotions. The system according to feature 1.

7. The acquisition unit is, The system automatically evaluates the importance of conversations based on their content and prioritizes retrieving important conversations. The system according to feature 1.

8. The acquisition unit is, It analyzes background and ambient sounds in conversations, removes noise, and obtains clear logs. The system according to feature 1.

Images