System

Abstract

An object of a system according to an embodiment is to propose a next venue in consideration of the hobbies and excitement of participants.SOLUTION: A system includes a conversation recording part, a profiling part, an excitement sensing part, and a hall proposal part. The conversation recording unit records conversation contents. The profiling unit analyzes the conversation content recorded by the conversation recording unit and estimates the number of participants, hobbies, and preferences. The excitement sensing unit senses the degree of excitement from the tone or volume of the voice on the basis of the profile generated by the profiling unit. A hall proposal part proposes the next hall on the basis of the profile and the degree of excitement.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to take into account the hobbies and excitement of participants when selecting the next venue for a drinking party or other gathering.

[0005] The system according to the embodiment aims to suggest the next venue taking into consideration the hobbies and excitement of the participants. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversation recording unit, a profiling unit, an excitement detection unit, and a venue suggestion unit. The conversation recording unit records the content of the conversation. The profiling unit analyzes the content of the conversation recorded by the conversation recording unit and estimates the number of participants, their hobbies, and preferences. The excitement detection unit detects the level of excitement from the tone and volume of the voices based on the profile generated by the profiling unit. The venue suggestion unit suggests the next venue based on the profile and the level of excitement. [Effects of the Invention]

[0007] The system according to the embodiment can suggest the next venue taking into consideration the hobbies and excitement of the participants. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The Navi Party system according to an embodiment of the present invention records and analyzes conversations, and uses AI to infer the number of participants, their hobbies, preferences, and level of excitement, and then suggests the next venue. This allows the Navi Party system to suggest the next venue based on the participants' profiles and level of excitement, facilitating smooth travel.

[0029] The navigation party system according to the embodiment includes a conversation recording unit, a profiling unit, an excitement detection unit, and a venue suggestion unit. The conversation recording unit records the content of the conversation. For example, by simply placing a smartphone on a table, an app automatically records the conversation. The conversation recording unit can also record the conversation in the background. The profiling unit analyzes the content of the conversation recorded by the conversation recording unit to estimate the number of participants, their hobbies, and preferences. For example, the generation AI reflects the participants' hobbies and preferences in a profile based on the text data of the conversation. The generation AI can also analyze remarks made during the conversation to estimate the number of participants. The excitement detection unit detects the level of excitement from the tone and volume of the voice based on the profile generated by the profiling unit. For example, the generation AI analyzes the frequency of laughter and cheers to determine the level of excitement. The generation AI can also identify peak times of excitement based on audio data. The venue suggestion unit suggests the next venue based on the profile and the level of excitement. For example, the generation AI can link with databases such as Tabelog to suggest the best venue for a second party based on the participant's profile and level of excitement. The generation AI can also suggest venues taking into account real-time congestion and event information. This allows the Navi Party system to suggest the next venue based on the participant's profile and level of excitement, facilitating smooth travel.

[0030] The conversation recording unit uses the generation AI to automatically classify conversation topics based on the recorded data of the conversation content and evaluate the importance of each topic. For example, the conversation recording unit analyzes the recorded data of the conversation content, and the generation AI classifies them by topic. For example, in a conversation at a drinking party, topics such as "travel," "work," and "hobbies" are automatically identified and the importance of each is evaluated. The conversation recording unit also analyzes the frequency and appearance patterns of topics based on the recorded data of the conversation and evaluates their importance. For example, frequently appearing topics are classified as having high importance. The conversation recording unit also analyzes the recorded data of the conversation content, and the generation AI evaluates the relevance of the topics. For example, highly related topics are grouped and evaluated for their importance. This automatically classifies conversation topics and evaluates their importance, enabling more accurate profiling.

[0031] The conversation recording unit can detect specific keywords and phrases used in a conversation in real time and analyze their frequency and context. For example, the conversation recording unit uses a generation AI to detect specific keywords and phrases in real time based on the recorded data of the conversation. For example, it detects phrases such as "cheers" and "good job" and analyzes their frequency. The conversation recording unit also analyzes the recorded data of the conversation, and the generation AI displays the frequency of keyword appearance in real time. For example, it analyzes how frequently keywords such as "travel" and "work" appear. The conversation recording unit also analyzes the context of keywords based on the recorded data of the conversation. For example, it analyzes the context in which the keyword "travel" is used and evaluates its relevance. This allows for a deeper understanding of the content of the conversation by detecting specific keywords and phrases in real time and analyzing their frequency and context.

[0032] The profiling unit can improve accuracy by comparing hobbies and preferences inferred from the content of a conversation with past behavioral history and social media data. For example, the profiling unit uses the generation AI to infer hobbies and preferences based on the text data of the conversation and compare them with past behavioral history. For example, it references speech history from past drinking parties. The profiling unit also analyzes the text data of the conversation, and the generation AI compares it with social media data to identify hobbies and preferences. For example, it creates a profile based on social media posts. The profiling unit also uses the text data of the conversation, and the generation AI integrates and analyzes past behavioral history and social media data. For example, it identifies hobbies and preferences based on past behavioral patterns. This improves the accuracy of profiling by comparing hobbies and preferences with past behavioral history and social media data.

[0033] The profiling unit can infer personality traits from the tone and vocabulary of participants' speech and reflect them in the profile. For example, the profiling unit uses text data of conversations to have the generation AI analyze the tone and vocabulary of speech to infer personality traits. For example, if there is a lot of positive language used, it may be determined that the person has an optimistic personality. The profiling unit also analyzes the text data of conversations, and the generation AI quantifies the tone of speech and reflects the personality traits in the profile. For example, if there is a lot of calm language used, it may be determined that the person has a cautious personality. The profiling unit also analyzes language patterns based on the text data of conversations to identify personality traits. For example, if there are a lot of humorous remarks, it may be determined that the person has a sociable personality. This allows for more detailed profiling by inferring personality traits from the tone and vocabulary of speech and reflecting them in the profile.

[0034] The profiling unit can make the profiling results available to other applications. For example, the profiling unit develops an API for linking the profiling results to other applications. For example, it provides profile data to dating apps and travel planners. The profiling unit also standardizes the data format so that the profiling results can be used by other applications. For example, it provides information on hobbies and preferences in a common format. The profiling unit also builds a system that automatically links the profiling results to other applications. For example, it provides profile data to dating apps in real time. This allows the profiling results to be used by other applications, improving data reusability.

[0035] The profiling unit updates the profile data in real time and can dynamically change it according to the participants' behavior and comments. In the profiling unit, the generation AI updates the profile data in real time based on, for example, text data of the conversation content. For example, the profile is updated when a new hobby or preference is mentioned. The profiling unit also analyzes recorded data of the conversation, and the generation AI dynamically changes the profile data. For example, the profile is updated when a participant's emotional state changes. In the profiling unit, the generation AI updates the profile data in real time based on text data of the conversation content, and changes the profile according to the participants' behavior. For example, the profile is updated when a new behavioral pattern is detected. This allows the profile data to be updated in real time and dynamically changed according to the participants' behavior and comments, enabling more accurate profiling.

[0036] The excitement detection unit analyzes not only the audio data but also the facial expressions and gestures of the participants, allowing for a multifaceted evaluation of the level of excitement. For example, the excitement detection unit uses a camera to analyze the facial expressions of the participants along with the recorded data of the conversation to evaluate the level of excitement. For example, it detects smiling and surprised expressions. The excitement detection unit also analyzes the movements of the participants along with the recorded data of the conversation using gesture recognition technology to evaluate the level of excitement. For example, it detects raising of hands and clapping. The excitement detection unit also integrates and analyzes facial and gesture data along with the recorded data of the conversation to evaluate the level of excitement from multiple angles. For example, it quantifies the level of excitement based on both facial expressions and gestures. This allows for a multifaceted evaluation of the level of excitement by analyzing not only the audio data but also facial expressions and gestures.

[0037] The excitement detection unit can identify peak moments of excitement and automatically take specific actions at that timing. For example, the excitement detection unit uses recorded conversation data to allow the generation AI to identify peak moments of excitement and automatically take photos. For example, it can activate the camera at the moment when there is a lot of laughter or cheering. The excitement detection unit also analyzes recorded conversation data and allows the generation AI to automatically start video recording at peak excitement. For example, it can activate the video camera at the peak of emotion. The excitement detection unit also builds a system where the generation AI triggers specific actions at peak excitement based on recorded conversation data. For example, it can display specific effects at peak excitement. This allows the generation AI to identify peak moments of excitement and automatically take specific actions at that timing, so important moments are not missed.

[0038] The excitement detection unit can make the excitement detection technology applicable to other events. For example, the excitement detection unit generalizes the excitement detection algorithm so that it can be used for sports events and concerts. For example, it analyzes the cheers and applause of the audience. The excitement detection unit also develops an interface to apply the results of excitement detection to other events. For example, it displays the level of excitement of a sports event in real time. The excitement detection unit also standardizes the data format to apply the results of excitement detection to other events. For example, it displays the level of excitement of a sports event or a concert in a common format. This allows the excitement detection technology to be used for other events, improving the versatility of the technology.

[0039] The excitement detection unit can share the excitement level in cooperation with other devices. For example, the excitement detection unit may link the excitement detection results with a smartwatch and display the excitement level in real time. For example, it may display an emotion score on the smartwatch screen. The excitement detection unit may also link the excitement detection results with a smart speaker and notify the excitement level by voice. For example, it may issue a voice alert when excitement peaks. The excitement detection unit may also develop an API for linking the excitement detection results with other devices. For example, it may provide data to a smartwatch or smart speaker. This may improve the consistency and convenience of information by linking and sharing the excitement level with other devices.

[0040] The venue suggestion unit can consider not only past reviews and ratings but also real-time congestion status and event information when selecting a venue to suggest. For example, the venue suggestion unit not only bases its selection on past reviews and ratings but also considers real-time congestion status when selecting a venue to suggest. For example, it selects a venue based on the current congestion level. Furthermore, the venue suggestion unit not only bases its selection on past reviews and ratings but also considers real-time event information when selecting a venue to suggest. For example, it selects a venue based on an event currently being held. Furthermore, the venue suggestion unit not only bases its selection on past reviews and ratings but also integrates and analyzes real-time congestion status and event information when selecting a venue to suggest. For example, it selects an optimal venue based on the congestion level and event information. In this way, by considering real-time congestion status and event information, it is possible to suggest a more appropriate venue.

[0041] The venue suggestion unit can customize the list of suggested venues based on the participant's profile, optimizing it to suit individual preferences. For example, the venue suggestion unit customizes the list of suggested venues based on the participant's profile. For example, it lists venues according to hobbies and preferences. The venue suggestion unit also optimizes the list of suggested venues based on the participant's profile data. For example, it suggests venues that reflect past activity history and preferences. The venue suggestion unit also updates the list of suggested venues in real time based on the participant's profile. For example, it updates the list when new hobbies or preferences are discovered. In this way, customizing the venue list based on the participant's profile makes it possible to make suggestions that are optimized to suit individual preferences.

[0042] The venue suggestion unit can make the after-party venue suggestion function usable in other situations. For example, the venue suggestion unit generalizes the after-party venue suggestion algorithm so that it can also be used for dates and family trips. For example, it can be used to suggest date plans and travel plans. The venue suggestion unit also develops an interface for applying the after-party venue suggestion results to other situations. For example, it can automatically suggest plans for dates and family trips. The venue suggestion unit also standardizes the data format for utilizing the after-party venue suggestion results in other situations. For example, it can display plans for dates and family trips in a common format. This allows the after-party venue suggestion function to be used in other situations, improving the versatility of the system.

[0043] The venue suggestion unit can update the list of suggested venues in conjunction with feedback and ratings from other users. For example, the venue suggestion unit updates the list of suggested venues in real time based on feedback and ratings from other users. For example, it suggests venues that reflect the latest reviews and ratings. The venue suggestion unit also optimizes the list of suggested venues in conjunction with feedback data from other users. For example, it prioritizes listing venues with many positive ratings. The venue suggestion unit also builds a system that dynamically updates the list of suggested venues based on feedback and ratings from other users. For example, it updates the list every time new feedback is added. In this way, by updating the venue list in conjunction with feedback and ratings from other users, more appropriate venue suggestions are possible.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The Navi Party system can also be equipped with a health management unit that monitors the health of participants. For example, it can obtain heart rate and stress levels from smartwatches and fitness trackers to monitor participants' health in real time. The health management unit can also suggest appropriate break times and ways to refresh based on participants' health. For example, it can suggest places to relax if a participant's heart rate becomes high. The health management unit can also suggest healthy food and drink menus based on participants' health data. This makes it possible to make suggestions that take into account the participants' health, providing a more comfortable party experience.

[0046] The Navi Party system can also be equipped with a mobility management unit that takes into account participants' means of transportation. For example, it can propose optimal routes based on participants' current locations and means of transportation. The mobility management unit can also obtain real-time traffic information and propose routes that avoid congestion and delays. For example, it can propose alternative routes based on train delay information. The mobility management unit can also propose venues based on participants' means of transportation. For example, it can propose venues with parking for participants traveling by car. This makes it possible to make proposals that take participants' means of transportation into consideration, supporting smooth movement.

[0047] The Navi Party system can also be equipped with a budget management unit that takes into account the participant's budget. For example, participants can input their budget information and suggest the most suitable venue within that range. The budget management unit can also obtain venue price information in real time and provide options within the budget. For example, it can suggest food and drink plans that can be used within a specific budget. The budget management unit can also provide discount information and coupons based on the participant's budget. For example, it can suggest discount coupons that can be used at a specific venue. This makes it possible to make suggestions that take into account the participant's budget, allowing for the provision of economical party plans.

[0048] The Navi Party system can also be equipped with a dietary management unit that takes into account participants' dietary restrictions. For example, participants can input allergy information and dietary restrictions and suggest appropriate food and drink menus based on that information. The dietary management unit can also obtain venue menu information in real time and provide menus that accommodate dietary restrictions. For example, it can suggest gluten-free or vegetarian menus. The dietary management unit can also suggest venues that meet participants' dietary restrictions. For example, it can suggest restaurants with a wide selection of allergy-friendly menus. This makes it possible to make suggestions that take into account participants' dietary restrictions, allowing them to enjoy their meals with peace of mind.

[0049] The Navi Party system can also be equipped with an interactive survey function to dig deeper into participants' interests. For example, it can display questions related to topics that come up in the conversation in real time and prompt participants to answer them. The survey function can also create a more detailed profile based on participants' responses. For example, it can identify travel destination preferences based on answers to travel-related questions. The survey function can also suggest related events and activities based on participants' interests. For example, it can provide information about travel fairs to participants who love traveling. This allows for deeper digging into participants' interests and makes it possible to make more personalized suggestions.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The conversation recorder records the conversation. For example, you can simply place your smartphone on a table and the app will automatically record the conversation. The conversation recorder can also record conversations in the background. Step 2: The profiling unit analyzes the conversation recorded by the conversation recording unit and estimates the number of participants, their hobbies, and preferences. For example, the generation AI reflects the participants' hobbies and preferences in their profiles based on the text data of the conversation. The generation AI can also analyze statements made during the conversation to estimate the number of participants. Step 3: The excitement detection unit detects the level of excitement from the tone and volume of the audio based on the profile generated by the profiling unit. For example, the generation AI analyzes the frequency of laughter and cheers to determine the level of excitement. The generation AI can also identify peak moments of excitement based on the audio data. Step 4: The venue suggestion unit suggests the next venue based on the profile and the level of excitement. For example, the generation AI can connect with databases such as Tabelog to suggest the optimal venue for the after-party based on the participant profiles and the level of excitement. The generation AI can also suggest venues taking into account real-time congestion and event information.

[0052] (Example 2) The Navi Party system according to an embodiment of the present invention records and analyzes conversations, and uses AI to infer the number of participants, their hobbies, preferences, and level of excitement, and then suggests the next venue. This allows the Navi Party system to suggest the next venue based on the participants' profiles and level of excitement, facilitating smooth travel.

[0053] The navigation party system according to the embodiment includes a conversation recording unit, a profiling unit, an excitement detection unit, and a venue suggestion unit. The conversation recording unit records the content of the conversation. For example, by simply placing a smartphone on a table, an app automatically records the conversation. The conversation recording unit can also record the conversation in the background. The profiling unit analyzes the content of the conversation recorded by the conversation recording unit to estimate the number of participants, their hobbies, and preferences. For example, the generation AI reflects the participants' hobbies and preferences in a profile based on the text data of the conversation. The generation AI can also analyze remarks made during the conversation to estimate the number of participants. The excitement detection unit detects the level of excitement from the tone and volume of the voice based on the profile generated by the profiling unit. For example, the generation AI analyzes the frequency of laughter and cheers to determine the level of excitement. The generation AI can also identify peak times of excitement based on audio data. The venue suggestion unit suggests the next venue based on the profile and the level of excitement. For example, the generation AI can link with databases such as Tabelog to suggest the best venue for a second party based on the participant's profile and level of excitement. The generation AI can also suggest venues taking into account real-time congestion and event information. This allows the Navi Party system to suggest the next venue based on the participant's profile and level of excitement, facilitating smooth travel.

[0054] The conversation recording unit uses the generation AI to automatically classify conversation topics based on the recorded data of the conversation content and evaluate the importance of each topic. For example, the conversation recording unit analyzes the recorded data of the conversation content, and the generation AI classifies them by topic. For example, in a conversation at a drinking party, topics such as "travel," "work," and "hobbies" are automatically identified and the importance of each is evaluated. The conversation recording unit also analyzes the frequency and appearance patterns of topics based on the recorded data of the conversation and evaluates their importance. For example, frequently appearing topics are classified as having high importance. The conversation recording unit also analyzes the recorded data of the conversation content, and the generation AI evaluates the relevance of the topics. For example, highly related topics are grouped and evaluated for their importance. This automatically classifies conversation topics and evaluates their importance, enabling more accurate profiling.

[0055] The conversation recording unit can detect specific keywords and phrases used in a conversation in real time and analyze their frequency and context. For example, the conversation recording unit uses a generation AI to detect specific keywords and phrases in real time based on the recorded data of the conversation. For example, it detects phrases such as "cheers" and "good job" and analyzes their frequency. The conversation recording unit also analyzes the recorded data of the conversation, and the generation AI displays the frequency of keyword appearance in real time. For example, it analyzes how frequently keywords such as "travel" and "work" appear. The conversation recording unit also analyzes the context of keywords based on the recorded data of the conversation. For example, it analyzes the context in which the keyword "travel" is used and evaluates its relevance. This allows for a deeper understanding of the content of the conversation by detecting specific keywords and phrases in real time and analyzing their frequency and context.

[0056] The excitement detection unit uses the emotion estimation function to track changes in emotions during a conversation and identify moments when particular emotions are strongly expressed. In the excitement detection unit, for example, the generation AI tracks changes in emotions in real time based on recorded data of the conversation content. For example, it identifies moments when laughter or anger is heard during a conversation. The excitement detection unit also analyzes the recorded data of the conversation, and the generation AI quantifies the intensity of emotions. For example, it identifies moments when emotions such as joy and surprise are strongly expressed. The excitement detection unit also graphs changes in emotions based on the recorded data of the conversation content. For example, it visually displays the timing of emotional peaks during a conversation. This makes it possible to track changes in emotions and identify moments when particular emotions are strongly expressed, thereby more accurately detecting the level of excitement.

[0057] The profiling unit can improve accuracy by comparing hobbies and preferences inferred from the content of a conversation with past behavioral history and social media data. For example, the profiling unit uses the generation AI to infer hobbies and preferences based on the text data of the conversation and compare them with past behavioral history. For example, it references speech history from past drinking parties. The profiling unit also analyzes the text data of the conversation, and the generation AI compares it with social media data to identify hobbies and preferences. For example, it creates a profile based on social media posts. The profiling unit also uses the text data of the conversation, and the generation AI integrates and analyzes past behavioral history and social media data. For example, it identifies hobbies and preferences based on past behavioral patterns. This improves the accuracy of profiling by comparing hobbies and preferences with past behavioral history and social media data.

[0058] The profiling unit can infer personality traits from the tone and vocabulary of participants' speech and reflect them in the profile. For example, the profiling unit uses text data of conversations to have the generation AI analyze the tone and vocabulary of speech to infer personality traits. For example, if there is a lot of positive language used, it may be determined that the person has an optimistic personality. The profiling unit also analyzes the text data of conversations, and the generation AI quantifies the tone of speech and reflects the personality traits in the profile. For example, if there is a lot of calm language used, it may be determined that the person has a cautious personality. The profiling unit also analyzes language patterns based on the text data of conversations to identify personality traits. For example, if there are a lot of humorous remarks, it may be determined that the person has a sociable personality. This allows for more detailed profiling by inferring personality traits from the tone and vocabulary of speech and reflecting them in the profile.

[0059] The profiling unit uses the emotion estimation function to add participants' emotional states to a profile and make suggestions based on their emotions. In the profiling unit, for example, the generation AI estimates an emotional state based on recorded data of the conversation and adds it to the profile. For example, it analyzes laughter or anger during a conversation to identify the emotional state. The profiling unit also analyzes the recorded data of the conversation, and the generation AI tracks changes in emotions and reflects them in the profile. For example, it identifies peak times of emotions and adds that information to the profile. The profiling unit also integrates the emotion estimation data into the profile based on the recorded data of the conversation and makes suggestions based on emotions. For example, it suggests places to relax or places to have fun. In this way, by adding emotional states to the profile and making suggestions based on emotions, more personalized suggestions become possible.

[0060] The profiling unit can make the profiling results available to other applications. For example, the profiling unit develops an API for linking the profiling results to other applications. For example, it provides profile data to dating apps and travel planners. The profiling unit also standardizes the data format so that the profiling results can be used by other applications. For example, it provides information on hobbies and preferences in a common format. The profiling unit also builds a system that automatically links the profiling results to other applications. For example, it provides profile data to dating apps in real time. This allows the profiling results to be used by other applications, improving data reusability.

[0061] The profiling unit updates the profile data in real time and can dynamically change it according to the participants' behavior and comments. In the profiling unit, the generation AI updates the profile data in real time based on, for example, text data of the conversation content. For example, the profile is updated when a new hobby or preference is mentioned. The profiling unit also analyzes recorded data of the conversation, and the generation AI dynamically changes the profile data. For example, the profile is updated when a participant's emotional state changes. In the profiling unit, the generation AI updates the profile data in real time based on text data of the conversation content, and changes the profile according to the participants' behavior. For example, the profile is updated when a new behavioral pattern is detected. This allows the profile data to be updated in real time and dynamically changed according to the participants' behavior and comments, enabling more accurate profiling.

[0062] The profiling unit can use the emotion estimation function to suggest customized entertainment content based on the emotions of participants. For example, the profiling unit uses a generation AI to estimate the emotional state based on recorded data of the conversation content and suggest customized entertainment content. For example, it can suggest relaxing music or exciting games. The profiling unit also analyzes the recorded data of the conversation, and the generation AI tracks changes in emotions and suggests entertainment content based on the emotions. For example, it can provide content that is appropriate for times when emotions are at their peak. The profiling unit also uses a generation AI to integrate emotion estimation data based on the recorded data of the conversation content and suggest customized entertainment content. For example, it can suggest movies or dramas that match the emotional state. In this way, suggesting customized entertainment content based on emotions improves participant satisfaction.

[0063] The excitement detection unit analyzes not only the audio data but also the facial expressions and gestures of the participants, allowing for a multifaceted evaluation of the level of excitement. For example, the excitement detection unit uses a camera to analyze the facial expressions of the participants along with the recorded data of the conversation to evaluate the level of excitement. For example, it detects smiling and surprised expressions. The excitement detection unit also analyzes the movements of the participants along with the recorded data of the conversation using gesture recognition technology to evaluate the level of excitement. For example, it detects raising of hands and clapping. The excitement detection unit also integrates and analyzes facial and gesture data along with the recorded data of the conversation to evaluate the level of excitement from multiple angles. For example, it quantifies the level of excitement based on both facial expressions and gestures. This allows for a multifaceted evaluation of the level of excitement by analyzing not only the audio data but also facial expressions and gestures.

[0064] The excitement detection unit can identify peak moments of excitement and automatically take specific actions at that timing. For example, the excitement detection unit uses recorded conversation data to allow the generation AI to identify peak moments of excitement and automatically take photos. For example, it can activate the camera at the moment when there is a lot of laughter or cheering. The excitement detection unit also analyzes recorded conversation data and allows the generation AI to automatically start video recording at peak excitement. For example, it can activate the video camera at the peak of emotion. The excitement detection unit also builds a system where the generation AI triggers specific actions at peak excitement based on recorded conversation data. For example, it can display specific effects at peak excitement. This allows the generation AI to identify peak moments of excitement and automatically take specific actions at that timing, so important moments are not missed.

[0065] The excitement detection unit can use the emotion estimation function to quantify the degree of excitement as emotional intensity and display it in real time. For example, the excitement detection unit uses a generation AI to quantify the intensity of emotions based on recorded data of the conversation content and display the degree of excitement in real time. For example, it displays an emotion score in a graph. The excitement detection unit also analyzes the recorded data of the conversation, and the generation AI tracks changes in emotions and quantifies the degree of excitement. For example, it displays a score at the peak of the emotion. The excitement detection unit also builds a system in which the generation AI displays emotion estimation data in real time based on recorded data of the conversation content. For example, it quantifies the intensity of emotions and displays it on a screen. In this way, by quantifying the degree of excitement as emotional intensity and displaying it in real time, the emotional state of the participants can be visually grasped.

[0066] The excitement detection unit can make the excitement detection technology applicable to other events. For example, the excitement detection unit generalizes the excitement detection algorithm so that it can be used for sports events and concerts. For example, it analyzes the cheers and applause of the audience. The excitement detection unit also develops an interface to apply the results of excitement detection to other events. For example, it displays the level of excitement of a sports event in real time. The excitement detection unit also standardizes the data format to apply the results of excitement detection to other events. For example, it displays the level of excitement of a sports event or a concert in a common format. This allows the excitement detection technology to be used for other events, improving the versatility of the technology.

[0067] The excitement detection unit can share the excitement level in cooperation with other devices. For example, the excitement detection unit may link the excitement detection results with a smartwatch and display the excitement level in real time. For example, it may display an emotion score on the smartwatch screen. The excitement detection unit may also link the excitement detection results with a smart speaker and notify the excitement level by voice. For example, it may issue a voice alert when excitement peaks. The excitement detection unit may also develop an API for linking the excitement detection results with other devices. For example, it may provide data to a smartwatch or smart speaker. This may improve the consistency and convenience of information by linking and sharing the excitement level with other devices.

[0068] The excitement detection unit can use the emotion estimation function to automatically trigger specific effects at the peak of excitement. For example, the excitement detection unit uses recorded conversation data to allow the generation AI to identify times when emotions are at their peak and automatically display a video of fireworks. For example, it plays a video of fireworks at the peak of excitement. The excitement detection unit also analyzes recorded conversation data, and the generation AI automatically changes the music at the peak of emotions. For example, it plays up-tempo music at the moment emotions are heightened. The excitement detection unit also builds a system in which the generation AI triggers specific effects at the peak of emotions based on recorded conversation data. For example, it plays specific videos or music at the peak of emotions. This allows the excitement of the event to be further increased by automatically triggering specific effects at the peak of excitement.

[0069] The venue suggestion unit can consider not only past reviews and ratings but also real-time congestion status and event information when selecting a venue to suggest. For example, the venue suggestion unit not only bases its selection on past reviews and ratings but also considers real-time congestion status when selecting a venue to suggest. For example, it selects a venue based on the current congestion level. Furthermore, the venue suggestion unit not only bases its selection on past reviews and ratings but also considers real-time event information when selecting a venue to suggest. For example, it selects a venue based on an event currently being held. Furthermore, the venue suggestion unit not only bases its selection on past reviews and ratings but also integrates and analyzes real-time congestion status and event information when selecting a venue to suggest. For example, it selects an optimal venue based on the congestion level and event information. In this way, by considering real-time congestion status and event information, it is possible to suggest a more appropriate venue.

[0070] The venue suggestion unit can customize the list of suggested venues based on the participant's profile, optimizing it to suit individual preferences. For example, the venue suggestion unit customizes the list of suggested venues based on the participant's profile. For example, it lists venues according to hobbies and preferences. The venue suggestion unit also optimizes the list of suggested venues based on the participant's profile data. For example, it suggests venues that reflect past activity history and preferences. The venue suggestion unit also updates the list of suggested venues in real time based on the participant's profile. For example, it updates the list when new hobbies or preferences are discovered. In this way, customizing the venue list based on the participant's profile makes it possible to make suggestions that are optimized to suit individual preferences.

[0071] The venue suggestion unit can use the emotion estimation function to suggest venues that match the emotional state of participants. For example, the venue suggestion unit uses the generation AI to estimate the emotional state based on recorded data of the conversation content and suggest a relaxing venue. For example, if emotions are calm, it will suggest a quiet place. The venue suggestion unit also analyzes the recorded data of the conversation, and the generation AI tracks changes in emotions and suggests an exciting venue. For example, if emotions are running high, it will suggest a lively place. The venue suggestion unit also integrates the emotion estimation data based on the recorded data of the conversation content and suggests a venue that matches the emotional state. For example, it will suggest the optimal venue when emotions are at their peak. In this way, by suggesting venues that match the emotional state, participant satisfaction is improved.

[0072] The venue suggestion unit can make the after-party venue suggestion function usable in other situations. For example, the venue suggestion unit generalizes the after-party venue suggestion algorithm so that it can also be used for dates and family trips. For example, it can be used to suggest date plans and travel plans. The venue suggestion unit also develops an interface for applying the after-party venue suggestion results to other situations. For example, it can automatically suggest plans for dates and family trips. The venue suggestion unit also standardizes the data format for utilizing the after-party venue suggestion results in other situations. For example, it can display plans for dates and family trips in a common format. This allows the after-party venue suggestion function to be used in other situations, improving the versatility of the system.

[0073] The venue suggestion unit can update the list of suggested venues in conjunction with feedback and ratings from other users. For example, the venue suggestion unit updates the list of suggested venues in real time based on feedback and ratings from other users. For example, it suggests venues that reflect the latest reviews and ratings. The venue suggestion unit also optimizes the list of suggested venues in conjunction with feedback data from other users. For example, it prioritizes listing venues with many positive ratings. The venue suggestion unit also builds a system that dynamically updates the list of suggested venues based on feedback and ratings from other users. For example, it updates the list every time new feedback is added. In this way, by updating the venue list in conjunction with feedback and ratings from other users, more appropriate venue suggestions are possible.

[0074] The venue suggestion unit uses the emotion estimation function to monitor participants' emotional reactions to the proposed venue in real time, allowing for continuous searching for the optimal venue. For example, the venue suggestion unit uses a generation AI to estimate emotional states based on recorded conversation data and monitor emotional reactions to the proposed venue in real time. For example, it displays an emotion score for the proposed venue. The venue suggestion unit also analyzes recorded conversation data, and the generation AI tracks changes in emotion and monitors emotional reactions to the proposed venue in real time. For example, it re-suggests the optimal venue when emotions are at their peak. The venue suggestion unit also integrates emotion estimation data based on recorded conversation data to build a system that monitors emotional reactions to the proposed venue in real time. For example, it dynamically adjusts the venue according to changes in emotion. This allows for continuous searching for the optimal venue by monitoring emotional reactions to the proposed venue in real time.

[0075] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0076] The Navi Party system can also be equipped with a health management unit that monitors the health of participants. For example, it can obtain heart rate and stress levels from smartwatches and fitness trackers to monitor participants' health in real time. The health management unit can also suggest appropriate break times and ways to refresh based on participants' health. For example, it can suggest places to relax if a participant's heart rate becomes high. The health management unit can also suggest healthy food and drink menus based on participants' health data. This makes it possible to make suggestions that take into account the participants' health, providing a more comfortable party experience.

[0077] The Navi Party system can also be equipped with a mobility management unit that takes into account participants' means of transportation. For example, it can propose optimal routes based on participants' current locations and means of transportation. The mobility management unit can also obtain real-time traffic information and propose routes that avoid congestion and delays. For example, it can propose alternative routes based on train delay information. The mobility management unit can also propose venues based on participants' means of transportation. For example, it can propose venues with parking for participants traveling by car. This makes it possible to make proposals that take participants' means of transportation into consideration, supporting smooth movement.

[0078] The Navi Party system can also be equipped with a budget management unit that takes into account the participant's budget. For example, participants can input their budget information and suggest the most suitable venue within that range. The budget management unit can also obtain venue price information in real time and provide options within the budget. For example, it can suggest food and drink plans that can be used within a specific budget. The budget management unit can also provide discount information and coupons based on the participant's budget. For example, it can suggest discount coupons that can be used at a specific venue. This makes it possible to make suggestions that take into account the participant's budget, allowing for the provision of economical party plans.

[0079] The Navi Party system can also be equipped with a dietary management unit that takes into account participants' dietary restrictions. For example, participants can input allergy information and dietary restrictions and suggest appropriate food and drink menus based on that information. The dietary management unit can also obtain venue menu information in real time and provide menus that accommodate dietary restrictions. For example, it can suggest gluten-free or vegetarian menus. The dietary management unit can also suggest venues that meet participants' dietary restrictions. For example, it can suggest restaurants with a wide selection of allergy-friendly menus. This makes it possible to make suggestions that take into account participants' dietary restrictions, allowing them to enjoy their meals with peace of mind.

[0080] The Navi Party system can also be equipped with an interactive survey function to dig deeper into participants' interests. For example, it can display questions related to topics that come up in the conversation in real time and prompt participants to answer them. The survey function can also create a more detailed profile based on participants' responses. For example, it can identify travel destination preferences based on answers to travel-related questions. The survey function can also suggest related events and activities based on participants' interests. For example, it can provide information about travel fairs to participants who love traveling. This allows for deeper digging into participants' interests and makes it possible to make more personalized suggestions.

[0081] The Navi Party System can also provide a relaxing environment by taking into account the emotional state of participants. For example, based on recorded conversation data, the generative AI can estimate the emotional state and suggest relaxing music and lighting. It can also suggest relaxing activities based on the emotional state. For example, it can suggest a yoga or meditation session if stress levels are high. It can also suggest relaxing places based on the emotional state. For example, it can suggest a quiet cafe or park. This allows for a more comfortable party experience by providing a relaxing environment that takes into account the emotional state of participants.

[0082] The Navi Party System can also customize entertainment content by taking into account the emotional state of participants. For example, the generative AI can estimate an emotional state based on recorded conversation data and suggest movies or music based on that emotion. It can also change the type of entertainment depending on the emotional state. For example, it can suggest an action movie if an emotion is high, and a comedy movie if an emotion is relaxed. It can also adjust the timing of entertainment based on the emotional state. For example, it can play exciting music when an emotion is at its peak. This allows for entertainment content that takes into account the emotional state of participants, resulting in a more satisfying party experience.

[0083] The Navi Party System can also adjust the atmosphere of the venue by taking into account the emotional state of participants. For example, the generative AI can estimate their emotional state based on recorded conversation data and adjust the lighting and music based on their emotions. It can also change the venue decorations according to their emotional state. For example, it can suggest colorful decorations when emotions are high and simple decorations when emotions are relaxed. It can also adjust the venue layout based on their emotional state. For example, it can expand the dance floor when emotions are at their peak. This allows for a more comfortable party experience by providing a venue atmosphere that takes into account the emotional state of participants.

[0084] The Navi Party System can also adjust the progress of the party by taking into account the emotional state of the participants. For example, the generative AI can estimate the emotional state based on recorded conversation data and propose a progress plan based on the emotions. It can also change party activities according to the emotional state. For example, it can suggest games or quizzes when emotions are high, and suggest talk sessions when emotions are relaxed. It can also adjust the party time schedule based on the emotional state. For example, it can arrange activities that will get the party going when emotions are at their peak. This allows for a more satisfying party experience by providing party progress that takes into account the emotional state of the participants.

[0085] The Navi Party System can also adjust the timing of the party's end by taking into account the emotional state of participants. For example, the generative AI can estimate their emotional state based on recorded conversation data and suggest an end time based on that emotion. It can also suggest relaxing activities before the party ends based on their emotional state. For example, it can play music to cool down if emotions are high, or provide quiet time if emotions are high. It can also suggest follow-up activities after the party ends based on their emotional state. For example, it can send a thank-you message when emotions are at their peak. This allows for a more satisfying party experience by providing an end time that takes into account the emotional state of participants.

[0086] The processing flow of the second embodiment will be briefly explained below.

[0087] Step 1: The conversation recorder records the conversation. For example, you can simply place your smartphone on a table and the app will automatically record the conversation. The conversation recorder can also record conversations in the background. Step 2: The profiling unit analyzes the conversation recorded by the conversation recording unit and estimates the number of participants, their hobbies, and preferences. For example, the generation AI reflects the participants' hobbies and preferences in their profiles based on the text data of the conversation. The generation AI can also analyze statements made during the conversation to estimate the number of participants. Step 3: The excitement detection unit detects the level of excitement from the tone and volume of the audio based on the profile generated by the profiling unit. For example, the generation AI analyzes the frequency of laughter and cheers to determine the level of excitement. The generation AI can also identify peak moments of excitement based on the audio data. Step 4: The venue suggestion unit suggests the next venue based on the profile and the level of excitement. For example, the generation AI can connect with databases such as Tabelog to suggest the optimal venue for the after-party based on the participant profiles and the level of excitement. The generation AI can also suggest venues taking into account real-time congestion and event information.

[0088] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0089] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0090] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0091] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0092] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0093] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0094] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0095] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0096] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0097] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0098] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0099] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0100] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0101] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0102] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0106] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0107] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0116] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0122] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0129] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0138] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0139] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0140] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0141] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0142] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0143] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0144] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0145] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0146] 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.

[0147] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0148] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0149] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0150] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0151] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0152] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0153] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0154] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0155] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a conversation recording unit that records the contents of the conversation; a profiling unit that analyzes the content of the conversation recorded by the conversation recording unit and estimates the number of participants, hobbies, and preferences; an excitement detection unit that detects an excitement level from a tone or volume of a voice based on the profile generated by the profiling unit; a venue suggestion unit that suggests the next venue based on the profile and the level of excitement. A system characterized by:

2. The conversation recording unit Based on the recorded conversation data, the generative AI automatically classifies the topics of the conversation and evaluates the importance of each topic.

2. The system of claim 1.

3. The conversation recording unit Detect specific keywords and phrases used in conversations in real time and analyze their frequency and context 2. The system of claim 1.

4. The swelling detection unit is Tracking emotional shifts in conversations and identifying moments when certain emotions are most prominent 2. The system of claim 1.

5. The profiling unit Accuracy is improved by comparing hobbies and preferences inferred from conversation content with past behavioral history and social media data.

2. The system of claim 1.

Images