System

Abstract

An object of the system according to the embodiment is to enable a user having a scene mutism to speak at will.SOLUTION: A system includes a conversation log recording part, a hobby and taste interpretation part, a speech listening part, a response candidate generation part, a response selection part, and a voice output part. The conversation log recording unit records a conversation log. The hobby and preference interpretation unit interprets the user's hobby and preference based on the conversation log recorded by the conversation log recording unit. The utterance listening unit listens to an utterance of another person in a scene in which it is difficult for the user to speak. The response candidate generation unit automatically generates a plurality of response candidates based on characteristics of the user on the basis of the speech heard by the speech hearing unit. The response selection unit selects a content that the user wants to say from the response candidates generated by the response candidate generation unit. The voice output unit outputs the content selected by the response selection unit by the user's voice.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult for users with selective mutism to speak freely.

[0005] The system according to the embodiment aims to enable a user with selective mutism to speak freely. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversation log recording unit, a hobby / preference interpretation unit, a utterance listening unit, a reply candidate generation unit, a reply selection unit, and an audio output unit. The conversation log recording unit records a conversation log. The hobby / preference interpretation unit interprets the user's hobby / preference based on the conversation log recorded by the conversation log recording unit. The utterance listening unit listens to what others say in situations where it is difficult for the user to speak. The reply candidate generation unit automatically generates multiple reply candidates based on the user's characteristics, based on the utterances heard by the utterance listening unit. The reply selection unit selects what the user wants to say from the reply candidates generated by the reply candidate generation unit. The audio output unit outputs the content selected by the reply selection unit in the user's voice. [Effects of the Invention]

[0007] Systems according to embodiments can enable users with selective mutism to speak freely. [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) A conversation replacement system according to an embodiment of the present invention uses a generative AI to replace conversations in order to solve the problem of limited spaces where users with selective mutism can speak freely. This system records conversation logs of situations in which the user can speak freely and interprets the user's interests and preferences based on this data. In this way, in situations where the user has difficulty speaking, the system listens to what others say and automatically generates multiple response candidates based on the user's characteristics. The user selects what they want to say from these candidates, and the selected response is output in the user's voice. This allows the conversation replacement system to solve the problem of limited spaces in which users with selective mutism can speak freely. For example, this can facilitate smooth communication at school or work, improving the user's social life. Furthermore, because responses are generated based on the user's interests and preferences, natural conversations are possible.

[0029] A conversation substitute system according to an embodiment includes a conversation log recording unit, an interest and preference interpretation unit, a utterance listening unit, a response candidate generation unit, a response selection unit, and a voice output unit. The conversation log recording unit records a conversation log. For example, it records conversations in situations where a user can speak freely, converts them into text format, and saves them. The conversation log recording unit can also record video footage. For example, it records video footage including the user's facial expressions and gestures, and analyzes non-verbal communication elements. The interest and preference interpretation unit interprets the user's interest and preferences based on the conversation log recorded by the conversation log recording unit. For example, it analyzes the frequency of occurrence of specific keywords and phrases in the conversation log to quantitatively evaluate the strength of the user's interests. It also uses an emotion estimation function to analyze changes in emotions included in the conversation log and interpret the interest and preferences in more detail based on the user's emotional state. The utterance listening unit listens to what others say in situations where it is difficult for the user to speak. For example, when a teacher asks a question during a school lesson, it listens to the question using voice recognition technology. The reply candidate generation unit automatically generates multiple reply candidates based on the user's characteristics, based on the utterances heard by the utterance listening unit. For example, a generation AI analyzes the context of the utterances of others and generates reply candidates after understanding the intention and purpose of the utterances. The reply selection unit selects what the user wants to say from the reply candidates generated by the reply candidate generation unit. For example, the reply candidate selection interface is customized to make it easier for the user to intuitively select. The voice output unit outputs the content selected by the reply selection unit in the user's voice. For example, speech synthesis technology is used to reproduce the characteristics of the user's voice. This allows the conversation replacement system according to the embodiment to solve the problem of users with selective mutism having limited opportunities to speak freely. For example, this facilitates communication at school, work, etc., improving the user's social life. Furthermore, because responses are generated based on the user's hobbies and preferences, natural conversation becomes possible.

[0030] The conversation log recording unit can analyze the frequency of occurrence of specific keywords and phrases in the conversation log and quantitatively evaluate the strength of the user's interest. The conversation log recording unit, for example, extracts specific keywords and phrases from the conversation log and analyzes their frequency of occurrence. For example, if keywords such as "movies" or "music" appear frequently, it is evaluated that the user has a strong interest in those topics. The unit also quantifies the strength of the user's interest using frequency analysis. For example, it calculates the percentage of the entire conversation log that a specific keyword occupies, and evaluates the strength of interest based on that percentage. The unit also analyzes the frequency of keyword occurrence over time to understand fluctuations in the user's interest. For example, if a specific keyword suddenly appears at a specific time, it is interpreted as meaning that the user had a strong interest in that topic at that time. This allows the unit to quantitatively evaluate the strength of the user's interest.

[0031] The conversation log recording unit records the conversation log not only using audio but also using video footage, and can analyze non-verbal communication elements. For example, the conversation log recording unit includes video footage in the conversation log record and analyzes the user's facial expressions and gestures. For example, it analyzes scenes in which the user is smiling while speaking and evaluates the user's interest in that topic. It also uses video footage to analyze non-verbal communication elements such as the user's gaze and posture. For example, it analyzes the user's posture of leaning forward when talking about a particular topic and evaluates the user's interest in that topic. It also analyzes audio and video footage together to comprehensively evaluate the user's emotional state and interest. For example, it analyzes the user's facial expressions and tone of voice when talking about a particular topic and evaluates the user's interest in that topic. This makes it possible to analyze non-verbal communication elements as well.

[0032] The conversation log recording unit can analyze conversation logs in different languages ​​and build a multilingual interest and preference interpretation system. The conversation log recording unit, for example, collects conversation logs in different languages ​​and builds an interest and preference interpretation system compatible with each language. For example, it analyzes conversation logs in English, French, etc., and interprets the user's interest and preferences. It also uses multilingual natural language processing technology to analyze conversation logs in different languages ​​and interpret the user's interest and preferences. For example, it extracts keywords and phrases in each language and evaluates the user's interests. It also integrates and analyzes conversation logs in different languages ​​to build a system that comprehensively interprets the user's interest and preferences. For example, it analyzes conversation logs in multiple languages ​​and identifies common interest and preferences. This makes it possible to build a multilingual interest and preference interpretation system.

[0033] The utterance listening unit can analyze the context of other people's utterances and generate reply candidates after understanding the intention and purpose of the utterance. The utterance listening unit, for example, analyzes the context of other people's utterances and understands the intention of the utterance. For example, it analyzes the background and purpose of the question and generates appropriate reply candidates based on that. It also analyzes the context of the utterance along the timeline to understand the flow and relevance of the utterance. For example, it analyzes previous and subsequent utterances and generates appropriate reply candidates. It also uses context analysis to understand the purpose of other people's utterances and generate reply candidates according to that purpose. For example, it generates reply candidates that include specific information in response to a utterance requesting information. In this way, it is possible to analyze the context of other people's utterances and generate reply candidates after understanding the intention and purpose of the utterance.

[0034] The utterance listening unit can learn the user's past reactions to other people's utterances and generate more appropriate reply candidates. The utterance listening unit, for example, stores the user's past reactions to other people's utterances in a database and generates reply candidates based on that data. For example, it analyzes how the user reacted to similar utterances in the past. It also builds a system that learns the user's past reactions and generates reply candidates based on the learning results. For example, it analyzes past reaction patterns and generates appropriate reply candidates. It also uses past reaction data to understand the user's reaction tendencies and generates reply candidates based on those tendencies. For example, it generates positive reply candidates for utterances to which the user has a positive reaction. In this way, it is possible to learn the user's past reactions to other people's utterances and generate more appropriate reply candidates.

[0035] The utterance listening unit can translate utterances made by others in real time, enabling the generation of response candidates even in different language environments. The utterance listening unit, for example, builds a system that translates utterances made by others in real time and generates response candidates even in different language environments. For example, it translates utterances in English into Japanese and generates response candidates in Japanese. Also, it uses real-time translation technology to translate utterances made by others into different languages ​​and generates response candidates based on the translation results. For example, it translates utterances made in French into English and generates response candidates in English. Also, in order to generate appropriate response candidates even in different language environments, a system is developed that translates utterances made by others in real time and generates response candidates based on the translation results. For example, it translates utterances made in Chinese into Japanese and generates response candidates in Japanese. This makes it possible to generate response candidates even in different language environments.

[0036] When selecting a reply candidate, the reply selection unit can learn the user's past selection history and prioritize presenting more appropriate reply candidates. The reply selection unit, for example, stores the user's past response selection history in a database and presents reply candidates based on that data. For example, reply candidates selected in the past are prioritized. Furthermore, a system is constructed that learns the past selection history and presents reply candidates based on the learning results. For example, past selection patterns are analyzed and appropriate reply candidates are presented. Furthermore, the selection history data is used to understand the user's selection tendencies and present reply candidates based on those tendencies. For example, if the user tends to select positive responses, positive reply candidates are prioritized. In this way, the user's past selection history can be learned and more appropriate reply candidates can be presented preferentially.

[0037] The response selection unit can customize the response candidate selection interface to make it easier for the user to make an intuitive selection. The response selection unit, for example, customizes the response candidate selection interface to make it easier for the user to make an intuitive selection. For example, it uses icons and colors to make it visually easier to understand. The response candidate selection interface is also customized to improve user operability. For example, it allows response candidates to be selected by drag and drop. The response candidate selection interface is also customized to suit the user's preferences. For example, it displays frequently used response candidates by the user as shortcuts. In this way, the response candidate selection interface can be customized to make it easier for the user to make an intuitive selection.

[0038] The response selection unit enables response candidates to be selected using voice commands or gestures, improving user convenience. The response selection unit, for example, builds a system that enables response candidates to be selected using voice commands. For example, the user can select a response candidate by saying, "Select the first response." In addition, gesture recognition technology is used to enable response candidates to be selected using gestures. For example, the user can select a response candidate by pointing. In addition, a system is developed that combines voice commands and gestures to enable response candidate selection. For example, candidates are displayed using voice commands, and a user selects using gestures. This enables response candidates to be selected using voice commands or gestures, improving user convenience.

[0039] The response selection unit can add a function to not only visually display response candidate options but also read them aloud. The response selection unit can, for example, not only visually display response candidate options but also read them aloud. For example, it can allow a user to check the options aloud while looking at them. Furthermore, a system can be built that uses a text-to-speech function to present response candidates to a user. For example, it can allow a visually impaired user to check response candidates aloud. Furthermore, a system can be developed that combines visual display and text-to-speech to present response candidates. For example, it can read visually displayed response candidates aloud. This can add a function to not only visually display response candidate options but also read them aloud.

[0040] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0041] The conversation replacement system may further include a health management unit that monitors the user's health condition. For example, it may measure the user's heart rate and blood pressure to assess their stress level. The health management unit may also analyze the user's sleep patterns and assess their fatigue level. This allows the system to provide appropriate conversation content and response candidates based on the user's health condition. For example, if the user indicates a high stress level, it may provide relaxing topics.

[0042] The conversation replacement system may further include an activity recording unit that records the user's activity history. For example, it may record the places the user has visited and the activities the user has performed. The activity recording unit may also analyze the user's movement patterns and identify places and activities of interest. This makes it possible to provide appropriate conversation content and response candidates based on the user's activity history. For example, it may provide topics related to places the user has recently visited.

[0043] The conversation substitute system may further include a food recording unit that records the user's dietary history. For example, it may record what the user has eaten and what nutrients the user has ingested. The food recording unit may also analyze the user's eating patterns and suggest healthy meals. This may allow the system to provide appropriate conversation content and response candidates based on the user's dietary history. For example, it may provide topics related to dishes the user has recently eaten.

[0044] The conversation replacement system may further include an exercise recording unit that records the user's exercise history. For example, it may record the type of exercise the user has performed and the amount of exercise performed. The exercise recording unit may also analyze the user's exercise patterns and suggest appropriate exercises. This may allow the system to provide appropriate conversation content and response candidates based on the user's exercise history. For example, it may provide topics related to the user's recent exercise.

[0045] The conversation substitute system may further include a reading recorder that records the user's reading history. For example, it may record what books the user has read and what genres the user is interested in. The reading recorder may also analyze the user's reading patterns and make appropriate reading suggestions. This makes it possible to provide appropriate conversation content and response candidates based on the user's reading history. For example, it may provide topics related to books the user has recently read.

[0046] The conversation substitute system can further include an information providing unit that provides related news and information based on the user's hobbies and preferences. For example, the latest news in fields in which the user is interested can be provided. The information providing unit can also select appropriate information based on the user's hobbies and preferences. This can provide information that matches the user's interests and broaden the scope of conversation. For example, if the user is interested in movies, the latest movie information can be provided.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The conversation log recording unit records the conversation log. For example, it records conversations in scenes where the user can speak freely, converts them into text format, and saves them. The conversation log recording unit can also record video footage. For example, it can record video footage that includes the user's facial expressions and gestures, and analyze non-verbal communication elements as well. Step 2: The hobby and preference interpretation unit interprets the user's hobby and preference based on the conversation log recorded by the conversation log recording unit. For example, it analyzes the frequency of occurrence of specific keywords and phrases in the conversation log to quantitatively evaluate the strength of the user's interests. It also uses an emotion estimation function to analyze changes in emotions contained in the conversation log and interprets the hobby and preference in more detail based on the user's emotional state. Step 3: The speech recognition unit listens to what others say in situations where it is difficult for the user to speak. For example, if a teacher asks a question during a class, the unit listens to the question using voice recognition technology. Step 4: The response candidate generator automatically generates multiple response candidates based on the user's characteristics, based on the utterances heard by the utterance listener. For example, the generation AI analyzes the context of the other person's utterances and generates response candidates after understanding the intention and purpose of the utterances. Step 5: The reply selection unit selects what the user wants to say from the reply candidates generated by the reply candidate generation unit. For example, the reply candidate selection interface may be customized to make it easier for the user to make an intuitive selection. Step 6: The voice output unit outputs the content selected by the response selection unit in the user's voice, for example, by using voice synthesis technology to reproduce the characteristics of the user's voice.

[0049] (Example 2) A conversation replacement system according to an embodiment of the present invention uses a generative AI to replace conversations in order to solve the problem of limited spaces where users with selective mutism can speak freely. This system records conversation logs of situations in which the user can speak freely and interprets the user's interests and preferences based on this data. In this way, in situations where the user has difficulty speaking, the system listens to what others say and automatically generates multiple response candidates based on the user's characteristics. The user selects what they want to say from these candidates, and the selected response is output in the user's voice. This allows the conversation replacement system to solve the problem of limited spaces in which users with selective mutism can speak freely. For example, this can facilitate smooth communication at school or work, improving the user's social life. Furthermore, because responses are generated based on the user's interests and preferences, natural conversations are possible.

[0050] A conversation substitute system according to an embodiment includes a conversation log recording unit, an interest and preference interpretation unit, a utterance listening unit, a response candidate generation unit, a response selection unit, and a voice output unit. The conversation log recording unit records a conversation log. For example, it records conversations in situations where a user can speak freely, converts them into text format, and saves them. The conversation log recording unit can also record video footage. For example, it records video footage including the user's facial expressions and gestures, and analyzes non-verbal communication elements. The interest and preference interpretation unit interprets the user's interest and preferences based on the conversation log recorded by the conversation log recording unit. For example, it analyzes the frequency of occurrence of specific keywords and phrases in the conversation log to quantitatively evaluate the strength of the user's interests. It also uses an emotion estimation function to analyze changes in emotions included in the conversation log and interpret the interest and preferences in more detail based on the user's emotional state. The utterance listening unit listens to what others say in situations where it is difficult for the user to speak. For example, when a teacher asks a question during a school lesson, it listens to the question using voice recognition technology. The reply candidate generation unit automatically generates multiple reply candidates based on the user's characteristics, based on the utterances heard by the utterance listening unit. For example, a generation AI analyzes the context of the utterances of others and generates reply candidates after understanding the intention and purpose of the utterances. The reply selection unit selects what the user wants to say from the reply candidates generated by the reply candidate generation unit. For example, the reply candidate selection interface is customized to make it easier for the user to intuitively select. The voice output unit outputs the content selected by the reply selection unit in the user's voice. For example, speech synthesis technology is used to reproduce the characteristics of the user's voice. This allows the conversation replacement system according to the embodiment to solve the problem of users with selective mutism having limited opportunities to speak freely. For example, this facilitates communication at school, work, etc., improving the user's social life. Furthermore, because responses are generated based on the user's hobbies and preferences, natural conversation becomes possible.

[0051] The conversation log recording unit analyzes changes in emotions contained in the conversation log and can interpret the user's hobbies and preferences in more detail based on the user's emotional state. The conversation log recording unit, for example, analyzes the user's emotional changes in the conversation log and evaluates the intensity of the emotion toward a specific topic. For example, if the user shows positive emotions when talking about a specific topic, it interprets this as a strong interest in that topic. The conversation log recording unit also analyzes the emotional changes in the conversation log along a time axis to understand the user's emotional fluctuation pattern. For example, it analyzes how emotions change between the beginning and end of a conversation to evaluate the sustainability of the user's interest. The emotion analysis is also used to identify topics about which the user shows particularly positive emotions and to interpret the hobbies and preferences related to those topics in more detail. For example, it prioritizes analysis of topics that the user talks about while smiling. This allows the user's hobbies and preferences to be interpreted in more detail based on the user's emotional state.

[0052] The conversation log recording unit can analyze the frequency of occurrence of specific keywords and phrases in the conversation log and quantitatively evaluate the strength of the user's interest. The conversation log recording unit, for example, extracts specific keywords and phrases from the conversation log and analyzes their frequency of occurrence. For example, if keywords such as "movies" or "music" appear frequently, it is evaluated that the user has a strong interest in those topics. The unit also quantifies the strength of the user's interest using frequency analysis. For example, it calculates the percentage of the entire conversation log that a specific keyword occupies, and evaluates the strength of interest based on that percentage. The unit also analyzes the frequency of keyword occurrence over time to understand fluctuations in the user's interest. For example, if a specific keyword suddenly appears at a specific time, it is interpreted as meaning that the user had a strong interest in that topic at that time. This allows the unit to quantitatively evaluate the strength of the user's interest.

[0053] The conversation log recording unit can use the emotion estimation function to identify topics for which the user shows particularly positive emotions and preferentially generate reply candidates related to those topics. The conversation log recording unit, for example, uses the emotion estimation function to identify topics for which the user shows positive emotions. For example, it analyzes topics that the user talks about with a smile and preferentially generates reply candidates related to those topics. It also identifies topics for which positive emotions are shown and extracts keywords and phrases related to those topics. For example, it generates reply candidates based on keywords related to topics that the user talks about with a happy attitude. It also preferentially analyzes topics for which the user shows particularly positive emotions based on the emotion estimation data and generates reply candidates related to those topics. For example, it preferentially generates reply candidates related to topics that the user talks about with excitement. This makes it possible to preferentially generate reply candidates related to topics for which the user shows particularly positive emotions.

[0054] The conversation log recording unit records the conversation log not only using audio but also using video footage, and can analyze non-verbal communication elements. For example, the conversation log recording unit includes video footage in the conversation log record and analyzes the user's facial expressions and gestures. For example, it analyzes scenes in which the user is smiling while speaking and evaluates the user's interest in that topic. It also uses video footage to analyze non-verbal communication elements such as the user's gaze and posture. For example, it analyzes the user's posture of leaning forward when talking about a particular topic and evaluates the user's interest in that topic. It also analyzes audio and video footage together to comprehensively evaluate the user's emotional state and interest. For example, it analyzes the user's facial expressions and tone of voice when talking about a particular topic and evaluates the user's interest in that topic. This makes it possible to analyze non-verbal communication elements as well.

[0055] The conversation log recording unit can analyze conversation logs in different languages ​​and build a multilingual interest and preference interpretation system. The conversation log recording unit, for example, collects conversation logs in different languages ​​and builds an interest and preference interpretation system compatible with each language. For example, it analyzes conversation logs in English, French, etc., and interprets the user's interest and preferences. It also uses multilingual natural language processing technology to analyze conversation logs in different languages ​​and interpret the user's interest and preferences. For example, it extracts keywords and phrases in each language and evaluates the user's interests. It also integrates and analyzes conversation logs in different languages ​​to build a system that comprehensively interprets the user's interest and preferences. For example, it analyzes conversation logs in multiple languages ​​and identifies common interest and preferences. This makes it possible to build a multilingual interest and preference interpretation system.

[0056] The conversation log recording unit uses the emotion estimation function to analyze the facial expressions and gestures of the user when speaking, and can generate more natural response candidates. The conversation log recording unit, for example, uses the emotion estimation function to analyze the facial expressions of the user when speaking and generate natural response candidates based on the facial expressions. For example, positive response candidates are generated when the user speaks with a smile. The conversation log recording unit also analyzes the user's gestures and generates natural response candidates based on the gestures. For example, response candidates indicating agreement are generated when the user nods. A system is also constructed that analyzes facial expressions and gestures together to generate more natural response candidates. For example, response candidates indicating positive agreement are generated when the user nods with a smile. This makes it possible to analyze the facial expressions and gestures of the user when speaking and generate more natural response candidates.

[0057] The utterance listening unit can analyze the context of other people's utterances and generate reply candidates after understanding the intention and purpose of the utterance. The utterance listening unit, for example, analyzes the context of other people's utterances and understands the intention of the utterance. For example, it analyzes the background and purpose of the question and generates appropriate reply candidates based on that. It also analyzes the context of the utterance along the timeline to understand the flow and relevance of the utterance. For example, it analyzes previous and subsequent utterances and generates appropriate reply candidates. It also uses context analysis to understand the purpose of other people's utterances and generate reply candidates according to that purpose. For example, it generates reply candidates that include specific information in response to a utterance requesting information. In this way, it is possible to analyze the context of other people's utterances and generate reply candidates after understanding the intention and purpose of the utterance.

[0058] The utterance listening unit can learn the user's past reactions to other people's utterances and generate more appropriate reply candidates. The utterance listening unit, for example, stores the user's past reactions to other people's utterances in a database and generates reply candidates based on that data. For example, it analyzes how the user reacted to similar utterances in the past. It also builds a system that learns the user's past reactions and generates reply candidates based on the learning results. For example, it analyzes past reaction patterns and generates appropriate reply candidates. It also uses past reaction data to understand the user's reaction tendencies and generates reply candidates based on those tendencies. For example, it generates positive reply candidates for utterances to which the user has a positive reaction. In this way, it is possible to learn the user's past reactions to other people's utterances and generate more appropriate reply candidates.

[0059] The utterance listening unit can use the emotion estimation function to analyze the emotion contained in the utterance of another person and generate reply candidates according to that emotion. The utterance listening unit, for example, uses the emotion estimation function to analyze the emotion contained in the utterance of another person. For example, the emotion is estimated from the tone and expression of the utterance, and reply candidates according to that emotion are generated. Furthermore, a system is constructed that analyzes the emotion of the utterance of another person and generates reply candidates according to that emotion. For example, a calm reply candidate is generated in response to a utterance that expresses anger. Furthermore, emotion analysis is used to understand the emotion contained in the utterance of another person and generate reply candidates according to that emotion. For example, a reply candidate that expresses empathy is generated in response to a utterance that expresses joy. In this way, the emotion contained in the utterance of another person can be analyzed and reply candidates according to that emotion can be generated.

[0060] The utterance listening unit can translate utterances made by others in real time, enabling the generation of response candidates even in different language environments. The utterance listening unit, for example, builds a system that translates utterances made by others in real time and generates response candidates even in different language environments. For example, it translates utterances in English into Japanese and generates response candidates in Japanese. Also, it uses real-time translation technology to translate utterances made by others into different languages ​​and generates response candidates based on the translation results. For example, it translates utterances made in French into English and generates response candidates in English. Also, in order to generate appropriate response candidates even in different language environments, a system is developed that translates utterances made by others in real time and generates response candidates based on the translation results. For example, it translates utterances made in Chinese into Japanese and generates response candidates in Japanese. This makes it possible to generate response candidates even in different language environments.

[0061] The speech listening unit can analyze the speech features of other people's speech and infer the speaker's emotional state to generate reply candidates. The speech listening unit, for example, analyzes the speech features of other people's speech to infer the speaker's emotional state. For example, it analyzes the tone and speed of voice to infer the speaker's emotions. Furthermore, a system is constructed that uses speech feature analysis to infer the speaker's emotional state and generate reply candidates according to that emotion. For example, a calm reply candidate is generated in response to a speech made in a calm tone. Furthermore, the speech features of the speaker are analyzed, the emotional state is inferred based on the features, and appropriate reply candidates are generated. For example, a reply candidate showing empathy is generated in response to a speech made in an excited tone. In this way, it is possible to analyze the speech features of other people's speech, infer the speaker's emotional state, and generate reply candidates.

[0062] The utterance listening unit can use the emotion estimation function to monitor the user's emotional reactions to other people's utterances in real time and generate optimal reply candidates. The utterance listening unit, for example, uses the emotion estimation function to monitor the user's emotional reactions to other people's utterances in real time. For example, the utterance listening unit analyzes the user's facial expressions and voice to estimate the emotional reaction. A system is also constructed that monitors the user's emotional reactions in real time and generates optimal reply candidates based on the reactions. For example, if the user shows positive emotions, a reply candidate showing empathy is generated. Furthermore, the user's emotional reaction is analyzed based on the emotion estimation data and a reply candidate corresponding to the reaction is generated. For example, if the user shows negative emotions, a reply candidate showing comfort is generated. In this way, the user's emotional reactions to other people's utterances can be monitored in real time and optimal reply candidates can be generated.

[0063] When selecting a reply candidate, the reply selection unit can learn the user's past selection history and prioritize presenting more appropriate reply candidates. The reply selection unit, for example, stores the user's past response selection history in a database and presents reply candidates based on that data. For example, reply candidates selected in the past are prioritized. Furthermore, a system is constructed that learns the past selection history and presents reply candidates based on the learning results. For example, past selection patterns are analyzed and appropriate reply candidates are presented. Furthermore, the selection history data is used to understand the user's selection tendencies and present reply candidates based on those tendencies. For example, if the user tends to select positive responses, positive reply candidates are prioritized. In this way, the user's past selection history can be learned and more appropriate reply candidates can be presented preferentially.

[0064] The response selection unit can customize the response candidate selection interface to make it easier for the user to make an intuitive selection. The response selection unit, for example, customizes the response candidate selection interface to make it easier for the user to make an intuitive selection. For example, it uses icons and colors to make it visually easier to understand. The response candidate selection interface is also customized to improve user operability. For example, it allows response candidates to be selected by drag and drop. The response candidate selection interface is also customized to suit the user's preferences. For example, it displays frequently used response candidates by the user as shortcuts. In this way, the response candidate selection interface can be customized to make it easier for the user to make an intuitive selection.

[0065] The response selection unit can use the emotion estimation function to analyze the emotional response to the response candidate selected by the user and reflect the result in generating the next response candidate. The response selection unit, for example, uses the emotion estimation function to analyze the emotional response to the response candidate selected by the user. For example, the response selection unit analyzes the user's facial expression and voice to estimate the emotional response. Furthermore, a system is constructed that analyzes the user's emotional response and reflects the results in generating the next response candidate. For example, response candidates that indicate a positive emotional response are preferentially generated. Furthermore, the user's emotional response is analyzed based on the emotion estimation data, and the next response candidate is generated based on that response. For example, response candidates that indicate a negative emotional response are avoided. In this way, the emotional response to the response candidate selected by the user can be analyzed and reflected in generating the next response candidate.

[0066] The response selection unit enables response candidates to be selected using voice commands or gestures, improving user convenience. The response selection unit, for example, builds a system that enables response candidates to be selected using voice commands. For example, the user can select a response candidate by saying, "Select the first response." In addition, gesture recognition technology is used to enable response candidates to be selected using gestures. For example, the user can select a response candidate by pointing. In addition, a system is developed that combines voice commands and gestures to enable response candidate selection. For example, candidates are displayed using voice commands, and a user selects using gestures. This enables response candidates to be selected using voice commands or gestures, improving user convenience.

[0067] The response selection unit can add a function to not only visually display response candidate options but also read them aloud. The response selection unit can, for example, not only visually display response candidate options but also read them aloud. For example, it can allow a user to check the options aloud while looking at them. Furthermore, a system can be built that uses a text-to-speech function to present response candidates to a user. For example, it can allow a visually impaired user to check response candidates aloud. Furthermore, a system can be developed that combines visual display and text-to-speech to present response candidates. For example, it can read visually displayed response candidates aloud. This can add a function to not only visually display response candidate options but also read them aloud.

[0068] The response selection unit uses the emotion estimation function to analyze the emotional reactions of others to the response candidates selected by the user, thereby improving the quality of communication. The response selection unit, for example, uses the emotion estimation function to analyze the emotional reactions of others to the response candidates selected by the user. For example, it analyzes the facial expressions and voice of others to estimate the emotional reactions. Furthermore, it analyzes the emotional reactions of others and builds a system that improves the quality of communication based on the results. For example, it preferentially generates response candidates that indicate positive emotional reactions. Furthermore, it analyzes the emotional reactions of others based on the emotion estimation data and generates next response candidates based on those reactions. For example, it avoids response candidates that indicate negative emotional reactions. In this way, it is possible to analyze the emotional reactions of others to the response candidates selected by the user and improve the quality of communication.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The conversation replacement system may further include a health management unit that monitors the user's health condition. For example, it may measure the user's heart rate and blood pressure to assess their stress level. The health management unit may also analyze the user's sleep patterns and assess their fatigue level. This allows the system to provide appropriate conversation content and response candidates based on the user's health condition. For example, if the user indicates a high stress level, it may provide relaxing topics.

[0071] The conversation replacement system may further include an activity recording unit that records the user's activity history. For example, it may record the places the user has visited and the activities the user has performed. The activity recording unit may also analyze the user's movement patterns and identify places and activities of interest. This makes it possible to provide appropriate conversation content and response candidates based on the user's activity history. For example, it may provide topics related to places the user has recently visited.

[0072] The conversation substitute system may further include a music player that plays music that the user prefers. For example, the music that the user prefers may be played when the user wants to relax. The music player may also select appropriate music based on the user's emotional state. This allows the system to provide music that matches the user's emotional state and support relaxation and a change of mood. For example, if the user is feeling stressed, relaxing music may be played.

[0073] The conversation substitute system may further include a food recording unit that records the user's dietary history. For example, it may record what the user has eaten and what nutrients the user has ingested. The food recording unit may also analyze the user's eating patterns and suggest healthy meals. This may allow the system to provide appropriate conversation content and response candidates based on the user's dietary history. For example, it may provide topics related to dishes the user has recently eaten.

[0074] The conversation replacement system may further include an exercise recording unit that records the user's exercise history. For example, it may record the type of exercise the user has performed and the amount of exercise performed. The exercise recording unit may also analyze the user's exercise patterns and suggest appropriate exercises. This may allow the system to provide appropriate conversation content and response candidates based on the user's exercise history. For example, it may provide topics related to the user's recent exercise.

[0075] The conversation substitute system may further include a reading recorder that records the user's reading history. For example, it may record what books the user has read and what genres the user is interested in. The reading recorder may also analyze the user's reading patterns and make appropriate reading suggestions. This makes it possible to provide appropriate conversation content and response candidates based on the user's reading history. For example, it may provide topics related to books the user has recently read.

[0076] The conversation replacement system can also monitor the user's emotional state in real time and generate response candidates according to the user's emotions. For example, it can analyze the user's facial expressions and voice to estimate the user's emotional state. It can also build a system that generates appropriate response candidates based on the user's emotional state. This allows for more natural conversation by providing response candidates according to the user's emotional state. For example, if the user is sad, it can provide words of comfort.

[0077] The conversation substitute system can further include an information providing unit that provides related news and information based on the user's hobbies and preferences. For example, the latest news in fields in which the user is interested can be provided. The information providing unit can also select appropriate information based on the user's hobbies and preferences. This can provide information that matches the user's interests and broaden the scope of conversation. For example, if the user is interested in movies, the latest movie information can be provided.

[0078] The conversation substitute system may further include an environmental sound playback unit that plays relaxing environmental sounds based on the user's emotional state. For example, if the user is feeling stressed, nature sounds or relaxing music may be played. The environmental sound playback unit may also select appropriate environmental sounds based on the user's emotional state. This provides environmental sounds that correspond to the user's emotional state, supporting relaxation and a change of mood. For example, if the user wants to relax, the sound of waves or birds chirping may be played.

[0079] The conversation substitution system may further include an activity suggestion unit that suggests an appropriate activity based on the user's emotional state. For example, if the user is feeling stressed, an activity that will help them relax may be suggested. The activity suggestion unit may also select an appropriate activity based on the user's emotional state. This allows the system to provide an activity that matches the user's emotional state and support relaxation or a change of mood. For example, if the user wants to relax, yoga or meditation may be suggested.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The conversation log recording unit records the conversation log. For example, it records conversations in scenes where the user can speak freely, converts them into text format, and saves them. The conversation log recording unit can also record video footage. For example, it can record video footage that includes the user's facial expressions and gestures, and analyze non-verbal communication elements as well. Step 2: The hobby and preference interpretation unit interprets the user's hobby and preference based on the conversation log recorded by the conversation log recording unit. For example, it analyzes the frequency of occurrence of specific keywords and phrases in the conversation log to quantitatively evaluate the strength of the user's interests. It also uses an emotion estimation function to analyze changes in emotions contained in the conversation log and interprets the hobby and preference in more detail based on the user's emotional state. Step 3: The speech recognition unit listens to what others say in situations where it is difficult for the user to speak. For example, if a teacher asks a question during a class, the unit listens to the question using voice recognition technology. Step 4: The response candidate generator automatically generates multiple response candidates based on the user's characteristics, based on the utterances heard by the utterance listener. For example, the generation AI analyzes the context of the other person's utterances and generates response candidates after understanding the intention and purpose of the utterances. Step 5: The reply selection unit selects what the user wants to say from the reply candidates generated by the reply candidate generation unit. For example, the reply candidate selection interface may be customized to make it easier for the user to make an intuitive selection. Step 6: The voice output unit outputs the content selected by the response selection unit in the user's voice, for example, by using voice synthesis technology to reproduce the characteristics of the user's voice.

[0082] 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.

[0083] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0084] 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.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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).

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0099] 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.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0114] 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.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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 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.

[0127] 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.

[0128] 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.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0136] 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."

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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]

[0149] 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 log recording unit that records a conversation log; a hobby / preference interpretation unit that interprets the user's hobby / preference based on the conversation log recorded by the conversation log recording unit; a speech listening unit that listens to speech from others in a scene where it is difficult for the user to speak; a reply candidate generating unit that automatically generates a plurality of reply candidates based on the characteristics of the user based on the utterances heard by the utterance listening unit; a response selection unit that selects a topic that the user wants to talk about from the response candidates generated by the response candidate generation unit; a voice output unit that outputs the content selected by the response selection unit in the user's voice; A system characterized by:

2. The conversation log recording unit Analyzing changes in emotions contained in the conversation log and interpreting the user's interests and preferences in more detail based on the user's emotional state.

2. The system of claim 1.

3. The conversation log recording unit The frequency of occurrence of specific keywords and phrases in the conversation log is analyzed, and the strength of the user's interest is quantitatively evaluated.

2. The system of claim 1.

4. The conversation log recording unit Identifying topics about which the user has particularly positive feelings and generating response candidates related to those topics with priority 2. The system of claim 1.

5. The conversation log recording unit The conversation log will be recorded not only as audio but also as video footage, and non-verbal communication elements will also be analyzed.

2. The system of claim 1.

Images