System

Abstract

An object of a system according to an embodiment is to impart humor to an interactive agent and realize an agent that is friendly to a user.SOLUTION: A system includes a learning unit, a generation unit, a presentation unit, and an analysis unit. The learning unit learns humor. The generation unit generates humor based on the humor learned by the learning unit. The exposure part exposes the humor generated by the generation part. The analysis unit analyzes the reaction of the user.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 technologies have had the problem that interactive agents are impersonal and users find it difficult to feel familiar with them.

[0005] The system according to the embodiment aims to add humor to the interactive agent and realize an agent that is easy for the user to relate to. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, a generating unit, a displaying unit, and an analyzing unit. The learning unit learns humor. The generating unit generates humor based on the humor learned by the learning unit. The displaying unit displays the humor generated by the generating unit. The analyzing unit analyzes user reactions. [Effects of the Invention]

[0007] The system according to the embodiment can add humor to the interactive agent, making it possible to realize an agent that is easy for the user to relate to. [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) An interactive agent system according to an embodiment of the present invention is a system that uses a generative AI to add humor. The interactive agent system uses the generative AI to learn humor from stand-up comedy videos and other entertainment formats, and generates and displays appropriate humor during a dialogue with a user. Furthermore, the system also includes a mechanism for analyzing user responses in real time and providing humor at appropriate times. For example, when a monitoring agent interacts with an elderly person, the system uses humor to help the elderly relax. Furthermore, when a chat agent interacts with a child, the system uses humor to help the child continue the dialogue while enjoying it. In this way, by adding humor to an agent using a generative AI, the system aims to create a friendly agent. This allows the interactive agent system to create a friendly agent that users can accept more naturally. For example, when a monitoring agent interacts with an elderly person, the system uses humor to help the elderly relax. Furthermore, when a chat agent interacts with a child, the system uses humor to help the child continue the dialogue while enjoying it.

[0029] An interactive agent system according to an embodiment includes a learning unit, a generation unit, a presentation unit, and an analysis unit. The learning unit learns humor. For example, the learning unit learns humor from stand-up comedy videos and other entertainment formats. The learning unit can also use a generation AI to analyze this data and extract humor elements. For example, the learning unit analyzes stand-up comedy videos and extracts humor elements such as gestures and pauses in conversation. The generation unit generates humor based on the humor learned by the learning unit. The generation unit generates appropriate humor based on, for example, a user's utterances and a situation. The generation unit can also use the generation AI to generate humor based on the user's utterances and a situation. For example, the generation unit analyzes a user's utterances and generates humor based on the content of the utterances. The presentation unit presents the humor generated by the generation unit. For example, the presentation unit presents humor based on a user's reaction. The presentation unit can also use AI to present humor based on a user's reaction. For example, the presentation unit analyzes a user's facial expression and tone of voice to adjust the timing of the humor. The analysis unit analyzes the user's reaction. For example, the analysis unit analyzes the user's facial expression and tone of voice to evaluate the effectiveness of the humor. The analysis unit can also use AI to analyze the user's reaction in real time. For example, the analysis unit analyzes changes in the user's facial expression to evaluate the effectiveness of the humor. In this way, the interactive agent system according to the embodiment can realize a friendly agent by learning, generating, displaying, and analyzing humor.

[0030] The learning unit can learn humor from stand-up comedy videos or other entertainment formats. Examples of stand-up comedy videos include, but are not limited to, comedy shows and stand-up comedy. The learning unit, for example, analyzes stand-up comedy videos and extracts humor elements. The learning unit can also learn humor from other entertainment formats. For example, the learning unit analyzes movies, television programs, plays, etc. and extracts humor elements. This allows a wide range of humor to be provided by learning humor from stand-up comedy videos and other entertainment formats. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input stand-up comedy videos into the generation AI and cause the generation AI to extract humor elements.

[0031] The generation unit can generate humor based on the user's utterances or the situation. Examples of the user's utterances include, but are not limited to, text and audio. The generation unit can, for example, analyze the user's utterances and generate humor based on the content of the utterances. The generation unit can also generate humor based on the user's situation. Examples of the situation include, but are not limited to, the time of day, location, and the user's state. For example, if the user is relaxed, the generation unit generates humor with a relaxed atmosphere. This enables more natural dialogue by generating humor based on the user's utterances and the situation. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's utterances into the generation AI and have the generation AI generate humor.

[0032] The presentation unit can present humor based on the user's reaction. User reactions include, but are not limited to, laughter, facial expressions, and comments. The presentation unit, for example, analyzes the user's facial expressions and adjusts the timing of the humor. The presentation unit can also analyze the user's tone of voice and adjust the timing of the humor. For example, the presentation unit analyzes changes in the user's tone of voice and adjusts the timing of the humor. This allows humor to be presented more effectively by presenting humor based on the user's reaction. Some or all of the above-described processing in the presentation unit may be performed using AI, or may be performed without using AI. For example, the presentation unit can input the user's facial expression data into the generation AI and cause the generation AI to adjust the timing of the humor.

[0033] The analysis unit can analyze the user's facial expressions and tone of voice to adjust the timing of humor. Facial expressions include, but are not limited to, smiles, surprise, sadness, etc. The analysis unit can, for example, analyze the user's facial expressions to adjust the timing of humor. The analysis unit can also analyze the user's tone of voice to adjust the timing of humor. Voice tone includes, but is not limited to, pitch, strength, and emotional expression, for example. For example, the analysis unit can analyze changes in the user's tone of voice to adjust the timing of humor. This allows the timing of humor to be optimized by analyzing the user's facial expressions and tone of voice. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the user's facial expression data into the generation AI and cause the generation AI to adjust the timing of humor.

[0034] The generation unit can generate light-hearted jokes or humor with deep meaning. Light-hearted jokes include, but are not limited to, short one-liners and simple wordplay. The generation unit, for example, generates short one-liners. The generation unit can also generate simple wordplay. Deep wit includes, but is not limited to, philosophical humor and satirical comments. For example, the generation unit generates philosophical humor. This allows for the generation of a wide range of humor to be adapted to various situations. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can cause the generation AI to generate light-hearted jokes.

[0035] The generation unit can provide humor according to the user's cultural background. Cultural backgrounds include, but are not limited to, nationality, religion, and regional customs. For example, the generation unit can provide humor based on Japanese culture. The generation unit can also provide humor based on American culture. For example, the generation unit can provide appropriate humor according to the user's cultural background. This enables more friendly dialogue by providing humor according to the user's cultural background. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can cause the generation AI to generate humor based on the user's cultural background.

[0036] The learning unit can learn gestures and facial expressions. Gestures include, but are not limited to, hand movements and facial expressions. The learning unit, for example, learns hand movements. The learning unit can also learn facial expressions. Facial expressions include, but are not limited to, smiles, surprise, sadness, and the like. For example, the learning unit learns smiles. By learning gestures and facial expressions, more natural humor can be provided. Some or all of the above-described processing in the learning unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the learning unit can cause the generation AI to learn gestures and facial expressions.

[0037] The learning unit can compare humor from different cultural spheres and extract similarities and differences. Cultural spheres include, but are not limited to, countries, regions, and language spheres. For example, the learning unit can compare Japanese manzai comedy with American stand-up comedy to extract common humor elements. The learning unit can also compare humor from French sitcoms with humor from Indian Bollywood films to learn cultural differences. For example, the learning unit can compare traditional Chinese comedy with British black humor to extract similarities and differences between the humor. This allows learning about a wide range of humor by comparing humor from different cultural spheres. Some or all of the above-described processing in the learning unit can be performed using or without the generation AI. For example, the learning unit can input humor data from different cultural spheres into the generation AI and have the generation AI extract similarities and differences.

[0038] The learning unit can apply different learning algorithms to different types of humor. Examples of learning algorithms include, but are not limited to, neural networks and support vector machines. For example, the learning unit can apply a language analysis algorithm to wordplay humor to learn. The learning unit can also apply a motion analysis algorithm to physical gags to learn. For example, the learning unit can apply a scenario analysis algorithm to situation comedies to learn. This improves the accuracy of learning by applying an appropriate learning algorithm to each type of humor. Some or all of the above-described processing in the learning unit can be performed using or without the generation AI. For example, the learning unit can cause the generation AI to apply different learning algorithms to each type of humor.

[0039] The learning unit can improve the accuracy of learning by referring to the user's past reaction data. Past reaction data includes, but is not limited to, text data, audio data, and image data. For example, the learning unit reflects humor patterns that the user laughed at in the past in the learning data. The learning unit can also exclude humor patterns that the user has not shown interest in in the past. For example, the learning unit evaluates the effectiveness of specific humor based on the user's past reaction data and reflects this in the learning. In this way, the accuracy of learning is improved by referring to the user's past reaction data. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the user's past reaction data into the generation AI and cause the generation AI to improve the accuracy of learning.

[0040] The learning unit can compare humor for different age groups and learn the characteristics of each age group. Age groups include, but are not limited to, children, young people, and middle-aged and elderly people. For example, the learning unit can compare children's anime with adult sitcoms to learn the characteristics of humor for each age group. The learning unit can also compare social media videos for young people with television programs for older people to learn the differences in humor for each age group. For example, the learning unit can compare YouTube videos for teenagers with dramas for middle-aged people to learn the characteristics of humor for each age group. By comparing humor for different age groups, humor appropriate for a wide range of age groups can be learned. Some or all of the above-described processing in the learning unit can be performed using or without the generation AI. For example, the learning unit can input humor data for different age groups into the generation AI and have the generation AI learn the characteristics.

[0041] The learning unit can collect the user's physiological responses and evaluate the effectiveness of humor. Physiological responses include, but are not limited to, heart rate and electrodermal activity. For example, the learning unit can collect changes in heart rate when the user laughs and evaluate the effectiveness of humor. The learning unit can also collect electrodermal responses when the user reacts to humor and evaluate the effectiveness of humor. For example, the learning unit collects the physiological responses of the user to humor and reflects them in learning. In this way, by collecting the user's physiological responses, the effectiveness of humor can be more accurately evaluated. Some or all of the above-mentioned processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the user's physiological response data into the generation AI and have the generation AI evaluate the effectiveness of humor.

[0042] The learning unit can analyze the user's social media activity and learn trending humor. Social media activity includes, but is not limited to, the content of posts, comments, and the number of likes. The learning unit, for example, captures humorous videos frequently shared by the user as learning data. The learning unit can also learn humor that receives many likes and comments on the user's social media. For example, the learning unit captures humor that receives many responses from the user's followers as learning data. This allows humor based on the latest trends to be learned by analyzing the user's social media activity. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input social media activity data into the generation AI and cause the generation AI to learn trending humor.

[0043] The generation unit can apply different generation algorithms to different types of humor. Examples of generation algorithms include, but are not limited to, text generation algorithms and image generation algorithms. For example, the generation unit can apply a language generation algorithm to wordplay humor. The generation unit can also apply an action generation algorithm to physical gags. For example, the generation unit can apply a scenario generation algorithm to situation comedy. This improves the accuracy of generation by applying an appropriate generation algorithm to each type of humor. Some or all of the above-described processing in the generation unit can be performed using a generation AI, or can be performed without using a generation AI. For example, the generation unit can cause the generation AI to apply a different generation algorithm to each type of humor.

[0044] The generation unit can improve the accuracy of humor by referring to the user's past reaction data. Past reaction data includes, but is not limited to, text data, audio data, and image data. For example, the generation unit reflects patterns of humor that the user laughed at in the past in the generation. The generation unit can also exclude patterns of humor that the user has not shown interest in in the past. For example, the generation unit evaluates the effectiveness of specific humor based on the user's past reaction data and reflects this in the generation. In this way, the accuracy of the generation is improved by referring to the user's past reaction data. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's past reaction data into the generation AI and cause the generation AI to improve the accuracy of the humor.

[0045] The generation unit can customize humor according to the user's current situation. Examples of the current situation include, but are not limited to, the time of day, location, and user status. For example, if the user is at home, the generation unit generates humor that can be used at home. Also, if the user is at work, the generation unit can generate humor that can be used at work. For example, if the user is with friends, the generation unit generates humor that can be shared with friends. This allows for more appropriate humor to be provided by customizing humor according to the user's current situation. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit may input data about the user's current situation into the generation AI and cause the generation AI to customize the humor.

[0046] The generation unit can customize the humor content according to the user's cultural background. Cultural backgrounds include, but are not limited to, nationality, religion, and regional customs. For example, the generation unit can generate humor based on Japanese culture. The generation unit can also generate humor based on American culture. For example, the generation unit generates appropriate humor according to the user's cultural background. This allows the user to customize the humor content according to their cultural background, thereby providing more familiar humor. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's cultural background data into the generation AI and have the generation AI customize the humor content.

[0047] The generation unit can adjust the use of technical terms in the humor depending on the user's level of expertise. Examples of levels of expertise include, but are not limited to, beginner, intermediate, and expert. For example, if the user is an expert, the generation unit can generate humor that uses a lot of technical terms. Furthermore, if the user is a beginner, the generation unit can generate humor that avoids technical terms. For example, the generation unit generates humor that uses appropriate technical terms depending on the user's level of expertise. This allows for more appropriate humor to be provided by adjusting the use of technical terms in the humor depending on the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms in the humor.

[0048] The generation unit can improve the content of the humor by reflecting the user's past feedback. Past feedback includes, but is not limited to, user comments, ratings, and reaction data. For example, the generation unit reflects the user's past favorite humor patterns in the generation. The generation unit can also exclude humor patterns that the user has previously expressed dissatisfaction with. For example, the generation unit evaluates the effectiveness of specific humor based on the user's past feedback and reflects this in the generation. In this way, the humor content can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the generation unit may be performed using a generation AI or may be performed without using a generation AI. For example, the generation unit can input the user's past feedback data into the generation AI and cause the generation AI to improve the content of the humor.

[0049] The revealing unit can select the optimal revealing method by referring to the user's past reaction data. Past reaction data includes, but is not limited to, text data, audio data, and image data. For example, the revealing unit selects a humor revealing method that the user previously preferred. The revealing unit can also avoid humor revealing methods that the user previously disliked. For example, the revealing unit evaluates the effectiveness of a particular humor based on the user's past reaction data and selects the optimal revealing method. In this way, the optimal revealing method can be selected by referring to the user's past reaction data. Some or all of the above-described processing in the revealing unit may be performed using AI or without AI. For example, the revealing unit can input the user's past reaction data into the generation AI and have the generation AI select the optimal revealing method.

[0050] The revealing unit can customize humor according to the user's current situation. Examples of the current situation include, but are not limited to, the time of day, location, and user status. For example, if the user is at home, the revealing unit reveals humor that can be used at home. Also, if the user is at work, the revealing unit can reveal humor that can be used at work. For example, if the user is with friends, the revealing unit reveals humor that can be shared with friends. This allows for more appropriate humor to be provided by customizing humor according to the user's current situation. Some or all of the above-described processing in the revealing unit may be performed using AI, or may be performed without using AI. For example, the revealing unit can input the user's current situation data into the generation AI and cause the generation AI to customize the humor.

[0051] The presentation unit can analyze the user's feedback in real time and reflect it in the next humor presentation. Examples of feedback include, but are not limited to, real-time comments and changes in facial expressions. For example, if the user laughs, the presentation unit will present the same humor again next time. Furthermore, if the user does not respond, the presentation unit can present a different type of humor next time. For example, the presentation unit adjusts the content and timing of the humor based on the user's real-time feedback. This allows the user's feedback to be analyzed in real time and reflected in the next humor presentation. Some or all of the above-described processing in the presentation unit may be performed using AI, or may be performed without AI. For example, the presentation unit can input the user's feedback data into a generation AI and have the generation AI execute a process to reflect the data in the next humor presentation.

[0052] The display unit can select the optimal display method based on the user's device information. Device information includes, but is not limited to, smartphones, tablets, and PCs. For example, if the user is using a smartphone, the display unit can provide a humor display method that matches the screen size. Furthermore, if the user is using a tablet, the display unit can also provide a humor display method that is optimized for a large screen. For example, if the user is using a smartwatch, the display unit can provide a simple and highly visible humor display method. This allows for more effective humor to be presented by selecting the optimal display method based on the user's device information. Some or all of the above-described processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can input the user's device information into the generation AI and have the generation AI select the optimal display method.

[0053] The presentation unit can make the humor multilingual based on the user's language settings. Language settings include, but are not limited to, the user's language and region settings. For example, the presentation unit automatically sets the language of the humor based on the language settings of the user's device. The presentation unit can also provide a language switching function when the user uses multiple languages. For example, if the user selects a specific language, the presentation unit presents the humor in that language. This makes it possible to accommodate a wider range of users by making the humor multilingual based on the user's language settings. Some or all of the above-described processing in the presentation unit may be performed using AI, or may be performed without AI. For example, the presentation unit can input the user's language setting data into the generation AI and cause the generation AI to perform multilingual support for the humor.

[0054] The presentation unit can customize the humor presentation method by reflecting the user's past feedback. Past feedback includes, but is not limited to, user comments, ratings, and reaction data. For example, the presentation unit selects a humor presentation method that the user has previously preferred. The presentation unit can also avoid humor presentation methods that the user has previously expressed dissatisfaction with. For example, the presentation unit evaluates the effectiveness of specific humor based on the user's past feedback and selects the optimal presentation method. This allows the humor presentation method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the presentation unit may be performed using AI or without AI. For example, the presentation unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the humor presentation method.

[0055] The analysis unit can analyze the user's facial expressions and tone of voice in real time to evaluate the effectiveness of humor. Facial expressions include, but are not limited to, smiles, surprise, sadness, etc. The analysis unit can, for example, analyze the user's facial expressions when laughing in real time to evaluate the effectiveness of humor. The analysis unit can also analyze the user's tone of voice when reacting to humor in real time to evaluate the effectiveness of humor. For example, the analysis unit can evaluate the effectiveness of humor based on the user's real-time facial expressions and tone of voice. This allows for more accurate evaluation of the effectiveness of humor by analyzing the user's facial expressions and tone of voice in real time. Some or all of the above-described processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input the user's facial expression data into a generation AI and have the generation AI evaluate the effectiveness of humor.

[0056] The analysis unit can collect the user's physiological responses and evaluate the effectiveness of the humor. Physiological responses include, but are not limited to, heart rate and electrodermal activity. For example, the analysis unit can collect changes in the user's heart rate when the user laughs and evaluate the effectiveness of the humor. The analysis unit can also collect electrodermal responses when the user reacts to the humor and evaluate the effectiveness of the humor. For example, the analysis unit collects the user's physiological responses to the humor and reflects this in the analysis. By collecting the user's physiological responses, the effectiveness of the humor can be more accurately evaluated. Some or all of the above-described processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input the user's physiological response data into the generation AI and have the generation AI evaluate the effectiveness of the humor.

[0057] The analysis unit can improve the accuracy of the analysis by referring to the user's past reaction data. Past reaction data includes, but is not limited to, text data, audio data, and image data. For example, the analysis unit reflects in the analysis patterns of humor that the user laughed at in the past. The analysis unit can also exclude humor patterns that the user has not shown interest in in the past. For example, the analysis unit evaluates the effectiveness of specific humor based on the user's past reaction data and reflects this in the analysis. In this way, the accuracy of the analysis is improved by referring to the user's past reaction data. Some or all of the above-described processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input the user's past reaction data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0058] The analysis unit can analyze the user's social media activity to understand humor trends. Social media activity includes, but is not limited to, the content of posts, comments, and the number of likes. For example, the analysis unit can capture humorous videos frequently shared by the user as analysis data. The analysis unit can also analyze humor that receives many likes and comments on the user's social media. For example, the analysis unit can capture humor that receives many responses from the user's followers as analysis data. By analyzing the user's social media activity, humor based on the latest trends can be provided. Some or all of the above-described processing by the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input social media activity data into a generation AI and cause the generation AI to understand humor trends.

[0059] The analysis unit can evaluate the effectiveness of humor by taking into account the user's cultural background. Cultural background includes, but is not limited to, nationality, religion, and regional customs. For example, the analysis unit can evaluate the effectiveness of humor based on Japanese culture. The analysis unit can also evaluate the effectiveness of humor based on American culture. For example, the analysis unit evaluates the appropriate effectiveness of humor depending on the user's cultural background. This allows for a more appropriate evaluation of the effectiveness of humor by taking the user's cultural background into consideration. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the user's cultural background data into the generation AI and cause the generation AI to evaluate the effectiveness of humor.

[0060] The analysis unit can customize the analysis method by reflecting the user's past feedback. Past feedback includes, but is not limited to, user comments, ratings, and reaction data. For example, the analysis unit reflects the user's past favorite humor patterns in the analysis. The analysis unit can also exclude humor patterns that the user has previously expressed dissatisfaction with. For example, the analysis unit evaluates the effectiveness of specific humor based on the user's past feedback and reflects this in the analysis. In this way, the analysis method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the analysis method.

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

[0062] The interactive agent system may further include an hobby learning unit that learns the user's hobbies and interests. The hobby learning unit analyzes the user's past interaction history and social media activity to identify the user's hobbies and interests. For example, if the user is interested in sports, the hobby learning unit may provide the generation unit with sports-related humor. Also, if the user is a movie fan, the hobby learning unit may generate movie-related jokes. This allows for more friendly interaction by providing humor that matches the user's hobbies and interests.

[0063] The interactive agent system can further include a learning management unit that manages the user's learning progress. The learning management unit keeps track of the content and progress of the user's learning, and provides humorous advice at appropriate times. For example, if the user is working on a math problem, the learning management unit can provide the generation unit with math-related jokes. Also, if the user is learning a language, the learning management unit can provide humor related to the learning content. This can increase motivation to study.

[0064] The interactive agent system may further include a history reference unit that references the user's past interaction history to customize the humor content. The history reference unit analyzes what kind of humor the user responded to in the past and reflects that in the next interaction. For example, the history reference unit may provide the generator with patterns of jokes that the user laughed at in the past. It may also be able to exclude patterns of humor that the user did not show interest in in the past. This allows for more effective interaction by customizing the humor based on the user's past reactions.

[0065] The interactive agent system can further include a device adaptation unit that customizes the way humor is presented based on the user's device information. The device adaptation unit selects the optimal way to present humor depending on the type and screen size of the device used by the user. For example, if the user is using a smartphone, the device adaptation unit can provide humor tailored to the screen size. Also, if the user is using a tablet, the device adaptation unit can provide humor optimized for a larger screen. This allows for more effective dialogue by customizing the way humor is presented based on the user's device information.

[0066] The interactive agent system can further include a trend learning unit that analyzes the user's social media activity and learns trending humor. The trend learning unit analyzes the user's social media posts, comments, number of likes, and other information to grasp the latest humor trends. For example, the trend learning unit can incorporate humorous videos frequently shared by the user as learning data. It can also learn humor that is most popular among the user's followers. This makes it possible to provide humor based on the latest trends by analyzing the user's social media activity.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: The learning unit learns humor. For example, it learns humor from stand-up comedy videos and other entertainment formats, and then uses generative AI to analyze this data and extract humorous elements. Specifically, it analyzes stand-up comedy videos and extracts humorous elements such as gestures and pauses in conversation. Step 2: The generation unit generates humor based on the humor learned by the learning unit. For example, it generates appropriate humor based on the user's comments and the situation, and uses a generation AI to generate humor that matches the user's comments and the situation. Specifically, it analyzes the user's comments and generates humor that matches their content. Step 3: The display unit displays the humor generated by the generator. For example, the display unit displays humor based on the user's reaction, and uses AI to display humor based on the user's reaction. Specifically, the display unit analyzes the user's facial expressions and tone of voice and adjusts the timing of the humor. Step 4: The analysis unit analyzes the user's reactions. For example, it analyzes the user's facial expressions and tone of voice to evaluate the effectiveness of the humor. AI is used to analyze the user's reactions in real time, specifically, to analyze changes in the user's facial expressions to evaluate the effectiveness of the humor.

[0069] (Example 2) An interactive agent system according to an embodiment of the present invention is a system that uses a generative AI to add humor. The interactive agent system uses the generative AI to learn humor from stand-up comedy videos and other entertainment formats, and generates and displays appropriate humor during a dialogue with a user. Furthermore, the system also includes a mechanism for analyzing user responses in real time and providing humor at appropriate times. For example, when a monitoring agent interacts with an elderly person, the system uses humor to help the elderly relax. Furthermore, when a chat agent interacts with a child, the system uses humor to help the child continue the dialogue while enjoying it. In this way, by adding humor to an agent using a generative AI, the system aims to create a friendly agent. This allows the interactive agent system to create a friendly agent that users can accept more naturally. For example, when a monitoring agent interacts with an elderly person, the system uses humor to help the elderly relax. Furthermore, when a chat agent interacts with a child, the system uses humor to help the child continue the dialogue while enjoying it.

[0070] An interactive agent system according to an embodiment includes a learning unit, a generation unit, a presentation unit, and an analysis unit. The learning unit learns humor. For example, the learning unit learns humor from stand-up comedy videos and other entertainment formats. The learning unit can also use a generation AI to analyze this data and extract humor elements. For example, the learning unit analyzes stand-up comedy videos and extracts humor elements such as gestures and pauses in conversation. The generation unit generates humor based on the humor learned by the learning unit. The generation unit generates appropriate humor based on, for example, a user's utterances and a situation. The generation unit can also use the generation AI to generate humor based on the user's utterances and a situation. For example, the generation unit analyzes a user's utterances and generates humor based on the content of the utterances. The presentation unit presents the humor generated by the generation unit. For example, the presentation unit presents humor based on a user's reaction. The presentation unit can also use AI to present humor based on a user's reaction. For example, the presentation unit analyzes a user's facial expression and tone of voice to adjust the timing of the humor. The analysis unit analyzes the user's reaction. For example, the analysis unit analyzes the user's facial expression and tone of voice to evaluate the effectiveness of the humor. The analysis unit can also use AI to analyze the user's reaction in real time. For example, the analysis unit analyzes changes in the user's facial expression to evaluate the effectiveness of the humor. In this way, the interactive agent system according to the embodiment can realize a friendly agent by learning, generating, displaying, and analyzing humor.

[0071] The learning unit can learn humor from stand-up comedy videos or other entertainment formats. Examples of stand-up comedy videos include, but are not limited to, comedy shows and stand-up comedy. The learning unit, for example, analyzes stand-up comedy videos and extracts humor elements. The learning unit can also learn humor from other entertainment formats. For example, the learning unit analyzes movies, television programs, plays, etc. and extracts humor elements. This allows a wide range of humor to be provided by learning humor from stand-up comedy videos and other entertainment formats. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input stand-up comedy videos into the generation AI and cause the generation AI to extract humor elements.

[0072] The generation unit can generate humor based on the user's utterances or the situation. Examples of the user's utterances include, but are not limited to, text and audio. The generation unit can, for example, analyze the user's utterances and generate humor based on the content of the utterances. The generation unit can also generate humor based on the user's situation. Examples of the situation include, but are not limited to, the time of day, location, and the user's state. For example, if the user is relaxed, the generation unit generates humor with a relaxed atmosphere. This enables more natural dialogue by generating humor based on the user's utterances and the situation. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's utterances into the generation AI and have the generation AI generate humor.

[0073] The presentation unit can present humor based on the user's reaction. User reactions include, but are not limited to, laughter, facial expressions, and comments. The presentation unit, for example, analyzes the user's facial expressions and adjusts the timing of the humor. The presentation unit can also analyze the user's tone of voice and adjust the timing of the humor. For example, the presentation unit analyzes changes in the user's tone of voice and adjusts the timing of the humor. This allows humor to be presented more effectively by presenting humor based on the user's reaction. Some or all of the above-described processing in the presentation unit may be performed using AI, or may be performed without using AI. For example, the presentation unit can input the user's facial expression data into the generation AI and cause the generation AI to adjust the timing of the humor.

[0074] The analysis unit can analyze the user's facial expressions and tone of voice to adjust the timing of humor. Facial expressions include, but are not limited to, smiles, surprise, sadness, etc. The analysis unit can, for example, analyze the user's facial expressions to adjust the timing of humor. The analysis unit can also analyze the user's tone of voice to adjust the timing of humor. Voice tone includes, but is not limited to, pitch, strength, and emotional expression, for example. For example, the analysis unit can analyze changes in the user's tone of voice to adjust the timing of humor. This allows the timing of humor to be optimized by analyzing the user's facial expressions and tone of voice. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the user's facial expression data into the generation AI and cause the generation AI to adjust the timing of humor.

[0075] The generation unit can generate light-hearted jokes or humor with deep meaning. Light-hearted jokes include, but are not limited to, short one-liners and simple wordplay. The generation unit, for example, generates short one-liners. The generation unit can also generate simple wordplay. Deep wit includes, but is not limited to, philosophical humor and satirical comments. For example, the generation unit generates philosophical humor. This allows for the generation of a wide range of humor to be adapted to various situations. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can cause the generation AI to generate light-hearted jokes.

[0076] The generation unit can provide humor according to the user's cultural background. Cultural backgrounds include, but are not limited to, nationality, religion, and regional customs. For example, the generation unit can provide humor based on Japanese culture. The generation unit can also provide humor based on American culture. For example, the generation unit can provide appropriate humor according to the user's cultural background. This enables more friendly dialogue by providing humor according to the user's cultural background. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can cause the generation AI to generate humor based on the user's cultural background.

[0077] The learning unit can learn gestures and facial expressions. Gestures include, but are not limited to, hand movements and facial expressions. The learning unit, for example, learns hand movements. The learning unit can also learn facial expressions. Facial expressions include, but are not limited to, smiles, surprise, sadness, and the like. For example, the learning unit learns smiles. By learning gestures and facial expressions, more natural humor can be provided. Some or all of the above-described processing in the learning unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the learning unit can cause the generation AI to learn gestures and facial expressions.

[0078] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. Emotions include, but are not limited to, joy, sadness, and anger. For example, if the user is relaxed, the learning unit can select a comedy video with a relaxed atmosphere as training data. Furthermore, if the user is feeling stressed, the learning unit can select a video containing humor that will relieve stress as training data. For example, if the user is having fun, the learning unit can select a comedy video with an energetic and fun atmosphere as training data. This allows for more effective humor to be learned by selecting training data based on the user's emotions. Some or all of the above-described processing in the learning unit can be performed using or without the generation AI. For example, the learning unit can input the user's emotion data into the generation AI and have the generation AI select the training data.

[0079] The learning unit can compare humor from different cultural spheres and extract similarities and differences. Cultural spheres include, but are not limited to, countries, regions, and language spheres. For example, the learning unit can compare Japanese manzai comedy with American stand-up comedy to extract common humor elements. The learning unit can also compare humor from French sitcoms with humor from Indian Bollywood films to learn cultural differences. For example, the learning unit can compare traditional Chinese comedy with British black humor to extract similarities and differences between the humor. This allows learning about a wide range of humor by comparing humor from different cultural spheres. Some or all of the above-described processing in the learning unit can be performed using or without the generation AI. For example, the learning unit can input humor data from different cultural spheres into the generation AI and have the generation AI extract similarities and differences.

[0080] The learning unit can apply different learning algorithms to different types of humor. Examples of learning algorithms include, but are not limited to, neural networks and support vector machines. For example, the learning unit can apply a language analysis algorithm to wordplay humor to learn. The learning unit can also apply a motion analysis algorithm to physical gags to learn. For example, the learning unit can apply a scenario analysis algorithm to situation comedies to learn. This improves the accuracy of learning by applying an appropriate learning algorithm to each type of humor. Some or all of the above-described processing in the learning unit can be performed using or without the generation AI. For example, the learning unit can cause the generation AI to apply different learning algorithms to each type of humor.

[0081] The learning unit can improve the accuracy of learning by referring to the user's past reaction data. Past reaction data includes, but is not limited to, text data, audio data, and image data. For example, the learning unit reflects humor patterns that the user laughed at in the past in the learning data. The learning unit can also exclude humor patterns that the user has not shown interest in in the past. For example, the learning unit evaluates the effectiveness of specific humor based on the user's past reaction data and reflects this in the learning. In this way, the accuracy of learning is improved by referring to the user's past reaction data. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the user's past reaction data into the generation AI and cause the generation AI to improve the accuracy of learning.

[0082] The learning unit can estimate the user's emotions and determine learning priorities based on the estimated user emotions. Emotions include, but are not limited to, joy, sadness, and anger. For example, if the user is relaxed, the learning unit can prioritize learning humor with a relaxed atmosphere. Furthermore, if the user is feeling stressed, the learning unit can prioritize learning humor that alleviates stress. For example, if the user is having fun, the learning unit can prioritize learning humor that is energetic and fun. This enables more effective learning by determining learning priorities based on the user's emotions. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the user's emotion data into the generation AI and have the generation AI determine the learning priorities.

[0083] The learning unit can compare humor for different age groups and learn the characteristics of each age group. Age groups include, but are not limited to, children, young people, and middle-aged and elderly people. For example, the learning unit can compare children's anime with adult sitcoms to learn the characteristics of humor for each age group. The learning unit can also compare social media videos for young people with television programs for older people to learn the differences in humor for each age group. For example, the learning unit can compare YouTube videos for teenagers with dramas for middle-aged people to learn the characteristics of humor for each age group. By comparing humor for different age groups, humor suitable for a wide range of age groups can be learned. Some or all of the above-described processing in the learning unit can be performed using or without the generation AI. For example, the learning unit can input humor data for different age groups into the generation AI and have the generation AI learn the characteristics.

[0084] The learning unit can collect the user's physiological responses and evaluate the effectiveness of humor. Physiological responses include, but are not limited to, heart rate and electrodermal activity. For example, the learning unit can collect changes in heart rate when the user laughs and evaluate the effectiveness of humor. The learning unit can also collect electrodermal responses when the user reacts to humor and evaluate the effectiveness of humor. For example, the learning unit collects the physiological responses of the user to humor and reflects them in learning. In this way, by collecting the user's physiological responses, the effectiveness of humor can be more accurately evaluated. Some or all of the above-mentioned processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input the user's physiological response data into the generation AI and have the generation AI evaluate the effectiveness of humor.

[0085] The learning unit can analyze the user's social media activity and learn trending humor. Social media activity includes, but is not limited to, the content of posts, comments, and the number of likes. The learning unit, for example, captures humorous videos frequently shared by the user as learning data. The learning unit can also learn humor that receives many likes and comments on the user's social media. For example, the learning unit captures humor that receives many responses from the user's followers as learning data. This allows humor based on the latest trends to be learned by analyzing the user's social media activity. Some or all of the above-described processing in the learning unit may be performed using or without the generation AI. For example, the learning unit can input social media activity data into the generation AI and cause the generation AI to learn trending humor.

[0086] The generation unit can estimate the user's emotions and adjust the way humor is expressed based on the estimated user's emotions. Emotions include, but are not limited to, joy, sadness, anger, etc. For example, the generation unit can express humor in a gentle tone when the user is relaxed. Furthermore, the generation unit can express humor in an energetic tone when the user is excited. For example, the generation unit can express humor in a gentle tone when the user is sad. This allows for more effective humor by adjusting the way humor is expressed based on the user's emotions. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the way humor is expressed.

[0087] The generation unit can apply different generation algorithms to different types of humor. Examples of generation algorithms include, but are not limited to, text generation algorithms and image generation algorithms. For example, the generation unit can apply a language generation algorithm to wordplay humor. The generation unit can also apply an action generation algorithm to physical gags. For example, the generation unit can apply a scenario generation algorithm to situation comedy. This improves the accuracy of generation by applying an appropriate generation algorithm to each type of humor. Some or all of the above-described processing in the generation unit can be performed using a generation AI, or can be performed without using a generation AI. For example, the generation unit can cause the generation AI to apply a different generation algorithm to each type of humor.

[0088] The generation unit can improve the accuracy of humor by referring to the user's past reaction data. Past reaction data includes, but is not limited to, text data, audio data, and image data. For example, the generation unit reflects patterns of humor that the user laughed at in the past in the generation. The generation unit can also exclude patterns of humor that the user has not shown interest in in the past. For example, the generation unit evaluates the effectiveness of specific humor based on the user's past reaction data and reflects this in the generation. In this way, the accuracy of the generation is improved by referring to the user's past reaction data. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's past reaction data into the generation AI and cause the generation AI to improve the accuracy of the humor.

[0089] The generation unit can customize humor according to the user's current situation. Examples of the current situation include, but are not limited to, the time of day, location, and user status. For example, if the user is at home, the generation unit generates humor that can be used at home. Also, if the user is at work, the generation unit can generate humor that can be used at work. For example, if the user is with friends, the generation unit generates humor that can be shared with friends. This allows for more appropriate humor to be provided by customizing humor according to the user's current situation. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit may input data about the user's current situation into the generation AI and cause the generation AI to customize the humor.

[0090] The generation unit can estimate the user's emotions and adjust the length of the humor based on the estimated user emotions. Emotions include, but are not limited to, joy, sadness, and anger. For example, the generation unit can generate longer humor when the user is relaxed. The generation unit can also generate shorter, more to-the-point humor when the user is in a hurry. For example, the generation unit can generate humor of an appropriate length when the user is having fun. This allows for more effective humor by adjusting the length of the humor based on the user's emotions. Some or all of the above-described processing in the generation unit can be performed using or without a generation AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the humor.

[0091] The generation unit can customize the humor content according to the user's cultural background. Cultural backgrounds include, but are not limited to, nationality, religion, and regional customs. For example, the generation unit can generate humor based on Japanese culture. The generation unit can also generate humor based on American culture. For example, the generation unit generates appropriate humor according to the user's cultural background. This allows the user to customize the humor content according to their cultural background, thereby providing more familiar humor. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's cultural background data into the generation AI and have the generation AI customize the humor content.

[0092] The generation unit can adjust the use of technical terms in the humor depending on the user's level of expertise. Examples of levels of expertise include, but are not limited to, beginner, intermediate, and expert. For example, if the user is an expert, the generation unit can generate humor that uses a lot of technical terms. Furthermore, if the user is a beginner, the generation unit can generate humor that avoids technical terms. For example, the generation unit generates humor that uses appropriate technical terms depending on the user's level of expertise. This allows for more appropriate humor to be provided by adjusting the use of technical terms in the humor depending on the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms in the humor.

[0093] The generation unit can improve the content of the humor by reflecting the user's past feedback. Past feedback includes, but is not limited to, user comments, ratings, and reaction data. For example, the generation unit reflects the user's past favorite humor patterns in the generation. The generation unit can also exclude humor patterns that the user has previously expressed dissatisfaction with. For example, the generation unit evaluates the effectiveness of specific humor based on the user's past feedback and reflects this in the generation. In this way, the humor content can be improved by reflecting the user's past feedback. Some or all of the above-described processing in the generation unit may be performed using a generation AI or may be performed without using a generation AI. For example, the generation unit can input the user's past feedback data into the generation AI and cause the generation AI to improve the content of the humor.

[0094] The revealing unit can estimate the user's emotions and adjust the timing of humor display based on the estimated user's emotions. Emotions include, but are not limited to, joy, sadness, anger, etc. For example, if the user is relaxed, the revealing unit can reveal humor at a timing that will relax the user. Also, if the user is nervous, the revealing unit can reveal humor at a timing that will relieve the user's tension. For example, if the user is having fun, the revealing unit can reveal humor at a timing that will amplify the user's enjoyment. In this way, by adjusting the timing of humor display based on the user's emotions, more effective humor can be provided. Some or all of the above-mentioned processing in the revealing unit may be performed using AI, or may be performed without using AI. For example, the revealing unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the timing of humor display.

[0095] The revealing unit can select the optimal revealing method by referring to the user's past reaction data. Past reaction data includes, but is not limited to, text data, audio data, and image data. For example, the revealing unit selects a humor revealing method that the user previously preferred. The revealing unit can also avoid humor revealing methods that the user previously disliked. For example, the revealing unit evaluates the effectiveness of a particular humor based on the user's past reaction data and selects the optimal revealing method. In this way, the optimal revealing method can be selected by referring to the user's past reaction data. Some or all of the above-described processing in the revealing unit may be performed using AI or without AI. For example, the revealing unit can input the user's past reaction data into the generation AI and have the generation AI select the optimal revealing method.

[0096] The revealing unit can customize humor according to the user's current situation. Examples of the current situation include, but are not limited to, the time of day, location, and user status. For example, if the user is at home, the revealing unit reveals humor that can be used at home. Also, if the user is at work, the revealing unit can reveal humor that can be used at work. For example, if the user is with friends, the revealing unit reveals humor that can be shared with friends. This allows for more appropriate humor to be provided by customizing humor according to the user's current situation. Some or all of the above-described processing in the revealing unit may be performed using AI, or may be performed without using AI. For example, the revealing unit can input the user's current situation data into the generation AI and cause the generation AI to customize the humor.

[0097] The presentation unit can analyze the user's feedback in real time and reflect it in the next humor presentation. Examples of feedback include, but are not limited to, real-time comments and changes in facial expressions. For example, if the user laughs, the presentation unit will present the same humor again next time. Furthermore, if the user does not respond, the presentation unit can present a different type of humor next time. For example, the presentation unit adjusts the content and timing of the humor based on the user's real-time feedback. This allows the user's feedback to be analyzed in real time and reflected in the next humor presentation. Some or all of the above-described processing in the presentation unit may be performed using AI, or may be performed without AI. For example, the presentation unit can input the user's feedback data into a generation AI and have the generation AI execute a process to reflect the data in the next humor presentation.

[0098] The presentation unit can estimate the user's emotions and adjust the way humor is presented based on the estimated user's emotions. Emotions include, but are not limited to, joy, sadness, anger, and the like. For example, if the user is relaxed, the presentation unit can present the humor in a gentle tone. Furthermore, if the user is nervous, the presentation unit can present the humor in a tone that alleviates tension. For example, if the user is having fun, the presentation unit can present the humor in an energetic tone. This allows for more effective humor by adjusting the way humor is presented based on the user's emotions. Some or all of the above-described processing in the presentation unit may be performed using AI, or may be performed without using AI. For example, the presentation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the way humor is presented.

[0099] The display unit can select the optimal display method based on the user's device information. Device information includes, but is not limited to, smartphones, tablets, and PCs. For example, if the user is using a smartphone, the display unit can provide a humor display method that matches the screen size. Furthermore, if the user is using a tablet, the display unit can also provide a humor display method that is optimized for a large screen. For example, if the user is using a smartwatch, the display unit can provide a simple and highly visible humor display method. This allows for more effective humor to be presented by selecting the optimal display method based on the user's device information. Some or all of the above-described processing in the display unit may be performed using AI, or may be performed without using AI. For example, the display unit can input the user's device information into the generation AI and have the generation AI select the optimal display method.

[0100] The presentation unit can make the humor multilingual based on the user's language settings. Language settings include, but are not limited to, the user's language and region settings. For example, the presentation unit automatically sets the language of the humor based on the language settings of the user's device. The presentation unit can also provide a language switching function when the user uses multiple languages. For example, if the user selects a specific language, the presentation unit presents the humor in that language. This makes it possible to accommodate a wider range of users by making the humor multilingual based on the user's language settings. Some or all of the above-described processing in the presentation unit may be performed using AI, or may be performed without AI. For example, the presentation unit can input the user's language setting data into the generation AI and cause the generation AI to perform multilingual support for the humor.

[0101] The presentation unit can customize the humor presentation method by reflecting the user's past feedback. Past feedback includes, but is not limited to, user comments, ratings, and reaction data. For example, the presentation unit selects a humor presentation method that the user has previously preferred. The presentation unit can also avoid humor presentation methods that the user has previously expressed dissatisfaction with. For example, the presentation unit evaluates the effectiveness of specific humor based on the user's past feedback and selects the optimal presentation method. This allows the humor presentation method to be customized by reflecting the user's past feedback. Some or all of the above-described processing in the presentation unit may be performed using AI or without AI. For example, the presentation unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the humor presentation method.

[0102] The analysis unit can estimate the user's emotions and determine analysis priorities based on the estimated user emotions. Emotions include, but are not limited to, joy, sadness, and anger. For example, if the user is relaxed, the analysis unit can prioritize analyzing reactions that reflect the relaxed state. Furthermore, if the user is tense, the analysis unit can prioritize analyzing reactions that alleviate tension. For example, if the user is having fun, the analysis unit can prioritize analyzing reactions that amplify the user's enjoyment. This enables more effective analysis by determining analysis priorities based on the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input the user's emotion data into a generation AI and have the generation AI determine the analysis priorities.

[0103] The analysis unit can analyze the user's facial expressions and tone of voice in real time to evaluate the effectiveness of humor. Facial expressions include, but are not limited to, smiles, surprise, sadness, etc. The analysis unit can, for example, analyze the user's facial expressions when laughing in real time to evaluate the effectiveness of humor. The analysis unit can also analyze the user's tone of voice when reacting to humor in real time to evaluate the effectiveness of humor. For example, the analysis unit can evaluate the effectiveness of humor based on the user's real-time facial expressions and tone of voice. This allows for more accurate evaluation of the effectiveness of humor by analyzing the user's facial expressions and tone of voice in real time. Some or all of the above-described processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input the user's facial expression data into a generation AI and have the generation AI evaluate the effectiveness of humor.

[0104] The analysis unit can collect the user's physiological responses and evaluate the effectiveness of the humor. Physiological responses include, but are not limited to, heart rate and electrodermal activity. For example, the analysis unit can collect changes in the user's heart rate when the user laughs and evaluate the effectiveness of the humor. The analysis unit can also collect electrodermal responses when the user reacts to the humor and evaluate the effectiveness of the humor. For example, the analysis unit collects the user's physiological responses to the humor and reflects this in the analysis. By collecting the user's physiological responses, the effectiveness of the humor can be more accurately evaluated. Some or all of the above-described processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input the user's physiological response data into the generation AI and have the generation AI evaluate the effectiveness of the humor.

[0105] The analysis unit can improve the accuracy of the analysis by referring to the user's past reaction data. Past reaction data includes, but is not limited to, text data, audio data, and image data. For example, the analysis unit reflects in the analysis patterns of humor that the user laughed at in the past. The analysis unit can also exclude humor patterns that the user has not shown interest in in the past. For example, the analysis unit evaluates the effectiveness of specific humor based on the user's past reaction data and reflects this in the analysis. In this way, the accuracy of the analysis is improved by referring to the user's past reaction data. Some or all of the above-described processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input the user's past reaction data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0106] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated user's emotions. Emotions include, but are not limited to, joy, sadness, and anger. For example, if the user is relaxed, the analysis unit can adjust the method for analyzing reactions in a relaxed state. Furthermore, if the user is tense, the analysis unit can also adjust the method for analyzing reactions to relieve tension. For example, if the user is having fun, the analysis unit can adjust the method for analyzing reactions to amplify the enjoyment. This allows for more effective analysis by adjusting the analysis method based on the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the analysis method.

[0107] The analysis unit can analyze the user's social media activity to understand humor trends. Social media activity includes, but is not limited to, the content of posts, comments, and the number of likes. For example, the analysis unit can capture humorous videos frequently shared by the user as analysis data. The analysis unit can also analyze humor that receives many likes and comments on the user's social media. For example, the analysis unit can capture humor that receives many responses from the user's followers as analysis data. By analyzing the user's social media activity, humor based on the latest trends can be provided. Some or all of the above-described processing by the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input social media activity data into a generation AI and cause the generation AI to understand humor trends.

[0108] The analysis unit can evaluate the effectiveness of humor by taking into account the user's cultural background. Cultural background includes, but is not limited to, nationality, religion, and regional customs. For example, the analysis unit can evaluate the effectiveness of humor based on Japanese culture. The analysis unit can also evaluate the effectiveness of humor based on American culture. For example, the analysis unit evaluates the appropriate effectiveness of humor depending on the user's cultural background. This allows for a more appropriate evaluation of the effectiveness of humor by taking the user's cultural background into consideration. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without using AI. For example, the analysis unit can input the user's cultural background data into the generation AI and cause the generation AI to evaluate the effectiveness of humor.

[0109] The analysis unit can customize the analysis method by reflecting the user's past feedback. Past feedback includes, but is not limited to, user comments, ratings, and reaction data. For example, the analysis unit reflects the user's past favorite humor patterns in the analysis. The analysis unit can also exclude humor patterns that the user has previously expressed dissatisfaction with. For example, the analysis unit evaluates the effectiveness of specific humor based on the user's past feedback and reflects this in the analysis. In this way, the analysis method can be customized by reflecting the user's past feedback. Some or all of the above-described processing in the analysis unit may be performed using AI or without AI. For example, the analysis unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the analysis method. === Hard Collateral 1-1 === Each of the multiple elements including the learning unit, generation unit, presentation unit, and analysis unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the presentation unit is realized by the output device 40 of the smart device 14. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned learning unit, generation unit, presentation unit, and analysis unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the presentation unit is realized by the speaker 240 of the smart glasses 214. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the learning unit, generation unit, presentation unit, and analysis unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the presentation unit is realized by the speaker 240 of the headset type terminal 314. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned learning unit, generation unit, presentation unit, and analysis unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the specific processing unit 290 of the data processing device 12. For example, the generation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the presentation unit is realized by the speaker 240 of the robot 414. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The interactive agent system may further include a health monitoring unit that monitors the user's health condition. The health monitoring unit collects physiological data such as the user's heart rate, blood pressure, and body temperature, and monitors the user's health condition in real time. For example, if the user is feeling stressed, the health monitoring unit can instruct the generation unit to generate humor to help the user relax. Also, if the user is tired, the health monitoring unit can lighten the user's mood by providing a light joke. This allows for more effective dialogue by providing humor that is appropriate for the user's health condition.

[0112] The interactive agent system may further include an hobby learning unit that learns the user's hobbies and interests. The hobby learning unit analyzes the user's past interaction history and social media activity to identify the user's hobbies and interests. For example, if the user is interested in sports, the hobby learning unit may provide the generation unit with sports-related humor. Also, if the user is a movie fan, the hobby learning unit may generate movie-related jokes. This allows for more friendly interaction by providing humor that matches the user's hobbies and interests.

[0113] The interactive agent system can further include a learning management unit that manages the user's learning progress. The learning management unit keeps track of the content and progress of the user's learning, and provides humorous advice at appropriate times. For example, if the user is working on a math problem, the learning management unit can provide the generation unit with math-related jokes. Also, if the user is learning a language, the learning management unit can provide humor related to the learning content. This can increase motivation to study.

[0114] The interactive agent system may further include an emotion selection unit that estimates the user's emotion and selects a type of humor based on the estimated emotion. The emotion selection unit analyzes the user's facial expression and tone of voice to estimate the user's emotion. For example, if the user is sad, the emotion selection unit can instruct the generation unit to provide gentle-toned humor. Alternatively, if the user is excited, the emotion selection unit can provide energetic humor. This allows for more effective dialogue by providing humor that matches the user's emotion.

[0115] The interactive agent system may further include a history reference unit that references the user's past interaction history to customize the humor content. The history reference unit analyzes what kind of humor the user responded to in the past and reflects that in the next interaction. For example, the history reference unit may provide the generator with patterns of jokes that the user laughed at in the past. It may also be able to exclude patterns of humor that the user did not show interest in in the past. This allows for more effective interaction by customizing the humor based on the user's past reactions.

[0116] The interactive agent system may further include a timing adjustment unit that estimates the user's emotions and adjusts the timing of humor based on the estimated emotions. The timing adjustment unit analyzes the user's facial expressions and tone of voice to determine the optimal timing for humor. For example, if the user is relaxed, the timing adjustment unit can show humor at a time when the user is relaxed. Also, if the user is nervous, the timing adjustment unit can show humor at a time that will relieve the user's tension. This allows for more effective dialogue by adjusting the timing of humor based on the user's emotions.

[0117] The interactive agent system can further include a device adaptation unit that customizes the way humor is presented based on the user's device information. The device adaptation unit selects the optimal way to present humor depending on the type and screen size of the device used by the user. For example, if the user is using a smartphone, the device adaptation unit can provide humor tailored to the screen size. Also, if the user is using a tablet, the device adaptation unit can provide humor optimized for a larger screen. This allows for more effective dialogue by customizing the way humor is presented based on the user's device information.

[0118] The interactive agent system may further include a content customization unit that estimates the user's emotions and customizes the humor content based on the estimated emotions. The content customization unit analyzes the user's facial expressions and tone of voice to select humor content that corresponds to the user's emotions. For example, the content customization unit may provide cheerful and fun humor if the user is happy, or may provide humor with a gentle tone if the user is sad. This allows for more effective dialogue by customizing the humor content based on the user's emotions.

[0119] The interactive agent system can further include a trend learning unit that analyzes the user's social media activity and learns trending humor. The trend learning unit analyzes the user's social media posts, comments, number of likes, and other information to grasp the latest humor trends. For example, the trend learning unit can incorporate humorous videos frequently shared by the user as learning data. It can also learn humor that is most popular among the user's followers. This makes it possible to provide humor based on the latest trends by analyzing the user's social media activity.

[0120] The interactive agent system may further include a length adjustment unit that estimates the user's emotions and adjusts the length of the humor based on the estimated emotions. The length adjustment unit analyzes the user's facial expressions and tone of voice to determine the optimal length of the humor. For example, the length adjustment unit may provide longer humor if the user is relaxed, or provide shorter, more to-the-point humor if the user is in a hurry. This allows for more effective dialogue by adjusting the length of the humor based on the user's emotions.

[0121] The processing flow of the second embodiment will be briefly explained below.

[0122] Step 1: The learning unit learns humor. For example, it learns humor from stand-up comedy videos and other entertainment formats, and then uses generative AI to analyze this data and extract humorous elements. Specifically, it analyzes stand-up comedy videos and extracts humorous elements such as gestures and pauses in conversation. Step 2: The generation unit generates humor based on the humor learned by the learning unit. For example, it generates appropriate humor based on the user's comments and the situation, and uses a generation AI to generate humor that matches the user's comments and the situation. Specifically, it analyzes the user's comments and generates humor that matches their content. Step 3: The display unit displays the humor generated by the generator. For example, the display unit displays humor based on the user's reaction, and uses AI to display humor based on the user's reaction. Specifically, the display unit analyzes the user's facial expressions and tone of voice and adjusts the timing of the humor. Step 4: The analysis unit analyzes the user's reactions. For example, it analyzes the user's facial expressions and tone of voice to evaluate the effectiveness of the humor. AI is used to analyze the user's reactions in real time, specifically, to analyze changes in the user's facial expressions to evaluate the effectiveness of the humor.

[0123] 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.

[0124] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] 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.

[0126] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0127] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0137] 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.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] 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.

[0142] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0143] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0144] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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 identification processing unit 290 using these models.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0160] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0171] 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.

[0172] 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.

[0173] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0174] 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.

[0175] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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).

[0180] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] [Explanation of symbols]

[0195] 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 learning department that learns humor, a generation unit that generates humor based on the humor learned by the learning unit; a display unit that displays the humor generated by the generation unit; an analysis unit that analyzes a user's reaction; Equipped with A system characterized by:

2. The learning unit Learn humor from stand-up comedy videos or other forms of entertainment 2. The system of claim 1.

3. The generation unit Generate humor based on user comments or situations 2. The system of claim 1.

4. The presentation section is Use humor based on user reactions 2. The system of claim 1.

5. The analysis unit It can analyze the user's facial expressions and tone of voice to adjust the timing of humor.

2. The system of claim 1.

6. The generation unit Generate light-hearted humor or deep wit 2. The system of claim 1.

7. The generation unit Providing humor that is culturally appropriate for users 2. The system of claim 1.

8. The learning unit Learn gestures and facial expressions 2. The system of claim 1.

9. The learning unit Estimate the user's emotions and select training data based on the estimated user emotions.

2. The system of claim 1.

10. The learning unit Compare humor from different cultures and identify commonalities and differences 2. The system of claim 1.

Images