system

Abstract

The system according to the embodiment aims to generate a character that is familiar to the user and provide conversation tailored to the individual. [Solution] A system according to an embodiment includes a setting unit, a generation unit, a conversation unit, an analysis unit, and a contact unit. The setting unit sets personal conditions for a user. The generation unit generates a character based on the conditions set by the setting unit. The conversation unit allows the character generated by the generation unit to have a conversation. The analysis unit analyzes the content of the conversation held by the conversation unit. The contact unit makes a contact when there is a high possibility that a problem detected by the analysis unit will occur.

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 not adequately generated characters that are user-friendly and provide personalized conversations, and there is room for improvement.

[0005] The system according to the embodiment aims to generate a character that is familiar to the user and provide conversation tailored to the individual. [Means for solving the problem]

[0006] The system according to the embodiment includes a setting unit, a generation unit, a conversation unit, an analysis unit, and a contact unit. The setting unit sets personal conditions for a user. The generation unit generates a character based on the conditions set by the setting unit. The conversation unit allows the character generated by the generation unit to have a conversation. The analysis unit analyzes the content of the conversation held by the conversation unit. The contact unit makes a contact when there is a high possibility that a problem detected by the analysis unit will occur. [Effects of the Invention]

[0007] The system according to the embodiment can generate a character that is friendly to the user and provide conversation tailored to the individual. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A conversation partner system according to an embodiment of the present invention generates a character based on a user's personal conditions, engages in conversation, and contacts the user if a problem is likely to arise. In the conversation partner system, the user sets personal conditions, such as their age, gender, occupation, hobbies, place of residence, likes, and dislikes, and a generation AI generates a friendly character for the user based on these conditions, which then becomes the user's conversation partner. The generation AI generates conversation content taking into account the user's set conditions to provide a conversation that is enjoyable for the user. Furthermore, the conversation content is analyzed by the AI, and if a problem is likely to arise, family members, government agencies, and the like are notified in advance. For example, in a conversation partner system, the user sets their own personal conditions, such as age, gender, occupation, hobbies, place of residence, likes, and dislikes. This information is input into the generation AI. The generation AI then analyzes the input information and generates a character that is friendly to the user. For example, if the user is a young woman, a female character of the same age is generated. This character generates conversation content taking into account the user's set conditions to provide a conversation that is enjoyable for the user. The generated character then begins a conversation with the user. For example, the conversation progresses on topics that interest the user, such as hobbies or favorite things. This allows the user to have a fun time. Furthermore, the conversation partner system uses AI to analyze the content of the conversation. For example, if the user is feeling stressed or a problem is about to occur, the AI ​​will detect this and contact family members or government agencies in advance. This ensures the user's safety. This allows the user to use the service with peace of mind. The conversation partner system generates a character based on the user's private conditions, engages in conversation, and contacts the user if a problem is about to occur, allowing the user to use the service with peace of mind. For example, even if an elderly person spends a lot of time alone, using this service can provide them with someone to talk to and reduce their sense of loneliness. Furthermore, the user's privacy is protected, and appropriate measures are taken when necessary, allowing the system to be used with peace of mind.

[0029] A conversation partner system according to an embodiment includes a setting unit, a generation unit, a conversation unit, an analysis unit, and a communication unit. The setting unit sets personal conditions of a user. The personal conditions include, for example, age, gender, occupation, hobbies, place of residence, likes, dislikes, etc., but are not limited to these examples. The setting unit, for example, stores information input by the user in a database and provides the information to the generation unit. The generation unit generates a character based on the conditions set by the setting unit using a generation AI. The generation AI generates the character's appearance and personality using, for example, a text generation AI (e.g., LLM). The generation unit can also generate the character's movements and voice using a multimodal generation AI. The generation AI generates a friendly character based on the user's conditions. The conversation unit causes the generated character to converse with the user. The conversation may be, for example, audio or text, but is not limited to these examples. The conversation unit uses the generation AI to generate conversation content that the user will find enjoyable. For example, the conversation unit provides topics related to the user's hobbies and favorite things. The conversation unit can also estimate the user's emotions and adjust the way the conversation progresses. The analysis unit analyzes the content of the conversation conducted by the conversation unit. The analysis is performed using, for example, natural language processing technology or emotion analysis technology. The analysis unit analyzes the content of the conversation and detects when a problem is likely to occur. For example, the analysis unit detects a problem based on the frequency of appearance of specific keywords or changes in emotions. The contact unit makes contact when a problem detected by the analysis unit is likely to occur. The contact is made, for example, by telephone or email, but is not limited to such examples. The contact unit contacts family members, government agencies, etc. to ensure the user's safety. As a result, the conversation partner system according to the embodiment generates a character based on the user's private conditions, conducts a conversation, and contacts the user when a problem is likely to occur, allowing the user to use the service with peace of mind.

[0030] The generation unit can generate characters based on conditions including the user's age, gender, occupation, hobbies, place of residence, likes, and dislikes. For example, the generation unit generates characters of the same age based on the user's age. The generation unit can also generate characters of the same gender based on the user's gender. The generation unit can also generate characters of a related occupation based on the user's occupation. For example, if the user is a doctor, the generation unit generates characters related to the medical field. The generation unit can also generate characters with related hobbies based on the user's hobbies. For example, if the user likes music, the generation unit generates characters that are knowledgeable about music. The generation unit can also generate characters that live in the same area based on the user's place of residence. For example, if the user lives in an urban area, the generation unit generates characters that live in the urban area. The generation unit can also generate related characters based on the user's likes and dislikes. For example, if the user likes dogs, the generation unit generates a character that owns a dog. This makes it possible to provide more friendly characters by generating characters based on the user's detailed conditions.

[0031] The conversation unit allows the generated character to have a conversation with the user. For example, the conversation unit allows the generated character to have a conversation with the user using audio. The conversation unit can also have a conversation with the user using text. The conversation unit can also provide topics related to the user's hobbies. For example, if the user likes movies, the conversation unit can provide topics about the latest movies. The conversation unit can also provide topics about the user's favorite things. For example, if the user likes coffee, the conversation unit can provide topics about types of coffee and how to brew it. The conversation unit can also estimate the user's emotions and adjust the way the conversation proceeds. For example, if the user is relaxed, the conversation unit can proceed the conversation at a leisurely pace. If the user is excited, the conversation unit can proceed the conversation at a lively pace. If the user is sad, the conversation unit can proceed the conversation in a gentle tone. This allows the generated character to have a conversation with the user, allowing the user to have a fun time.

[0032] The analysis unit can analyze the content of the conversation and detect when a problem is likely to occur. The analysis unit, for example, analyzes the content of the conversation using natural language processing technology. For example, the analysis unit determines that a problem is likely to occur if a specific keyword appears frequently in the conversation. The analysis unit can also analyze changes in the user's emotions using emotion analysis technology. For example, the analysis unit determines that a problem is likely to occur if the user is feeling stressed. The analysis unit can also analyze the flow and context of the conversation to detect when a problem is likely to occur. For example, the analysis unit determines that a problem is likely to occur if an inconsistency occurs in the conversation. The analysis unit can also analyze the user's past conversation history to detect when a problem is likely to occur. For example, the analysis unit learns patterns of conversations that have caused problems in the past and detects a problem when a similar pattern appears again. In this way, by analyzing the content of the conversation, it is possible to detect when a problem is likely to occur in advance.

[0033] The communication unit can contact family members or government agencies when there is a high possibility that the detected problem will occur. For example, the communication unit can contact family members or government agencies via telephone. The communication unit can also contact them via email. The communication unit can also contact them using a notification system. For example, the communication unit can send a notification to family members through a smartphone app. The communication unit can also obtain the user's location information and contact the nearest government agency. For example, if the user is in a specific area, the communication unit can contact the local government agency. The communication unit can also analyze the user's past communication history and select the optimal communication method. For example, the communication unit can contact the user based on the communication method the user preferred in the past. The communication unit can also estimate the user's emotions and adjust the communication method. For example, if the user is relaxed, the communication unit can select a gentle communication method. If the user is in a hurry, the communication unit can select a quick communication method. This ensures the user's safety by contacting the user in advance when a problem is likely to occur.

[0034] The setting unit can analyze the user's past setting history and suggest the optimal setting method. For example, the setting unit automatically displays as candidates conditions that the user has frequently set in the past. The setting unit can also preferentially suggest setting methods (voice, text, etc.) that the user has used in the past. The setting unit can also predict and suggest settings to be used in a specific time period based on the user's past setting history. For example, if the user has previously made settings at night, the setting unit can suggest setting options that are suitable for nighttime. The setting unit can also analyze the user's past setting history and understand the user's preferences and tendencies. In this way, the setting unit can suggest the optimal setting method to the user by analyzing the past setting history.

[0035] The setting unit can perform filtering based on the user's current living situation and areas of interest during setup. For example, when the user inputs their current living situation, the setting unit prioritizes displaying related setting options. The setting unit can also filter and display related setting options based on the user's areas of interest. The setting unit can also suggest an optimal setting method taking into account the user's current living situation and areas of interest. For example, when the user inputs "busy" as their current living situation, the setting unit prioritizes displaying concise setting options. When the user selects "sports" as their area of ​​interest, the setting unit filters and displays sports-related setting options. This enables more appropriate setup by filtering based on the user's current living situation and areas of interest.

[0036] The setting unit can select the optimal setting means depending on the user's input method during setting. For example, if the user selects voice input, the setting unit performs setting using voice recognition technology. Furthermore, if the user selects text input, the setting unit can also perform setting using text analysis technology. Furthermore, if the user selects image input, the setting unit can also perform setting using image recognition technology. For example, if the user inputs an image using a smartphone camera, the setting unit analyzes the image and displays related setting options. Furthermore, the setting unit has an algorithm for selecting the optimal setting means depending on the user's input method. This facilitates setting by selecting the optimal setting means depending on the user's input method.

[0037] During setup, the setting unit can prioritize highly relevant conditions by taking into account the user's geographical location information. For example, if the user is in a specific area, the setting unit prioritizes setting conditions related to that area. The setting unit can also display related setting options based on the user's current location. The setting unit can also suggest an optimal setting method by taking into account the user's geographical location information. For example, if the user is in an urban area, the setting unit can prioritize displaying setting options related to urban areas. Also, if the user is in a rural area, the setting unit can prioritize displaying setting options related to rural areas. This enables more appropriate setup by prioritizing highly relevant conditions by taking into account the user's geographical location information.

[0038] During the setting process, the setting unit can analyze the user's social media activity and set related conditions. For example, the setting unit can set related conditions based on information shared by the user on social media. The setting unit can also analyze the user's social media activity and suggest related setting options. The setting unit can also set related conditions based on the activity of the user's friends on social media. For example, if the user frequently posts about "travel" on social media, the setting unit can suggest travel-related setting options. The setting unit can also analyze the number of "likes" and "comments" on the user's social media and set related conditions. In this way, related conditions can be set by analyzing the user's social media activity.

[0039] The setting unit can customize the setting method by reflecting the user's past feedback during setting. The setting unit customizes the setting method based on, for example, feedback provided by the user in the past. The setting unit can also analyze the user's past feedback and suggest an optimal setting method. The setting unit can also improve the setting interface by reflecting the user's feedback. For example, if the user has previously given feedback that "settings are difficult," the setting unit can provide a simple interface. If the user has given feedback that "I would like more detailed settings," the setting unit can also provide more detailed setting options. In this way, the setting method can be customized by reflecting the user's past feedback.

[0040] The generation unit can adjust the level of detail of the character based on important conditions of the user when generating the character. For example, if the user desires a detailed character, the generation unit can generate a character that is depicted in great detail. Also, if the user desires a simple character, the generation unit can generate a character with a simple design. Also, the generation unit can generate a character with an optimal level of detail based on conditions set by the user. For example, if the user desires a "realistic appearance," the generation unit can generate a character with a realistic appearance. Also, if the user desires an "anime-style appearance," the generation unit can generate a character with an anime-style appearance. In this way, by adjusting the level of detail of the character based on important conditions of the user, a more appropriate character can be provided.

[0041] The generation unit can apply different generation algorithms depending on the user category when generating a character. For example, if the user is a child, the generation unit can apply a character generation algorithm for children. Also, if the user is elderly, the generation unit can apply a character generation algorithm for elderly people. Also, the generation unit can apply an optimal character generation algorithm depending on the user's occupation or hobby. For example, if the user is a doctor, the generation unit can apply a medical-related character generation algorithm. Also, if the user is a musician, the generation unit can apply a character generation algorithm related to music. In this way, by applying different generation algorithms depending on the user category, a more appropriate character can be provided.

[0042] When generating a character, the generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit generates an optimal character based on characters generated by the user in the past. The generation unit can also analyze the user's past generation results and improve the generation algorithm. The generation unit can also improve the accuracy of generation by reflecting user feedback. For example, if the user previously provided feedback such as "I like this character," the generation unit generates a similar character. Also, if the user provided feedback such as "I don't like this character," the generation unit can improve the generation algorithm based on that feedback. In this way, the accuracy of generation can be improved by referring to the user's past generation results.

[0043] When generating a character, the generation unit can determine a generation priority based on the time of submission by the user. For example, if the user is in a hurry, the generation unit can quickly generate a character. Also, if the user has time, the generation unit can generate a detailed character. Also, the generation unit can determine an optimal generation schedule based on the time of submission by the user. For example, if the user requests "I want a character right away," the generation unit can quickly generate a character. Also, if the user requests "I want a detailed character that will take time," the generation unit can generate a detailed character. In this way, by determining a generation priority based on the time of submission by the user, it is possible to provide a more appropriate character.

[0044] When generating characters, the generation unit can adjust the order of generation based on the user's relevance. For example, if the user preferentially desires a specific character, the generation unit generates that character first. The generation unit can also adjust the order of generation based on the user's relevance. The generation unit can also determine the optimal order of generation based on conditions set by the user. For example, if the user desires that "a specific character be generated first," the generation unit generates that character preferentially. The generation unit can also adjust the order of generation based on the user's relevance. In this way, by adjusting the order of generation based on the user's relevance, it is possible to provide a more appropriate character.

[0045] When generating a character, the generation unit can adjust the character's use of technical terminology according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates a character that uses a lot of technical terminology. Furthermore, if the user is a beginner, the generation unit can generate a character that avoids technical terminology. Furthermore, the generation unit can adjust the use of optimal technical terminology according to the user's level of expertise. For example, if the user sets "desiring technical conversation," the generation unit generates a character that uses a lot of technical terminology. Furthermore, if the user sets "desiring conversation for beginners," the generation unit can generate a character that avoids technical terminology. In this way, by adjusting the character's use of technical terminology according to the user's level of expertise, a more appropriate character can be provided.

[0046] The conversation unit can adjust the level of detail of the conversation based on important topics for the user during the conversation. For example, the conversation unit provides detailed information about topics in which the user is interested. The conversation unit can also provide a brief explanation about topics in which the user is not interested. The conversation unit can also adjust the optimal level of detail of the conversation based on important topics for the user. For example, if the user requests "detailed information," the conversation unit provides detailed information. If the user requests "concise information," the conversation unit can also provide a brief explanation. In this way, by adjusting the level of detail of the conversation based on important topics for the user, a more appropriate conversation can be provided.

[0047] The conversation unit can apply different conversation algorithms depending on the user category during conversation. For example, if the user is a child, the conversation unit can apply a conversation algorithm for children. Furthermore, if the user is elderly, the conversation unit can also apply a conversation algorithm for elderly people. Furthermore, the conversation unit can apply the most appropriate conversation algorithm depending on the user's occupation or hobby. For example, if the user is a doctor, the conversation unit can apply a medical-related conversation algorithm. Furthermore, if the user is a musician, the conversation unit can also apply a music-related conversation algorithm. In this way, by applying different conversation algorithms depending on the user category, more appropriate conversation can be provided.

[0048] The conversation unit can improve the accuracy of a conversation by referring to the user's past conversation results during the conversation. The conversation unit, for example, provides an optimal conversation based on the user's past conversations. The conversation unit can also analyze the user's past conversation results and improve the conversation algorithm. The conversation unit can also improve the accuracy of a conversation by reflecting user feedback. For example, if the user has previously given feedback that "this conversation was good," the conversation unit can provide a similar conversation. Also, if the user has given feedback that "this conversation was not to my liking," the conversation unit can improve the conversation algorithm based on that feedback. In this way, the accuracy of a conversation can be improved by referring to the user's past conversation results.

[0049] The conversation unit can determine the priority of a conversation based on the time of submission by the user during the conversation. For example, if the user is in a hurry, the conversation unit can start the conversation quickly. Also, if the user has time, the conversation unit can provide a detailed conversation. Also, the conversation unit can determine an optimal conversation schedule based on the time of submission by the user. For example, if the user desires to "start the conversation immediately," the conversation unit can start the conversation quickly. Also, if the user desires to "take time to have a detailed conversation," the conversation unit can provide a detailed conversation. In this way, by determining the priority of a conversation based on the time of submission by the user, more appropriate conversations can be provided.

[0050] The conversation unit can adjust the order of conversations based on the user's relevance during a conversation. For example, if the user preferentially desires to discuss a specific topic, the conversation unit will discuss that topic first. The conversation unit can also adjust the order of conversations based on the user's relevance. The conversation unit can also determine the optimal conversation order based on conditions set by the user. For example, if the user desires to "discuss a specific topic first," the conversation unit will discuss that topic first. The conversation unit can also adjust the order of conversations based on the user's relevance. In this way, by adjusting the order of conversations based on the user's relevance, a more appropriate conversation can be provided.

[0051] The conversation unit can adjust the use of technical terms in the conversation during the conversation according to the user's level of expertise. For example, if the user has technical expertise, the conversation unit can provide a conversation that uses a lot of technical terms. Furthermore, if the user is a beginner, the conversation unit can provide a conversation that avoids technical terms. Furthermore, the conversation unit can adjust the use of optimal technical terms according to the user's level of expertise. For example, if the user sets "I want a technical conversation," the conversation unit can provide a conversation that uses a lot of technical terms. Furthermore, if the user sets "I want a conversation for beginners," the conversation unit can provide a conversation that avoids technical terms. In this way, by adjusting the use of technical terms in the conversation according to the user's level of expertise, it is possible to provide a more appropriate conversation.

[0052] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships between conversations during analysis. The analysis unit can, for example, perform a more accurate analysis by taking into account the context of the conversation. The analysis unit can also analyze the interrelationships between conversations and extract related information. The analysis unit can also apply an optimal analysis method by taking into account the flow of the conversation. For example, the analysis unit can understand the context based on the context of the conversation and perform a more accurate analysis. The analysis unit can also analyze the interrelationships between conversations and extract related information. In this way, the accuracy of the analysis can be improved by taking into account the interrelationships between conversations.

[0053] The analysis unit can perform analysis taking into account user attribute information. The analysis unit performs appropriate analysis taking into account, for example, the user's age and gender. The analysis unit can also analyze related information taking into account the user's occupation and hobbies. The analysis unit can also apply the optimal analysis method taking into account the user's place of residence and living situation. For example, the analysis unit analyzes related information based on the user's age and gender. The analysis unit can also analyze related information taking into account the user's occupation and hobbies. This enables more appropriate analysis by taking into account the user's attribute information.

[0054] During analysis, the analysis unit can weight the analysis based on the frequency of conversation. For example, the analysis unit performs analysis by placing emphasis on frequently occurring conversations. The analysis unit can also extract important information based on the frequency of conversations. The analysis unit can also apply an optimal analysis method taking into account the frequency of conversations. For example, the analysis unit performs analysis by placing emphasis on frequently occurring conversations. The analysis unit can also extract important information based on the frequency of conversations. In this way, by weighting the analysis based on the frequency of conversations, more important information can be extracted.

[0055] The analysis unit can perform the analysis while taking into account the geographical distribution of the conversation. For example, the analysis unit analyzes related information while taking into account the location where the conversation occurred. The analysis unit can also analyze the conversation trend based on the geographical distribution. The analysis unit can also apply an optimal analysis method while taking into account the geographical distribution of the conversation. For example, the analysis unit analyzes related information based on the location where the conversation occurred. The analysis unit can also analyze the conversation trend based on the geographical distribution. This enables more appropriate analysis by taking into account the geographical distribution of the conversation.

[0056] During analysis, the analysis unit can improve the accuracy of the analysis by referring to literature related to the conversation. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the content of the conversation. The analysis unit can also analyze background information of the conversation based on the related literature. The analysis unit can also apply an optimal analysis method by referring to literature related to the conversation. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the content of the conversation. The analysis unit can also analyze background information of the conversation based on the related literature. In this way, by referring to literature related to the conversation, the accuracy of the analysis can be improved.

[0057] The analysis unit can perform the analysis while taking into account the market value of the conversation. For example, the analysis unit evaluates the market value of the conversation content and extracts important information. The analysis unit can also analyze the conversation trend based on the market value. The analysis unit can also apply an optimal analysis method while taking into account the market value of the conversation. For example, the analysis unit evaluates the market value of the conversation content and extracts important information. The analysis unit can also analyze the conversation trend based on the market value. In this way, by taking into account the market value of the conversation, more important information can be extracted.

[0058] When contacting a user, the contact unit can analyze the user's past contact history and select the optimal contact method. For example, the contact unit selects the optimal contact method based on contact methods used by the user in the past. The contact unit can also analyze the user's past contact history and suggest the optimal contact method. The contact unit can also improve the contact method by reflecting user feedback. For example, if the user has previously given feedback that "this contact method was good," the contact unit selects a similar contact method. Also, if the user has given feedback that "this contact method is not my preference," the contact unit can improve the contact method based on that feedback. In this way, the optimal contact method can be selected by analyzing the user's past contact history.

[0059] The contact unit can customize the contact method based on the user's current living situation when making contact. For example, if the user is busy, the contact unit selects a simple contact method. Also, if the user is relaxed, the contact unit can select a detailed contact method. Also, the contact unit can suggest the optimal contact method taking the user's current living situation into consideration. For example, if the user sets "busy," the contact unit selects a simple contact method. Also, if the user sets "relaxed," the contact unit can select a detailed contact method. In this way, customizing the contact method based on the user's current living situation enables more appropriate contact.

[0060] The contact unit can improve the contact method by reflecting the user's feedback when making a contact. For example, the contact unit improves the contact method based on feedback provided by the user in the past. The contact unit can also analyze the user's feedback and suggest the optimal contact method. The contact unit can also improve the contact interface by reflecting the user's feedback. For example, if the user has previously given feedback that the contact is slow, the contact unit can select a quick contact method. If the user has given feedback that the contact is too frequent, the contact unit can also adjust the frequency of contact. In this way, the contact method can be improved by reflecting the user's feedback.

[0061] When making contact, the contact unit can select the optimal contact method by taking into account the user's geographical location information. For example, if the user is in a specific area, the contact unit selects a contact method related to that area. The contact unit can also suggest the optimal contact method based on the user's current location. The contact unit can also select the optimal contact method by taking into account the user's geographical location information. For example, if the user is in an urban area, the contact unit selects a contact method related to urban areas. Also, if the user is in a rural area, the contact unit can select a contact method related to rural areas. In this way, the optimal contact method can be selected by taking into account the user's geographical location information.

[0062] When contacting the user, the contact unit can analyze the user's social media activity and suggest a means of contact. For example, the contact unit can suggest the most appropriate means of contact based on information shared by the user on social media. The contact unit can also analyze the user's social media activity and suggest related means of contact. The contact unit can also suggest the most appropriate means of contact based on the activity of the user's friends on social media. For example, if the user frequently posts about "travel" on social media, the contact unit can suggest travel-related means of contact. The contact unit can also analyze the number of "likes" and "comments" on the user's social media and suggest related means of contact. In this way, the most appropriate means of contact can be suggested by analyzing the user's social media activity.

[0063] The contact unit can customize the contact method by reflecting the user's past feedback when contacting the user. For example, the contact unit customizes the contact method based on feedback provided by the user in the past. The contact unit can also analyze the user's past feedback and suggest the optimal contact method. The contact unit can also improve the contact interface by reflecting the user's feedback. For example, if the user has previously given feedback that the contact is slow, the contact unit can select a quick contact method. If the user has given feedback that the contact is too frequent, the contact unit can also adjust the frequency of contact. In this way, the contact method can be customized by reflecting the user's past feedback.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] The generation unit can acquire real-time activity data of the user and adjust the character's behavior and conversation content based on that data. For example, if the user is exercising, the generation unit can provide topics related to exercise. Also, if the user is cooking, the generation unit can provide cooking advice and recipes. Furthermore, the generation unit can adjust the character's behavior in real time based on the user's activity data. For example, if the user is walking, the character will also walk along with the user. This makes it possible to provide the character's behavior and conversation content according to the user's real-time activity.

[0066] When analyzing conversation content, the analysis unit can improve the accuracy of the analysis by taking into account the user's past health data. For example, if the user has had stress-related health problems in the past, the analysis unit will particularly carefully analyze stress-related keywords and phrases. The analysis unit can also prioritize analysis of conversation content related to specific health conditions based on the user's past health data. Furthermore, the analysis unit can predict future health risks based on the user's health data and provide appropriate advice. This enables highly accurate analysis tailored to the user's health condition.

[0067] The setting unit can analyze the user's social media activity and automatically set topics that interest the user. For example, if the user frequently posts about "travel" on social media, the setting unit can prioritize travel-related topics. Also, if the user frequently posts about "cooking," the setting unit can set cooking-related topics. Furthermore, the setting unit can suggest related topics based on the activity of the user's friends on social media. This enables personalized settings based on the user's social media activity.

[0068] The generator can customize the character's appearance and personality by reflecting the user's past feedback. For example, if a user previously provided feedback such as "I like this character's appearance," the generator can generate a character with a similar appearance. Also, if a user provides feedback such as "I don't like this character's personality," the generator can adjust the personality based on that feedback. Furthermore, the character's movements and voice can also be customized based on the user's feedback. This makes it possible to provide a character that meets the user's preferences.

[0069] The conversation unit can analyze the user's past conversation history and automatically apply the user's preferred conversation style. For example, if the user has previously preferred humorous conversations, the conversation unit can apply a humorous conversation style. Alternatively, if the user has previously preferred serious conversations, the conversation unit can apply that style. Furthermore, the conversation unit can analyze the user's reactions to specific topics from the user's past conversation history and select an appropriate conversation style. This makes it possible to provide a conversation experience that suits the user's preferences.

[0070] When analyzing conversation content, the analysis unit can improve the accuracy of the analysis by taking into account the user's current lifestyle. For example, if the user is currently busy, the analysis unit can extract important information in a short time. On the other hand, if the user is relaxed, the analysis unit can perform a detailed analysis. Furthermore, it can prioritize analysis of information related to specific topics based on the user's lifestyle. This enables highly accurate analysis that is tailored to the user's lifestyle.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The setting unit sets the user's personal conditions. Personal conditions include age, gender, occupation, hobbies, place of residence, likes, dislikes, etc. The setting unit stores the information entered by the user in a database and provides it to the generation unit. Step 2: The generation unit uses the generation AI to generate a character based on the conditions set by the setting unit. The generation AI can generate the character's appearance and personality using a text generation AI (e.g., LLM), and can also generate the character's movements and voice using a multimodal generation AI. The generation AI generates a friendly character based on the user's conditions. Step 3: In the conversation section, the generated character converses with the user. The conversation takes place via voice or text. The conversation section uses a generative AI to generate conversation content that will entertain the user. For example, the conversation section can provide topics related to the user's hobbies and favorite things, estimate the user's emotions, and adjust how the conversation progresses. Step 4: The analysis unit analyzes the content of the conversation carried out by the conversation unit. The analysis is carried out using natural language processing technology and sentiment analysis technology. The analysis unit analyzes the content of the conversation and detects cases where there is a high possibility of a problem occurring. For example, it detects problems based on the frequency of appearance of specific keywords or changes in sentiment. Step 5: The communication department will contact the user if there is a high possibility that a problem detected by the analysis department will occur. The communication will be by phone or email. The communication department will contact family members, government agencies, etc. to ensure the user's safety.

[0073] (Example 2) A conversation partner system according to an embodiment of the present invention generates a character based on a user's personal conditions, engages in conversation, and contacts the user if a problem is likely to arise. In the conversation partner system, the user sets personal conditions, such as their age, gender, occupation, hobbies, place of residence, likes, and dislikes, and a generation AI generates a friendly character for the user based on these conditions, which then becomes the user's conversation partner. The generation AI generates conversation content taking into account the user's set conditions to provide a conversation that is enjoyable for the user. Furthermore, the conversation content is analyzed by the AI, and if a problem is likely to arise, family members, government agencies, and the like are notified in advance. For example, in a conversation partner system, the user sets their own personal conditions, such as age, gender, occupation, hobbies, place of residence, likes, and dislikes. This information is input into the generation AI. The generation AI then analyzes the input information and generates a character that is friendly to the user. For example, if the user is a young woman, a female character of the same age is generated. This character generates conversation content taking into account the user's set conditions to provide a conversation that is enjoyable for the user. The generated character then begins a conversation with the user. For example, the conversation progresses on topics that interest the user, such as hobbies or favorite things. This allows the user to have a fun time. Furthermore, the conversation partner system uses AI to analyze the content of the conversation. For example, if the user is feeling stressed or a problem is about to occur, the AI ​​will detect this and contact family members or government agencies in advance. This ensures the user's safety. This allows the user to use the service with peace of mind. The conversation partner system generates a character based on the user's private conditions, engages in conversation, and contacts the user if a problem is about to occur, allowing the user to use the service with peace of mind. For example, even if an elderly person spends a lot of time alone, using this service can provide them with someone to talk to and reduce their sense of loneliness. Furthermore, the user's privacy is protected, and appropriate measures are taken when necessary, allowing the system to be used with peace of mind.

[0074] A conversation partner system according to an embodiment includes a setting unit, a generation unit, a conversation unit, an analysis unit, and a communication unit. The setting unit sets personal conditions of a user. The personal conditions include, for example, age, gender, occupation, hobbies, place of residence, likes, dislikes, etc., but are not limited to these examples. The setting unit, for example, stores information input by the user in a database and provides the information to the generation unit. The generation unit generates a character based on the conditions set by the setting unit using a generation AI. The generation AI generates the character's appearance and personality using, for example, a text generation AI (e.g., LLM). The generation unit can also generate the character's movements and voice using a multimodal generation AI. The generation AI generates a friendly character based on the user's conditions. The conversation unit causes the generated character to converse with the user. The conversation may be, for example, audio or text, but is not limited to these examples. The conversation unit uses the generation AI to generate conversation content that the user will find enjoyable. For example, the conversation unit provides topics related to the user's hobbies and favorite things. The conversation unit can also estimate the user's emotions and adjust the way the conversation progresses. The analysis unit analyzes the content of the conversation conducted by the conversation unit. The analysis is performed using, for example, natural language processing technology or emotion analysis technology. The analysis unit analyzes the content of the conversation and detects when a problem is likely to occur. For example, the analysis unit detects a problem based on the frequency of appearance of specific keywords or changes in emotions. The contact unit makes contact when a problem detected by the analysis unit is likely to occur. The contact is made, for example, by telephone or email, but is not limited to such examples. The contact unit contacts family members, government agencies, etc. to ensure the user's safety. As a result, the conversation partner system according to the embodiment generates a character based on the user's private conditions, conducts a conversation, and contacts the user when a problem is likely to occur, allowing the user to use the service with peace of mind.

[0075] The generation unit can generate characters based on conditions including the user's age, gender, occupation, hobbies, place of residence, likes, and dislikes. For example, the generation unit generates characters of the same age based on the user's age. The generation unit can also generate characters of the same gender based on the user's gender. The generation unit can also generate characters of a related occupation based on the user's occupation. For example, if the user is a doctor, the generation unit generates characters related to the medical field. The generation unit can also generate characters with related hobbies based on the user's hobbies. For example, if the user likes music, the generation unit generates characters that are knowledgeable about music. The generation unit can also generate characters that live in the same area based on the user's place of residence. For example, if the user lives in an urban area, the generation unit generates characters that live in the urban area. The generation unit can also generate related characters based on the user's likes and dislikes. For example, if the user likes dogs, the generation unit generates a character that owns a dog. This makes it possible to provide more friendly characters by generating characters based on the user's detailed conditions.

[0076] The conversation unit allows the generated character to have a conversation with the user. For example, the conversation unit allows the generated character to have a conversation with the user using audio. The conversation unit can also have a conversation with the user using text. The conversation unit can also provide topics related to the user's hobbies. For example, if the user likes movies, the conversation unit can provide topics about the latest movies. The conversation unit can also provide topics about the user's favorite things. For example, if the user likes coffee, the conversation unit can provide topics about types of coffee and how to brew it. The conversation unit can also estimate the user's emotions and adjust the way the conversation proceeds. For example, if the user is relaxed, the conversation unit can proceed the conversation at a leisurely pace. If the user is excited, the conversation unit can proceed the conversation at a lively pace. If the user is sad, the conversation unit can proceed the conversation in a gentle tone. This allows the generated character to have a conversation with the user, allowing the user to have a fun time.

[0077] The analysis unit can analyze the content of the conversation and detect when a problem is likely to occur. The analysis unit, for example, analyzes the content of the conversation using natural language processing technology. For example, the analysis unit determines that a problem is likely to occur if a specific keyword appears frequently in the conversation. The analysis unit can also analyze changes in the user's emotions using emotion analysis technology. For example, the analysis unit determines that a problem is likely to occur if the user is feeling stressed. The analysis unit can also analyze the flow and context of the conversation to detect when a problem is likely to occur. For example, the analysis unit determines that a problem is likely to occur if an inconsistency occurs in the conversation. The analysis unit can also analyze the user's past conversation history to detect when a problem is likely to occur. For example, the analysis unit learns patterns of conversations that have caused problems in the past and detects a problem when a similar pattern appears again. In this way, by analyzing the content of the conversation, it is possible to detect when a problem is likely to occur in advance.

[0078] The communication unit can contact family members or government agencies when there is a high possibility that the detected problem will occur. For example, the communication unit can contact family members or government agencies via telephone. The communication unit can also contact them via email. The communication unit can also contact them using a notification system. For example, the communication unit can send a notification to family members through a smartphone app. The communication unit can also obtain the user's location information and contact the nearest government agency. For example, if the user is in a specific area, the communication unit can contact the local government agency. The communication unit can also analyze the user's past communication history and select the optimal communication method. For example, the communication unit can contact the user based on the communication method the user preferred in the past. The communication unit can also estimate the user's emotions and adjust the communication method. For example, if the user is relaxed, the communication unit can select a gentle communication method. If the user is in a hurry, the communication unit can select a quick communication method. This ensures the user's safety by contacting the user in advance when a problem is likely to occur.

[0079] The setting unit can estimate the user's emotions and adjust the settings of the private conditions based on the estimated user emotions. For example, the setting unit can analyze the user's facial expressions to estimate the emotions. The setting unit can also analyze the user's voice to estimate the emotions. The setting unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotions. For example, the setting unit can estimate the emotions based on heart rate fluctuations. The setting unit can also adjust the settings of the private conditions based on the estimated emotions. For example, if the user is feeling stressed, the setting unit can provide a simple interface and minimize the setting steps. If the user is relaxed, the setting unit can provide detailed setting options and suggest a customizable setting method. If the user is in a hurry, the setting unit can prioritize voice input to enable quick setting of the private conditions. This allows the settings of the private conditions to be adjusted according to the user's emotions, thereby enabling more appropriate settings.

[0080] The setting unit can analyze the user's past setting history and suggest the optimal setting method. For example, the setting unit automatically displays as candidates conditions that the user has frequently set in the past. The setting unit can also preferentially suggest setting methods (voice, text, etc.) that the user has used in the past. The setting unit can also predict and suggest settings to be used in a specific time period based on the user's past setting history. For example, if the user has previously made settings at night, the setting unit can suggest setting options that are suitable for nighttime. The setting unit can also analyze the user's past setting history and understand the user's preferences and tendencies. In this way, the setting unit can suggest the optimal setting method to the user by analyzing the past setting history.

[0081] The setting unit can perform filtering based on the user's current living situation and areas of interest during setup. For example, when the user inputs their current living situation, the setting unit prioritizes displaying related setting options. The setting unit can also filter and display related setting options based on the user's areas of interest. The setting unit can also suggest an optimal setting method taking into account the user's current living situation and areas of interest. For example, when the user inputs "busy" as their current living situation, the setting unit prioritizes displaying concise setting options. When the user selects "sports" as their area of ​​interest, the setting unit filters and displays sports-related setting options. This enables more appropriate setup by filtering based on the user's current living situation and areas of interest.

[0082] The setting unit can select the optimal setting means depending on the user's input method during setting. For example, if the user selects voice input, the setting unit performs setting using voice recognition technology. Furthermore, if the user selects text input, the setting unit can also perform setting using text analysis technology. Furthermore, if the user selects image input, the setting unit can also perform setting using image recognition technology. For example, if the user inputs an image using a smartphone camera, the setting unit analyzes the image and displays related setting options. Furthermore, the setting unit has an algorithm for selecting the optimal setting means depending on the user's input method. This facilitates setting by selecting the optimal setting means depending on the user's input method.

[0083] The setting unit can estimate the user's emotion and determine the priority of conditions to be set based on the estimated user's emotion. The setting unit, for example, analyzes the user's facial expression to estimate the emotion. The setting unit can also analyze the user's voice to estimate the emotion. The setting unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotion. For example, the setting unit estimates the emotion based on heart rate fluctuations. The setting unit also determines the priority of conditions to be set based on the estimated emotion. For example, if the user is feeling stressed, important conditions can be set with priority. Also, if the user is relaxed, detailed conditions can be set with priority. Also, if the user is in a hurry, conditions that can be set quickly can be set with priority. In this way, by determining the priority of conditions to be set based on the user's emotion, more appropriate settings can be achieved.

[0084] During setup, the setting unit can prioritize highly relevant conditions by taking into account the user's geographical location information. For example, if the user is in a specific area, the setting unit prioritizes setting conditions related to that area. The setting unit can also display related setting options based on the user's current location. The setting unit can also suggest an optimal setting method by taking into account the user's geographical location information. For example, if the user is in an urban area, the setting unit can prioritize displaying setting options related to urban areas. Also, if the user is in a rural area, the setting unit can prioritize displaying setting options related to rural areas. This enables more appropriate setup by prioritizing highly relevant conditions by taking into account the user's geographical location information.

[0085] During the setting process, the setting unit can analyze the user's social media activity and set related conditions. For example, the setting unit can set related conditions based on information shared by the user on social media. The setting unit can also analyze the user's social media activity and suggest related setting options. The setting unit can also set related conditions based on the activity of the user's friends on social media. For example, if the user frequently posts about "travel" on social media, the setting unit can suggest travel-related setting options. The setting unit can also analyze the number of "likes" and "comments" on the user's social media and set related conditions. In this way, related conditions can be set by analyzing the user's social media activity.

[0086] The setting unit can customize the setting method by reflecting the user's past feedback during setting. The setting unit customizes the setting method based on, for example, feedback provided by the user in the past. The setting unit can also analyze the user's past feedback and suggest an optimal setting method. The setting unit can also improve the setting interface by reflecting the user's feedback. For example, if the user has previously given feedback that "settings are difficult," the setting unit can provide a simple interface. If the user has given feedback that "I would like more detailed settings," the setting unit can also provide more detailed setting options. In this way, the setting method can be customized by reflecting the user's past feedback.

[0087] The generation unit can estimate the user's emotion and adjust the character's expression based on the estimated user's emotion. The generation unit, for example, analyzes the user's facial expression to estimate the emotion. The generation unit can also analyze the user's voice to estimate the emotion. The generation unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotion. For example, the generation unit estimates the emotion based on heart rate fluctuations. The generation unit also adjusts the character's expression based on the estimated emotion. For example, if the user is relaxed, a character with a calm expression can be generated. If the user is excited, a character with a lively expression can be generated. If the user is sad, a character with a gentle expression can be generated. In this way, by adjusting the character's expression based on the user's emotion, a more approachable character can be provided.

[0088] The generation unit can adjust the level of detail of the character based on important conditions of the user when generating the character. For example, if the user desires a detailed character, the generation unit can generate a character that is depicted in great detail. Also, if the user desires a simple character, the generation unit can generate a character with a simple design. Also, the generation unit can generate a character with an optimal level of detail based on conditions set by the user. For example, if the user desires a "realistic appearance," the generation unit can generate a character with a realistic appearance. Also, if the user desires an "anime-style appearance," the generation unit can generate a character with an anime-style appearance. In this way, by adjusting the level of detail of the character based on important conditions of the user, a more appropriate character can be provided.

[0089] The generation unit can apply different generation algorithms depending on the user category when generating a character. For example, if the user is a child, the generation unit can apply a character generation algorithm for children. Also, if the user is elderly, the generation unit can apply a character generation algorithm for elderly people. Also, the generation unit can apply an optimal character generation algorithm depending on the user's occupation or hobby. For example, if the user is a doctor, the generation unit can apply a medical-related character generation algorithm. Also, if the user is a musician, the generation unit can apply a character generation algorithm related to music. In this way, by applying different generation algorithms depending on the user category, a more appropriate character can be provided.

[0090] When generating a character, the generation unit can improve the accuracy of generation by referring to the user's past generation results. For example, the generation unit generates an optimal character based on characters generated by the user in the past. The generation unit can also analyze the user's past generation results and improve the generation algorithm. The generation unit can also improve the accuracy of generation by reflecting user feedback. For example, if the user previously provided feedback such as "I like this character," the generation unit generates a similar character. Also, if the user provided feedback such as "I don't like this character," the generation unit can improve the generation algorithm based on that feedback. In this way, the accuracy of generation can be improved by referring to the user's past generation results.

[0091] The generation unit can estimate the user's emotion and adjust the character's appearance based on the estimated user's emotion. The generation unit, for example, analyzes the user's facial expression to estimate the emotion. The generation unit can also analyze the user's voice to estimate the emotion. The generation unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotion. For example, the generation unit estimates the emotion based on heart rate fluctuations. The generation unit also adjusts the character's appearance based on the estimated emotion. For example, if the user is relaxed, a character with a calm appearance can be generated. If the user is excited, a character with a lively appearance can be generated. If the user is sad, a character with a gentle appearance can be generated. In this way, by adjusting the character's appearance based on the user's emotion, a more approachable character can be provided.

[0092] When generating a character, the generation unit can determine a generation priority based on the time of submission by the user. For example, if the user is in a hurry, the generation unit can quickly generate a character. Also, if the user has time, the generation unit can generate a detailed character. Also, the generation unit can determine an optimal generation schedule based on the time of submission by the user. For example, if the user requests "I want a character right away," the generation unit can quickly generate a character. Also, if the user requests "I want a detailed character that will take time," the generation unit can generate a detailed character. In this way, by determining a generation priority based on the time of submission by the user, it is possible to provide a more appropriate character.

[0093] When generating characters, the generation unit can adjust the order of generation based on the user's relevance. For example, if the user preferentially desires a specific character, the generation unit generates that character first. The generation unit can also adjust the order of generation based on the user's relevance. The generation unit can also determine the optimal order of generation based on conditions set by the user. For example, if the user desires that "a specific character be generated first," the generation unit generates that character preferentially. The generation unit can also adjust the order of generation based on the user's relevance. In this way, by adjusting the order of generation based on the user's relevance, it is possible to provide a more appropriate character.

[0094] When generating a character, the generation unit can adjust the character's use of technical terminology according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates a character that uses a lot of technical terminology. Furthermore, if the user is a beginner, the generation unit can generate a character that avoids technical terminology. Furthermore, the generation unit can adjust the use of optimal technical terminology according to the user's level of expertise. For example, if the user sets "desiring technical conversation," the generation unit generates a character that uses a lot of technical terminology. Furthermore, if the user sets "desiring conversation for beginners," the generation unit can generate a character that avoids technical terminology. In this way, by adjusting the character's use of technical terminology according to the user's level of expertise, a more appropriate character can be provided.

[0095] The conversation unit can estimate the user's emotions and adjust the way the conversation proceeds based on the estimated user's emotions. The conversation unit, for example, analyzes the user's facial expressions to estimate the emotions. The conversation unit can also analyze the user's voice to estimate the emotions. The conversation unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotions. For example, the conversation unit estimates the emotions based on heart rate fluctuations. The conversation unit also adjusts the way the conversation proceeds based on the estimated emotions. For example, if the user is relaxed, the conversation can proceed at a leisurely pace. If the user is excited, the conversation can proceed at a lively pace. If the user is sad, the conversation can proceed in a gentle tone. In this way, by adjusting the way the conversation proceeds based on the user's emotions, a more appropriate conversation can be provided.

[0096] The conversation unit can adjust the level of detail of the conversation based on important topics for the user during the conversation. For example, the conversation unit provides detailed information about topics in which the user is interested. The conversation unit can also provide a brief explanation about topics in which the user is not interested. The conversation unit can also adjust the optimal level of detail of the conversation based on important topics for the user. For example, if the user requests "detailed information," the conversation unit provides detailed information. If the user requests "concise information," the conversation unit can also provide a brief explanation. In this way, by adjusting the level of detail of the conversation based on important topics for the user, a more appropriate conversation can be provided.

[0097] The conversation unit can apply different conversation algorithms depending on the user category during conversation. For example, if the user is a child, the conversation unit can apply a conversation algorithm for children. Furthermore, if the user is elderly, the conversation unit can also apply a conversation algorithm for elderly people. Furthermore, the conversation unit can apply the most appropriate conversation algorithm depending on the user's occupation or hobby. For example, if the user is a doctor, the conversation unit can apply a medical-related conversation algorithm. Furthermore, if the user is a musician, the conversation unit can also apply a music-related conversation algorithm. In this way, by applying different conversation algorithms depending on the user category, more appropriate conversation can be provided.

[0098] The conversation unit can improve the accuracy of a conversation by referring to the user's past conversation results during the conversation. The conversation unit, for example, provides an optimal conversation based on the user's past conversations. The conversation unit can also analyze the user's past conversation results and improve the conversation algorithm. The conversation unit can also improve the accuracy of a conversation by reflecting user feedback. For example, if the user has previously given feedback that "this conversation was good," the conversation unit can provide a similar conversation. Also, if the user has given feedback that "this conversation was not to my liking," the conversation unit can improve the conversation algorithm based on that feedback. In this way, the accuracy of a conversation can be improved by referring to the user's past conversation results.

[0099] The conversation unit can estimate the user's emotions and adjust the length of the conversation based on the estimated user's emotions. The conversation unit, for example, analyzes the user's facial expressions to estimate the emotions. The conversation unit can also analyze the user's voice to estimate the emotions. The conversation unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotions. For example, the conversation unit estimates the emotions based on heart rate fluctuations. The conversation unit also adjusts the length of the conversation based on the estimated emotions. For example, if the user is relaxed, a longer conversation can be provided. If the user is in a hurry, a short, to-the-point conversation can be provided. If the user is excited, a conversation of an appropriate length can be provided. In this way, by adjusting the length of the conversation based on the user's emotions, a more appropriate conversation can be provided.

[0100] The conversation unit can determine the priority of a conversation based on the time of submission by the user during the conversation. For example, if the user is in a hurry, the conversation unit can start the conversation quickly. Also, if the user has time, the conversation unit can provide a detailed conversation. Also, the conversation unit can determine an optimal conversation schedule based on the time of submission by the user. For example, if the user desires to "start the conversation immediately," the conversation unit can start the conversation quickly. Also, if the user desires to "take time to have a detailed conversation," the conversation unit can provide a detailed conversation. In this way, by determining the priority of a conversation based on the time of submission by the user, more appropriate conversations can be provided.

[0101] The conversation unit can adjust the order of conversations based on the user's relevance during a conversation. For example, if the user preferentially desires to discuss a specific topic, the conversation unit will discuss that topic first. The conversation unit can also adjust the order of conversations based on the user's relevance. The conversation unit can also determine the optimal conversation order based on conditions set by the user. For example, if the user desires to "discuss a specific topic first," the conversation unit will discuss that topic first. The conversation unit can also adjust the order of conversations based on the user's relevance. In this way, by adjusting the order of conversations based on the user's relevance, a more appropriate conversation can be provided.

[0102] The conversation unit can adjust the use of technical terms in the conversation during the conversation according to the user's level of expertise. For example, if the user has technical expertise, the conversation unit can provide a conversation that uses a lot of technical terms. Furthermore, if the user is a beginner, the conversation unit can provide a conversation that avoids technical terms. Furthermore, the conversation unit can adjust the use of optimal technical terms according to the user's level of expertise. For example, if the user sets "I want a technical conversation," the conversation unit can provide a conversation that uses a lot of technical terms. Furthermore, if the user sets "I want a conversation for beginners," the conversation unit can provide a conversation that avoids technical terms. In this way, by adjusting the use of technical terms in the conversation according to the user's level of expertise, it is possible to provide a more appropriate conversation.

[0103] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated user's emotions. The analysis unit, for example, analyzes the user's facial expressions to estimate emotions. The analysis unit can also analyze the user's voice to estimate emotions. The analysis unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate emotions. For example, the analysis unit estimates emotions based on heart rate fluctuations. The analysis unit also adjusts the analysis criteria based on the estimated emotions. For example, if the user is relaxed, a detailed analysis can be performed. If the user is in a hurry, a brief analysis can be performed. If the user is excited, an analysis with an appropriate level of detail can be performed. In this way, adjusting the analysis criteria based on the user's emotions enables more appropriate analysis.

[0104] The analysis unit can improve the accuracy of the analysis by taking into account the interrelationships between conversations during analysis. The analysis unit can, for example, perform a more accurate analysis by taking into account the context of the conversation. The analysis unit can also analyze the interrelationships between conversations and extract related information. The analysis unit can also apply an optimal analysis method by taking into account the flow of the conversation. For example, the analysis unit can understand the context based on the context of the conversation and perform a more accurate analysis. The analysis unit can also analyze the interrelationships between conversations and extract related information. In this way, the accuracy of the analysis can be improved by taking into account the interrelationships between conversations.

[0105] The analysis unit can perform analysis taking into account user attribute information. The analysis unit performs appropriate analysis taking into account, for example, the user's age and gender. The analysis unit can also analyze related information taking into account the user's occupation and hobbies. The analysis unit can also apply the optimal analysis method taking into account the user's place of residence and living situation. For example, the analysis unit analyzes related information based on the user's age and gender. The analysis unit can also analyze related information taking into account the user's occupation and hobbies. This enables more appropriate analysis by taking into account the user's attribute information.

[0106] During analysis, the analysis unit can weight the analysis based on the frequency of conversation. For example, the analysis unit performs analysis by placing emphasis on frequently occurring conversations. The analysis unit can also extract important information based on the frequency of conversations. The analysis unit can also apply an optimal analysis method taking into account the frequency of conversations. For example, the analysis unit performs analysis by placing emphasis on frequently occurring conversations. The analysis unit can also extract important information based on the frequency of conversations. In this way, by weighting the analysis based on the frequency of conversations, more important information can be extracted.

[0107] The analysis unit can estimate the user's emotions and adjust the order in which the analysis results are displayed based on the estimated user's emotions. The analysis unit, for example, analyzes the user's facial expressions to estimate the emotions. The analysis unit can also analyze the user's voice to estimate the emotions. The analysis unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotions. For example, the analysis unit estimates the emotions based on heart rate fluctuations. The analysis unit also adjusts the order in which the analysis results are displayed based on the estimated emotions. For example, if the user is relaxed, detailed analysis results can be displayed preferentially. If the user is in a hurry, analysis results that focus on the main points can be displayed preferentially. If the user is excited, analysis results that are visually easy to understand can be displayed preferentially. In this way, by adjusting the order in which the analysis results are displayed based on the user's emotions, more appropriate information can be provided.

[0108] The analysis unit can perform the analysis while taking into account the geographical distribution of the conversation. For example, the analysis unit analyzes related information while taking into account the location where the conversation occurred. The analysis unit can also analyze the conversation trend based on the geographical distribution. The analysis unit can also apply an optimal analysis method while taking into account the geographical distribution of the conversation. For example, the analysis unit analyzes related information based on the location where the conversation occurred. The analysis unit can also analyze the conversation trend based on the geographical distribution. This enables more appropriate analysis by taking into account the geographical distribution of the conversation.

[0109] During analysis, the analysis unit can improve the accuracy of the analysis by referring to literature related to the conversation. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the content of the conversation. The analysis unit can also analyze background information of the conversation based on the related literature. The analysis unit can also apply an optimal analysis method by referring to literature related to the conversation. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the content of the conversation. The analysis unit can also analyze background information of the conversation based on the related literature. In this way, by referring to literature related to the conversation, the accuracy of the analysis can be improved.

[0110] The analysis unit can perform the analysis while taking into account the market value of the conversation. For example, the analysis unit evaluates the market value of the conversation content and extracts important information. The analysis unit can also analyze the conversation trend based on the market value. The analysis unit can also apply an optimal analysis method while taking into account the market value of the conversation. For example, the analysis unit evaluates the market value of the conversation content and extracts important information. The analysis unit can also analyze the conversation trend based on the market value. In this way, by taking into account the market value of the conversation, more important information can be extracted.

[0111] The communication unit can estimate the user's emotions and adjust the method of communication based on the estimated user's emotions. The communication unit, for example, analyzes the user's facial expressions to estimate the emotions. The communication unit can also analyze the user's voice to estimate the emotions. The communication unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotions. For example, the communication unit estimates the emotions based on heart rate fluctuations. The communication unit can also adjust the method of communication based on the estimated emotions. For example, if the user is relaxed, a gentle method of communication can be selected. If the user is in a hurry, a quick method of communication can be selected. If the user is excited, a moderate method of communication can be selected. In this way, adjusting the method of communication based on the user's emotions enables more appropriate communication.

[0112] When contacting a user, the contact unit can analyze the user's past contact history and select the optimal contact method. For example, the contact unit selects the optimal contact method based on contact methods used by the user in the past. The contact unit can also analyze the user's past contact history and suggest the optimal contact method. The contact unit can also improve the contact method by reflecting user feedback. For example, if the user has previously given feedback that "this contact method was good," the contact unit selects a similar contact method. Also, if the user has given feedback that "this contact method is not my preference," the contact unit can improve the contact method based on that feedback. In this way, the optimal contact method can be selected by analyzing the user's past contact history.

[0113] The contact unit can customize the contact method based on the user's current living situation when making contact. For example, if the user is busy, the contact unit selects a simple contact method. Also, if the user is relaxed, the contact unit can select a detailed contact method. Also, the contact unit can suggest the optimal contact method taking the user's current living situation into consideration. For example, if the user sets "busy," the contact unit selects a simple contact method. Also, if the user sets "relaxed," the contact unit can select a detailed contact method. In this way, customizing the contact method based on the user's current living situation enables more appropriate contact.

[0114] The contact unit can improve the contact method by reflecting the user's feedback when making a contact. For example, the contact unit improves the contact method based on feedback provided by the user in the past. The contact unit can also analyze the user's feedback and suggest the optimal contact method. The contact unit can also improve the contact interface by reflecting the user's feedback. For example, if the user has previously given feedback that the contact is slow, the contact unit can select a quick contact method. If the user has given feedback that the contact is too frequent, the contact unit can also adjust the frequency of contact. In this way, the contact method can be improved by reflecting the user's feedback.

[0115] The communication unit can estimate the user's emotions and determine the priority of communications based on the estimated user emotions. The communication unit, for example, analyzes the user's facial expressions to estimate the emotions. The communication unit can also analyze the user's voice to estimate the emotions. The communication unit can also analyze the user's biometric data (heart rate and electrodermal activity) to estimate the emotions. For example, the communication unit estimates the emotions based on heart rate fluctuations. The communication unit also determines the priority of communications based on the estimated emotions. For example, if the user is relaxed, important communications can be prioritized. If the user is in a hurry, quick communications can be made. If the user is excited, appropriate communications can be made. In this way, by determining the priority of communications based on the user's emotions, more appropriate communications can be made.

[0116] When making contact, the contact unit can select the optimal contact method by taking into account the user's geographical location information. For example, if the user is in a specific area, the contact unit selects a contact method related to that area. The contact unit can also suggest the optimal contact method based on the user's current location. The contact unit can also select the optimal contact method by taking into account the user's geographical location information. For example, if the user is in an urban area, the contact unit selects a contact method related to urban areas. Also, if the user is in a rural area, the contact unit can select a contact method related to rural areas. In this way, the optimal contact method can be selected by taking into account the user's geographical location information.

[0117] When contacting the user, the contact unit can analyze the user's social media activity and suggest a means of contact. For example, the contact unit can suggest the most appropriate means of contact based on information shared by the user on social media. The contact unit can also analyze the user's social media activity and suggest related means of contact. The contact unit can also suggest the most appropriate means of contact based on the activity of the user's friends on social media. For example, if the user frequently posts about "travel" on social media, the contact unit can suggest travel-related means of contact. The contact unit can also analyze the number of "likes" and "comments" on the user's social media and suggest related means of contact. In this way, the most appropriate means of contact can be suggested by analyzing the user's social media activity.

[0118] The contact unit can customize the contact method by reflecting the user's past feedback when contacting the user. For example, the contact unit customizes the contact method based on feedback provided by the user in the past. The contact unit can also analyze the user's past feedback and suggest the optimal contact method. The contact unit can also improve the contact interface by reflecting the user's feedback. For example, if the user has previously given feedback that the contact is slow, the contact unit can select a quick contact method. If the user has given feedback that the contact is too frequent, the contact unit can also adjust the frequency of contact. In this way, the contact method can be customized by reflecting the user's past feedback. === Hard Collateral 1-1 === Each of the multiple elements including the setting unit, generation unit, conversation unit, analysis unit, and communication 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 setting unit is realized by the control unit 46A of the smart device 14, and stores information input by the user in the database 24 and provides it to the generation unit. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a character using a generation AI. The conversation unit is realized by the control unit 46A of the smart device 14, and the generated character converses with the user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the content of the conversation. The communication unit is realized by the specific processing unit 290 of the data processing device 12, and makes a contact when there is a high possibility of a problem occurring. === Hard Collateral 1-2 === Each of the multiple elements including the setting unit, generation unit, conversation unit, analysis unit, and communication unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the smart glasses 214, and stores information input by the user in the database 24 and provides it to the generation unit. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a character using a generation AI. The conversation unit is realized by the control unit 46A of the smart glasses 214, and the generated character converses with the user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the content of the conversation. The communication unit is realized by the specific processing unit 290 of the data processing device 12, and makes a contact when there is a high possibility of a problem occurring. === Hard Collateral 1-3 === Each of the multiple elements including the setting unit, generation unit, conversation unit, analysis unit, and communication 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 setting unit is realized by the control unit 46A of the headset type terminal 314, and stores information input by the user in the database 24 and provides it to the generation unit. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a character using a generation AI. The conversation unit is realized by the control unit 46A of the headset type terminal 314, and the generated character converses with the user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the content of the conversation. The communication unit is realized by the specific processing unit 290 of the data processing device 12, and makes a contact when there is a high possibility that a problem will occur. === Hard Collateral 1-4 === Each of the multiple elements including the setting unit, generation unit, conversation unit, analysis unit, and communication unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the setting unit is realized by the control unit 46A of the robot 414, and stores information input by the user in the database 24 and provides it to the generation unit. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates a character using a generation AI. The conversation unit is realized by the control unit 46A of the robot 414, and the generated character converses with the user. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the content of the conversation. The communication unit is realized by the specific processing unit 290 of the data processing device 12, and makes contact when there is a high possibility that a problem will occur.

[0119] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0120] The setting unit can analyze the user's past conversation history and automatically suggest conversation topics that the user prefers. For example, if the user has frequently had conversations about music in the past, the setting unit will preferentially suggest topics related to music. Also, if the user prefers conversations about a particular season or event, the setting unit can suggest topics that are appropriate for that season. Furthermore, the setting unit can suggest topics related to a particular emotional state based on the user's past conversation history. For example, if the user is feeling stressed, the setting unit can suggest topics that will help them relax. This makes it possible to provide a more personalized conversation experience by utilizing the user's past conversation history.

[0121] The generation unit can acquire real-time activity data of the user and adjust the character's behavior and conversation content based on that data. For example, if the user is exercising, the generation unit can provide topics related to exercise. Also, if the user is cooking, the generation unit can provide cooking advice and recipes. Furthermore, the generation unit can adjust the character's behavior in real time based on the user's activity data. For example, if the user is walking, the character will also walk along with the user. This makes it possible to provide the character's behavior and conversation content according to the user's real-time activity.

[0122] The conversation unit can estimate the user's emotions and adjust the tone and pace of the conversation based on the estimated emotions. For example, if the user is tired, the conversation unit can conduct the conversation at a slow pace in a gentle tone. If the user is excited, the conversation unit can conduct the conversation at a fast pace in a lively tone. Furthermore, if the user is sad, the conversation unit can provide comforting conversation in a gentle tone. This makes it possible to provide an appropriate conversation experience according to the user's emotions.

[0123] When analyzing conversation content, the analysis unit can improve the accuracy of the analysis by taking into account the user's past health data. For example, if the user has had stress-related health problems in the past, the analysis unit will particularly carefully analyze stress-related keywords and phrases. The analysis unit can also prioritize analysis of conversation content related to specific health conditions based on the user's past health data. Furthermore, the analysis unit can predict future health risks based on the user's health data and provide appropriate advice. This enables highly accurate analysis tailored to the user's health condition.

[0124] The communication unit can estimate the user's emotions and adjust the content of the communication based on the estimated emotions. For example, if the user is feeling stressed, the communication unit can provide advice and resources for reducing stress. Also, if the user is relaxed, the communication unit can provide information for maintaining relaxation. Furthermore, if the user is excited, the communication unit can suggest ways to reduce excitement. In this way, it is possible to provide appropriate communication content according to the user's emotions.

[0125] The setting unit can analyze the user's social media activity and automatically set topics that interest the user. For example, if the user frequently posts about "travel" on social media, the setting unit can prioritize travel-related topics. Also, if the user frequently posts about "cooking," the setting unit can set cooking-related topics. Furthermore, the setting unit can suggest related topics based on the activity of the user's friends on social media. This enables personalized settings based on the user's social media activity.

[0126] The generator can customize the character's appearance and personality by reflecting the user's past feedback. For example, if a user previously provided feedback such as "I like this character's appearance," the generator can generate a character with a similar appearance. Also, if a user provides feedback such as "I don't like this character's personality," the generator can adjust the personality based on that feedback. Furthermore, the character's movements and voice can also be customized based on the user's feedback. This makes it possible to provide a character that meets the user's preferences.

[0127] The conversation unit can analyze the user's past conversation history and automatically apply the user's preferred conversation style. For example, if the user has previously preferred humorous conversations, the conversation unit can apply a humorous conversation style. Alternatively, if the user has previously preferred serious conversations, the conversation unit can apply that style. Furthermore, the conversation unit can analyze the user's reactions to specific topics from the user's past conversation history and select an appropriate conversation style. This makes it possible to provide a conversation experience that suits the user's preferences.

[0128] When analyzing conversation content, the analysis unit can improve the accuracy of the analysis by taking into account the user's current lifestyle. For example, if the user is currently busy, the analysis unit can extract important information in a short time. On the other hand, if the user is relaxed, the analysis unit can perform a detailed analysis. Furthermore, it can prioritize analysis of information related to specific topics based on the user's lifestyle. This enables highly accurate analysis that is tailored to the user's lifestyle.

[0129] The communication unit can estimate the user's emotions and adjust the timing of contact based on the estimated emotions. For example, if the user is relaxed, the communication unit can select the timing to make an important contact. If the user is busy, the communication unit can postpone contact. Furthermore, if the user is excited, the communication unit can refrain from contacting. This makes it possible to provide appropriate contact timing according to the user's emotions.

[0130] The processing flow of the second embodiment will be briefly explained below.

[0131] Step 1: The setting unit sets the user's personal conditions. Personal conditions include age, gender, occupation, hobbies, place of residence, likes, dislikes, etc. The setting unit stores the information entered by the user in a database and provides it to the generation unit. Step 2: The generation unit uses the generation AI to generate a character based on the conditions set by the setting unit. The generation AI can generate the character's appearance and personality using a text generation AI (e.g., LLM), and can also generate the character's movements and voice using a multimodal generation AI. The generation AI generates a friendly character based on the user's conditions. Step 3: In the conversation section, the generated character converses with the user. The conversation takes place via voice or text. The conversation section uses a generative AI to generate conversation content that will entertain the user. For example, the conversation section can provide topics related to the user's hobbies and favorite things, estimate the user's emotions, and adjust how the conversation progresses. Step 4: The analysis unit analyzes the content of the conversation carried out by the conversation unit. The analysis is carried out using natural language processing technology and sentiment analysis technology. The analysis unit analyzes the content of the conversation and detects cases where there is a high possibility of a problem occurring. For example, it detects problems based on the frequency of appearance of specific keywords or changes in sentiment. Step 5: The communication department will contact the user if there is a high possibility that a problem detected by the analysis department will occur. The communication will be by phone or email. The communication department will contact family members, government agencies, etc. to ensure the user's safety.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0136] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0137] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0152] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0168] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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).

[0189] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0190] 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."

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Explanation of symbols]

[0204] 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 setting unit for setting personal conditions of a user; a generation unit that generates a character based on the conditions set by the setting unit; a conversation unit in which the character generated by the generation unit converses; an analysis unit that analyzes the content of the conversation carried out by the conversation unit; a contact unit that makes a contact when there is a high possibility that the problem detected by the analysis unit will occur. A system characterized by:

2. The generation unit Generate characters based on user criteria, including age, gender, occupation, hobbies, place of residence, likes and dislikes 2. The system of claim 1.

3. The conversation unit is The generated character converses with the user 2. The system of claim 1.

4. The analysis unit Analyze conversations to detect potential problems 2. The system of claim 1.

5. The communication unit Notify family or government agencies if detected issues are likely to occur 2. The system of claim 1.

6. The setting unit Inferring user emotions and adjusting private condition settings based on the estimated user emotions 2. The system of claim 1.

7. The setting unit Analyzes the user's past settings history and suggests optimal settings 2. The system of claim 1.

8. The setting unit During setup, filtering is performed based on the user's current life situation and interests.

2. The system of claim 1.

Images