System

Abstract

To provide a system capable of interrupting conversations to bring up a new topic at the right time at a drinking party, etc.SOLUTION: A system in an embodiment includes a collection unit, an analysis unit, an interrupt unit, and a new topic introduction unit. The collection unit collects the profile information of a service subscriber. The analysis unit analyzes the information collected by the collection unit. The interrupt unit interjects into a conversation at the right time based on the information analyzed by the analysis unit. The new topic introduction unit brings up a new topic in the conversation interrupted by an interrupt unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to interrupt a conversation at an appropriate time and bring up a topic at a drinking party or other such event.

[0005] The system according to the embodiment aims to interrupt conversations at appropriate times and bring up topics at events such as drinking parties. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, an interruption unit, and a topic proposal unit. The collection unit collects profile information of service registrants. The analysis unit analyzes the information collected by the collection unit. The interruption unit interrupts a conversation at a timing based on the information analyzed by the analysis unit. The topic proposal unit proposes a topic based on the conversation interrupted by the interruption unit. Effect of the Invention

[0007] The system according to the embodiment can interrupt a conversation at an appropriate time and bring up a topic at a drinking party or the like. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The conversation support system according to the embodiment of the present invention is a system in which an AI listens to the surrounding conversation at a drinking party or the like based on the profile information of the service registrant in advance, interrupts the conversation at an appropriate timing, and sets up a topic that makes it easy for the registrant to talk. This conversation support system collects the profile information of the service registrant, and the AI ​​analyzes the surrounding conversation in real time at a drinking party or the like, and interrupts the conversation at an appropriate timing, making it easy for the registrant to talk. For example, the profile information of the service registrant is collected in advance. At this time, detailed information such as the registrant's hobbies, interests, and past experiences is collected. For example, if the registrant likes sports, that information is collected. This information is input to the AI. Next, the AI ​​analyzes the surrounding conversation in real time at a drinking party or the like. The AI ​​listens to and analyzes the surrounding conversation to understand the content and tone of the conversation. For example, if the surrounding conversation is about sports, the AI ​​analyzes that information. Finally, the AI ​​interrupts the conversation at an appropriate timing. The AI ​​understands the flow of the surrounding conversation and interrupts the conversation at an appropriate timing, making it easy for the registrant to participate in the conversation. For example, when the topic of sports comes up, the AI ​​will suggest something like, "You like sports too, don't you?" This system allows registered users to participate in conversations in a natural way, making communication smoother at events such as drinking parties. For example, even if a registered user meets someone for the first time, it will be easier to find common topics and have a lively conversation. In addition, the AI ​​can interrupt the conversation at the right time, allowing the conversation to progress smoothly without disrupting the flow of conversation. This allows the conversation support system to interrupt the conversation at the right time and suggest a topic based on the registered user's profile information.

[0029] The conversation support system according to the embodiment includes a collection unit, an analysis unit, an interruption unit, and a topic proposal unit. The collection unit collects profile information of service registrants. The profile information of the service registrants includes, for example, name, age, hobbies, and occupation, but is not limited to such examples. The collection unit collects the profile information using, for example, a questionnaire. The collection unit can also collect the profile information using social media analysis. For example, the collection unit analyzes the content of posts on social media to grasp the hobbies and interests of the registrants. The analysis unit analyzes the information collected by the collection unit. The analysis unit analyzes the profile information using, for example, data mining technology. The analysis unit can also analyze the profile information using natural language processing technology. For example, the analysis unit analyzes the collected text data to extract the interests and concerns of the registrants. The interruption unit interrupts the conversation at an appropriate timing based on the information analyzed by the analysis unit. The interruption unit determines the timing based on, for example, the length of the conversation or the appearance of a specific keyword. The interruption unit can also interrupt by voice or text message. For example, when a pause in a conversation becomes long, the interruption unit interrupts by saying, "You're also interested in this topic, aren't you?" The topic prompting unit prompts a topic based on the conversation interrupted by the interruption unit. The topic prompting unit provides topics related to the hobbies of the registered user, for example. The topic prompting unit can also prompt a topic based on the latest news. For example, if the registered user likes sports, the topic prompting unit prompts a question such as "What do you think about the recent game?" This allows the conversation support system according to the embodiment to interrupt a conversation at an appropriate time and prompt a topic based on the profile information of the registered user.

[0030] The collection unit collects profile information of the service registrant. The profile information of the service registrant includes, for example, name, age, hobbies, occupation, etc., but is not limited to such examples. The collection unit collects the profile information using, for example, a questionnaire. The questionnaire is provided in the form of an online form or a question in an app, and is collected by the registrant entering his / her information. The collection unit can also collect the profile information using social media analysis. For example, the collection unit analyzes the content of posts on social media to understand the hobbies and interests of the registrant. Specifically, the API of the social media is used to collect the post content and reactions such as "likes", and the collected information is analyzed using text mining technology. This makes it possible to extract keywords and hashtags frequently mentioned by the registrant and identify the hobbies and interests. Furthermore, the collection unit also collects information on groups in which the registrant participates and accounts followed by the registrant, and can obtain more detailed profile information. This allows the collection unit to collect comprehensive profile information from various information sources and improve the accuracy and effectiveness of the entire system.

[0031] The analysis unit analyzes the information collected by the collection unit. The analysis unit analyzes the profile information using, for example, data mining technology. Data mining technology is a method for extracting useful patterns and relationships from a large amount of data, and is useful for identifying interests and concerns from the profile information of a registrant. The analysis unit can also analyze the profile information using natural language processing technology. Natural language processing technology is a technology for analyzing text data and understanding meanings and emotions, and analyzes the collected text data to extract the interests and concerns of the registrant. For example, the analysis unit tokenizes the collected text data and analyzes the frequency of occurrence and co-occurrence of each token to identify topics in which the registrant is interested. Furthermore, the analysis unit can predict the behavioral patterns and preferences of the registrant from the collected data using a machine learning algorithm. This allows the analysis unit to analyze the collected information from multiple angles and grasp the profile information of the registrant in detail.

[0032] The interruption unit interrupts the conversation at an appropriate timing based on the information analyzed by the analysis unit. The interruption unit determines the timing based on, for example, the length of the gap in the conversation or the appearance of a specific keyword. Specifically, the interruption unit interrupts when the gap in the conversation continues for a certain period of time or when a specific keyword appears. The interruption unit can also interrupt by voice or text message. For example, when the gap in the conversation becomes long, the interruption unit interrupts by voice saying, "X-san, you're also interested in this topic, aren't you?" Furthermore, the interruption unit can use natural language processing technology to understand the context of the conversation and interrupt at an appropriate timing. This allows the interruption unit to interrupt at an appropriate timing while maintaining a smooth flow of the conversation.

[0033] The topic prompting unit prompts a topic based on the conversation interrupted by the interruption unit. The topic prompting unit, for example, provides a topic related to the hobbies of the registered user. Specifically, the topic prompting unit provides a related topic based on the hobbies and interests of the registered user identified by the analysis unit. The topic prompting unit can also prompt a topic based on the latest news. For example, if the registered user likes sports, the topic prompting unit prompts a topic such as "What do you think about the recent game?" Furthermore, the topic prompting unit can use natural language processing technology to understand the flow and context of the conversation and prompt a topic at an appropriate time. This allows the topic prompting unit to provide an appropriate topic while maintaining a smooth flow of the conversation.

[0034] The analysis unit can analyze the tone or keywords of the surrounding conversation. The analysis unit, for example, uses a voice analysis technology to analyze the tone of the surrounding conversation. For example, the analysis unit analyzes the pitch of the voice and the strength of the emotion to grasp the tone of the conversation. The analysis unit can also analyze the keywords of the surrounding conversation using a natural language processing technology. For example, the analysis unit extracts frequently occurring words or words with high importance to grasp the keywords of the conversation. By analyzing the tone and keywords of the surrounding conversation, it is possible to interrupt the conversation at an appropriate timing. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can input the voice data of the surrounding conversation to the generation AI and cause the generation AI to execute the analysis of the tone and keywords.

[0035] The topic suggestion unit can generate the content of the topic suggestion based on the profile information of the registrant. The topic suggestion unit generates, for example, a topic related to the hobby of the registrant. For example, if the registrant likes sports, the topic suggestion unit provides a topic related to sports. The topic suggestion unit can also generate the content of the topic suggestion based on the latest news. For example, the topic suggestion unit analyzes recent news and provides a topic that the registrant is likely to be interested in. As a result, the content of the topic suggestion is generated based on the profile information of the registrant, so that the conversation progresses smoothly. A part or all of the above-mentioned processing in the topic suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the topic suggestion unit can input the profile information of the registrant to the generation AI and cause the generation AI to generate the content of the topic suggestion.

[0036] The interruption unit can grasp the flow of the conversation and interrupt the conversation at an appropriate timing. The interruption unit, for example, analyzes the transition of the topic of the conversation and grasps the flow of the conversation. For example, the interruption unit analyzes the timing of the change of the topic of the conversation and interrupts at an appropriate timing. The interruption unit can also analyze the change of speaker and grasp the flow of the conversation. For example, the interruption unit analyzes the timing of the change of speaker and interrupts at an appropriate timing. As a result, the conversation progresses naturally by grasping the flow of the conversation and interrupting the conversation at an appropriate timing. A part or all of the above-mentioned processing in the interruption unit may be performed, for example, using AI or may be performed without using AI. For example, the interruption unit can input the transition data of the topic of the conversation to the generation AI and cause the generation AI to grasp the flow of the conversation.

[0037] The collection unit can collect information such as the hobbies, interests, and past experiences of the registrant. The collection unit, for example, uses a questionnaire to collect information such as the hobbies, interests, and past experiences of the registrant. For example, the collection unit asks the registrant questions about their hobbies and interests and collects their answers. The collection unit can also collect information such as the hobbies, interests, and past experiences of the registrant using social media analysis. For example, the collection unit analyzes the content of social media posts to understand the hobbies, interests, and past experiences of the registrant. This allows for more appropriate plot development by collecting detailed profile information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input social media posting data to the generation AI and cause the generation AI to perform an analysis of the hobbies, interests, and past experiences.

[0038] The collection unit can analyze the user's past profile information and select a collection method. The collection unit, for example, analyzes past questionnaire results and asks detailed questions to collect deeper information. For example, the collection unit asks related questions based on information provided by the user in the past. The collection unit can also analyze social media history and select questions in a format that is easy for the user to answer. For example, the collection unit analyzes the user's past answer patterns and selects questions in a format that is easy for the user to answer. Furthermore, the collection unit can avoid duplicate questions from the past profile information and efficiently collect information. For example, the collection unit avoids duplicate questions and efficiently collects information based on the user's past profile information. This makes it possible to efficiently collect information by analyzing the past profile information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input past questionnaire data to the generation AI and cause the generation AI to select a collection method.

[0039] The collection unit can perform filtering based on the user's current living situation and field of interest when collecting profile information. For example, the collection unit prioritizes questions related to the field in which the user is currently interested. For example, the collection unit prioritizes questions related to the field in which the user is currently interested. The collection unit can also collect highly relevant information according to the user's living situation. For example, the collection unit collects highly relevant information according to the user's living situation. Furthermore, the collection unit can omit unnecessary questions based on the user's field of interest and efficiently collect information. For example, the collection unit omits unnecessary questions based on the user's field of interest and efficiently collects information. This makes it possible to efficiently collect information by filtering information based on the user's living situation and field of interest. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's field of interest data to the generation AI and cause the generation AI to perform filtering.

[0040] When collecting profile information, the collection unit can preferentially collect highly relevant information based on the geographical location information of the user. For example, the collection unit preferentially collects information related to the location where the user is currently located. For example, the collection unit preferentially collects information related to the location where the user is currently located. The collection unit can also collect area-specific information based on the geographical location of the user. For example, the collection unit collects area-specific information based on the geographical location of the user. Furthermore, the collection unit can also collect highly relevant information taking into account the movement history of the user. For example, the collection unit collects highly relevant information taking into account the movement history of the user. As a result, highly relevant information can be efficiently collected by taking into account the geographical location information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location data of the user to the generation AI and cause the generation AI to execute collection of highly relevant information.

[0041] The collection unit can analyze the user's social media activity and collect related information when collecting the profile information. The collection unit, for example, analyzes the user's social media posting content and collects information on the field of interest. For example, the collection unit analyzes the user's social media posting content and collects information on the field of interest. The collection unit can also collect related information taking into account the user's social media friend relationships. For example, the collection unit collects related information taking into account the user's social media friend relationships. Furthermore, the collection unit can analyze the user's social media activity frequency and collect appropriate information. For example, the collection unit analyzes the user's social media activity frequency and collects appropriate information. In this way, related information can be efficiently collected by analyzing social media activity. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's social media data to the generation AI and cause the generation AI to execute collection of related information.

[0042] The analysis unit can adjust the details of the analysis based on the importance of the conversation during analysis. The analysis unit, for example, evaluates the importance of the conversation based on the content of the conversation and the roles of the participants. For example, the analysis unit evaluates the importance of the conversation based on the content of the conversation and the roles of the participants. The analysis unit can also perform detailed data analysis based on the importance of the conversation. For example, the analysis unit performs detailed data analysis in the case of an important conversation. Furthermore, the analysis unit can also provide a concise summary in the case of a general conversation. For example, the analysis unit provides a concise summary in the case of a general conversation. This allows the analysis to be performed efficiently by adjusting the level of detail of the analysis based on the importance of the conversation. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input content data of the conversation to the generation AI and cause the generation AI to execute the evaluation of the importance and the adjustment of the level of detail.

[0043] The analysis unit can apply a different analysis algorithm depending on the category of the conversation during analysis. For example, the analysis unit classifies the category of the conversation into business conversation, private conversation, etc. For example, the analysis unit classifies the category of the conversation into business conversation, private conversation, etc. The analysis unit can also apply a natural language processing algorithm depending on the category of the conversation. For example, in the case of a business conversation, the analysis unit applies a natural language processing algorithm specialized for business. Furthermore, the analysis unit can also apply a machine learning algorithm depending on the category of the conversation. For example, in the case of a conversation about entertainment, the analysis unit applies a machine learning algorithm specialized for entertainment. In this way, by applying different analysis algorithms depending on the category of the conversation, more appropriate analysis results can be provided. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation category data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0044] The analysis unit can determine the priority of the analysis based on the time when the conversation occurred during the analysis. The analysis unit evaluates the time when the conversation occurred based on, for example, the start time and duration of the conversation. For example, the analysis unit evaluates the time when the conversation occurred based on the start time and duration of the conversation. The analysis unit can also prioritize the analysis of conversations with high importance based on the time when the conversation occurred. For example, the analysis unit prioritizes the analysis of recent conversations. Furthermore, the analysis unit can also postpone past conversations. For example, the analysis unit postpones past conversations. In this way, the analysis can be performed efficiently by determining the priority of the analysis based on the time when the conversation occurred. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data on the time when the conversation occurred to the generation AI and cause the generation AI to execute the determination of the priority.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the conversations during analysis. The analysis unit evaluates the relevance of the conversations based on, for example, the commonality of the conversation topics and the commonality of the participants. For example, the analysis unit evaluates the relevance of the conversations based on the commonality of the conversation topics and the commonality of the participants. The analysis unit can also preferentially analyze highly relevant conversations based on the relevance of the conversations. For example, the analysis unit preferentially analyzes highly relevant conversations. Furthermore, the analysis unit can also postpone conversations with low relevance. For example, the analysis unit postpones conversations with low relevance. As a result, the analysis can be performed efficiently by adjusting the order of analysis based on the relevance of the conversations. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance data of the conversations to the generation AI and cause the generation AI to adjust the order.

[0046] The interruption unit can select an interruption method by analyzing the flow of the conversation at the time of interruption. The interruption unit analyzes the flow of the conversation based on, for example, a change in the topic of the conversation or a change in the speaker. For example, the interruption unit analyzes the flow of the conversation based on a change in the topic of the conversation or a change in the speaker. In addition, the interruption unit can interrupt in a natural flow when the conversation is lively. For example, the interruption unit interrupts in a natural flow when the conversation is lively. In addition, the interruption unit can actively interrupt when the conversation is stagnating. For example, the interruption unit actively interrupts when the conversation is stagnating. As a result, the conversation progresses naturally by analyzing the flow of the conversation and selecting the optimal interruption method. A part or all of the above-mentioned processing in the interruption unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the interruption unit can input conversation flow data to the generation AI and cause the generation AI to select the interruption method.

[0047] The interrupt unit can interrupt by considering attribute information of the participants in the conversation at the time of interruption. The interrupt unit considers attribute information such as age, sex, and occupation of the participants in the conversation. For example, the interrupt unit considers attribute information such as age, sex, and occupation of the participants in the conversation. In addition, the interrupt unit can interrupt at an appropriate timing when there are many participants in the conversation. For example, the interrupt unit interrupts at an appropriate timing when there are many participants in the conversation. In addition, the interrupt unit can actively interrupt when there are few participants in the conversation. For example, the interrupt unit actively interrupts when there are few participants in the conversation. This enables more appropriate interruption by considering the attribute information of the participants in the conversation. Part or all of the above-mentioned processing in the interrupt unit may be performed, for example, using AI, or may be performed without using AI. For example, the interrupt unit can input attribute data of the participants in the conversation to the generation AI and cause the generation AI to execute the interrupt.

[0048] The interruption unit can interrupt in consideration of the geographical distribution of the conversation when interrupting. For example, when the conversation is related to a specific region, the interruption unit provides information about the region. For example, when the conversation is related to a specific region, the interruption unit provides information about the region. In addition, when the conversation is related to a wide region, the interruption unit can also provide related information. For example, when the conversation is related to a wide region, the interruption unit provides related information. Furthermore, the interruption unit can select an appropriate interruption method based on the geographical distribution of the conversation. For example, the interruption unit selects an appropriate interruption method based on the geographical distribution of the conversation. This makes it possible to interrupt more appropriately by taking the geographical distribution of the conversation into consideration. Part or all of the above-mentioned processing in the interruption unit may be performed, for example, using AI, or may be performed without using AI. For example, the interruption unit can input geographical distribution data of the conversation to the generation AI and cause the generation AI to execute the interruption.

[0049] The interruption unit can improve the accuracy of interruption by referring to the literature related to the conversation at the time of interruption. The interruption unit, for example, refers to the literature related to the conversation and provides appropriate information. For example, the interruption unit refers to the literature related to the conversation and provides appropriate information. The interruption unit can also select an appropriate interruption method based on the literature related to the conversation. For example, the interruption unit selects an appropriate interruption method based on the literature related to the conversation. Furthermore, the interruption unit can also improve the accuracy of interruption by referring to the literature related to the conversation. For example, the interruption unit improves the accuracy of interruption by referring to the literature related to the conversation. As a result, the accuracy of interruption can be improved by referring to the literature related to the conversation. A part or all of the above-mentioned processing in the interruption unit may be performed, for example, using AI, or may be performed without using AI. For example, the interruption unit can input the literature data related to the conversation to the generation AI and cause the generation AI to execute the interruption.

[0050] The topic presentation unit can select a topic presentation method by analyzing the user's past conversation history when presenting a topic. The topic presentation unit, for example, provides related topics based on the user's past conversation history. For example, the topic presentation unit provides related topics based on the user's past conversation history. The topic presentation unit can also provide topics related to fields of interest from the user's past conversation history. For example, the topic presentation unit provides topics related to fields of interest from the user's past conversation history. Furthermore, the topic presentation unit can analyze the user's past conversation history and select an optimal topic presentation method. For example, the topic presentation unit analyzes the user's past conversation history and selects an optimal topic presentation method. As a result, more appropriate topic presentation is possible by analyzing the past conversation history. A part or all of the above-mentioned processing in the topic presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the topic presentation unit can input the user's conversation history data to the generation AI and cause the generation AI to select a topic presentation method.

[0051] The joke presentation unit can customize the means of presenting the joke based on the user's current living situation when presenting the joke. The joke presentation unit, for example, provides a relevant joke according to the user's current living situation. For example, the joke presentation unit provides a relevant joke according to the user's current living situation. The joke presentation unit can also select an appropriate joke presentation method based on the user's living situation. For example, the joke presentation unit selects an appropriate joke presentation method based on the user's living situation. Furthermore, the joke presentation unit can also customize the means of presenting the joke in consideration of the user's current living situation. For example, the joke presentation unit customizes the means of presenting the joke in consideration of the user's current living situation. This makes it possible to present the joke more appropriately by customizing the means of presenting the joke based on the current living situation. A part or all of the above-mentioned processing in the joke presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the joke presentation unit can input the user's living situation data to the generation AI and cause the generation AI to execute customization of the means of presenting the joke.

[0052] The joke input unit can select a joke input method based on the geographical distribution of the conversation when inputting a joke. For example, when the conversation is related to a specific region, the joke input unit provides a joke related to the region. For example, when the conversation is related to a specific region, the joke input unit provides a joke related to the region. In addition, when the conversation is related to a wide region, the joke input unit can also provide a related joke. For example, when the conversation is related to a wide region, the joke input unit provides a related joke. In addition, the joke input unit can also select an appropriate joke input method based on the geographical distribution of the conversation. For example, the joke input unit selects an appropriate joke input method based on the geographical distribution of the conversation. This makes it possible to input a more appropriate joke by taking into account the geographical distribution of the conversation. A part or all of the above-mentioned processing in the joke input unit may be performed, for example, using AI, or may be performed without using AI. For example, the joke input unit can input the geographical distribution data of the conversation to the generation AI and cause the generation AI to select a joke input method.

[0053] The topic presentation unit can improve the accuracy of topic presentation by referring to the literature related to the conversation when presenting a topic. The topic presentation unit, for example, refers to the literature related to the conversation and provides an appropriate topic. For example, the topic presentation unit refers to the literature related to the conversation and provides an appropriate topic. The topic presentation unit can also select an appropriate topic presentation method based on the literature related to the conversation. For example, the topic presentation unit selects an appropriate topic presentation method based on the literature related to the conversation. Furthermore, the topic presentation unit can also improve the accuracy of topic presentation by referring to the literature related to the conversation. For example, the topic presentation unit improves the accuracy of topic presentation by referring to the literature related to the conversation. As a result, the accuracy of topic presentation can be improved by referring to the literature related to the conversation. A part or all of the above-mentioned processing in the topic presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the topic presentation unit can input the literature data related to the conversation to the generation AI and cause the generation AI to execute topic presentation.

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

[0055] The analysis unit can analyze not only the content of the conversation, but also the speed of the conversation and the length of the pauses. For example, if the conversation is fast, the analysis unit can set up a topic that matches that speed. Also, if there are long pauses in the conversation, the analysis unit can provide a topic to fill the gap. Furthermore, if the speed of the conversation changes, the analysis unit can set up a topic that matches the change. This makes it possible to set up an appropriate topic according to the speed and pauses of the conversation.

[0056] The topic-initiating unit can analyze the user's past conversation history and reuse topics that have been successful in the past. For example, if the conversation was lively on the topic of sports in the past, the topic of sports can be brought up again. It can also avoid topic-initiating that has failed in the past. Furthermore, it can grasp the changes in the user's interests from the past conversation history and initiate topics based on the user's latest interests. This makes it possible to more effectively initiate topics by utilizing the past conversation history.

[0057] The interruption unit can take into account attribute information of the participants in the conversation and select an appropriate interruption method for a specific attribute. For example, if there are many young participants, casual topics can be provided. Also, in a business setting, formal topics can be provided. Furthermore, interesting topics can be provided depending on the gender and occupation of the participants. This makes it possible to interrupt appropriately according to the attributes of the participants.

[0058] The collection unit can collect region-specific topics based on the user's geographical location information. For example, if the user is in a specific region, topics related to that region can be provided. Also, if the user is traveling, topics related to the travel destination can be provided. Furthermore, based on the user's geographical location information, local events and news can be collected and provided as topics. In this way, by utilizing the geographical location information, more relevant topics can be provided.

[0059] The collection unit can analyze the user's social media activity and collect information on areas of interest. For example, it can provide related topics based on themes that the user frequently posts about. It can also provide common topics taking into account the user's friendships. It can also analyze the frequency of the user's social media activity and select an appropriate information collection method. This makes it possible to collect more relevant information by utilizing social media activities.

[0060] The analysis unit can apply different analysis algorithms depending on the category of the conversation. For example, in the case of a business conversation, a natural language processing algorithm specialized for business can be applied. In addition, in the case of a conversation related to entertainment, a machine learning algorithm specialized for entertainment can be applied. Furthermore, in the case of a private conversation, an analysis algorithm that takes privacy into consideration can be applied. This makes it possible to perform appropriate analysis according to the category of the conversation.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The collection unit collects profile information of service registrants. The profile information of service registrants includes name, age, hobbies, occupation, etc. The collection unit collects the profile information using questionnaires and social media analysis. For example, the content of social media posts is analyzed to understand the hobbies and interests of the registrants. Step 2: The analysis unit analyzes the information collected by the collection unit. The analysis unit analyzes the profile information using data mining technology and natural language processing technology to extract the interests and concerns of the registrant. Step 3: The interruption unit interrupts the conversation at the appropriate time based on the information analyzed by the analysis unit. The interruption unit determines the timing based on the length of the pause in the conversation or the appearance of specific keywords, and interrupts with a voice or text message. For example, when there is a long pause in the conversation, the interruption unit interrupts with a voice message saying, "I'm sure you're also interested in this topic, Mr. / Ms. XX." Step 4: The joke suggester suggests a joke based on the conversation interrupted by the interruption unit. The joke suggester suggests a joke based on topics related to the registrant's hobbies or the latest news. For example, if the registrant likes sports, the joke suggester suggests a joke such as "What do you think about the recent games?"

[0063] (Example 2) The conversation support system according to the embodiment of the present invention is a system in which an AI listens to the surrounding conversation at a drinking party or the like based on the profile information of the service registrant in advance, interrupts the conversation at an appropriate timing, and sets up a topic that makes it easy for the registrant to talk. This conversation support system collects the profile information of the service registrant, and the AI ​​analyzes the surrounding conversation in real time at a drinking party or the like, and interrupts the conversation at an appropriate timing, making it easy for the registrant to talk. For example, the profile information of the service registrant is collected in advance. At this time, detailed information such as the registrant's hobbies, interests, and past experiences is collected. For example, if the registrant likes sports, that information is collected. This information is input to the AI. Next, the AI ​​analyzes the surrounding conversation in real time at a drinking party or the like. The AI ​​listens to and analyzes the surrounding conversation to understand the content and tone of the conversation. For example, if the surrounding conversation is about sports, the AI ​​analyzes that information. Finally, the AI ​​interrupts the conversation at an appropriate timing. The AI ​​understands the flow of the surrounding conversation and interrupts the conversation at an appropriate timing, making it easy for the registrant to participate in the conversation. For example, when the topic of sports comes up, the AI ​​will suggest something like, "You like sports too, don't you?" This system allows registered users to participate in conversations in a natural way, making communication smoother at events such as drinking parties. For example, even if a registered user meets someone for the first time, it will be easier to find common topics and have a lively conversation. In addition, the AI ​​can interrupt the conversation at the right time, allowing the conversation to progress smoothly without disrupting the flow of conversation. This allows the conversation support system to interrupt the conversation at the right time and suggest a topic based on the registered user's profile information.

[0064] The conversation support system according to the embodiment includes a collection unit, an analysis unit, an interruption unit, and a topic proposal unit. The collection unit collects profile information of service registrants. The profile information of the service registrants includes, for example, name, age, hobbies, and occupation, but is not limited to such examples. The collection unit collects the profile information using, for example, a questionnaire. The collection unit can also collect the profile information using social media analysis. For example, the collection unit analyzes the content of posts on social media to grasp the hobbies and interests of the registrants. The analysis unit analyzes the information collected by the collection unit. The analysis unit analyzes the profile information using, for example, data mining technology. The analysis unit can also analyze the profile information using natural language processing technology. For example, the analysis unit analyzes the collected text data to extract the interests and concerns of the registrants. The interruption unit interrupts the conversation at an appropriate timing based on the information analyzed by the analysis unit. The interruption unit determines the timing based on, for example, the length of the conversation or the appearance of a specific keyword. The interruption unit can also interrupt by voice or text message. For example, when a pause in a conversation becomes long, the interruption unit interrupts by saying, "You're also interested in this topic, aren't you?" The topic prompting unit prompts a topic based on the conversation interrupted by the interruption unit. The topic prompting unit provides topics related to the hobbies of the registered user, for example. The topic prompting unit can also prompt a topic based on the latest news. For example, if the registered user likes sports, the topic prompting unit prompts a question such as "What do you think about the recent game?" This allows the conversation support system according to the embodiment to interrupt a conversation at an appropriate time and prompt a topic based on the profile information of the registered user.

[0065] The collection unit collects profile information of the service registrant. The profile information of the service registrant includes, for example, name, age, hobbies, occupation, etc., but is not limited to such examples. The collection unit collects the profile information using, for example, a questionnaire. The questionnaire is provided in the form of an online form or a question in an app, and is collected by the registrant entering his / her information. The collection unit can also collect the profile information using social media analysis. For example, the collection unit analyzes the content of posts on social media to understand the hobbies and interests of the registrant. Specifically, the API of the social media is used to collect the post content and reactions such as "likes", and the collected information is analyzed using text mining technology. This makes it possible to extract keywords and hashtags frequently mentioned by the registrant and identify the hobbies and interests. Furthermore, the collection unit also collects information on groups in which the registrant participates and accounts followed by the registrant, and can obtain more detailed profile information. This allows the collection unit to collect comprehensive profile information from various information sources and improve the accuracy and effectiveness of the entire system.

[0066] The analysis unit analyzes the information collected by the collection unit. The analysis unit analyzes the profile information using, for example, data mining technology. Data mining technology is a method for extracting useful patterns and relationships from a large amount of data, and is useful for identifying interests and concerns from the profile information of a registrant. The analysis unit can also analyze the profile information using natural language processing technology. Natural language processing technology is a technology for analyzing text data and understanding meanings and emotions, and analyzes the collected text data to extract the interests and concerns of the registrant. For example, the analysis unit tokenizes the collected text data and analyzes the frequency of occurrence and co-occurrence of each token to identify topics in which the registrant is interested. Furthermore, the analysis unit can predict the behavioral patterns and preferences of the registrant from the collected data using a machine learning algorithm. This allows the analysis unit to analyze the collected information from multiple angles and grasp the profile information of the registrant in detail.

[0067] The interruption unit interrupts the conversation at an appropriate timing based on the information analyzed by the analysis unit. The interruption unit determines the timing based on, for example, the length of the gap in the conversation or the appearance of a specific keyword. Specifically, the interruption unit interrupts when the gap in the conversation continues for a certain period of time or when a specific keyword appears. The interruption unit can also interrupt by voice or text message. For example, when the gap in the conversation becomes long, the interruption unit interrupts by voice saying, "X-san, you're also interested in this topic, aren't you?" Furthermore, the interruption unit can use natural language processing technology to understand the context of the conversation and interrupt at an appropriate timing. This allows the interruption unit to interrupt at an appropriate timing while maintaining a smooth flow of the conversation.

[0068] The topic prompting unit prompts a topic based on the conversation interrupted by the interruption unit. The topic prompting unit, for example, provides a topic related to the hobbies of the registered user. Specifically, the topic prompting unit provides a related topic based on the hobbies and interests of the registered user identified by the analysis unit. The topic prompting unit can also prompt a topic based on the latest news. For example, if the registered user likes sports, the topic prompting unit prompts a topic such as "What do you think about the recent game?" Furthermore, the topic prompting unit can use natural language processing technology to understand the flow and context of the conversation and prompt a topic at an appropriate time. This allows the topic prompting unit to provide an appropriate topic while maintaining a smooth flow of the conversation.

[0069] The analysis unit can analyze the tone or keywords of the surrounding conversation. The analysis unit, for example, uses a voice analysis technology to analyze the tone of the surrounding conversation. For example, the analysis unit analyzes the pitch of the voice and the strength of the emotion to grasp the tone of the conversation. The analysis unit can also analyze the keywords of the surrounding conversation using a natural language processing technology. For example, the analysis unit extracts frequently occurring words or words with high importance to grasp the keywords of the conversation. By analyzing the tone and keywords of the surrounding conversation, it is possible to interrupt the conversation at an appropriate timing. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can input the voice data of the surrounding conversation to the generation AI and cause the generation AI to execute the analysis of the tone and keywords.

[0070] The topic suggestion unit can generate the content of the topic suggestion based on the profile information of the registrant. The topic suggestion unit generates, for example, a topic related to the hobby of the registrant. For example, if the registrant likes sports, the topic suggestion unit provides a topic related to sports. The topic suggestion unit can also generate the content of the topic suggestion based on the latest news. For example, the topic suggestion unit analyzes recent news and provides a topic that the registrant is likely to be interested in. As a result, the content of the topic suggestion is generated based on the profile information of the registrant, so that the conversation progresses smoothly. A part or all of the above-mentioned processing in the topic suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the topic suggestion unit can input the profile information of the registrant to the generation AI and cause the generation AI to generate the content of the topic suggestion.

[0071] The interruption unit can grasp the flow of the conversation and interrupt the conversation at an appropriate timing. The interruption unit, for example, analyzes the transition of the topic of the conversation and grasps the flow of the conversation. For example, the interruption unit analyzes the timing of the change of the topic of the conversation and interrupts at an appropriate timing. The interruption unit can also analyze the change of speaker and grasp the flow of the conversation. For example, the interruption unit analyzes the timing of the change of speaker and interrupts at an appropriate timing. As a result, the conversation progresses naturally by grasping the flow of the conversation and interrupting the conversation at an appropriate timing. A part or all of the above-mentioned processing in the interruption unit may be performed, for example, using AI or may be performed without using AI. For example, the interruption unit can input the transition data of the topic of the conversation to the generation AI and cause the generation AI to grasp the flow of the conversation.

[0072] The collection unit can collect information such as the hobbies, interests, and past experiences of the registrant. The collection unit, for example, uses a questionnaire to collect information such as the hobbies, interests, and past experiences of the registrant. For example, the collection unit asks the registrant questions about their hobbies and interests and collects their answers. The collection unit can also collect information such as the hobbies, interests, and past experiences of the registrant using social media analysis. For example, the collection unit analyzes the content of social media posts to understand the hobbies, interests, and past experiences of the registrant. This allows for more appropriate plot development by collecting detailed profile information. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input social media posting data to the generation AI and cause the generation AI to perform an analysis of the hobbies, interests, and past experiences.

[0073] The collection unit can estimate the user's emotion and adjust the information collection timing based on the estimated user's emotion. The collection unit estimates the user's emotion using, for example, a voice analysis technique. For example, the collection unit analyzes the tone and speed of the user's voice to estimate the emotion. The collection unit can also estimate the user's emotion using a facial expression analysis technique. For example, the collection unit analyzes changes in the user's facial expression to estimate the emotion. The collection unit adjusts the information collection timing based on the estimated user's emotion. For example, when the user is relaxed, a long interview format is adopted to collect detailed profile information. Also, when the user is busy, a concise question format can be adopted to collect necessary information in a short time. Furthermore, when the user is stressed, the collection timing can be changed to a later date so that the user can provide information in a relaxed state. This allows more appropriate information collection by adjusting the collection timing according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input the user's voice data to the generation AI and cause the generation AI to estimate emotions.

[0074] The collection unit can analyze the user's past profile information and select a collection method. The collection unit, for example, analyzes past questionnaire results and asks detailed questions to collect deeper information. For example, the collection unit asks related questions based on information provided by the user in the past. The collection unit can also analyze social media history and select questions in a format that is easy for the user to answer. For example, the collection unit analyzes the user's past answer patterns and selects questions in a format that is easy for the user to answer. Furthermore, the collection unit can avoid duplicate questions from the past profile information and efficiently collect information. For example, the collection unit avoids duplicate questions and efficiently collects information based on the user's past profile information. This makes it possible to efficiently collect information by analyzing the past profile information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input past questionnaire data to the generation AI and cause the generation AI to select a collection method.

[0075] The collection unit can perform filtering based on the user's current living situation and field of interest when collecting profile information. For example, the collection unit prioritizes questions related to the field in which the user is currently interested. For example, the collection unit prioritizes questions related to the field in which the user is currently interested. The collection unit can also collect highly relevant information according to the user's living situation. For example, the collection unit collects highly relevant information according to the user's living situation. Furthermore, the collection unit can omit unnecessary questions based on the user's field of interest and efficiently collect information. For example, the collection unit omits unnecessary questions based on the user's field of interest and efficiently collects information. This makes it possible to efficiently collect information by filtering information based on the user's living situation and field of interest. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's field of interest data to the generation AI and cause the generation AI to perform filtering.

[0076] The collection unit can estimate the user's emotion and determine the priority of information collection based on the estimated user's emotion. The collection unit estimates the user's emotion using, for example, a voice analysis technique. For example, the collection unit analyzes the tone and speed of the user's voice to estimate the emotion. The collection unit can also estimate the user's emotion using a facial expression analysis technique. For example, the collection unit analyzes changes in the user's facial expression to estimate the emotion. The collection unit determines the priority of information collection based on the estimated user's emotion. For example, when the user is relaxed, detailed information is preferentially collected. Also, when the user is in a hurry, basic information can be preferentially collected. Furthermore, when the user is excited, information related to the field in which the user is interested can be preferentially collected. In this way, by determining the priority of information according to the user's emotion, information can be efficiently collected. The emotion estimation is realized using, for example, an emotion engine or a generation AI using an emotion estimation function. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input the user's voice data to the generation AI and cause the generation AI to estimate emotions.

[0077] When collecting profile information, the collection unit can preferentially collect highly relevant information based on the geographical location information of the user. For example, the collection unit preferentially collects information related to the location where the user is currently located. For example, the collection unit preferentially collects information related to the location where the user is currently located. The collection unit can also collect area-specific information based on the geographical location of the user. For example, the collection unit collects area-specific information based on the geographical location of the user. Furthermore, the collection unit can also collect highly relevant information taking into account the movement history of the user. For example, the collection unit collects highly relevant information taking into account the movement history of the user. As a result, highly relevant information can be efficiently collected by taking into account the geographical location information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location data of the user to the generation AI and cause the generation AI to execute collection of highly relevant information.

[0078] The collection unit can analyze the user's social media activity and collect related information when collecting the profile information. The collection unit, for example, analyzes the user's social media posting content and collects information on the field of interest. For example, the collection unit analyzes the user's social media posting content and collects information on the field of interest. The collection unit can also collect related information taking into account the user's social media friend relationships. For example, the collection unit collects related information taking into account the user's social media friend relationships. Furthermore, the collection unit can analyze the user's social media activity frequency and collect appropriate information. For example, the collection unit analyzes the user's social media activity frequency and collects appropriate information. In this way, related information can be efficiently collected by analyzing social media activity. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's social media data to the generation AI and cause the generation AI to execute collection of related information.

[0079] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. The analysis unit estimates the user's emotion using, for example, a voice analysis technique. For example, the analysis unit analyzes the tone and speed of the user's voice to estimate the emotion. The analysis unit can also estimate the user's emotion using a facial expression analysis technique. For example, the analysis unit analyzes changes in the user's facial expression to estimate the emotion. The analysis unit adjusts the expression method of the analysis based on the estimated user's emotion. For example, when the user is relaxed, a detailed analysis result is provided. Also, when the user is in a hurry, a concise analysis result can be provided. Furthermore, when the user is excited, a visually stimulating analysis result can be provided. In this way, by adjusting the expression method of the analysis according to the user's emotion, a more appropriate analysis result can be provided. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the user's voice data to the generation AI and cause the generation AI to estimate emotions.

[0080] The analysis unit can adjust the details of the analysis based on the importance of the conversation during analysis. The analysis unit, for example, evaluates the importance of the conversation based on the content of the conversation and the roles of the participants. For example, the analysis unit evaluates the importance of the conversation based on the content of the conversation and the roles of the participants. The analysis unit can also perform detailed data analysis based on the importance of the conversation. For example, the analysis unit performs detailed data analysis in the case of an important conversation. Furthermore, the analysis unit can also provide a concise summary in the case of a general conversation. For example, the analysis unit provides a concise summary in the case of a general conversation. This allows the analysis to be performed efficiently by adjusting the level of detail of the analysis based on the importance of the conversation. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input content data of the conversation to the generation AI and cause the generation AI to execute the evaluation of the importance and the adjustment of the level of detail.

[0081] The analysis unit can apply a different analysis algorithm depending on the category of the conversation during analysis. For example, the analysis unit classifies the category of the conversation into business conversation, private conversation, etc. For example, the analysis unit classifies the category of the conversation into business conversation, private conversation, etc. The analysis unit can also apply a natural language processing algorithm depending on the category of the conversation. For example, in the case of a business conversation, the analysis unit applies a natural language processing algorithm specialized for business. Furthermore, the analysis unit can also apply a machine learning algorithm depending on the category of the conversation. For example, in the case of a conversation about entertainment, the analysis unit applies a machine learning algorithm specialized for entertainment. In this way, by applying different analysis algorithms depending on the category of the conversation, more appropriate analysis results can be provided. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conversation category data to the generation AI and cause the generation AI to apply the analysis algorithm.

[0082] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. The analysis unit estimates the user's emotion using, for example, a voice analysis technique. For example, the analysis unit analyzes the tone and speed of the user's voice to estimate the emotion. The analysis unit can also estimate the user's emotion using a facial expression analysis technique. For example, the analysis unit analyzes changes in the user's facial expression to estimate the emotion. The analysis unit adjusts the length of the analysis based on the estimated user's emotion. For example, when the user is relaxed, a detailed analysis is performed. Also, when the user is in a hurry, a brief analysis can be performed. Furthermore, when the user is excited, a visually stimulating analysis can be performed. In this way, by adjusting the length of the analysis according to the user's emotion, a more appropriate analysis result can be provided. The emotion estimation is realized using, for example, an emotion engine or a generation AI using an emotion estimation function. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input a user's voice data into the generation AI and have the generation AI perform emotion estimation.

[0083] The analysis unit can determine the priority of the analysis based on the time when the conversation occurred during the analysis. The analysis unit evaluates the time when the conversation occurred based on, for example, the start time and duration of the conversation. For example, the analysis unit evaluates the time when the conversation occurred based on the start time and duration of the conversation. The analysis unit can also prioritize the analysis of conversations with high importance based on the time when the conversation occurred. For example, the analysis unit prioritizes the analysis of recent conversations. Furthermore, the analysis unit can also postpone past conversations. For example, the analysis unit postpones past conversations. In this way, the analysis can be performed efficiently by determining the priority of the analysis based on the time when the conversation occurred. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data on the time when the conversation occurred to the generation AI and cause the generation AI to execute the determination of the priority.

[0084] The analysis unit can adjust the order of analysis based on the relevance of the conversations during analysis. The analysis unit evaluates the relevance of the conversations based on, for example, the commonality of the conversation topics and the commonality of the participants. For example, the analysis unit evaluates the relevance of the conversations based on the commonality of the conversation topics and the commonality of the participants. The analysis unit can also preferentially analyze highly relevant conversations based on the relevance of the conversations. For example, the analysis unit preferentially analyzes highly relevant conversations. Furthermore, the analysis unit can also postpone conversations with low relevance. For example, the analysis unit postpones conversations with low relevance. As a result, the analysis can be performed efficiently by adjusting the order of analysis based on the relevance of the conversations. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance data of the conversations to the generation AI and cause the generation AI to adjust the order.

[0085] The interrupt unit can estimate the user's emotion and adjust the timing of interruption based on the estimated user's emotion. The interrupt unit estimates the user's emotion using, for example, a voice analysis technique. For example, the interrupt unit analyzes the tone and speed of the user's voice to estimate the emotion. The interrupt unit can also estimate the user's emotion using a facial expression analysis technique. For example, the interrupt unit analyzes changes in the user's facial expression to estimate the emotion. The interrupt unit adjusts the timing of interruption based on the estimated user's emotion. For example, when the user is relaxed, the interruption is performed at a natural timing. Also, when the user is in a hurry, the interruption can be performed quickly. Furthermore, when the user is excited, the interruption can be performed at an appropriate timing. In this way, by adjusting the timing of interruption according to the user's emotion, the conversation can be interrupted at a more appropriate timing. The estimation of emotion is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the interrupt unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the interrupt unit may input the user's voice data to the generation AI and cause the generation AI to estimate the emotion.

[0086] The interruption unit can select an interruption method by analyzing the flow of the conversation at the time of interruption. The interruption unit analyzes the flow of the conversation based on, for example, a change in the topic of the conversation or a change in the speaker. For example, the interruption unit analyzes the flow of the conversation based on a change in the topic of the conversation or a change in the speaker. In addition, the interruption unit can interrupt in a natural flow when the conversation is lively. For example, the interruption unit interrupts in a natural flow when the conversation is lively. In addition, the interruption unit can actively interrupt when the conversation is stagnating. For example, the interruption unit actively interrupts when the conversation is stagnating. As a result, the conversation progresses naturally by analyzing the flow of the conversation and selecting the optimal interruption method. A part or all of the above-mentioned processing in the interruption unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the interruption unit can input conversation flow data to the generation AI and cause the generation AI to select the interruption method.

[0087] The interrupt unit can interrupt by considering attribute information of the participants in the conversation at the time of interruption. The interrupt unit considers attribute information such as age, sex, and occupation of the participants in the conversation. For example, the interrupt unit considers attribute information such as age, sex, and occupation of the participants in the conversation. In addition, the interrupt unit can interrupt at an appropriate timing when there are many participants in the conversation. For example, the interrupt unit interrupts at an appropriate timing when there are many participants in the conversation. In addition, the interrupt unit can actively interrupt when there are few participants in the conversation. For example, the interrupt unit actively interrupts when there are few participants in the conversation. This enables more appropriate interruption by considering the attribute information of the participants in the conversation. Part or all of the above-mentioned processing in the interrupt unit may be performed, for example, using AI, or may be performed without using AI. For example, the interrupt unit can input attribute data of the participants in the conversation to the generation AI and cause the generation AI to execute the interrupt.

[0088] The interrupt unit can estimate the user's emotion and determine the priority of interruption based on the estimated user's emotion. The interrupt unit estimates the user's emotion using, for example, a voice analysis technique. For example, the interrupt unit analyzes the tone and speed of the user's voice to estimate the emotion. The interrupt unit can also estimate the user's emotion using a facial expression analysis technique. For example, the interrupt unit analyzes changes in the user's facial expression to estimate the emotion. The interrupt unit determines the priority of interruption based on the estimated user's emotion. For example, when the user is relaxed, the interruption is performed at a natural timing. Also, when the user is in a hurry, the interruption can be performed quickly. Furthermore, when the user is excited, the interruption can be performed at an appropriate timing. In this way, by determining the priority of interruption according to the user's emotion, it is possible to interrupt the conversation at a more appropriate timing. The estimation of emotion is realized using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the interrupt unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the interrupt unit may input the user's voice data to the generation AI and cause the generation AI to estimate the emotion.

[0089] The interruption unit can interrupt in consideration of the geographical distribution of the conversation when interrupting. For example, when the conversation is related to a specific region, the interruption unit provides information about the region. For example, when the conversation is related to a specific region, the interruption unit provides information about the region. In addition, when the conversation is related to a wide region, the interruption unit can also provide related information. For example, when the conversation is related to a wide region, the interruption unit provides related information. Furthermore, the interruption unit can select an appropriate interruption method based on the geographical distribution of the conversation. For example, the interruption unit selects an appropriate interruption method based on the geographical distribution of the conversation. This makes it possible to interrupt more appropriately by taking the geographical distribution of the conversation into consideration. Part or all of the above-mentioned processing in the interruption unit may be performed, for example, using AI, or may be performed without using AI. For example, the interruption unit can input geographical distribution data of the conversation to the generation AI and cause the generation AI to execute the interruption.

[0090] The interruption unit can improve the accuracy of interruption by referring to the literature related to the conversation at the time of interruption. The interruption unit, for example, refers to the literature related to the conversation and provides appropriate information. For example, the interruption unit refers to the literature related to the conversation and provides appropriate information. The interruption unit can also select an appropriate interruption method based on the literature related to the conversation. For example, the interruption unit selects an appropriate interruption method based on the literature related to the conversation. Furthermore, the interruption unit can also improve the accuracy of interruption by referring to the literature related to the conversation. For example, the interruption unit improves the accuracy of interruption by referring to the literature related to the conversation. As a result, the accuracy of interruption can be improved by referring to the literature related to the conversation. A part or all of the above-mentioned processing in the interruption unit may be performed, for example, using AI, or may be performed without using AI. For example, the interruption unit can input the literature data related to the conversation to the generation AI and cause the generation AI to execute the interruption.

[0091] The joke presentation unit can estimate the user's emotions and adjust the content of the joke presentation based on the estimated user's emotions. The joke presentation unit estimates the user's emotions using, for example, a voice analysis technique. For example, the joke presentation unit analyzes the tone and speed of the user's voice to estimate the emotions. The joke presentation unit can also estimate the user's emotions using a facial expression analysis technique. For example, the joke presentation unit analyzes changes in the user's facial expressions to estimate the emotions. The joke presentation unit adjusts the content of the joke presentation based on the estimated user's emotions. For example, when the user is relaxed, a detailed joke presentation is made. Also, when the user is in a hurry, a concise joke presentation can be made. Furthermore, when the user is excited, a visually stimulating joke presentation can be made. This allows for more appropriate joke presentation by adjusting the content of the joke presentation according to the user's emotions. The emotion estimation is realized using, for example, an emotion engine or a generation AI, or the like, using an emotion estimation function. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the joke presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the joke presentation unit may input the user's voice data to the generation AI and cause the generation AI to estimate the emotion.

[0092] The topic presentation unit can select a topic presentation method by analyzing the user's past conversation history when presenting a topic. The topic presentation unit, for example, provides related topics based on the user's past conversation history. For example, the topic presentation unit provides related topics based on the user's past conversation history. The topic presentation unit can also provide topics related to fields of interest from the user's past conversation history. For example, the topic presentation unit provides topics related to fields of interest from the user's past conversation history. Furthermore, the topic presentation unit can analyze the user's past conversation history and select an optimal topic presentation method. For example, the topic presentation unit analyzes the user's past conversation history and selects an optimal topic presentation method. As a result, more appropriate topic presentation is possible by analyzing the past conversation history. A part or all of the above-mentioned processing in the topic presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the topic presentation unit can input the user's conversation history data to the generation AI and cause the generation AI to select a topic presentation method.

[0093] The joke presentation unit can customize the means of presenting the joke based on the user's current living situation when presenting the joke. The joke presentation unit, for example, provides a relevant joke according to the user's current living situation. For example, the joke presentation unit provides a relevant joke according to the user's current living situation. The joke presentation unit can also select an appropriate joke presentation method based on the user's living situation. For example, the joke presentation unit selects an appropriate joke presentation method based on the user's living situation. Furthermore, the joke presentation unit can also customize the means of presenting the joke in consideration of the user's current living situation. For example, the joke presentation unit customizes the means of presenting the joke in consideration of the user's current living situation. This makes it possible to present the joke more appropriately by customizing the means of presenting the joke based on the current living situation. A part or all of the above-mentioned processing in the joke presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the joke presentation unit can input the user's living situation data to the generation AI and cause the generation AI to execute customization of the means of presenting the joke.

[0094] The joke presentation unit can estimate the user's emotions and determine the priority of joke presentation based on the estimated user's emotions. The joke presentation unit estimates the user's emotions using, for example, a voice analysis technique. For example, the joke presentation unit analyzes the tone and speed of the user's voice to estimate the emotions. The joke presentation unit can also estimate the user's emotions using facial expression analysis technique. For example, the joke presentation unit analyzes changes in the user's facial expressions to estimate the emotions. The joke presentation unit determines the priority of joke presentation based on the estimated user's emotions. For example, when the user is relaxed, detailed joke presentation is given priority. Also, when the user is in a hurry, concise joke presentation can be given priority. Furthermore, when the user is excited, visually stimulating joke presentation can be given priority. This allows more appropriate joke presentation by determining the priority of joke presentation according to the user's emotions. The emotion estimation is realized using, for example, an emotion engine or a generation AI, or the like, using an emotion estimation function. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the joke presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the joke presentation unit may input the user's voice data to the generation AI and cause the generation AI to estimate the emotion.

[0095] The joke input unit can select a joke input method based on the geographical distribution of the conversation when inputting a joke. For example, when the conversation is related to a specific region, the joke input unit provides a joke related to the region. For example, when the conversation is related to a specific region, the joke input unit provides a joke related to the region. In addition, when the conversation is related to a wide region, the joke input unit can also provide a related joke. For example, when the conversation is related to a wide region, the joke input unit provides a related joke. In addition, the joke input unit can also select an appropriate joke input method based on the geographical distribution of the conversation. For example, the joke input unit selects an appropriate joke input method based on the geographical distribution of the conversation. This makes it possible to input a more appropriate joke by taking into account the geographical distribution of the conversation. A part or all of the above-mentioned processing in the joke input unit may be performed, for example, using AI, or may be performed without using AI. For example, the joke input unit can input the geographical distribution data of the conversation to the generation AI and cause the generation AI to select a joke input method.

[0096] The topic presentation unit can improve the accuracy of topic presentation by referring to the literature related to the conversation when presenting a topic. The topic presentation unit, for example, refers to the literature related to the conversation and provides an appropriate topic. For example, the topic presentation unit refers to the literature related to the conversation and provides an appropriate topic. The topic presentation unit can also select an appropriate topic presentation method based on the literature related to the conversation. For example, the topic presentation unit selects an appropriate topic presentation method based on the literature related to the conversation. Furthermore, the topic presentation unit can also improve the accuracy of topic presentation by referring to the literature related to the conversation. For example, the topic presentation unit improves the accuracy of topic presentation by referring to the literature related to the conversation. As a result, the accuracy of topic presentation can be improved by referring to the literature related to the conversation. A part or all of the above-mentioned processing in the topic presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the topic presentation unit can input the literature data related to the conversation to the generation AI and cause the generation AI to execute topic presentation.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The conversation support system may further include an emotion analysis unit that analyzes the tone and speed of the user's voice and estimates the user's emotions. For example, the emotion analysis unit may provide a topic to relax the user if the user is nervous. Also, if the user is excited, it may provide a topic to maintain the user's excitement. Furthermore, if the user is sad, it may provide a topic to comfort the user. In this way, the conversation can proceed more smoothly by providing an appropriate topic according to the user's emotions.

[0099] The analysis unit can analyze not only the content of the conversation, but also the speed of the conversation and the length of the pauses. For example, if the conversation is fast, the analysis unit can set up a topic that matches that speed. Also, if there are long pauses in the conversation, the analysis unit can provide a topic to fill the gap. Furthermore, if the speed of the conversation changes, the analysis unit can set up a topic that matches the change. This makes it possible to set up an appropriate topic according to the speed and pauses of the conversation.

[0100] The topic-initiating unit can analyze the user's past conversation history and reuse topics that have been successful in the past. For example, if the conversation was lively on the topic of sports in the past, the topic of sports can be brought up again. It can also avoid topic-initiating that has failed in the past. Furthermore, it can grasp the changes in the user's interests from the past conversation history and initiate topics based on the user's latest interests. This makes it possible to more effectively initiate topics by utilizing the past conversation history.

[0101] The interruption unit can take into account attribute information of the participants in the conversation and select an appropriate interruption method for a specific attribute. For example, if there are many young participants, casual topics can be provided. Also, in a business setting, formal topics can be provided. Furthermore, interesting topics can be provided depending on the gender and occupation of the participants. This makes it possible to interrupt appropriately according to the attributes of the participants.

[0102] The collection unit can collect region-specific topics based on the user's geographical location information. For example, if the user is in a specific region, topics related to that region can be provided. Also, if the user is traveling, topics related to the travel destination can be provided. Furthermore, based on the user's geographical location information, local events and news can be collected and provided as topics. In this way, by utilizing the geographical location information, more relevant topics can be provided.

[0103] The collection unit can estimate the user's emotions and adjust the method of information collection based on the estimated emotions. For example, if the user is relaxed, a detailed questionnaire can be conducted. If the user is busy, a simple question format can be adopted. Furthermore, if the user is stressed, the timing of information collection can be changed to a later date. This makes it possible to collect appropriate information according to the user's emotions.

[0104] The collection unit can analyze the user's social media activity and collect information on areas of interest. For example, it can provide related topics based on themes that the user frequently posts about. It can also provide common topics taking into account the user's friendships. It can also analyze the frequency of the user's social media activity and select an appropriate information collection method. This makes it possible to collect more relevant information by utilizing social media activities.

[0105] The analysis unit can apply different analysis algorithms depending on the category of the conversation. For example, in the case of a business conversation, a natural language processing algorithm specialized for business can be applied. In addition, in the case of a conversation related to entertainment, a machine learning algorithm specialized for entertainment can be applied. Furthermore, in the case of a private conversation, an analysis algorithm that takes privacy into consideration can be applied. This makes it possible to perform appropriate analysis according to the category of the conversation.

[0106] The interruption unit can estimate the user's emotion and adjust the timing of interruption based on the estimated emotion. For example, if the user is relaxed, the interruption unit can interrupt at a natural timing. If the user is in a hurry, the interruption unit can interrupt quickly. Furthermore, if the user is excited, the interruption unit can interrupt at a timing that maintains the excitement. This makes it possible to interrupt appropriately according to the user's emotion.

[0107] The joke presentation unit can estimate the user's emotions and adjust the content of the joke presentation based on the estimated emotions. For example, if the user is relaxed, detailed joke presentation can be performed. If the user is in a hurry, a concise joke presentation can be performed. Furthermore, if the user is excited, a visually stimulating joke presentation can be performed. This makes it possible to present appropriate joke presentation according to the user's emotions.

[0108] The process flow of the second embodiment will be briefly described below.

[0109] Step 1: The collection unit collects profile information of service registrants. The profile information of service registrants includes name, age, hobbies, occupation, etc. The collection unit collects the profile information using questionnaires and social media analysis. For example, the content of social media posts is analyzed to understand the hobbies and interests of the registrants. Step 2: The analysis unit analyzes the information collected by the collection unit. The analysis unit analyzes the profile information using data mining technology and natural language processing technology to extract the interests and concerns of the registrant. Step 3: The interruption unit interrupts the conversation at the appropriate time based on the information analyzed by the analysis unit. The interruption unit determines the timing based on the length of the pause in the conversation or the appearance of specific keywords, and interrupts with a voice or text message. For example, when there is a long pause in the conversation, the interruption unit interrupts with a voice message saying, "I'm sure you're also interested in this topic, Mr. / Ms. XX." Step 4: The joke suggester suggests a joke based on the conversation interrupted by the interruption unit. The joke suggester suggests a joke based on topics related to the registrant's hobbies or the latest news. For example, if the registrant likes sports, the joke suggester suggests a joke such as "What do you think about the recent games?"

[0110] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0111] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0112] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements including the above-mentioned collection unit, analysis unit, interrupt unit, and topic suggestion unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart device 14, and collects profile information through questionnaires and social media analysis. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information using data mining technology and natural language processing technology. The interrupt unit is realized, for example, by the control unit 46A of the smart device 14, and determines timing based on the length of a conversation or the appearance of a specific keyword. The topic suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests a topic based on a topic related to the registrant's hobby or the latest news. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0117] 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.

[0118] 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 the voice according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0120] 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 performed in a secure state.

[0121] Fig. 4 shows an example of 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.

[0122] 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.

[0123] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0125] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0126] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0127] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0128] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements including the above-mentioned collection unit, analysis unit, interrupt unit, and joke suggestion unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart glasses 214, and collects profile information through questionnaires and social media analysis. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information using data mining technology and natural language processing technology. The interrupt unit is realized, for example, by the control unit 46A of the smart glasses 214, and determines timing based on the length of a conversation or the appearance of a specific keyword. The joke suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests a joke based on a topic related to the registrant's hobby or the latest news. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0133] 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.

[0134] 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 the voice according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0136] 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 performed in a secure state.

[0137] 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.

[0138] 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.

[0139] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0140] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[0141] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0142] 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 voice indicating a user input for 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.

[0143] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0144] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements including the above-mentioned collection unit, analysis unit, interrupt unit, and joke suggestion unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the headset type terminal 314, and collects profile information through questionnaires and social media analysis. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information using data mining technology and natural language processing technology. The interrupt unit is realized, for example, by the control unit 46A of the headset type terminal 314, and determines timing based on the length of a conversation or the appearance of a specific keyword. The joke suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests a joke based on topics related to the registrant's hobbies or the latest news. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0149] 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.

[0150] 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 the voice according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0152] 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 performed in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0154] 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.

[0155] 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.

[0156] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0158] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] 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 a voice indicating a user input for 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.

[0160] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0162] Each of the multiple elements including the above-mentioned collection unit, analysis unit, interrupt unit, and topic suggestion unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the robot 414, and collects profile information through questionnaires and social media analysis. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected information using data mining technology and natural language processing technology. The interrupt unit is realized, for example, by the control unit 46A of the robot 414, and determines timing based on the length of a conversation interval or the appearance of a specific keyword. The topic suggestion unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and suggests a topic based on a topic related to the registrant's hobby or the latest news. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0164] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0166] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0167] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0168] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0170] 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.

[0171] 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 Universal Serial Bus (USB) 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.

[0172] In addition, 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 upon request from the data processing device 12.

[0173] 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.

[0174] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0175] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0176] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0177] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0179] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0181] (Appendix 1) A collection unit that collects profile information of service registrants; an analysis unit that analyzes the information collected by the collection unit; an interruption unit that interrupts the conversation at a timing based on the information analyzed by the analysis unit; a unit for presenting a joke based on the conversation interrupted by the interrupt unit, A system characterized by: (Appendix 2) The analysis unit is Analyze the tone or keywords of surrounding conversations 2. The system of claim 1, (Appendix 3) The material presentation unit is Generate content for the joke based on the subscriber's profile information 2. The system of claim 1, (Appendix 4) The interrupt unit is Understand the flow of conversation and jump in at the right time 2. The system of claim 1, (Appendix 5) The collecting unit includes: Collect information about your hobbies, interests, past experiences, etc. 2. The system of claim 1, (Appendix 6) The collecting unit includes: To estimate a user's emotions and adjust the timing of information collection based on the estimated user's emotions. 2. The system of claim 1, (Appendix 7) The collecting unit includes: Analyze the user's past profile information and select collection methods 2. The system of claim 1, (Appendix 8) The collecting unit includes: Filtering profile information as it is collected based on the user's current life situation or interests 2. The system of claim 1, (Appendix 9) The collecting unit includes: Estimate user emotions and determine the priority of information collection based on the estimated user emotions 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting profile information, prioritize collecting information that is more relevant based on the user's geographic location 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting profile information, we analyze your social media activity to gather related information 2. The system of claim 1, (Appendix 12) The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1, (Appendix 13) The analysis unit is During analysis, adjust analysis details based on the importance of the conversation 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, different analysis algorithms are applied depending on the category of the conversation. 2. The system of claim 1, (Appendix 15) The analysis unit is Infer user sentiment and adjust the length of the analysis based on the inferred user sentiment 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, prioritize analysis based on when the conversation occurred 2. The system of claim 1, (Appendix 17) The analysis unit is During analysis, adjust the order of analysis based on conversation relevance 2. The system of claim 1, (Appendix 18) The interrupt unit is To estimate a user's emotion and adjust the timing of interruption based on the estimated user's emotion. 2. The system of claim 1, (Appendix 19) The interrupt unit is When interrupting, analyze the flow of the conversation and choose how to interrupt 2. The system of claim 1, (Appendix 20) The interrupt unit is When interrupting, interrupt based on the attribute information of the conversation participants 2. The system of claim 1, (Appendix 21) The interrupt unit is Estimating a user's emotions and determining interrupt priority based on the estimated user's emotions 2. The system of claim 1, (Appendix 22) The interrupt unit is umber (Appendix 23) The interrupt unit is When interrupting, improve the accuracy of interruptions based on relevant literature in the conversation 2. The system of claim 1, (Appendix 24) The material presentation unit is The system estimates the user's emotions and adjusts the content of the joke based on the estimated user emotions. 2. The system of claim 1, (Appendix 25) The material presentation unit is When suggesting a topic, the method of suggesting a topic is selected by analyzing the user's past conversation history. 2. The system of claim 1, (Appendix 26) The material presentation unit is To customize a method of suggesting a topic based on a user's current life situation when suggesting a topic. 2. The system of claim 1, (Appendix 27) The material presentation unit is Estimate the user's emotions and determine the priority of jokes based on the estimated user's emotions. 2. The system of claim 1, (Appendix 28) The material presentation unit is When setting a topic, the method of setting a topic is selected based on the geographic distribution of the conversation. 2. The system of claim 1, (Appendix 29) The material presentation unit is Improve the accuracy of joke-setting based on related literature in conversations 2. The system of claim 1, [Explanation of symbols]

[0182] 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 collection unit that collects profile information of service registrants; an analysis unit that analyzes the information collected by the collection unit; an interruption unit that interrupts the conversation at a timing based on the information analyzed by the analysis unit; a unit for presenting a joke based on the conversation interrupted by the interrupt unit, A system characterized by:

2. The analysis unit is Analyze the tone or keywords of surrounding conversations 2. The system of claim 1 .

3. The material presentation unit is Generate content for the joke based on the subscriber's profile information 2. The system of claim 1 .

4. The interrupt unit is Understand the flow of conversation and jump in at the right time 2. The system of claim 1 .

5. The collecting unit includes: Collect information about your hobbies, interests, past experiences, etc.

2. The system of claim 1 .

6. The collecting unit includes: To estimate a user's emotions and adjust the timing of information collection based on the estimated user's emotions.

2. The system of claim 1 .

7. The collecting unit includes: Analyze the user's past profile information and select collection methods 2. The system of claim 1 .

8. The collecting unit includes: Filtering profile information as it is collected based on the user's current life situation or interests 2. The system of claim 1 .

Images