System

Abstract

An object of the system according to the embodiment is to realistically reproduce a conversation with a person in history designated by a user.SOLUTION: A system according to an embodiment includes an acquisition unit, an analysis unit, a generation unit, a provision unit, and an update unit. The acquisition unit acquires data of a person designated by the user. The analysis unit analyzes the data acquired by the acquisition unit. The generation unit generates a conversation based on the data analyzed by the analysis unit. The providing unit provides the conversation generated by the generating unit to the user. The updating unit updates the conversation data generated by the generating 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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] Conventional techniques have had the problem of making it difficult to realistically reproduce a conversation with a historical figure specified by a user.

[0005] The system according to the embodiment aims to realistically reproduce a conversation between a user and a historical figure designated by the user. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, an analysis unit, a generation unit, a provision unit, and an update unit. The acquisition unit acquires data of a person designated by a user. The analysis unit analyzes the data acquired by the acquisition unit. The generation unit generates a conversation based on the data analyzed by the analysis unit. The provision unit provides the conversation generated by the generation unit to the user. The update unit updates the data of the conversation generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can realistically reproduce a conversation between a user and a historical figure designated by the user. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A conversation system according to an embodiment of the present invention is a system in which a user can pose as a historical figure designated by the user and converse with the figure. This conversation system acquires data about the person designated by the user, uses a generation AI to analyze the data, and generates a conversation that reproduces the designated figure's tone of voice and knowledge, providing the conversation to the user. For example, a user can designate a historical figure with whom they would like to converse, and the generation AI generates a conversation based on that person's data. The generated conversation is provided in a dialogue format with the user. This allows the user to experience a conversation that feels as if they are conversing directly with the historical figure. Furthermore, the generation AI constantly updates its data, enabling conversations based on the latest research findings and new historical facts. This allows the conversation system to pose as a historical figure designated by the user and converse with the figure. For example, users can deepen their historical knowledge through conversations with historical figures. The system is also expected to be useful in the fields of education and entertainment. For example, using a generation AI to have students converse with historical figures in history classes can enhance learning. Furthermore, users can enjoy conversations with their favorite historical figures as entertainment.

[0029] A conversation system according to an embodiment includes an acquisition unit, an analysis unit, a generation unit, a provision unit, and an update unit. The acquisition unit acquires data of a person designated by a user. For example, the acquisition unit collects data of the designated person based on information input by the user. The analysis unit analyzes the data acquired by the acquisition unit. For example, the analysis unit analyzes the tone of voice and knowledge of the designated person based on the collected data. The generation unit generates a conversation based on the data analyzed by the analysis unit. For example, the generation unit generates a conversation that reproduces the tone of voice and knowledge of the designated person using a generation AI. The provision unit provides the conversation generated by the generation unit to a user. For example, the provision unit provides the generated conversation to the user in an interactive format. The update unit updates the data of the conversation generated by the generation unit. For example, the update unit constantly collects the latest data and updates the learning data of the generation AI. This allows the conversation system according to an embodiment to engage in a conversation while pretending to be the historical person designated by the user.

[0030] The acquisition unit can collect data on a specified person based on information input by a user. The acquisition unit collects data on a specified person based on, for example, a name or keyword input by a user. For example, if a user inputs "Napoleon," the acquisition unit collects data on Napoleon. The acquisition unit can also collect data on a specified person based on an image input by a user. For example, if a user inputs an image of Napoleon, the acquisition unit analyzes the image and collects data on Napoleon. This allows data on a specified person to be collected efficiently. Some or all of the above-described processing in the acquisition unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the acquisition unit can input information input by a user to a generation AI and cause the generation AI to collect data on the specified person.

[0031] The analysis unit can analyze the designated person's tone of voice and knowledge based on the collected data. The analysis unit, for example, analyzes collected text data to analyze the designated person's tone of voice and knowledge. For example, the analysis unit analyzes text data of Napoleon's speeches and letters to extract Napoleon's tone of voice and knowledge. The analysis unit can also analyze collected audio data to analyze the designated person's speaking pattern. For example, the analysis unit analyzes audio data of Napoleon's speeches to extract Napoleon's speaking characteristics. The analysis unit can also analyze collected image data to analyze the designated person's facial expressions and gestures. For example, the analysis unit analyzes a portrait of Napoleon to extract Napoleon's facial expressions and gesture characteristics. This allows the designated person's tone of voice and knowledge to be accurately analyzed. Some or all of the above-mentioned processing in the analysis unit may be performed using or without a generation AI. For example, the analysis unit can input the collected data into the generation AI and have the generation AI analyze the tone of voice and knowledge of a specified person.

[0032] The generation unit can use a generation AI to generate a conversation that reproduces the tone of speech and knowledge of a specified person. The generation unit, for example, uses a generation AI to generate a conversation that reproduces the tone of speech and knowledge of a specified person. For example, the generation unit uses a generation AI (e.g., GPT-3 or BERT) to generate a conversation that reproduces Napoleon's tone of speech and knowledge. The generation unit can also use the generation AI to develop an algorithm for reproducing the tone of speech and knowledge of a specified person. For example, the generation unit develops a specific algorithm for reproducing Napoleon's tone of speech and knowledge and generates a conversation using that algorithm. The generation unit can also use the generation AI to create a dataset for reproducing the tone of speech and knowledge of a specified person. For example, the generation unit creates a dataset of Napoleon's speeches and letters and generates a conversation using that dataset. This makes it possible to generate a conversation that reproduces the tone of speech and knowledge of a specified person. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the data analyzed by the analysis unit into the generation AI and cause the generation AI to generate a conversation that reproduces the tone of voice and knowledge of a specified person.

[0033] The providing unit can provide the generated conversation to the user in an interactive format. The providing unit, for example, provides the generated conversation to the user in an interactive format. For example, the providing unit provides the generated conversation to the user in a chat format. The providing unit can also provide the generated conversation to the user in a voice interactive format. For example, the providing unit provides the generated conversation to the user as audio using speech synthesis technology. The providing unit can also provide the generated conversation to the user in text format. For example, the providing unit sends the generated conversation to the user as a text message. This allows the generated conversation to be provided to the user in an interactive format. Some or all of the above-described processing in the providing unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the generated conversation to the generation AI and cause the generation AI to provide it in an interactive format.

[0034] The update unit can constantly collect the latest data and update the learning data of the generation AI. The update unit, for example, collects the latest news articles and research papers and updates the learning data of the generation AI. For example, the update unit collects newly discovered historical documents and adds the data to the learning data of the generation AI. The update unit can also periodically collect data and update the learning data of the generation AI. For example, the update unit collects the latest data every month and updates the learning data of the generation AI. The update unit can also collect data in real time and update the learning data of the generation AI. For example, the update unit collects the latest information on the Internet in real time and adds the data to the learning data of the generation AI. This allows the learning data of the generation AI to be kept up to date. Some or all of the above-described processing in the update unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the update unit can input the latest collected data into the generation AI and cause the generation AI to update the learning data of the generation AI.

[0035] The acquisition unit can analyze the user's past designation history and select the optimal data acquisition method. For example, the acquisition unit analyzes the data acquisition methods of people previously designated by the user and selects the most efficient method. For example, the acquisition unit selects the optimal acquisition timing based on the data acquisition times of people previously designated by the user. The acquisition unit can also prioritize the use of specific data sources based on the user's past designation history. For example, the acquisition unit prioritizes the use of data sources related to people previously designated by the user. This allows the optimal data acquisition method to be selected based on the user's past designation history. Some or all of the above-described processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's past designation history into the generation AI and cause the generation AI to select the optimal data acquisition method.

[0036] When acquiring data of a specified person, the acquisition unit can filter the data based on the user's current interests and areas of interest. For example, the acquisition unit prioritizes acquiring data related to historical events in which the user is currently interested. For example, the acquisition unit filters the data based on the user's areas of interest (politics, war, culture, etc.). The acquisition unit can also prioritize acquiring related data by referring to the user's current search history. For example, the acquisition unit prioritizes acquiring data related to keywords recently searched by the user. This makes it possible to filter data based on the user's interests and areas of interest. Some or all of the above-mentioned processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's current interests and areas of interest into the generation AI and have the generation AI perform data filtering.

[0037] When acquiring data of a specified person, the acquisition unit can select the optimal acquisition means according to the user's input method. For example, when the user specifies the person by voice, the acquisition unit acquires data using voice recognition technology. For example, when the user specifies "Napoleon" by voice, the acquisition unit acquires data related to Napoleon using voice recognition technology. In addition, when the user specifies the person by text, the acquisition unit can also acquire data using text analysis technology. For example, when the user specifies "Napoleon" by text, the acquisition unit acquires data related to Napoleon using text analysis technology. In addition, when the user specifies the person by image, the acquisition unit can also acquire data using image recognition technology. For example, when the user inputs an image of Napoleon, the acquisition unit acquires data related to Napoleon using image recognition technology. This allows the optimal acquisition means to be selected according to the user's input method. Some or all of the above-described processing in the acquisition unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the acquisition unit can input the user's input method into the generation AI and cause the generation AI to select the optimal acquisition means.

[0038] When acquiring data of a specified person, the acquisition unit can prioritize acquiring highly relevant data by taking into account the user's geographical location information. For example, if the user is in a specific area, the acquisition unit prioritizes acquiring data related to that area. For example, if the user is traveling, the acquisition unit prioritizes acquiring data related to the travel destination. Furthermore, if the user is in a specific historical location, the acquisition unit can prioritize acquiring data related to that location. For example, if the user is in a historical battlefield, the acquisition unit prioritizes acquiring data related to the battlefield. This allows highly relevant data to be acquired preferentially based on the user's geographical location information. Some or all of the above-described processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's geographical location information to the generation AI and cause the generation AI to acquire highly relevant data.

[0039] When acquiring data of a specified person, the acquisition unit can analyze the user's social media activity and acquire related data. For example, the acquisition unit prioritizes acquiring data related to people mentioned by the user on social media. For example, the acquisition unit analyzes the content of the user's social media posts and acquires related data. The acquisition unit can also acquire related data by referring to the activities of the user's friends on social media. For example, the acquisition unit prioritizes acquiring data related to people mentioned by the user's friends. This makes it possible to acquire related data based on the user's social media activity. Some or all of the above-mentioned processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's social media activity into the generation AI and cause the generation AI to acquire related data.

[0040] When acquiring data of a specified person, the acquisition unit can customize the acquisition method by reflecting the user's past feedback. The acquisition unit, for example, optimizes the data acquisition method based on feedback provided by the user in the past. For example, the acquisition unit prioritizes the use of a specific data source based on the user's past feedback. The acquisition unit can also adjust the timing of data acquisition by referring to the user's past feedback. For example, the acquisition unit optimizes the timing of data acquisition based on feedback provided by the user in the past. This allows the acquisition method to be customized based on the user's past feedback. Some or all of the above-mentioned processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's past feedback into the generation AI and cause the generation AI to customize the acquisition method.

[0041] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the designated person. For example, if the designated person is historically important, the analysis unit performs a detailed analysis. For example, the analysis unit performs a detailed analysis on a historically important person such as Napoleon. The analysis unit can also perform a concise analysis if the designated person is not well known. For example, the analysis unit performs a concise analysis on a lesser-known historical figure. The analysis unit can also adjust the depth of the analysis according to the importance of the designated person. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the designated person. This allows the level of detail of the analysis to be adjusted based on the importance of the designated person. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit can input the importance of the designated person to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the specified person. For example, if the specified person is a politician, the analysis unit applies an analysis algorithm based on the political background. For example, the analysis unit applies an analysis algorithm based on the political background to a politician like Napoleon. Furthermore, if the specified person is a scientist, the analysis unit can also apply an analysis algorithm based on scientific knowledge. For example, the analysis unit applies an analysis algorithm based on scientific knowledge to a scientist like Einstein. Furthermore, if the specified person is an artist, the analysis unit can also apply an analysis algorithm based on the artistic background. For example, the analysis unit applies an analysis algorithm based on the artistic background to an artist like Picasso. This allows the optimal analysis algorithm to be applied depending on the category of the specified person. Some or all of the above-described processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit can input the category of the specified person into the generation AI and cause the generation AI to apply different analysis algorithms.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, optimizes the analysis algorithm based on analysis results provided by the user in the past. For example, the analysis unit adjusts the analysis algorithm based on feedback provided by the user in the past. The analysis unit can also preferentially use a specific data source based on the user's past analysis results. For example, the analysis unit selects the optimal data source based on data sources used by the user in the past. The analysis unit can also improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the accuracy of the analysis based on analysis results provided by the user in the past. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0044] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the data of the designated person. For example, if the data of the designated person is new, the analysis unit prioritizes analysis. For example, the analysis unit prioritizes analysis of the most recently submitted data. Furthermore, if the data of the designated person is old, the analysis unit can postpone analysis. For example, the analysis unit analyzes old data later. Furthermore, the analysis unit can also determine the priority of analysis based on the time of submission of the data of the designated person. For example, the analysis unit determines the priority of analysis based on the time of submission. This makes it possible to determine the priority of analysis based on the time of submission of the data of the designated person. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit can input the time of submission of the data of the designated person to the generation AI and have the generation AI determine the priority of analysis.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the designated person. For example, if the designated person is important to the user, the analysis unit performs analysis with priority. For example, the analysis unit performs analysis with priority on people in whom the user is particularly interested. Furthermore, if the designated person is not very relevant, the analysis unit can postpone analysis. For example, the analysis unit postpones analysis of people with low relevance. Furthermore, the analysis unit can adjust the order of analysis based on the relevance of the designated person. For example, the analysis unit adjusts the order of analysis based on the relevance. This makes it possible to adjust the order of analysis based on the relevance of the designated person. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the relevance of the designated person into the generation AI and cause the generation AI to adjust the order of analysis.

[0046] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit provides an analysis that uses a lot of technical terms. For example, the analysis unit performs an analysis that uses a lot of technical terms for a user with technical expertise. The analysis unit can also provide a concise and easy-to-understand analysis if the user does not have technical expertise. For example, the analysis unit performs a concise and easy-to-understand analysis for a user without technical expertise. The analysis unit can also adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit adjusts the use of technical terms based on the user's level of expertise. This allows the use of technical terms in the analysis to be adjusted according to the user's level of expertise. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the user's level of expertise to the generation AI and cause the generation AI to adjust the use of technical terms.

[0047] When generating a conversation, the generation unit can adjust the level of detail of the conversation based on the importance of the designated person. For example, if the designated person is historically important, the generation unit generates detailed conversation. For example, the generation unit generates detailed conversation for a historically important person such as Napoleon. The generation unit can also generate concise conversation if the designated person is not well known. For example, the generation unit generates concise conversation for a little-known historical figure. The generation unit can also adjust the depth of the conversation according to the importance of the designated person. For example, the generation unit adjusts the level of detail of the conversation based on the importance of the designated person. This allows the level of detail of the conversation to be adjusted based on the importance of the designated person. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI or may be performed without using a generation AI. For example, the generation unit can input the importance of the designated person to the generation AI and cause the generation AI to adjust the level of detail of the conversation.

[0048] When generating a conversation, the generation unit can apply different generation algorithms depending on the category of the specified person. For example, if the specified person is a politician, the generation unit applies a generation algorithm based on the political background. For example, the generation unit applies a generation algorithm based on the political background to a politician such as Napoleon. Furthermore, if the specified person is a scientist, the generation unit can apply a generation algorithm based on scientific knowledge. For example, the generation unit applies a generation algorithm based on scientific knowledge to a scientist such as Einstein. Furthermore, if the specified person is an artist, the generation unit can apply a generation algorithm based on the artistic background. For example, the generation unit applies a generation algorithm based on the artistic background to an artist such as Picasso. This allows the optimal generation algorithm to be applied depending on the category of the specified person. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the category of the specified person into the generation AI and cause the generation AI to apply different generation algorithms.

[0049] When generating a conversation, the generation unit can improve the accuracy of the conversation by referring to the user's past conversation results. The generation unit, for example, optimizes the generation algorithm based on conversation results provided by the user in the past. For example, the generation unit adjusts the generation algorithm based on feedback provided by the user in the past. The generation unit can also preferentially use a specific data source based on the user's past conversation results. For example, the generation unit selects an optimal data source based on data sources used by the user in the past. The generation unit can also improve the accuracy of the conversation by referring to the user's past conversation results. For example, the generation unit improves the accuracy of the conversation based on conversation results provided by the user in the past. In this way, the accuracy of the conversation can be improved by referring to the user's past conversation results. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI or may be performed without using a generation AI. For example, the generation unit can input the user's past conversation results into the generation AI and cause the generation AI to improve the accuracy of the conversation.

[0050] When generating a conversation, the generation unit can determine the priority of the conversation based on the time of submission of the data of the specified person. For example, if the data of the specified person is new, the generation unit generates the conversation with priority. For example, the generation unit preferentially reflects the most recently submitted data in the conversation. Furthermore, if the data of the specified person is old, the generation unit can generate the conversation later. For example, the generation unit generates the conversation with older data later. Furthermore, the generation unit can determine the priority of the conversation based on the time of submission of the data of the specified person. For example, the generation unit determines the priority of the conversation based on the time of submission. This makes it possible to determine the priority of the conversation based on the time of submission of the data of the specified person. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the time of submission of the data of the specified person to the generation AI and cause the generation AI to determine the priority of the conversation.

[0051] When generating a conversation, the generation unit can adjust the order of the conversations based on the relevance of the designated person. For example, if the designated person is important to the user, the generation unit generates the conversation with priority. For example, the generation unit generates the conversation with priority for a person in whom the user is particularly interested. Furthermore, if the designated person is not very relevant, the generation unit can generate the conversation later. For example, the generation unit postpones the conversation of a person with low relevance. Furthermore, the generation unit can adjust the order of the conversations based on the relevance of the designated person. For example, the generation unit adjusts the order of the conversations based on the relevance. In this way, the order of the conversations can be adjusted based on the relevance of the designated person. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the relevance of the designated person to the generation AI and cause the generation AI to adjust the order of the conversations.

[0052] When generating a conversation, the generation unit can adjust the use of technical terms in the conversation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates a conversation that uses a lot of technical terms. For example, the generation unit generates a conversation that uses a lot of technical terms for a user with technical expertise. The generation unit can also generate concise and easy-to-understand conversation if the user does not have technical expertise. For example, the generation unit generates concise and easy-to-understand conversation for a user without technical expertise. The generation unit can also adjust the use of technical terms in the conversation according to the user's level of expertise. For example, the generation unit adjusts the use of technical terms based on the user's level of expertise. This makes it possible to adjust the use of technical terms in the conversation according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's level of expertise to the generation AI and cause the generation AI to adjust the use of technical terms.

[0053] When providing a conversation, the providing unit can select the optimal delivery method by referring to the user's past operation history. For example, the providing unit selects the optimal method based on the user's past preferred delivery methods. For example, the providing unit selects the optimal delivery method based on the user's past preferred delivery format (text, audio, etc.). The providing unit can also preferentially use a specific delivery method based on the user's past operation history. For example, the providing unit preferentially uses a delivery method that the user has used frequently in the past. The providing unit can also customize the delivery method by referring to the user's past operation history. For example, the providing unit customizes the delivery method based on the user's past operation history. This makes it possible to select the optimal delivery method based on the user's past operation history. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input the user's past operation history into the generation AI and cause the generation AI to select the optimal delivery method.

[0054] The providing unit can customize the provided content according to the user's current task when providing a conversation. For example, if the user is studying, the providing unit can prioritize providing educational content. For example, if the user is using the device during a history class, the providing unit can prioritize providing educational content. The providing unit can also prioritize providing fun content if the user is seeking entertainment. For example, if the user is using the device while relaxing, the providing unit can prioritize providing fun content. The providing unit can also customize the provided content according to the user's current task. For example, the providing unit customizes the provided content based on the task the user is currently performing. This allows the provided content to be customized according to the user's current task. Some or all of the above-described processing in the providing unit may be performed using a generation AI or may be performed without using a generation AI. For example, the providing unit can input the user's current task to the generation AI and cause the generation AI to customize the provided content.

[0055] When providing a conversation, the providing unit can select the optimal delivery method by taking into account the user's device information. For example, if the user is using a smartphone, the providing unit provides a delivery method tailored to the screen size. For example, the providing unit provides a delivery method optimized for the small screen of a smartphone. Furthermore, if the user is using a tablet, the providing unit can also provide a delivery method optimized for a large screen. For example, the providing unit provides a delivery method optimized for the large screen of a tablet. Furthermore, if the user is using a smartwatch, the providing unit can also provide a delivery method that is concise and highly visible. For example, the providing unit provides a delivery method optimized for the small screen of a smartwatch. This allows the optimal delivery method to be selected based on the user's device information. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit may input the user's device information into the generation AI and cause the generation AI to select the optimal delivery method.

[0056] When providing the conversation, the providing unit can make the provided content multilingual in accordance with the user's language setting. The providing unit, for example, automatically sets the language of the conversation based on the language setting of the user's device. For example, if the user's device is set to English, the providing unit provides the conversation in English. The providing unit can also provide a language switching function when the user uses multiple languages. For example, if the user uses English and Japanese, the providing unit can provide the conversation in that language when the user selects a specific language. For example, if the user selects French, the providing unit provides the conversation in French. This makes it possible to make the provided content multilingual based on the user's language setting. Some or all of the above-described processing in the providing unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the user's language setting into the generation AI and cause the generation AI to provide multilingual support.

[0057] The providing unit can analyze the user's social media activity and provide related information when providing a conversation. For example, the providing unit provides information about people mentioned by the user on social media. For example, if the user mentions Napoleon on social media, the providing unit provides information about Napoleon. The providing unit can also analyze the content of the user's social media posts and provide related information. For example, if the user posts about a historical war on social media, the providing unit provides information about that war. The providing unit can also provide related information by referring to the activities of the user's friends on social media. For example, the providing unit provides information about people mentioned by the user's friends on social media. This makes it possible to provide related information based on the user's social media activity. Some or all of the above-mentioned processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input the user's social media activity into the generation AI and cause the generation AI to provide related information.

[0058] During an update, the update unit can optimize the update algorithm by referring to past update data. The update unit, for example, selects an optimal update algorithm based on past update data. For example, the update unit analyzes past update data and selects an optimal update algorithm. The update unit can also preferentially use a specific data source from the past update data. For example, the update unit preferentially use a specific data source based on past update data. The update unit can also optimize the update algorithm by referring to the past update data. For example, the update unit optimizes the update algorithm based on past update data. This makes it possible to optimize the update algorithm by referring to the past update data. Some or all of the above-described processing in the update unit may be performed using or without using the generation AI. For example, the update unit can input past update data to the generation AI and cause the generation AI to optimize the update algorithm.

[0059] The update unit can update the update data by reflecting user feedback during an update. The update unit, for example, optimizes the update data based on feedback provided by the user. For example, the update unit adjusts the update data based on user feedback. The update unit can also prioritize the use of a specific data source based on user feedback. For example, the update unit prioritizes the use of a specific data source based on user feedback. The update unit can also update the update data by referring to user feedback. For example, the update unit updates the update data based on user feedback. In this way, the update data can be updated by reflecting user feedback. Some or all of the above-described processing in the update unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the update unit can input user feedback to the generation AI and cause the generation AI to update the update data.

[0060] During updating, the update unit can weight the update data based on the time of submission of the data of the designated person. For example, if the data of the designated person is new, the update unit increases the weighting. For example, the update unit increases the weighting for recently submitted data. The update unit can also decrease the weighting for old data if the data of the designated person is old. For example, the update unit decreases the weighting for old data. The update unit can also weight the update data based on the time of submission of the data of the designated person. For example, the update unit weights the update data based on the time of submission. This makes it possible to weight the update data based on the time of submission of the data of the designated person. Some or all of the above-described processing in the update unit may be performed using or without the generation AI. For example, the update unit can input the time of submission of the data of the designated person to the generation AI and cause the generation AI to weight the update data.

[0061] The update unit can integrate information from different data sources to enrich the updated data during an update. The update unit, for example, integrates information from different data sources to enrich the updated data. For example, the update unit integrates information from an external database or an internal database to enrich the updated data. The update unit can also compare information from different data sources to select optimal data. For example, the update unit compares information from multiple data sources to select optimal data. The update unit can also optimize the updated data based on information from different data sources. For example, the update unit optimizes the updated data based on information from different data sources. This allows the information from different data sources to be integrated and enriched. Some or all of the above-described processing in the update unit may be performed using or without the generation AI. For example, the update unit can input information from different data sources to the generation AI and have the generation AI integrate the information.

[0062] The update unit can optimize the update data by reflecting the user's past feedback during updating. The update unit optimizes the update data, for example, based on feedback provided by the user in the past. For example, the update unit adjusts the update data based on the user's past feedback. The update unit can also preferentially use a specific data source based on the user's past feedback. For example, the update unit preferentially use a specific data source based on the user's past feedback. The update unit can also optimize the update data by referring to the user's past feedback. For example, the update unit optimizes the update data based on the user's past feedback. In this way, the update data can be optimized by reflecting the user's past feedback. Some or all of the above-described processing in the update unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the update unit can input the user's past feedback into the generation AI and cause the generation AI to optimize the update data.

[0063] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0064] The acquisition unit can also monitor the user's current activity status and determine the optimal timing for data acquisition. For example, it can delay data acquisition when the user is busy and accelerate data acquisition when the user is relaxed. The acquisition unit can also refer to the user's schedule information and adjust the timing of data acquisition. For example, it can acquire data during meetings or breaks based on the user's calendar information. Furthermore, the acquisition unit can also acquire data taking into account the remaining battery level of the user's device. For example, it can refrain from acquiring data when the battery is low and acquire data while the device is charging. This enables flexible data acquisition according to the user's activity status.

[0065] The analysis unit can also analyze the user's past conversation history to more accurately analyze the designated person's tone of voice and knowledge. For example, it can extract characteristics of the designated person's tone of voice and knowledge based on the content of the user's past conversations. The analysis unit can also customize the analysis results taking into account the user's preferences and interests. For example, if the user is interested in a particular historical event, it can prioritize analysis of knowledge related to that event. Furthermore, the analysis unit can adjust the analysis algorithm based on user feedback. For example, it can improve the accuracy of the analysis results based on feedback provided by the user. This enables flexible analysis that meets the user's needs.

[0066] The acquisition unit can also analyze the user's past search history and select the optimal data acquisition method. For example, it can prioritize acquisition of related data based on keywords that the user has searched for frequently in the past. The acquisition unit can also prioritize the use of specific data sources based on the user's past search history. For example, it can select the optimal data source based on data sources that the user has used frequently in the past. Furthermore, the acquisition unit can adjust the timing of data acquisition based on the user's past search history. For example, if the user has performed many searches during a specific time period in the past, it can acquire data during that time period. This enables flexible data acquisition based on the user's past search history.

[0067] When analyzing data on a specified person, the analysis unit can also integrate information from different data sources to improve the accuracy of the analysis. For example, it can integrate information from books, papers, interview articles, etc. related to the specified person and perform the analysis. The analysis unit can also compare information from different data sources and select the most reliable information. For example, it can compare information from multiple data sources and prioritize the use of matching information. Furthermore, the analysis unit can complement the analysis results based on information from different data sources. For example, it can complement the content of an interview article based on information obtained from a book. This enables flexible analysis that integrates information from different data sources.

[0068] The generation unit can also analyze the user's past conversation history and optimize the conversation generation method. For example, the generation unit can adjust the topic and style of the conversation based on the content of the user's past conversations. The generation unit can also extract specific conversation patterns from the user's past conversation history and generate conversations based on them. For example, the generation unit generates conversations based on conversation patterns that the user has preferred in the past. Furthermore, the generation unit can adjust the length and level of detail of the conversation based on the user's past conversation history. For example, if the user has preferred short conversations in the past, the generation unit generates short conversations. This enables flexible conversation generation based on the user's past conversation history.

[0069] The providing unit can also monitor the user's current device status and select the optimal providing method. For example, if the user is using a smartphone, the providing unit can select a providing method optimized for the screen size, and if the user is using a PC, the providing unit can provide detailed information. The providing unit can also adjust the providing method taking into account the remaining battery level of the user's device. For example, if the battery is low, the information is provided in text format, and if the battery is sufficient, the information is provided using images or videos. The providing unit can also adjust the providing method taking into account the connection status of the user's device. For example, if the Internet connection is unstable, the information is provided in a format that can be viewed offline. This enables flexible information provision according to the user's device status.

[0070] The update unit can also analyze the user's past feedback and optimize the selection of update data. For example, a specific data source can be used preferentially based on feedback provided by the user in the past. The update unit can also adjust the format of the update data based on the user's past feedback. For example, the update unit selects the format of the update data based on the data format (text, image, video, etc.) that the user has preferred in the past. Furthermore, the update unit can adjust the frequency of updates based on the user's past feedback. For example, if the user desires frequent updates, the update frequency can be increased, and if the user desires infrequent updates, the update frequency can be decreased. This enables flexible updates based on the user's past feedback.

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

[0072] Step 1: The acquisition unit acquires data of a person designated by a user. For example, the acquisition unit collects data of the designated person based on information input by a user. Step 2: The analysis unit analyzes the data acquired by the acquisition unit. For example, the analysis unit analyzes the tone of voice and knowledge of the designated person based on the collected data. Step 3: The generator generates a conversation based on the data analyzed by the analyzer. For example, the generator uses a generation AI to generate a conversation that reproduces the tone and knowledge of the specified person. Step 4: The providing unit provides the conversation generated by the generating unit to the user. For example, the providing unit provides the generated conversation to the user in an interactive format. Step 5: The update unit updates the conversation data generated by the generation unit. For example, the update unit constantly collects the latest data and updates the learning data of the generation AI.

[0073] (Example 2) A conversation system according to an embodiment of the present invention is a system in which a user can pose as a historical figure designated by the user and converse with the figure. This conversation system acquires data about the person designated by the user, uses a generation AI to analyze the data, and generates a conversation that reproduces the designated figure's tone of voice and knowledge, providing the conversation to the user. For example, a user can designate a historical figure with whom they would like to converse, and the generation AI generates a conversation based on that person's data. The generated conversation is provided in a dialogue format with the user. This allows the user to experience a conversation that feels as if they are conversing directly with the historical figure. Furthermore, the generation AI constantly updates its data, enabling conversations based on the latest research findings and new historical facts. This allows the conversation system to pose as a historical figure designated by the user and converse with the figure. For example, users can deepen their historical knowledge through conversations with historical figures. The system is also expected to be useful in the fields of education and entertainment. For example, using a generation AI to have students converse with historical figures in history classes can enhance learning. Furthermore, users can enjoy conversations with their favorite historical figures as entertainment.

[0074] A conversation system according to an embodiment includes an acquisition unit, an analysis unit, a generation unit, a provision unit, and an update unit. The acquisition unit acquires data of a person designated by a user. For example, the acquisition unit collects data of the designated person based on information input by the user. The analysis unit analyzes the data acquired by the acquisition unit. For example, the analysis unit analyzes the tone of voice and knowledge of the designated person based on the collected data. The generation unit generates a conversation based on the data analyzed by the analysis unit. For example, the generation unit generates a conversation that reproduces the tone of voice and knowledge of the designated person using a generation AI. The provision unit provides the conversation generated by the generation unit to a user. For example, the provision unit provides the generated conversation to the user in an interactive format. The update unit updates the data of the conversation generated by the generation unit. For example, the update unit constantly collects the latest data and updates the learning data of the generation AI. This allows the conversation system according to an embodiment to engage in a conversation while pretending to be the historical person designated by the user.

[0075] The acquisition unit can collect data on a specified person based on information input by a user. The acquisition unit collects data on a specified person based on, for example, a name or keyword input by a user. For example, if a user inputs "Napoleon," the acquisition unit collects data on Napoleon. The acquisition unit can also collect data on a specified person based on an image input by a user. For example, if a user inputs an image of Napoleon, the acquisition unit analyzes the image and collects data on Napoleon. This allows data on a specified person to be collected efficiently. Some or all of the above-described processing in the acquisition unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the acquisition unit can input information input by a user to a generation AI and cause the generation AI to collect data on the specified person.

[0076] The analysis unit can analyze the designated person's tone of voice and knowledge based on the collected data. The analysis unit, for example, analyzes collected text data to analyze the designated person's tone of voice and knowledge. For example, the analysis unit analyzes text data of Napoleon's speeches and letters to extract Napoleon's tone of voice and knowledge. The analysis unit can also analyze collected audio data to analyze the designated person's speaking pattern. For example, the analysis unit analyzes audio data of Napoleon's speeches to extract Napoleon's speaking characteristics. The analysis unit can also analyze collected image data to analyze the designated person's facial expressions and gestures. For example, the analysis unit analyzes a portrait of Napoleon to extract Napoleon's facial expressions and gesture characteristics. This allows the designated person's tone of voice and knowledge to be accurately analyzed. Some or all of the above-mentioned processing in the analysis unit may be performed using or without a generation AI. For example, the analysis unit can input the collected data into the generation AI and have the generation AI analyze the tone of voice and knowledge of a specified person.

[0077] The generation unit can use a generation AI to generate a conversation that reproduces the tone of speech and knowledge of a specified person. The generation unit, for example, uses a generation AI to generate a conversation that reproduces the tone of speech and knowledge of a specified person. For example, the generation unit uses a generation AI (e.g., GPT-3 or BERT) to generate a conversation that reproduces Napoleon's tone of speech and knowledge. The generation unit can also use the generation AI to develop an algorithm for reproducing the tone of speech and knowledge of a specified person. For example, the generation unit develops a specific algorithm for reproducing Napoleon's tone of speech and knowledge and generates a conversation using that algorithm. The generation unit can also use the generation AI to create a dataset for reproducing the tone of speech and knowledge of a specified person. For example, the generation unit creates a dataset of Napoleon's speeches and letters and generates a conversation using that dataset. This makes it possible to generate a conversation that reproduces the tone of speech and knowledge of a specified person. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the data analyzed by the analysis unit into the generation AI and cause the generation AI to generate a conversation that reproduces the tone of voice and knowledge of a specified person.

[0078] The providing unit can provide the generated conversation to the user in an interactive format. The providing unit, for example, provides the generated conversation to the user in an interactive format. For example, the providing unit provides the generated conversation to the user in a chat format. The providing unit can also provide the generated conversation to the user in a voice interactive format. For example, the providing unit provides the generated conversation to the user as audio using speech synthesis technology. The providing unit can also provide the generated conversation to the user in text format. For example, the providing unit sends the generated conversation to the user as a text message. This allows the generated conversation to be provided to the user in an interactive format. Some or all of the above-described processing in the providing unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the generated conversation to the generation AI and cause the generation AI to provide it in an interactive format.

[0079] The update unit can constantly collect the latest data and update the learning data of the generation AI. The update unit, for example, collects the latest news articles and research papers and updates the learning data of the generation AI. For example, the update unit collects newly discovered historical documents and adds the data to the learning data of the generation AI. The update unit can also periodically collect data and update the learning data of the generation AI. For example, the update unit collects the latest data every month and updates the learning data of the generation AI. The update unit can also collect data in real time and update the learning data of the generation AI. For example, the update unit collects the latest information on the Internet in real time and adds the data to the learning data of the generation AI. This allows the learning data of the generation AI to be kept up to date. Some or all of the above-described processing in the update unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the update unit can input the latest collected data into the generation AI and cause the generation AI to update the learning data of the generation AI.

[0080] The acquisition unit can estimate the user's emotion and adjust the timing of data acquisition for a specified person based on the estimated user's emotion. For example, the acquisition unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the acquisition unit calculates an emotion score based on changes in facial expression and adjusts the data acquisition timing. The acquisition unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the acquisition unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the data acquisition timing. The acquisition unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the acquisition unit calculates an emotion score based on heart rate fluctuations and adjusts the data acquisition timing. This allows the data acquisition timing to be adjusted according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the acquisition unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the acquisition unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0081] The acquisition unit can analyze the user's past designation history and select the optimal data acquisition method. For example, the acquisition unit analyzes the data acquisition methods of people previously designated by the user and selects the most efficient method. For example, the acquisition unit selects the optimal acquisition timing based on the data acquisition times of people previously designated by the user. The acquisition unit can also prioritize the use of specific data sources based on the user's past designation history. For example, the acquisition unit prioritizes the use of data sources related to people previously designated by the user. This allows the optimal data acquisition method to be selected based on the user's past designation history. Some or all of the above-described processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's past designation history into the generation AI and cause the generation AI to select the optimal data acquisition method.

[0082] When acquiring data of a specified person, the acquisition unit can filter the data based on the user's current interests and areas of interest. For example, the acquisition unit prioritizes acquiring data related to historical events in which the user is currently interested. For example, the acquisition unit filters the data based on the user's areas of interest (politics, war, culture, etc.). The acquisition unit can also prioritize acquiring related data by referring to the user's current search history. For example, the acquisition unit prioritizes acquiring data related to keywords recently searched by the user. This makes it possible to filter data based on the user's interests and areas of interest. Some or all of the above-mentioned processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's current interests and areas of interest into the generation AI and have the generation AI perform data filtering.

[0083] When acquiring data of a specified person, the acquisition unit can select the optimal acquisition means according to the user's input method. For example, when the user specifies the person by voice, the acquisition unit acquires data using voice recognition technology. For example, when the user specifies "Napoleon" by voice, the acquisition unit acquires data related to Napoleon using voice recognition technology. In addition, when the user specifies the person by text, the acquisition unit can also acquire data using text analysis technology. For example, when the user specifies "Napoleon" by text, the acquisition unit acquires data related to Napoleon using text analysis technology. In addition, when the user specifies the person by image, the acquisition unit can also acquire data using image recognition technology. For example, when the user inputs an image of Napoleon, the acquisition unit acquires data related to Napoleon using image recognition technology. This allows the optimal acquisition means to be selected according to the user's input method. Some or all of the above-described processing in the acquisition unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the acquisition unit can input the user's input method into the generation AI and cause the generation AI to select the optimal acquisition means.

[0084] The acquisition unit can estimate the user's emotions and determine the priority of data to be acquired based on the estimated user emotions. For example, the acquisition unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the acquisition unit calculates an emotion score based on changes in facial expression and determines the priority of data. The acquisition unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the acquisition unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the priority of data. The acquisition unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the acquisition unit calculates an emotion score based on heart rate fluctuations and determines the priority of data. This allows the priority of data to be determined based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the acquisition unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the acquisition unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0085] When acquiring data of a specified person, the acquisition unit can prioritize acquiring highly relevant data by taking into account the user's geographical location information. For example, if the user is in a specific area, the acquisition unit prioritizes acquiring data related to that area. For example, if the user is traveling, the acquisition unit prioritizes acquiring data related to the travel destination. Furthermore, if the user is in a specific historical location, the acquisition unit can prioritize acquiring data related to that location. For example, if the user is in a historical battlefield, the acquisition unit prioritizes acquiring data related to the battlefield. This allows highly relevant data to be acquired preferentially based on the user's geographical location information. Some or all of the above-described processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's geographical location information to the generation AI and cause the generation AI to acquire highly relevant data.

[0086] When acquiring data of a specified person, the acquisition unit can analyze the user's social media activity and acquire related data. For example, the acquisition unit prioritizes acquiring data related to people mentioned by the user on social media. For example, the acquisition unit analyzes the content of the user's social media posts and acquires related data. The acquisition unit can also acquire related data by referring to the activities of the user's friends on social media. For example, the acquisition unit prioritizes acquiring data related to people mentioned by the user's friends. This makes it possible to acquire related data based on the user's social media activity. Some or all of the above-mentioned processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's social media activity into the generation AI and cause the generation AI to acquire related data.

[0087] When acquiring data of a specified person, the acquisition unit can customize the acquisition method by reflecting the user's past feedback. The acquisition unit, for example, optimizes the data acquisition method based on feedback provided by the user in the past. For example, the acquisition unit prioritizes the use of a specific data source based on the user's past feedback. The acquisition unit can also adjust the timing of data acquisition by referring to the user's past feedback. For example, the acquisition unit optimizes the timing of data acquisition based on feedback provided by the user in the past. This allows the acquisition method to be customized based on the user's past feedback. Some or all of the above-mentioned processing in the acquisition unit may be performed using or without the generation AI. For example, the acquisition unit can input the user's past feedback into the generation AI and cause the generation AI to customize the acquisition method.

[0088] The analysis unit can estimate the user's emotions and adjust the analysis presentation method based on the estimated user emotions. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expressions and adjusts the analysis presentation method. The analysis unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the analysis presentation method. The analysis unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations and adjusts the analysis presentation method. This allows the analysis presentation method to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input image data of the user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0089] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the designated person. For example, if the designated person is historically important, the analysis unit performs a detailed analysis. For example, the analysis unit performs a detailed analysis on a historically important person such as Napoleon. The analysis unit can also perform a concise analysis if the designated person is not well known. For example, the analysis unit performs a concise analysis on a lesser-known historical figure. The analysis unit can also adjust the depth of the analysis according to the importance of the designated person. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the designated person. This allows the level of detail of the analysis to be adjusted based on the importance of the designated person. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit can input the importance of the designated person to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0090] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the specified person. For example, if the specified person is a politician, the analysis unit applies an analysis algorithm based on the political background. For example, the analysis unit applies an analysis algorithm based on the political background to a politician like Napoleon. Furthermore, if the specified person is a scientist, the analysis unit can also apply an analysis algorithm based on scientific knowledge. For example, the analysis unit applies an analysis algorithm based on scientific knowledge to a scientist like Einstein. Furthermore, if the specified person is an artist, the analysis unit can also apply an analysis algorithm based on the artistic background. For example, the analysis unit applies an analysis algorithm based on the artistic background to an artist like Picasso. This allows the optimal analysis algorithm to be applied depending on the category of the specified person. Some or all of the above-described processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit can input the category of the specified person into the generation AI and cause the generation AI to apply different analysis algorithms.

[0091] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, optimizes the analysis algorithm based on analysis results provided by the user in the past. For example, the analysis unit adjusts the analysis algorithm based on feedback provided by the user in the past. The analysis unit can also preferentially use a specific data source based on the user's past analysis results. For example, the analysis unit selects the optimal data source based on data sources used by the user in the past. The analysis unit can also improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the accuracy of the analysis based on analysis results provided by the user in the past. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0092] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on changes in facial expressions and adjusts the length of the analysis. The analysis unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the analysis unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the length of the analysis. The analysis unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the analysis unit calculates an emotion score based on heart rate fluctuations and adjusts the length of the analysis. This allows the length of the analysis to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input image data of the user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0093] During analysis, the analysis unit can determine the priority of analysis based on the time of submission of the data of the designated person. For example, if the data of the designated person is new, the analysis unit prioritizes analysis. For example, the analysis unit prioritizes analysis of the most recently submitted data. Furthermore, if the data of the designated person is old, the analysis unit can postpone analysis. For example, the analysis unit analyzes old data later. Furthermore, the analysis unit can also determine the priority of analysis based on the time of submission of the data of the designated person. For example, the analysis unit determines the priority of analysis based on the time of submission. This makes it possible to determine the priority of analysis based on the time of submission of the data of the designated person. Some or all of the above-mentioned processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit can input the time of submission of the data of the designated person to the generation AI and have the generation AI determine the priority of analysis.

[0094] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the designated person. For example, if the designated person is important to the user, the analysis unit performs analysis with priority. For example, the analysis unit performs analysis with priority on people in whom the user is particularly interested. Furthermore, if the designated person is not very relevant, the analysis unit can postpone analysis. For example, the analysis unit postpones analysis of people with low relevance. Furthermore, the analysis unit can adjust the order of analysis based on the relevance of the designated person. For example, the analysis unit adjusts the order of analysis based on the relevance. This makes it possible to adjust the order of analysis based on the relevance of the designated person. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the relevance of the designated person into the generation AI and cause the generation AI to adjust the order of analysis.

[0095] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit provides an analysis that uses a lot of technical terms. For example, the analysis unit performs an analysis that uses a lot of technical terms for a user with technical expertise. The analysis unit can also provide a concise and easy-to-understand analysis if the user does not have technical expertise. For example, the analysis unit performs a concise and easy-to-understand analysis for a user without technical expertise. The analysis unit can also adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit adjusts the use of technical terms based on the user's level of expertise. This allows the use of technical terms in the analysis to be adjusted according to the user's level of expertise. Some or all of the above-mentioned processing in the analysis unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input the user's level of expertise to the generation AI and cause the generation AI to adjust the use of technical terms.

[0096] The generation unit can estimate the user's emotions and adjust the conversation generation method based on the estimated user emotions. For example, the generation unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expressions and adjusts the conversation generation method. The generation unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the conversation generation method. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations and adjusts the conversation generation method. This makes it possible to adjust the conversation generation method based on the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0097] When generating a conversation, the generation unit can adjust the level of detail of the conversation based on the importance of the designated person. For example, if the designated person is historically important, the generation unit generates detailed conversation. For example, the generation unit generates detailed conversation for a historically important person such as Napoleon. The generation unit can also generate concise conversation if the designated person is not well known. For example, the generation unit generates concise conversation for a little-known historical figure. The generation unit can also adjust the depth of the conversation according to the importance of the designated person. For example, the generation unit adjusts the level of detail of the conversation based on the importance of the designated person. This allows the level of detail of the conversation to be adjusted based on the importance of the designated person. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI or may be performed without using a generation AI. For example, the generation unit can input the importance of the designated person to the generation AI and cause the generation AI to adjust the level of detail of the conversation.

[0098] When generating a conversation, the generation unit can apply different generation algorithms depending on the category of the specified person. For example, if the specified person is a politician, the generation unit applies a generation algorithm based on the political background. For example, the generation unit applies a generation algorithm based on the political background to a politician such as Napoleon. Furthermore, if the specified person is a scientist, the generation unit can apply a generation algorithm based on scientific knowledge. For example, the generation unit applies a generation algorithm based on scientific knowledge to a scientist such as Einstein. Furthermore, if the specified person is an artist, the generation unit can apply a generation algorithm based on the artistic background. For example, the generation unit applies a generation algorithm based on the artistic background to an artist such as Picasso. This allows the optimal generation algorithm to be applied depending on the category of the specified person. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the category of the specified person into the generation AI and cause the generation AI to apply different generation algorithms.

[0099] When generating a conversation, the generation unit can improve the accuracy of the conversation by referring to the user's past conversation results. The generation unit, for example, optimizes the generation algorithm based on conversation results provided by the user in the past. For example, the generation unit adjusts the generation algorithm based on feedback provided by the user in the past. The generation unit can also preferentially use a specific data source based on the user's past conversation results. For example, the generation unit selects an optimal data source based on data sources used by the user in the past. The generation unit can also improve the accuracy of the conversation by referring to the user's past conversation results. For example, the generation unit improves the accuracy of the conversation based on conversation results provided by the user in the past. In this way, the accuracy of the conversation can be improved by referring to the user's past conversation results. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI or may be performed without using a generation AI. For example, the generation unit can input the user's past conversation results into the generation AI and cause the generation AI to improve the accuracy of the conversation.

[0100] The generation unit can estimate the user's emotion and adjust the length of the conversation based on the estimated user emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expression and adjusts the length of the conversation. The generation unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the length of the conversation. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations and adjusts the length of the conversation. This makes it possible to adjust the length of the conversation based on the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions.

[0101] When generating a conversation, the generation unit can determine the priority of the conversation based on the time of submission of the data of the specified person. For example, if the data of the specified person is new, the generation unit generates the conversation with priority. For example, the generation unit preferentially reflects the most recently submitted data in the conversation. Furthermore, if the data of the specified person is old, the generation unit can generate the conversation later. For example, the generation unit generates the conversation with older data later. Furthermore, the generation unit can determine the priority of the conversation based on the time of submission of the data of the specified person. For example, the generation unit determines the priority of the conversation based on the time of submission. This makes it possible to determine the priority of the conversation based on the time of submission of the data of the specified person. Some or all of the above-mentioned processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the time of submission of the data of the specified person to the generation AI and cause the generation AI to determine the priority of the conversation.

[0102] When generating a conversation, the generation unit can adjust the order of the conversations based on the relevance of the designated person. For example, if the designated person is important to the user, the generation unit generates the conversation with priority. For example, the generation unit generates the conversation with priority for a person in whom the user is particularly interested. Furthermore, if the designated person is not very relevant, the generation unit can generate the conversation later. For example, the generation unit postpones the conversation of a person with low relevance. Furthermore, the generation unit can adjust the order of the conversations based on the relevance of the designated person. For example, the generation unit adjusts the order of the conversations based on the relevance. In this way, the order of the conversations can be adjusted based on the relevance of the designated person. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the relevance of the designated person to the generation AI and cause the generation AI to adjust the order of the conversations.

[0103] When generating a conversation, the generation unit can adjust the use of technical terms in the conversation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates a conversation that uses a lot of technical terms. For example, the generation unit generates a conversation that uses a lot of technical terms for a user with technical expertise. The generation unit can also generate concise and easy-to-understand conversation if the user does not have technical expertise. For example, the generation unit generates concise and easy-to-understand conversation for a user without technical expertise. The generation unit can also adjust the use of technical terms in the conversation according to the user's level of expertise. For example, the generation unit adjusts the use of technical terms based on the user's level of expertise. This makes it possible to adjust the use of technical terms in the conversation according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's level of expertise to the generation AI and cause the generation AI to adjust the use of technical terms.

[0104] The providing unit can estimate the user's emotions and adjust the conversation provision method based on the estimated user emotions. For example, the providing unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on changes in facial expressions and adjusts the conversation provision method. The providing unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the providing unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the conversation provision method. The providing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on heart rate fluctuations and adjusts the conversation provision method. This makes it possible to adjust the conversation provision method based on the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit may input image data of the user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0105] When providing a conversation, the providing unit can select the optimal delivery method by referring to the user's past operation history. For example, the providing unit selects the optimal method based on the user's past preferred delivery methods. For example, the providing unit selects the optimal delivery method based on the user's past preferred delivery format (text, audio, etc.). The providing unit can also preferentially use a specific delivery method based on the user's past operation history. For example, the providing unit preferentially uses a delivery method that the user has used frequently in the past. The providing unit can also customize the delivery method by referring to the user's past operation history. For example, the providing unit customizes the delivery method based on the user's past operation history. This makes it possible to select the optimal delivery method based on the user's past operation history. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input the user's past operation history into the generation AI and cause the generation AI to select the optimal delivery method.

[0106] The providing unit can customize the provided content according to the user's current task when providing a conversation. For example, if the user is studying, the providing unit can prioritize providing educational content. For example, if the user is using the device during a history class, the providing unit can prioritize providing educational content. The providing unit can also prioritize providing fun content if the user is seeking entertainment. For example, if the user is using the device while relaxing, the providing unit can prioritize providing fun content. The providing unit can also customize the provided content according to the user's current task. For example, the providing unit customizes the provided content based on the task the user is currently performing. This allows the provided content to be customized according to the user's current task. Some or all of the above-described processing in the providing unit may be performed using a generation AI or may be performed without using a generation AI. For example, the providing unit can input the user's current task to the generation AI and cause the generation AI to customize the provided content.

[0107] The providing unit can estimate the user's emotions and adjust the conversation provision procedure based on the estimated user's emotions. For example, the providing unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on changes in facial expression and adjusts the conversation provision procedure. The providing unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the providing unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the conversation provision procedure. The providing unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the providing unit calculates an emotion score based on heart rate fluctuations and adjusts the conversation provision procedure. This makes it possible to adjust the conversation provision procedure based on the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the providing unit may input image data of the user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0108] When providing a conversation, the providing unit can select the optimal delivery method by taking into account the user's device information. For example, if the user is using a smartphone, the providing unit provides a delivery method tailored to the screen size. For example, the providing unit provides a delivery method optimized for the small screen of a smartphone. Furthermore, if the user is using a tablet, the providing unit can also provide a delivery method optimized for a large screen. For example, the providing unit provides a delivery method optimized for the large screen of a tablet. Furthermore, if the user is using a smartwatch, the providing unit can also provide a delivery method that is concise and highly visible. For example, the providing unit provides a delivery method optimized for the small screen of a smartwatch. This allows the optimal delivery method to be selected based on the user's device information. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit may input the user's device information into the generation AI and cause the generation AI to select the optimal delivery method.

[0109] When providing the conversation, the providing unit can make the provided content multilingual in accordance with the user's language setting. The providing unit, for example, automatically sets the language of the conversation based on the language setting of the user's device. For example, if the user's device is set to English, the providing unit provides the conversation in English. The providing unit can also provide a language switching function when the user uses multiple languages. For example, if the user uses English and Japanese, the providing unit can provide the conversation in that language when the user selects a specific language. For example, if the user selects French, the providing unit provides the conversation in French. This makes it possible to make the provided content multilingual based on the user's language setting. Some or all of the above-described processing in the providing unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the user's language setting into the generation AI and cause the generation AI to provide multilingual support.

[0110] The providing unit can analyze the user's social media activity and provide related information when providing a conversation. For example, the providing unit provides information about people mentioned by the user on social media. For example, if the user mentions Napoleon on social media, the providing unit provides information about Napoleon. The providing unit can also analyze the content of the user's social media posts and provide related information. For example, if the user posts about a historical war on social media, the providing unit provides information about that war. The providing unit can also provide related information by referring to the activities of the user's friends on social media. For example, the providing unit provides information about people mentioned by the user's friends on social media. This makes it possible to provide related information based on the user's social media activity. Some or all of the above-mentioned processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input the user's social media activity into the generation AI and cause the generation AI to provide related information.

[0111] The update unit can estimate the user's emotion and select update data based on the estimated user emotion. For example, the update unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the update unit calculates an emotion score based on changes in facial expression and selects update data. The update unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the update unit analyzes the tone and speed of the voice, calculates an emotion score, and selects update data. The update unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the update unit calculates an emotion score based on heart rate fluctuations and selects update data. This makes it possible to select update data based on the user's emotion. Emotion estimation is achieved using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the update unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the update unit may input image data of the user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0112] During an update, the update unit can optimize the update algorithm by referring to past update data. The update unit, for example, selects an optimal update algorithm based on past update data. For example, the update unit analyzes past update data and selects an optimal update algorithm. The update unit can also preferentially use a specific data source from the past update data. For example, the update unit preferentially use a specific data source based on past update data. The update unit can also optimize the update algorithm by referring to the past update data. For example, the update unit optimizes the update algorithm based on past update data. This makes it possible to optimize the update algorithm by referring to the past update data. Some or all of the above-described processing in the update unit may be performed using or without using the generation AI. For example, the update unit can input past update data to the generation AI and cause the generation AI to optimize the update algorithm.

[0113] The update unit can update the update data by reflecting user feedback during an update. The update unit, for example, optimizes the update data based on feedback provided by the user. For example, the update unit adjusts the update data based on user feedback. The update unit can also prioritize the use of a specific data source based on user feedback. For example, the update unit prioritizes the use of a specific data source based on user feedback. The update unit can also update the update data by referring to user feedback. For example, the update unit updates the update data based on user feedback. In this way, the update data can be updated by reflecting user feedback. Some or all of the above-described processing in the update unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the update unit can input user feedback to the generation AI and cause the generation AI to update the update data.

[0114] The update unit can estimate the user's emotion and adjust the update frequency based on the estimated user's emotion. For example, the update unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the update unit calculates an emotion score based on changes in facial expression and adjusts the update frequency. The update unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the update unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the update frequency. The update unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the update unit calculates an emotion score based on heart rate fluctuations and adjusts the update frequency. This allows the update frequency to be adjusted based on the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the update unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the update unit may input image data of the user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0115] During updating, the update unit can weight the update data based on the time of submission of the data of the designated person. For example, if the data of the designated person is new, the update unit increases the weighting. For example, the update unit increases the weighting for recently submitted data. The update unit can also decrease the weighting for old data if the data of the designated person is old. For example, the update unit decreases the weighting for old data. The update unit can also weight the update data based on the time of submission of the data of the designated person. For example, the update unit weights the update data based on the time of submission. This makes it possible to weight the update data based on the time of submission of the data of the designated person. Some or all of the above-described processing in the update unit may be performed using or without the generation AI. For example, the update unit can input the time of submission of the data of the designated person to the generation AI and cause the generation AI to weight the update data.

[0116] The update unit can integrate information from different data sources to enrich the updated data during an update. The update unit, for example, integrates information from different data sources to enrich the updated data. For example, the update unit integrates information from an external database or an internal database to enrich the updated data. The update unit can also compare information from different data sources to select optimal data. For example, the update unit compares information from multiple data sources to select optimal data. The update unit can also optimize the updated data based on information from different data sources. For example, the update unit optimizes the updated data based on information from different data sources. This allows the information from different data sources to be integrated and enriched. Some or all of the above-described processing in the update unit may be performed using or without the generation AI. For example, the update unit can input information from different data sources to the generation AI and have the generation AI integrate the information.

[0117] The update unit can optimize the update data by reflecting the user's past feedback during updating. The update unit optimizes the update data, for example, based on feedback provided by the user in the past. For example, the update unit adjusts the update data based on the user's past feedback. The update unit can also preferentially use a specific data source based on the user's past feedback. For example, the update unit preferentially use a specific data source based on the user's past feedback. The update unit can also optimize the update data by referring to the user's past feedback. For example, the update unit optimizes the update data based on the user's past feedback. In this way, the update data can be optimized by reflecting the user's past feedback. Some or all of the above-described processing in the update unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the update unit can input the user's past feedback into the generation AI and cause the generation AI to optimize the update data. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned acquisition unit, analysis unit, generation unit, provision unit, and update unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit collects data on a designated person based on information input by a user via the control unit 46A of the smart device 14. The analysis unit analyzes the designated person's tone of voice and knowledge based on the data collected by the specific processing unit 290 of the data processing device 12. The generation unit generates a conversation that reproduces the designated person's tone of voice and knowledge using a generation AI via the specific processing unit 290 of the data processing device 12. The provision unit provides the conversation generated by the control unit 46A of the smart device 14 to the user in an interactive format. The update unit constantly collects the latest data via the specific processing unit 290 of the data processing device 12 and updates the learning data of the generation AI. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned acquisition unit, analysis unit, generation unit, provision unit, and update unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit collects data of a designated person based on information input by a user via the control unit 46A of the smart glasses 214. The analysis unit analyzes the designated person's tone of voice and knowledge based on the data collected by the identification processing unit 290 of the data processing device 12. The generation unit generates a conversation that reproduces the designated person's tone of voice and knowledge using a generation AI via the identification processing unit 290 of the data processing device 12. The provision unit provides the conversation generated by the control unit 46A of the smart glasses 214 to the user in an interactive format. The update unit constantly collects the latest data via the identification processing unit 290 of the data processing device 12 and updates the learning data of the generation AI. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned acquisition unit, analysis unit, generation unit, provision unit, and update unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the acquisition unit collects data on a designated person based on information input by a user via the control unit 46A of the headset-type terminal 314. The analysis unit analyzes the designated person's tone of voice and knowledge based on the data collected by the identification processing unit 290 of the data processing device 12. The generation unit generates a conversation that reproduces the designated person's tone of voice and knowledge using a generation AI via the identification processing unit 290 of the data processing device 12. The provision unit provides the conversation generated by the control unit 46A of the headset-type terminal 314 to the user in an interactive format. The update unit constantly collects the latest data via the identification processing unit 290 of the data processing device 12 and updates the learning data of the generation AI. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned acquisition unit, analysis unit, generation unit, provision unit, and update unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the acquisition unit collects data on a designated person based on information input by a user via the control unit 46A of the robot 414. The analysis unit analyzes the designated person's tone of voice and knowledge based on the data collected by the specific processing unit 290 of the data processing device 12. The generation unit generates a conversation that reproduces the designated person's tone of voice and knowledge using a generation AI via the specific processing unit 290 of the data processing device 12. The provision unit provides the conversation generated by the control unit 46A of the robot 414 to the user in an interactive format. The update unit constantly collects the latest data via the specific processing unit 290 of the data processing device 12 and updates the learning data of the generation AI.

[0118] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0119] The acquisition unit can also monitor the user's current activity status and determine the optimal timing for data acquisition. For example, it can delay data acquisition when the user is busy and accelerate data acquisition when the user is relaxed. The acquisition unit can also refer to the user's schedule information and adjust the timing of data acquisition. For example, it can acquire data during meetings or breaks based on the user's calendar information. Furthermore, the acquisition unit can also acquire data taking into account the remaining battery level of the user's device. For example, it can refrain from acquiring data when the battery is low and acquire data while the device is charging. This enables flexible data acquisition according to the user's activity status.

[0120] The analysis unit can also analyze the user's past conversation history to more accurately analyze the designated person's tone of voice and knowledge. For example, it can extract characteristics of the designated person's tone of voice and knowledge based on the content of the user's past conversations. The analysis unit can also customize the analysis results taking into account the user's preferences and interests. For example, if the user is interested in a particular historical event, it can prioritize analysis of knowledge related to that event. Furthermore, the analysis unit can adjust the analysis algorithm based on user feedback. For example, it can improve the accuracy of the analysis results based on feedback provided by the user. This enables flexible analysis that meets the user's needs.

[0121] The generation unit can also estimate the user's emotions and adjust the tone and content of the conversation based on the estimated user's emotions. For example, if the user is excited, the tone of the conversation can be adjusted to be calmer, and if the user is depressed, the generation unit can generate encouraging content. The generation unit can also adjust the length of the conversation based on the user's emotions. For example, if the user is tired, the generation unit generates a short conversation, and if the user is relaxed, the generation unit generates a long conversation. Furthermore, the generation unit can select the theme of the conversation based on the user's emotions. For example, the generation unit generates a conversation based on a theme that the user is interested in. This enables flexible conversation generation according to the user's emotions.

[0122] The providing unit can also estimate the user's emotions and adjust the way the conversation is provided based on the estimated user's emotions. For example, if the user is nervous, the conversation can be provided while playing relaxing music in the background. Also, if the user is concentrating, the conversation can be provided with minimal notifications. Furthermore, the providing unit can adjust the display format of the conversation according to the user's emotions. For example, if the user prefers visual information, the conversation can be provided using images and graphs. This makes it possible to provide flexible conversations according to the user's emotions.

[0123] The update unit can also estimate the user's emotions and select update data based on the estimated user's emotions. For example, if the user is excited, new information is provided preferentially, and if the user is calm, detailed information is provided. The update unit can also adjust the frequency of updates according to the user's emotions. For example, if the user is interested, updates are performed frequently, and if the user is losing interest, updates are refrained from. Furthermore, the update unit can select the format of update data based on the user's emotions. For example, if the user prefers visual information, update data using images or videos is provided. This enables flexible updates according to the user's emotions.

[0124] The acquisition unit can also analyze the user's past search history and select the optimal data acquisition method. For example, it can prioritize acquisition of related data based on keywords that the user has searched for frequently in the past. The acquisition unit can also prioritize the use of specific data sources based on the user's past search history. For example, it can select the optimal data source based on data sources that the user has used frequently in the past. Furthermore, the acquisition unit can adjust the timing of data acquisition based on the user's past search history. For example, if the user has performed many searches during a specific time period in the past, it can acquire data during that time period. This enables flexible data acquisition based on the user's past search history.

[0125] When analyzing data on a specified person, the analysis unit can also integrate information from different data sources to improve the accuracy of the analysis. For example, it can integrate information from books, papers, interview articles, etc. related to the specified person and perform the analysis. The analysis unit can also compare information from different data sources and select the most reliable information. For example, it can compare information from multiple data sources and prioritize the use of matching information. Furthermore, the analysis unit can complement the analysis results based on information from different data sources. For example, it can complement the content of an interview article based on information obtained from a book. This enables flexible analysis that integrates information from different data sources.

[0126] The generation unit can also analyze the user's past conversation history and optimize the conversation generation method. For example, the generation unit can adjust the topic and style of the conversation based on the content of the user's past conversations. The generation unit can also extract specific conversation patterns from the user's past conversation history and generate conversations based on them. For example, the generation unit generates conversations based on conversation patterns that the user has preferred in the past. Furthermore, the generation unit can adjust the length and level of detail of the conversation based on the user's past conversation history. For example, if the user has preferred short conversations in the past, the generation unit generates short conversations. This enables flexible conversation generation based on the user's past conversation history.

[0127] The providing unit can also monitor the user's current device status and select the optimal providing method. For example, if the user is using a smartphone, the providing unit can select a providing method optimized for the screen size, and if the user is using a PC, the providing unit can provide detailed information. The providing unit can also adjust the providing method taking into account the remaining battery level of the user's device. For example, if the battery is low, the information is provided in text format, and if the battery is sufficient, the information is provided using images or videos. The providing unit can also adjust the providing method taking into account the connection status of the user's device. For example, if the Internet connection is unstable, the information is provided in a format that can be viewed offline. This enables flexible information provision according to the user's device status.

[0128] The update unit can also analyze the user's past feedback and optimize the selection of update data. For example, a specific data source can be used preferentially based on feedback provided by the user in the past. The update unit can also adjust the format of the update data based on the user's past feedback. For example, the update unit selects the format of the update data based on the data format (text, image, video, etc.) that the user has preferred in the past. Furthermore, the update unit can adjust the frequency of updates based on the user's past feedback. For example, if the user desires frequent updates, the update frequency can be increased, and if the user desires infrequent updates, the update frequency can be decreased. This enables flexible updates based on the user's past feedback.

[0129] The processing flow of the second embodiment will be briefly explained below.

[0130] Step 1: The acquisition unit acquires data of a person designated by a user. For example, the acquisition unit collects data of the designated person based on information input by a user. Step 2: The analysis unit analyzes the data acquired by the acquisition unit. For example, the analysis unit analyzes the tone of voice and knowledge of the designated person based on the collected data. Step 3: The generator generates a conversation based on the data analyzed by the analyzer. For example, the generator uses a generation AI to generate a conversation that reproduces the tone and knowledge of the specified person. Step 4: The providing unit provides the conversation generated by the generating unit to the user. For example, the providing unit provides the generated conversation to the user in an interactive format. Step 5: The update unit updates the conversation data generated by the generation unit. For example, the update unit constantly collects the latest data and updates the learning data of the generation AI.

[0131] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0135] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0136] 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.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] 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.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0142] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] 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.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0145] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0152] 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.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0154] 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.

[0155] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0157] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0158] 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.

[0159] 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.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0163] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0165] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0168] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0169] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0170] 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.

[0171] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0173] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0174] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0175] 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.

[0176] 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.

[0177] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0178] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0179] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0180] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0181] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0182] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0183] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0184] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0185] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0186] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0187] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0188] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0189] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0190] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0191] 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.

[0192] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0193] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0194] 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.

[0195] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0196] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0197] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0198] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0199] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0200] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0201] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0202] [Explanation of symbols]

[0203] 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. an acquisition unit that acquires data of a person designated by a user; an analysis unit that analyzes the data acquired by the acquisition unit; a generation unit that generates a conversation based on the data analyzed by the analysis unit; a providing unit that provides the conversation generated by the generating unit to a user; an update unit that updates the conversation data generated by the generation unit; A system characterized by:

2. The acquisition unit Collect data about specified people based on information entered by users 2. The system of claim 1.

3. The analysis unit Analyze the tone and knowledge of the designated person based on the collected data 2. The system of claim 1.

4. The generation unit Using generative AI to generate conversations that reproduce the tone and knowledge of a specified person 2. The system of claim 1.

5. The providing unit Present the generated conversation to the user in an interactive format 2. The system of claim 1.

6. The update unit Always collect the latest data and update the learning data for the generative AI 2. The system of claim 1.

7. The acquisition unit The system estimates the user's emotions and adjusts the timing of data acquisition for a specified person based on the estimated user emotions.

2. The system of claim 1.

8. The acquisition unit Analyze the user's past selection history and select the optimal data acquisition method 2. The system of claim 1.

Images