System

Abstract

To provide a system for selecting and presenting an appropriate topic for activating a brain of a dementia patient through conversation.SOLUTION: A system includes a storage section, an analysis section, a selection section, and a presentation section. The preservation section stores conversation history. The analysis section analyzes conversation history stored by the storage section. The selection section selects a topic on the basis of a result analyzed by the analysis section. The presentation section presents a topic selected by the selection section to a user.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to select appropriate topics to stimulate the minds of dementia patients through conversation.

[0005] The system according to the embodiment aims to select and present appropriate topics for stimulating the mind through conversation with dementia patients. [Means for solving the problem]

[0006] The system according to the embodiment includes a storage unit, an analysis unit, a selection unit, and a presentation unit. The storage unit stores a conversation history. The analysis unit analyzes the conversation history stored by the storage unit. The selection unit selects a topic based on a result of the analysis by the analysis unit. The presentation unit presents the topic selected by the selection unit to a user. Effect of the Invention

[0007] The system according to the embodiment can select and present appropriate topics for stimulating the mind through conversation with a dementia patient. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A conversation support system according to an embodiment of the present invention is a system for suppressing the progression of dementia. In this conversation support system, a user starts a conversation, records the conversation, and saves it as a conversation history. Next, the system analyzes the saved conversation history and automatically selects old stories and memories that the user is likely to be interested in. The selected topic is presented to the user by the system to promote the conversation. This system is characterized by analyzing the conversation history using a generation AI and selecting an appropriate topic. For example, a user starts a conversation. For example, the conversation starts with a simple question such as "What did you do today?". This conversation is recorded as audio by the system and converted into text data. Next, the system analyzes the recorded conversation history. The generation AI understands the content of the conversation and selects a topic that the user is likely to be interested in. For example, if the user says "I went on a trip with my family a long time ago," the system selects a topic related to that trip. The selected topic is presented to the user by the system. For example, the system automatically generates a question such as "Where did you go on that trip?" and presents it to the user. This gives the user more opportunities to talk about past memories, stimulating conversation. The system also analyzes the user's reactions in real time and presents the next question at an appropriate time, allowing the conversation to continue without interruption. This system gives dementia patients more opportunities to talk about past memories, stimulating their minds. Continuing the conversation also reduces feelings of loneliness and promotes mental stability. For example, if a user says, "I once went camping with my family," the system will generate a question such as "What did you do on that camping trip?" and present it to the user. This allows the user to talk about fun memories from the past, stimulating the conversation. In this way, the conversation support system can slow the progression of dementia and promote mental stability for the user.

[0029] The conversation support system according to the embodiment includes a storage unit, an analysis unit, a selection unit, and a presentation unit. The storage unit stores a history of a conversation. The history of a conversation includes, for example, voice data, text data, metadata, and the like, but is not limited to such examples. The storage unit stores, for example, voice data and uses it for later analysis. The storage unit can also store text data and convert it into a format that is easy for the analysis unit to analyze. Furthermore, the storage unit can also store metadata and record information such as the content, time, and location of the conversation. The analysis unit uses a generation AI to analyze the history of the conversation stored by the storage unit. The analysis is performed, for example, by a method such as natural language processing technology, emotion analysis, and keyword extraction, but is not limited to such examples. For example, the analysis unit uses natural language processing technology to analyze the content of the conversation and extracts topics that the user is likely to be interested in. Furthermore, the analysis unit can also analyze the user's emotions using emotion analysis and select an appropriate topic. Furthermore, the analysis unit can also use keyword extraction technology to extract important keywords in the conversation and select a topic based on the keywords. The selection unit uses the generation AI to select an appropriate topic based on the results of the analysis by the analysis unit. The selection of the topic is performed based on criteria such as, for example, the user's interest, past conversation history, and trends, but is not limited to such examples. For example, the selection unit selects a topic based on the user's interest. The selection unit can also select a topic based on past conversation history. Furthermore, the selection unit can also select a topic based on trends. The presentation unit presents the topic selected by the selection unit to the user. The presentation is performed by, for example, a method such as text display, audio output, and notification, but is not limited to such examples. For example, the presentation unit presents the topic using text display. Furthermore, the presentation unit can also present the topic using audio output. Furthermore, the presentation unit can also present the topic using notification. As a result, the conversation support system according to the embodiment can store and analyze the conversation history, select and present an appropriate topic, and thereby suppress the progression of dementia.

[0030] The storage unit stores the history of the conversation. The history of the conversation includes, for example, voice data, text data, metadata, etc., but is not limited to such examples. The storage unit, for example, stores the voice data and uses it for later analysis. Specifically, the voice data is stored in a high-quality format, and may be subjected to noise removal and preprocessing for voice recognition. The storage unit can also store the text data and convert it into a format that is easy for the analysis unit to analyze. Text data is often automatically generated from the voice data, and is accurately transcribed using voice recognition technology. Furthermore, the storage unit can also store metadata and record information such as the content, time, and location of the conversation. The metadata includes the date and time when the conversation took place, information about the participants, the topic of the conversation, etc., and these pieces of information play an important role in later analysis. The storage unit has a database for centrally managing these data and making them quickly accessible as needed. The database is provided with security measures to protect the data and ensure privacy. Furthermore, the storage unit has a data backup function and can prepare for data loss or damage. This allows the storage unit to efficiently and safely store the history of the conversation and use it for later analysis and use.

[0031] The analysis unit uses the generation AI to analyze the conversation history stored by the storage unit. The analysis is performed by, for example, natural language processing technology, emotion analysis, keyword extraction, and other methods, but is not limited to these examples. Specifically, the content of the conversation is analyzed using natural language processing technology to extract topics that the user is likely to be interested in. Natural language processing technology includes morphological analysis, context analysis, semantic analysis, and the like, and these are combined to analyze the content of the conversation in detail. The analysis unit can also analyze the user's emotions using emotion analysis to select appropriate topics. Emotion analysis estimates the user's emotional state from the tone of the voice and the expression of the text, and classifies it into emotion categories such as positive, negative, and neutral. Furthermore, the analysis unit can use keyword extraction technology to extract important keywords in the conversation and select topics based on them. Keyword extraction is performed to identify frequently occurring words and words with high importance, and to clarify the subject and concerns of the conversation. The analysis unit combines these technologies to accurately grasp the user's interests and concerns, and generates basic data for providing appropriate topics. Furthermore, the analysis unit can perform more accurate analysis by utilizing past conversation history and user profile information. This allows the analysis unit to perform advanced analysis according to the user's needs and maximize the effectiveness of the conversation support system.

[0032] The selection unit uses the generation AI to select an appropriate topic based on the results of the analysis by the analysis unit. The selection of the topic is performed based on criteria such as, for example, the user's interest, past conversation history, and trends, but is not limited to such examples. Specifically, the selection unit selects a topic based on the user's interest. The user's interest is extracted from past conversation history and user profile, and the generation AI analyzes it to propose the optimal topic. The selection unit can also select a topic based on past conversation history. The past conversation history records what topics the user was interested in and how he or she responded, and the generation AI selects an appropriate topic based on this. Furthermore, the selection unit can also select a topic based on trends. Trends are extracted from news on the Internet and social media data, and the generation AI analyzes them to provide the latest topics. The selection unit combines these criteria to select the most interesting and appropriate topic for the user. The selection unit can also provide a feedback loop to ensure that the selected topic is beneficial to the user and improves the quality of the conversation. This enables the selection unit to provide optimal topics according to the user's interests and concerns, thereby improving the effectiveness of the conversation support system.

[0033] The presentation unit presents the topic selected by the selection unit to the user. The presentation is performed, for example, by a method such as text display, audio output, or notification, but is not limited to such examples. Specifically, the presentation unit presents the topic using text display. The text display displays the topic on the screen of the user's device to provide information visually. The presentation unit can also present the topic using audio output. The audio output conveys the topic by audio through a speaker or headphones, and can provide information to users with visual impairments or in situations where visual information is difficult to receive. Furthermore, the presentation unit can also present the topic using notification. The notification uses the notification function of a smartphone or tablet to quickly convey important information to the user. The presentation unit can combine these methods to present the topic in the most effective form for the user. Furthermore, the presentation unit can collect user feedback and use it to improve the presentation method. For example, it analyzes which presentation method the user prefers and which presentation method is most effective, and optimizes the presentation method. As a result, the presentation unit can effectively present appropriate topics to the user and maximize the effect of the conversation support system.

[0034] The conversation support system includes a conversion unit that converts the conversation history into text data. The conversion unit converts the conversation history into text data. The text data includes, for example, voice recognition technology, OCR technology, and the like, but is not limited to such examples. For example, the conversion unit converts voice data into text data using voice recognition technology. The conversion unit can also convert handwritten notes into text data using OCR technology. Furthermore, the conversion unit can also convert voice data into text data in real time using voice recognition technology. Thereby, by converting the conversation history into text data, analysis becomes easier. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit inputs voice data to a generation AI and causes the generation AI to execute conversion from voice data to text data.

[0035] The conversation support system includes a reaction analysis unit that analyzes the user's reaction in real time and promotes the next conversation. The reaction analysis unit analyzes the user's reaction in real time. Specific methods and techniques for analyzing in real time include, but are not limited to, streaming data analysis and real-time emotion analysis. For example, the reaction analysis unit analyzes the user's reaction in real time using streaming data analysis. The reaction analysis unit can also analyze the user's emotion in real time using real-time emotion analysis. Furthermore, the reaction analysis unit can also analyze the user's reaction in real time and provide feedback to promote the next conversation. As a result, the conversation can be continued without interruption by analyzing the user's reaction in real time. A part or all of the above-mentioned processing in the reaction analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the reaction analysis unit can input the user's real-time reaction data to the generation AI and cause the generation AI to execute the analysis of the reaction data.

[0036] The storage unit can determine the priority of storage based on the importance of the conversation when storing. For example, when the user is talking about important memories, the storage unit prioritizes storing the conversation. In addition, the storage unit can set the priority of storage to low when the user is talking about everyday topics. Furthermore, the storage unit can also save the conversation with a medium priority when the user is talking about emotional topics. In this way, important conversations can be prioritized by determining the priority of storage based on the importance of the conversation. Part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or may be performed without using AI. For example, the storage unit can determine the priority of storage using an AI model that evaluates the importance of the conversation.

[0037] The storage unit can change the storage method according to the category of the conversation when saving. For example, when the user is talking about his / her family, the storage unit saves the conversation in a specific folder. In addition, when the user is talking about traveling, the storage unit can also save the conversation by linking it with photos and maps. Furthermore, when the user is talking about a hobby, the storage unit can also save the conversation together with related information. This makes it easier to manage the conversation by applying different storage methods according to the category of the conversation. Part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or may be performed without using AI. For example, the storage unit can change the storage method using an AI model that classifies the category of the conversation.

[0038] The storage unit can, at the time of storage, preferentially store highly relevant conversations in consideration of the geographical location information of the user. For example, when the user is talking at a specific location, the storage unit preferentially stores conversations related to that location. In addition, when the user is talking while traveling, the storage unit can also preferentially store conversations related to the travel destination. Furthermore, when the user is talking at home, the storage unit can also preferentially store everyday conversations. In this way, by storing conversations in consideration of the geographical location information of the user, highly relevant conversations can be preferentially stored. Part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or may be performed without using AI. For example, the storage unit can use an AI model that acquires the geographical location information of the user and determines the storage priority of conversations based on the information.

[0039] At the time of saving, the storage unit can analyze the user's social media activity and save highly relevant conversations. The storage unit can save, for example, conversations related to the content shared by the user on social media. The storage unit can also save conversations related to the content commented on by the user on social media. Furthermore, the storage unit can also save conversations related to the content on which the user pressed "Like" on social media. In this way, by analyzing the user's social media activity and saving the conversations, highly relevant conversations can be saved preferentially. A part or all of the above-mentioned processing in the storage unit can be performed, for example, using AI or can be performed without using AI. For example, the storage unit can save the related conversations using an AI model that analyzes social media activity.

[0040] The analysis unit can adjust the level of detail of the analysis based on the content of the conversation during the analysis. For example, when the user is talking about an important topic, the analysis unit performs a detailed analysis. In addition, when the user is talking about an everyday topic, the analysis unit can also set the level of detail of the analysis to be low. Furthermore, when the user is talking about an emotional topic, the analysis unit can also perform a detailed emotion analysis. As a result, by adjusting the level of detail of the analysis based on the content of the conversation, important conversations can be analyzed in detail. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the level of detail of the analysis using an AI model that analyzes the content of the conversation.

[0041] The analysis unit can change the analysis algorithm according to the category of the conversation during analysis. For example, when the user is talking about his / her family, the analysis unit applies an analysis algorithm related to the family. In addition, when the user is talking about travel, the analysis unit can also apply an analysis algorithm related to travel. In addition, when the user is talking about a hobby, the analysis unit can also apply an analysis algorithm related to the hobby. This improves the accuracy of the analysis by applying different analysis algorithms according to the category of the conversation. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can change the analysis algorithm using an AI model that classifies the category of the conversation.

[0042] The analysis unit can determine the order of analysis based on the submission time of the conversation during analysis. For example, the analysis unit prioritizes analysis of the most recent conversation. In addition, when analyzing past conversations, the analysis unit can also determine the priority based on the importance. Furthermore, the analysis unit can also prioritize analysis of conversations related to a specific event. In this way, by determining the priority of analysis based on the submission time of the conversation, the most recent conversation can be analyzed with priority. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use an AI model that determines the order of analysis based on the submission time.

[0043] The analysis unit can determine the order of analysis based on the relevance of the conversations during analysis. For example, the analysis unit prioritizes analysis of highly relevant conversations. The analysis unit can also postpone analysis of less relevant conversations. Furthermore, the analysis unit can analyze the relevance of the conversations and perform the analysis in an optimal order. This allows the analysis of highly relevant conversations to be prioritized by adjusting the order of analysis based on the relevance of the conversations. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can determine the order of analysis using an AI model that evaluates the relevance of the conversations.

[0044] The selection unit can improve the accuracy of the selection based on the interrelationships of conversations at the time of selection. For example, the selection unit selects a related topic based on the content that the user has spoken in the past. The selection unit can also select a topic related to the content that the user is currently speaking. Furthermore, the selection unit can select a topic that the user is likely to be interested in based on the interrelationships. This improves the accuracy of the selection by selecting a topic taking into account the interrelationships of conversations. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can select a topic using an AI model that evaluates the interrelationships of conversations.

[0045] The selection unit can make a selection based on attribute information of the person who submitted the conversation. The selection unit selects an appropriate topic based on, for example, the age of the user. The selection unit can also select an appropriate topic based on the gender of the user. Furthermore, the selection unit can select an appropriate topic based on the hobbies and interests of the user. In this way, an appropriate topic can be selected by selecting a topic taking into consideration the attribute information of the person who submitted the conversation. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can use an AI model that acquires attribute information of the person who submitted the conversation and selects a topic based on the information.

[0046] The selection unit can make a selection while taking into consideration the geographical distribution of the conversation. For example, when the user is speaking at a specific location, the selection unit selects a topic related to that location. In addition, when the user is speaking while traveling, the selection unit can also select a topic related to the travel destination. Furthermore, when the user is speaking at home, the selection unit can also select an everyday topic. In this way, by selecting a topic while taking into consideration the geographical distribution of the conversation, an appropriate topic can be selected. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can select a topic using an AI model that evaluates the geographical distribution.

[0047] The selection unit can improve the accuracy of the selection based on the literature related to the conversation at the time of selection. For example, the selection unit refers to literature related to the content of the user's conversation and selects an appropriate topic. The selection unit can also refer to literature related to topics that the user may be interested in. Furthermore, the selection unit can also refer to literature related to content that the user has previously spoken and select an appropriate topic. As a result, the accuracy of the selection is improved by selecting a topic by referring to literature related to the conversation. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can select a topic using an AI model that refers to related literature.

[0048] The presentation unit can adjust the level of detail of the presentation based on the importance of the topic at the time of presentation. For example, when presenting an important topic, the presentation unit presents detailed information. Furthermore, when presenting an everyday topic, the presentation unit can present the topic briefly. Furthermore, when presenting an emotional topic, the presentation unit can present the topic including detailed emotion analysis. In this way, appropriate information can be provided by adjusting the level of detail of the presentation based on the importance of the topic. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can adjust the level of detail of the presentation using an AI model that evaluates the importance of the topic.

[0049] The presentation unit can change the presentation algorithm according to the topic category at the time of presentation. For example, when presenting a topic about family, the presentation unit applies an algorithm related to family. Furthermore, when presenting a topic about travel, the presentation unit can also apply an algorithm related to travel. Furthermore, when presenting a topic about hobbies, the presentation unit can also apply an algorithm related to hobbies. This enables appropriate presentation by applying different presentation algorithms according to the topic category. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can change the presentation algorithm using an AI model that classifies topic categories.

[0050] The presentation unit can determine the order of presentation based on the submission time of the topic at the time of presentation. For example, the presentation unit preferentially presents the most recent topic. When presenting a past topic, the presentation unit can also determine the priority order based on the importance. Furthermore, the presentation unit can also preferentially present a topic related to a specific event. In this way, by determining the priority order of presentation based on the submission time of the topic, the most recent topic can be presented preferentially. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can use an AI model that determines the order of presentation based on the submission time.

[0051] The presentation unit can determine the order of presentation based on the relevance of the topics at the time of presentation. For example, the presentation unit preferentially presents highly relevant topics. The presentation unit can also postpone less relevant topics. Furthermore, the presentation unit can analyze the relevance of the topics and present them in an optimal order. This allows highly relevant topics to be presented preferentially by adjusting the order of presentation based on the relevance of the topics. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can determine the order of presentation using an AI model that evaluates the relevance of topics.

[0052] The conversion unit can adjust the level of detail of the conversion based on the content of the conversation during conversion. For example, when converting an important conversation, the conversion unit converts the data into detailed text data. In addition, when converting an everyday conversation, the conversion unit can also convert the data into concise text data. Furthermore, when converting an emotional conversation, the conversion unit can also convert the data into text data including detailed emotion analysis. This allows appropriate text data to be generated by adjusting the level of detail of the conversion based on the content of the conversation. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversion unit can adjust the level of detail of the conversion using an AI model that analyzes the content of the conversation.

[0053] The conversion unit can determine the order of conversion based on the submission time of the conversation during conversion. For example, the conversion unit preferentially converts the most recent conversation. In addition, when converting past conversations, the conversion unit can also determine the priority based on the importance. Furthermore, the conversion unit can also preferentially convert conversations related to a specific event. In this way, by determining the priority of conversion based on the submission time of the conversation, the most recent conversation can be preferentially converted. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can use an AI model that determines the order of conversion based on the submission time.

[0054] The reaction analysis unit can select the optimal analysis method based on the user's past reaction history during reaction analysis. The reaction analysis unit selects the optimal analysis method based on, for example, the user's past emotional reaction history. The reaction analysis unit can also select a normal analysis method based on the user's past calm reaction history. Furthermore, the reaction analysis unit can also select the optimal analysis method based on the user's past excited reaction history. This allows for appropriate analysis by selecting the optimal analysis method with reference to the user's past reaction history. Part or all of the above-mentioned processing in the reaction analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the reaction analysis unit can select the optimal analysis method using an AI model that refers to the past reaction history.

[0055] The reaction analysis unit can select the optimal analysis method based on the device information of the user during reaction analysis. For example, when the user is using a smartphone, the reaction analysis unit applies the optimal analysis method for the device. In addition, when the user is using a tablet, the reaction analysis unit can also apply the optimal analysis method for the device. In addition, when the user is using a smartwatch, the reaction analysis unit can also apply the optimal analysis method for the device. This enables appropriate analysis by selecting the optimal analysis method in consideration of the device information of the user. Part or all of the above-mentioned processing in the reaction analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the reaction analysis unit can use an AI model that acquires device information and selects the optimal analysis method based on the information.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] The conversation support system can analyze the user's conversation history and generate new topics based on the content of the user's past conversations. For example, if the user has talked about travel in the past, a new topic related to the travel can be generated. Also, if the user has talked about his / her family in the past, a new topic related to the family can be generated. Furthermore, if the user has talked about a hobby in the past, a new topic related to the hobby can be generated. In this way, by generating new topics based on the user's past conversation history, the conversation can be continued without interruption.

[0058] The conversation support system can suggest new topics that the user may be interested in based on the user's conversation history. For example, if the user has talked about sports in the past, a new topic related to that sport can be suggested. Also, if the user has talked about cooking in the past, a new topic related to that cooking can be suggested. Furthermore, if the user has talked about music in the past, a new topic related to that music can be suggested. In this way, conversations can be enriched by suggesting new topics based on the user's conversation history.

[0059] The conversation support system can generate a new conversation by reusing the contents of the user's past conversations based on the user's conversation history. For example, if the user has talked about travel in the past, a new conversation related to the travel can be generated. Also, if the user has talked about his / her family in the past, a new conversation related to the family can be generated. Furthermore, if the user has talked about a hobby in the past, a new conversation related to the hobby can be generated. In this way, the conversation can be continued without interruption by generating a new conversation by reusing the user's past conversation history.

[0060] The conversation support system can summarize and present content that the user has spoken in the past based on the user's conversation history. For example, if the user has talked about traveling in the past, content related to that travel can be summarized and presented. If the user has talked about his or her family in the past, content related to that family can be summarized and presented. Furthermore, if the user has talked about hobbies in the past, content related to that hobby can be summarized and presented. In this way, by summarizing and presenting the user's past conversation history, the conversation can progress more smoothly.

[0061] The conversation support system can extract conversation patterns by analyzing the contents of past conversations by the user based on the user's conversation history. For example, if the user has frequently talked about a particular topic in the past, a pattern related to that topic can be extracted. Also, if the user has expressed a particular emotion in the past, a pattern related to that emotion can be extracted. Furthermore, if the user has spoken at a particular time in the past, a pattern related to that time can be extracted. In this way, more effective conversation support can be provided by analyzing the user's conversation history and extracting conversation patterns.

[0062] The process flow of the first embodiment will be briefly described below.

[0063] Step 1: The storage unit stores the conversation history. The conversation history includes voice data, text data, metadata, etc. For example, the voice data is stored and used for later analysis. The text data can also be stored and converted into a format that is easy for the analysis unit to analyze. Furthermore, metadata can also be stored to record information such as the content, time, and location of the conversation. Step 2: The analysis unit uses the generation AI to analyze the conversation history stored by the storage unit. The analysis is performed using methods such as natural language processing technology, sentiment analysis, and keyword extraction. For example, natural language processing technology is used to analyze the content of the conversation and extract topics that are likely to interest the user. Sentiment analysis can also be used to analyze the user's emotions and select appropriate topics. Furthermore, keyword extraction technology can be used to extract important keywords in the conversation and select topics based on them. Step 3: The selection unit uses the generation AI to select an appropriate topic based on the results of the analysis by the analysis unit. Topics are selected based on criteria such as the user's interests, past conversation history, and trends. For example, topics are selected based on the user's interests. Topics can also be selected based on past conversation history. Topics can also be selected based on trends. Step 4: The presentation unit presents the topic selected by the selection unit to the user. The presentation is performed by a method such as text display, voice output, or notification. For example, the topic is presented using text display. The topic can also be presented using voice output. Furthermore, the topic can also be presented using notification.

[0064] (Example 2) A conversation support system according to an embodiment of the present invention is a system for suppressing the progression of dementia. In this conversation support system, a user starts a conversation, records the conversation, and saves it as a conversation history. Next, the system analyzes the saved conversation history and automatically selects old stories and memories that the user is likely to be interested in. The selected topic is presented to the user by the system to promote the conversation. This system is characterized by analyzing the conversation history using a generation AI and selecting an appropriate topic. For example, a user starts a conversation. For example, the conversation starts with a simple question such as "What did you do today?". This conversation is recorded as audio by the system and converted into text data. Next, the system analyzes the recorded conversation history. The generation AI understands the content of the conversation and selects a topic that the user is likely to be interested in. For example, if the user says "I went on a trip with my family a long time ago," the system selects a topic related to that trip. The selected topic is presented to the user by the system. For example, the system automatically generates a question such as "Where did you go on that trip?" and presents it to the user. This gives the user more opportunities to talk about past memories, stimulating conversation. The system also analyzes the user's reactions in real time and presents the next question at an appropriate time, allowing the conversation to continue without interruption. This system gives dementia patients more opportunities to talk about past memories, stimulating their minds. Continuing the conversation also reduces feelings of loneliness and promotes mental stability. For example, if a user says, "I once went camping with my family," the system will generate a question such as "What did you do on that camping trip?" and present it to the user. This allows the user to talk about fun memories from the past, stimulating the conversation. In this way, the conversation support system can slow the progression of dementia and promote mental stability for the user.

[0065] The conversation support system according to the embodiment includes a storage unit, an analysis unit, a selection unit, and a presentation unit. The storage unit stores a history of a conversation. The history of a conversation includes, for example, voice data, text data, metadata, and the like, but is not limited to such examples. The storage unit stores, for example, voice data and uses it for later analysis. The storage unit can also store text data and convert it into a format that is easy for the analysis unit to analyze. Furthermore, the storage unit can also store metadata and record information such as the content, time, and location of the conversation. The analysis unit uses a generation AI to analyze the history of the conversation stored by the storage unit. The analysis is performed, for example, by a method such as natural language processing technology, emotion analysis, and keyword extraction, but is not limited to such examples. For example, the analysis unit uses natural language processing technology to analyze the content of the conversation and extracts topics that the user is likely to be interested in. Furthermore, the analysis unit can also analyze the user's emotions using emotion analysis and select an appropriate topic. Furthermore, the analysis unit can also use keyword extraction technology to extract important keywords in the conversation and select a topic based on the keywords. The selection unit uses the generation AI to select an appropriate topic based on the results of the analysis by the analysis unit. The selection of the topic is performed based on criteria such as, for example, the user's interest, past conversation history, and trends, but is not limited to such examples. For example, the selection unit selects a topic based on the user's interest. The selection unit can also select a topic based on past conversation history. Furthermore, the selection unit can also select a topic based on trends. The presentation unit presents the topic selected by the selection unit to the user. The presentation is performed by, for example, a method such as text display, audio output, and notification, but is not limited to such examples. For example, the presentation unit presents the topic using text display. Furthermore, the presentation unit can also present the topic using audio output. Furthermore, the presentation unit can also present the topic using notification. As a result, the conversation support system according to the embodiment can store and analyze the conversation history, select and present an appropriate topic, and thereby suppress the progression of dementia.

[0066] The storage unit stores the history of the conversation. The history of the conversation includes, for example, voice data, text data, metadata, etc., but is not limited to such examples. The storage unit, for example, stores the voice data and uses it for later analysis. Specifically, the voice data is stored in a high-quality format, and may be subjected to noise removal and preprocessing for voice recognition. The storage unit can also store the text data and convert it into a format that is easy for the analysis unit to analyze. Text data is often automatically generated from the voice data, and is accurately transcribed using voice recognition technology. Furthermore, the storage unit can also store metadata and record information such as the content, time, and location of the conversation. The metadata includes the date and time when the conversation took place, information about the participants, the topic of the conversation, etc., and these pieces of information play an important role in later analysis. The storage unit has a database for centrally managing these data and making them quickly accessible as needed. The database is provided with security measures to protect the data and ensure privacy. Furthermore, the storage unit has a data backup function and can prepare for data loss or damage. This allows the storage unit to efficiently and safely store the history of the conversation and use it for later analysis and use.

[0067] The analysis unit uses the generation AI to analyze the conversation history stored by the storage unit. The analysis is performed by, for example, natural language processing technology, emotion analysis, keyword extraction, and other methods, but is not limited to these examples. Specifically, the content of the conversation is analyzed using natural language processing technology to extract topics that the user is likely to be interested in. Natural language processing technology includes morphological analysis, context analysis, semantic analysis, and the like, and these are combined to analyze the content of the conversation in detail. The analysis unit can also analyze the user's emotions using emotion analysis to select appropriate topics. Emotion analysis estimates the user's emotional state from the tone of the voice and the expression of the text, and classifies it into emotion categories such as positive, negative, and neutral. Furthermore, the analysis unit can use keyword extraction technology to extract important keywords in the conversation and select topics based on them. Keyword extraction is performed to identify frequently occurring words and words with high importance, and to clarify the subject and concerns of the conversation. The analysis unit combines these technologies to accurately grasp the user's interests and concerns, and generates basic data for providing appropriate topics. Furthermore, the analysis unit can perform more accurate analysis by utilizing past conversation history and user profile information. This allows the analysis unit to perform advanced analysis according to the user's needs and maximize the effectiveness of the conversation support system.

[0068] The selection unit uses the generation AI to select an appropriate topic based on the results of the analysis by the analysis unit. The selection of the topic is performed based on criteria such as, for example, the user's interest, past conversation history, and trends, but is not limited to such examples. Specifically, the selection unit selects a topic based on the user's interest. The user's interest is extracted from past conversation history and user profile, and the generation AI analyzes it to propose the optimal topic. The selection unit can also select a topic based on past conversation history. The past conversation history records what topics the user was interested in and how he or she responded, and the generation AI selects an appropriate topic based on this. Furthermore, the selection unit can also select a topic based on trends. Trends are extracted from news on the Internet and social media data, and the generation AI analyzes them to provide the latest topics. The selection unit combines these criteria to select the most interesting and appropriate topic for the user. The selection unit can also provide a feedback loop to ensure that the selected topic is beneficial to the user and improves the quality of the conversation. This enables the selection unit to provide optimal topics according to the user's interests and concerns, thereby improving the effectiveness of the conversation support system.

[0069] The presentation unit presents the topic selected by the selection unit to the user. The presentation is performed, for example, by a method such as text display, audio output, or notification, but is not limited to such examples. Specifically, the presentation unit presents the topic using text display. The text display displays the topic on the screen of the user's device to provide information visually. The presentation unit can also present the topic using audio output. The audio output conveys the topic by audio through a speaker or headphones, and can provide information to users with visual impairments or in situations where visual information is difficult to receive. Furthermore, the presentation unit can also present the topic using notification. The notification uses the notification function of a smartphone or tablet to quickly convey important information to the user. The presentation unit can combine these methods to present the topic in the most effective form for the user. Furthermore, the presentation unit can collect user feedback and use it to improve the presentation method. For example, it analyzes which presentation method the user prefers and which presentation method is most effective, and optimizes the presentation method. As a result, the presentation unit can effectively present appropriate topics to the user and maximize the effect of the conversation support system.

[0070] The conversation support system includes a conversion unit that converts the conversation history into text data. The conversion unit converts the conversation history into text data. The text data includes, for example, voice recognition technology, OCR technology, and the like, but is not limited to such examples. For example, the conversion unit converts voice data into text data using voice recognition technology. The conversion unit can also convert handwritten notes into text data using OCR technology. Furthermore, the conversion unit can also convert voice data into text data in real time using voice recognition technology. Thereby, by converting the conversation history into text data, analysis becomes easier. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit inputs voice data to a generation AI and causes the generation AI to execute conversion from voice data to text data.

[0071] The conversation support system includes a reaction analysis unit that analyzes the user's reaction in real time and promotes the next conversation. The reaction analysis unit analyzes the user's reaction in real time. Specific methods and techniques for analyzing in real time include, but are not limited to, streaming data analysis and real-time emotion analysis. For example, the reaction analysis unit analyzes the user's reaction in real time using streaming data analysis. The reaction analysis unit can also analyze the user's emotion in real time using real-time emotion analysis. Furthermore, the reaction analysis unit can also analyze the user's reaction in real time and provide feedback to promote the next conversation. As a result, the conversation can be continued without interruption by analyzing the user's reaction in real time. A part or all of the above-mentioned processing in the reaction analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the reaction analysis unit can input the user's real-time reaction data to the generation AI and cause the generation AI to execute the analysis of the reaction data.

[0072] The storage unit can analyze the user's emotions and adjust the conversation saving frequency based on the analyzed user's emotions. For example, when the user is excited, the storage unit increases the conversation saving frequency and keeps a detailed record. Also, when the user is relaxed, the storage unit can set the conversation saving frequency to normal and maintain a natural conversation flow. Furthermore, when the user is tired, the storage unit can lower the conversation saving frequency and record only important parts. In this way, important conversations can be saved in detail by adjusting the conversation saving frequency according to the user's emotions. The emotion analysis is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion analysis.

[0073] The storage unit can determine the priority of storage based on the importance of the conversation when storing. For example, when the user is talking about important memories, the storage unit prioritizes storing the conversation. In addition, the storage unit can set the priority of storage to low when the user is talking about everyday topics. Furthermore, the storage unit can also save the conversation with a medium priority when the user is talking about emotional topics. In this way, important conversations can be prioritized by determining the priority of storage based on the importance of the conversation. Part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or may be performed without using AI. For example, the storage unit can determine the priority of storage using an AI model that evaluates the importance of the conversation.

[0074] The storage unit can change the storage method according to the category of the conversation when saving. For example, when the user is talking about his / her family, the storage unit saves the conversation in a specific folder. In addition, when the user is talking about traveling, the storage unit can also save the conversation by linking it with photos and maps. Furthermore, when the user is talking about a hobby, the storage unit can also save the conversation together with related information. This makes it easier to manage the conversation by applying different storage methods according to the category of the conversation. Part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or may be performed without using AI. For example, the storage unit can change the storage method using an AI model that classifies the category of the conversation.

[0075] The storage unit can estimate the user's emotion and select the conversation to be saved based on the estimated user's emotion. For example, when the user is speaking emotionally, the storage unit prioritizes saving the conversation. Also, when the user is speaking calmly, the storage unit can set the priority of saving to be low. Furthermore, when the user is excited, the storage unit can save the conversation in detail. In this way, important conversations can be saved preferentially by selecting conversations based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the storage unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the storage unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion estimation.

[0076] The storage unit can, at the time of storage, preferentially store highly relevant conversations in consideration of the geographical location information of the user. For example, when the user is talking at a specific location, the storage unit preferentially stores conversations related to that location. In addition, when the user is talking while traveling, the storage unit can also preferentially store conversations related to the travel destination. Furthermore, when the user is talking at home, the storage unit can also preferentially store everyday conversations. In this way, by storing conversations in consideration of the geographical location information of the user, highly relevant conversations can be preferentially stored. Part or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or may be performed without using AI. For example, the storage unit can use an AI model that acquires the geographical location information of the user and determines the storage priority of conversations based on the information.

[0077] At the time of saving, the storage unit can analyze the user's social media activity and save highly relevant conversations. The storage unit can save, for example, conversations related to the content shared by the user on social media. The storage unit can also save conversations related to the content commented on by the user on social media. Furthermore, the storage unit can also save conversations related to the content on which the user pressed "Like" on social media. In this way, by analyzing the user's social media activity and saving the conversations, highly relevant conversations can be saved preferentially. A part or all of the above-mentioned processing in the storage unit can be performed, for example, using AI or can be performed without using AI. For example, the storage unit can save the related conversations using an AI model that analyzes social media activity.

[0078] The analysis unit can analyze the user's emotions and adjust the accuracy of the analysis based on the analyzed user's emotions. For example, when the user is speaking emotionally, the analysis unit increases the accuracy of the analysis to perform a detailed analysis. In addition, when the user is speaking calmly, the analysis unit can also set the accuracy of the analysis to normal. Furthermore, when the user is excited, the analysis unit can increase the accuracy of the analysis to analyze the change in emotions in detail. This allows for detailed analysis by adjusting the accuracy of the analysis based on the user's emotions. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion analysis.

[0079] The analysis unit can adjust the level of detail of the analysis based on the content of the conversation during the analysis. For example, when the user is talking about an important topic, the analysis unit performs a detailed analysis. In addition, when the user is talking about an everyday topic, the analysis unit can also set the level of detail of the analysis to be low. Furthermore, when the user is talking about an emotional topic, the analysis unit can also perform a detailed emotion analysis. As a result, by adjusting the level of detail of the analysis based on the content of the conversation, important conversations can be analyzed in detail. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the level of detail of the analysis using an AI model that analyzes the content of the conversation.

[0080] The analysis unit can change the analysis algorithm according to the category of the conversation during analysis. For example, when the user is talking about his / her family, the analysis unit applies an analysis algorithm related to the family. In addition, when the user is talking about travel, the analysis unit can also apply an analysis algorithm related to travel. In addition, when the user is talking about a hobby, the analysis unit can also apply an analysis algorithm related to the hobby. This improves the accuracy of the analysis by applying different analysis algorithms according to the category of the conversation. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can change the analysis algorithm using an AI model that classifies the category of the conversation.

[0081] The analysis unit can analyze the user's emotions and determine the priority of the analysis based on the analyzed user's emotions. For example, when the user is speaking emotionally, the analysis unit prioritizes the analysis of the conversation. Also, when the user is speaking calmly, the analysis unit can set the analysis priority to low. Furthermore, when the user is excited, the analysis unit can analyze the conversation in detail. As a result, important conversations can be analyzed preferentially by determining the analysis priority based on the user's emotions. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion analysis.

[0082] The analysis unit can determine the order of analysis based on the submission time of the conversation during analysis. For example, the analysis unit prioritizes analysis of the most recent conversation. In addition, when analyzing past conversations, the analysis unit can also determine the priority based on the importance. Furthermore, the analysis unit can also prioritize analysis of conversations related to a specific event. In this way, by determining the priority of analysis based on the submission time of the conversation, the most recent conversation can be analyzed with priority. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use an AI model that determines the order of analysis based on the submission time.

[0083] The analysis unit can determine the order of analysis based on the relevance of the conversations during analysis. For example, the analysis unit prioritizes analysis of highly relevant conversations. The analysis unit can also postpone analysis of less relevant conversations. Furthermore, the analysis unit can analyze the relevance of the conversations and perform the analysis in an optimal order. This allows the analysis of highly relevant conversations to be prioritized by adjusting the order of analysis based on the relevance of the conversations. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can determine the order of analysis using an AI model that evaluates the relevance of the conversations.

[0084] The selection unit can analyze the user's emotions and determine the priority of topics to be selected based on the analyzed user's emotions. For example, when the user is speaking emotionally, the selection unit preferentially selects topics related to the emotions. In addition, when the user is speaking calmly, the selection unit can also select general topics. Furthermore, when the user is excited, the selection unit can also preferentially select topics related to the excitement. In this way, by determining the priority of topics based on the user's emotions, appropriate topics can be preferentially selected. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion analysis.

[0085] The selection unit can improve the accuracy of the selection based on the interrelationships of conversations at the time of selection. For example, the selection unit selects a related topic based on the content that the user has spoken in the past. The selection unit can also select a topic related to the content that the user is currently speaking. Furthermore, the selection unit can select a topic that the user is likely to be interested in based on the interrelationships. This improves the accuracy of the selection by selecting a topic taking into account the interrelationships of conversations. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can select a topic using an AI model that evaluates the interrelationships of conversations.

[0086] The selection unit can make a selection based on attribute information of the person who submitted the conversation. The selection unit selects an appropriate topic based on, for example, the age of the user. The selection unit can also select an appropriate topic based on the gender of the user. Furthermore, the selection unit can select an appropriate topic based on the hobbies and interests of the user. In this way, an appropriate topic can be selected by selecting a topic taking into consideration the attribute information of the person who submitted the conversation. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI or may be performed without using AI. For example, the selection unit can use an AI model that acquires attribute information of the person who submitted the conversation and selects a topic based on the information.

[0087] The selection unit can analyze the user's emotions and adjust the display method of the selected topic based on the analyzed user's emotions. For example, when the user is speaking emotionally, the selection unit highlights and displays topics related to the emotion. Also, when the user is speaking calmly, the selection unit can present general topics in a normal display method. Furthermore, when the user is excited, the selection unit can visually highlight and display topics related to the excitement. This allows appropriate display by adjusting the display method of the topic based on the user's emotions. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the selection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the selection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion analysis.

[0088] The selection unit can make a selection while taking into consideration the geographical distribution of the conversation. For example, when the user is speaking at a specific location, the selection unit selects a topic related to that location. In addition, when the user is speaking while traveling, the selection unit can also select a topic related to the travel destination. Furthermore, when the user is speaking at home, the selection unit can also select an everyday topic. In this way, by selecting a topic while taking into consideration the geographical distribution of the conversation, an appropriate topic can be selected. Part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can select a topic using an AI model that evaluates the geographical distribution.

[0089] The selection unit can improve the accuracy of the selection based on the literature related to the conversation at the time of selection. For example, the selection unit refers to literature related to the content of the user's conversation and selects an appropriate topic. The selection unit can also refer to literature related to topics that the user may be interested in. Furthermore, the selection unit can also refer to literature related to content that the user has previously spoken and select an appropriate topic. As a result, the accuracy of the selection is improved by selecting a topic by referring to literature related to the conversation. A part or all of the above-mentioned processing in the selection unit may be performed, for example, using AI, or may be performed without using AI. For example, the selection unit can select a topic using an AI model that refers to related literature.

[0090] The presentation unit can analyze the user's emotions and adjust the presentation expression method based on the analyzed user's emotions. For example, when the user is speaking emotionally, the presentation unit presents the topic in an expression method that matches the emotion. In addition, when the user is speaking calmly, the presentation unit can also present the topic in a normal expression method. Furthermore, when the user is excited, the presentation unit can also present the topic in a visually stimulating expression method that matches the excitement. Thereby, by adjusting the presentation expression method based on the user's emotions, appropriate expression becomes possible. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the presentation unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion analysis.

[0091] The presentation unit can adjust the level of detail of the presentation based on the importance of the topic at the time of presentation. For example, when presenting an important topic, the presentation unit presents detailed information. Furthermore, when presenting an everyday topic, the presentation unit can present the topic briefly. Furthermore, when presenting an emotional topic, the presentation unit can present the topic including detailed emotion analysis. In this way, appropriate information can be provided by adjusting the level of detail of the presentation based on the importance of the topic. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can adjust the level of detail of the presentation using an AI model that evaluates the importance of the topic.

[0092] The presentation unit can change the presentation algorithm according to the topic category at the time of presentation. For example, when presenting a topic about family, the presentation unit applies an algorithm related to family. Furthermore, when presenting a topic about travel, the presentation unit can also apply an algorithm related to travel. Furthermore, when presenting a topic about hobbies, the presentation unit can also apply an algorithm related to hobbies. This enables appropriate presentation by applying different presentation algorithms according to the topic category. A part or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can change the presentation algorithm using an AI model that classifies topic categories.

[0093] The presentation unit can analyze the user's emotions and adjust the presentation length based on the analyzed user's emotions. For example, when the user is speaking emotionally, the presentation unit adjusts the presentation length to match the emotion. In addition, when the user is speaking calmly, the presentation unit can also present at a normal length. Furthermore, when the user is excited, the presentation unit can adjust the presentation length to match the excitement. In this way, by adjusting the presentation length based on the user's emotions, information can be provided at an appropriate length. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the presentation unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion analysis.

[0094] The presentation unit can determine the order of presentation based on the submission time of the topic at the time of presentation. For example, the presentation unit preferentially presents the most recent topic. When presenting a past topic, the presentation unit can also determine the priority order based on the importance. Furthermore, the presentation unit can also preferentially present a topic related to a specific event. In this way, by determining the priority order of presentation based on the submission time of the topic, the most recent topic can be presented preferentially. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can use an AI model that determines the order of presentation based on the submission time.

[0095] The presentation unit can determine the order of presentation based on the relevance of the topics at the time of presentation. For example, the presentation unit preferentially presents highly relevant topics. The presentation unit can also postpone less relevant topics. Furthermore, the presentation unit can analyze the relevance of the topics and present them in an optimal order. This allows highly relevant topics to be presented preferentially by adjusting the order of presentation based on the relevance of the topics. A part or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can determine the order of presentation using an AI model that evaluates the relevance of topics.

[0096] The conversion unit can analyze the user's emotions and adjust the method of conversion to text data based on the analyzed user's emotions. For example, when the user is speaking emotionally, the conversion unit converts the data into text data reflecting the emotions. In addition, when the user is speaking calmly, the conversion unit can also convert the data into normal text data. Furthermore, when the user is excited, the conversion unit can also convert the data into text data reflecting the excitement. In this way, appropriate text data can be generated by adjusting the method of conversion to text data based on the user's emotions. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion analysis.

[0097] The conversion unit can adjust the level of detail of the conversion based on the content of the conversation during conversion. For example, when converting an important conversation, the conversion unit converts the data into detailed text data. In addition, when converting an everyday conversation, the conversion unit can also convert the data into concise text data. Furthermore, when converting an emotional conversation, the conversion unit can also convert the data into text data including detailed emotion analysis. This allows appropriate text data to be generated by adjusting the level of detail of the conversion based on the content of the conversation. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversion unit can adjust the level of detail of the conversion using an AI model that analyzes the content of the conversation.

[0098] The conversion unit can analyze the user's emotions and determine the priority of conversion based on the analyzed user's emotions. For example, when the user is speaking emotionally, the conversion unit converts the conversation with priority. Also, when the user is speaking calmly, the conversion unit can set the conversion priority to low. Furthermore, when the user is excited, the conversion unit can convert the conversation in detail. In this way, important conversations can be converted with priority by determining the conversion priority based on the user's emotions. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion analysis.

[0099] The conversion unit can determine the order of conversion based on the submission time of the conversation during conversion. For example, the conversion unit preferentially converts the most recent conversation. In addition, when converting past conversations, the conversion unit can also determine the priority based on the importance. Furthermore, the conversion unit can also preferentially convert conversations related to a specific event. In this way, by determining the priority of conversion based on the submission time of the conversation, the most recent conversation can be preferentially converted. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can use an AI model that determines the order of conversion based on the submission time.

[0100] The reaction analysis unit can analyze the user's emotions and adjust the reaction analysis method based on the analyzed user's emotions. For example, when the user is reacting emotionally, the reaction analysis unit applies an analysis method that reflects the emotion. In addition, when the user is reacting calmly, the reaction analysis unit can also apply a normal analysis method. In addition, when the user is reacting excitedly, the reaction analysis unit can also apply an analysis method that reflects the excitement. This allows appropriate analysis by adjusting the reaction analysis method based on the user's emotions. The emotion analysis is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reaction analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reaction analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute emotion analysis.

[0101] The reaction analysis unit can select the optimal analysis method based on the user's past reaction history during reaction analysis. The reaction analysis unit selects the optimal analysis method based on, for example, the user's past emotional reaction history. The reaction analysis unit can also select a normal analysis method based on the user's past calm reaction history. Furthermore, the reaction analysis unit can also select the optimal analysis method based on the user's past excited reaction history. This allows for appropriate analysis by selecting the optimal analysis method with reference to the user's past reaction history. Part or all of the above-mentioned processing in the reaction analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the reaction analysis unit can select the optimal analysis method using an AI model that refers to the past reaction history.

[0102] The reaction analysis unit can analyze the user's emotions and determine the priority of the reaction analysis based on the analyzed user's emotions. For example, when the user is reacting emotionally, the reaction analysis unit prioritizes the analysis of the reaction. In addition, when the user is reacting calmly, the reaction analysis unit can also set the analysis priority to be low. Furthermore, when the user is reacting excitedly, the reaction analysis unit can also analyze the reaction in detail. In this way, by determining the priority of the reaction analysis based on the user's emotions, important reactions can be analyzed preferentially. The analysis of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reaction analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reaction analysis unit can input the user's emotion data to the generation AI and cause the generation AI to execute the emotion analysis.

[0103] The reaction analysis unit can select the optimal analysis method based on the device information of the user during reaction analysis. For example, when the user is using a smartphone, the reaction analysis unit applies the optimal analysis method for the device. In addition, when the user is using a tablet, the reaction analysis unit can also apply the optimal analysis method for the device. In addition, when the user is using a smartwatch, the reaction analysis unit can also apply the optimal analysis method for the device. This enables appropriate analysis by selecting the optimal analysis method in consideration of the device information of the user. Part or all of the above-mentioned processing in the reaction analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the reaction analysis unit can use an AI model that acquires device information and selects the optimal analysis method based on the information.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The conversation support system can learn the conversation patterns of the user and predict how the user will react to a particular topic. For example, if the user reacts positively to a particular topic, the system can present the topic with priority. If the user reacts negatively to a particular topic, the system can avoid the topic. Furthermore, if the user reacts neutrally to a particular topic, the system can present the topic at an appropriate time. This allows for more effective conversation support by selecting topics based on the user's conversation patterns.

[0106] The conversation support system can analyze the user's conversation history and generate new topics based on the content of the user's past conversations. For example, if the user has talked about travel in the past, a new topic related to the travel can be generated. Also, if the user has talked about his / her family in the past, a new topic related to the family can be generated. Furthermore, if the user has talked about a hobby in the past, a new topic related to the hobby can be generated. In this way, by generating new topics based on the user's past conversation history, the conversation can be continued without interruption.

[0107] The conversation support system can analyze the user's emotions and adjust the tone of the conversation based on the analyzed user's emotions. For example, if the user is speaking emotionally, the system can continue the conversation in a tone that matches the emotion. Also, if the user is speaking calmly, the system can continue the conversation in a normal tone. Furthermore, if the user is excited, the system can continue the conversation in a tone that matches the excitement. In this way, by adjusting the tone of the conversation based on the user's emotions, a more natural conversation is possible.

[0108] The conversation support system can suggest new topics that the user may be interested in based on the user's conversation history. For example, if the user has talked about sports in the past, a new topic related to that sport can be suggested. Also, if the user has talked about cooking in the past, a new topic related to that cooking can be suggested. Furthermore, if the user has talked about music in the past, a new topic related to that music can be suggested. In this way, conversations can be enriched by suggesting new topics based on the user's conversation history.

[0109] The conversation support system can analyze the user's emotions and adjust the conversation progress speed based on the analyzed user's emotions. For example, if the user is speaking emotionally, the system can slow down the conversation progress speed to make it easier for the user to express his / her emotions. Also, if the user is speaking calmly, the system can continue the conversation at a normal progress speed. Furthermore, if the user is excited, the system can speed up the conversation progress speed to maintain the user's excitement. This allows for more effective conversation support by adjusting the conversation progress speed based on the user's emotions.

[0110] The conversation support system can generate a new conversation by reusing the contents of the user's past conversations based on the user's conversation history. For example, if the user has talked about travel in the past, a new conversation related to the travel can be generated. Also, if the user has talked about his / her family in the past, a new conversation related to the family can be generated. Furthermore, if the user has talked about a hobby in the past, a new conversation related to the hobby can be generated. In this way, the conversation can be continued without interruption by generating a new conversation by reusing the user's past conversation history.

[0111] The conversation support system can analyze the user's emotions and adjust the content of the conversation based on the analyzed user's emotions. For example, if the user is speaking emotionally, the system can continue the conversation with content that matches the user's emotions. If the user is speaking calmly, the system can also continue the conversation with normal content. Furthermore, if the user is excited, the system can also continue the conversation with content that matches the user's excitement. In this way, by adjusting the content of the conversation based on the user's emotions, more natural conversations are possible.

[0112] The conversation support system can summarize and present content that the user has spoken in the past based on the user's conversation history. For example, if the user has talked about traveling in the past, content related to that travel can be summarized and presented. If the user has talked about his or her family in the past, content related to that family can be summarized and presented. Furthermore, if the user has talked about hobbies in the past, content related to that hobby can be summarized and presented. In this way, by summarizing and presenting the user's past conversation history, the conversation can progress more smoothly.

[0113] The conversation support system can analyze the user's emotions and select a conversation topic based on the analyzed user's emotions. For example, if the user is speaking emotionally, a topic related to the emotion can be selected. If the user is speaking calmly, a general topic can be selected. Furthermore, if the user is excited, a topic related to the excitement can be selected. In this way, more effective conversation support can be achieved by selecting a conversation topic based on the user's emotions.

[0114] The conversation support system can extract conversation patterns by analyzing the contents of past conversations by the user based on the user's conversation history. For example, if the user has frequently talked about a particular topic in the past, a pattern related to that topic can be extracted. Also, if the user has expressed a particular emotion in the past, a pattern related to that emotion can be extracted. Furthermore, if the user has spoken at a particular time in the past, a pattern related to that time can be extracted. In this way, more effective conversation support can be provided by analyzing the user's conversation history and extracting conversation patterns.

[0115] The process flow of the second embodiment will be briefly described below.

[0116] Step 1: The storage unit stores the conversation history. The conversation history includes voice data, text data, metadata, etc. For example, the voice data is stored and used for later analysis. The text data can also be stored and converted into a format that is easy for the analysis unit to analyze. Furthermore, metadata can also be stored to record information such as the content, time, and location of the conversation. Step 2: The analysis unit uses the generation AI to analyze the conversation history stored by the storage unit. The analysis is performed using methods such as natural language processing technology, sentiment analysis, and keyword extraction. For example, natural language processing technology is used to analyze the content of the conversation and extract topics that are likely to interest the user. Sentiment analysis can also be used to analyze the user's emotions and select appropriate topics. Furthermore, keyword extraction technology can be used to extract important keywords in the conversation and select topics based on them. Step 3: The selection unit uses the generation AI to select an appropriate topic based on the results of the analysis by the analysis unit. Topics are selected based on criteria such as the user's interests, past conversation history, and trends. For example, topics are selected based on the user's interests. Topics can also be selected based on past conversation history. Topics can also be selected based on trends. Step 4: The presentation unit presents the topic selected by the selection unit to the user. The presentation is performed by a method such as text display, voice output, or notification. For example, the topic is presented using text display. The topic can also be presented using voice output. Furthermore, the topic can also be presented using notification.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0118] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0119] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0120] Each of the multiple elements including the above-mentioned storage unit, analysis unit, selection unit, and presentation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the storage unit stores the conversation history in the storage 50 of the smart device 14 or the storage 32 of the data processing device 12. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the stored conversation history using a generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and selects an appropriate topic based on the analysis result. The presentation unit is realized, for example, by the control unit 46A of the smart device 14, and presents the selected topic to the user. The conversion unit is realized, for example, by the control unit 46A of the smart device 14, and converts voice data into text data. The reaction analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the user's reaction in real time. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 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.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] 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.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0128] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] 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.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0131] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0135] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements including the above-mentioned storage unit, analysis unit, selection unit, and presentation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the storage unit stores the conversation history in the storage 50 of the smart glasses 214 or the storage 32 of the data processing device 12. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the stored conversation history using a generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and selects an appropriate topic based on the analysis result. The presentation unit is realized, for example, by the control unit 46A of the smart glasses 214, and presents the selected topic to the user. The conversion unit is realized, for example, by the control unit 46A of the smart glasses 214, and converts voice data into text data. The reaction analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the user's reaction in real time. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 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.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] 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.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0144] 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.

[0145] 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.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0147] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0151] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements including the above-mentioned storage unit, analysis unit, selection unit, and presentation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the storage unit stores the conversation history in the storage 50 of the headset type terminal 314 or the storage 32 of the data processing device 12. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the stored conversation history using a generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and selects an appropriate topic based on the analysis result. The presentation unit is realized, for example, by the control unit 46A of the headset type terminal 314, and presents the selected topic to the user. The conversion unit is realized, for example, by the control unit 46A of the headset type terminal 314, and converts voice data into text data. The reaction analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the user's reaction in real time. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] 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.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0160] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0161] 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.

[0162] 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.

[0163] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0164] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0165] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0166] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0168] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0169] Each of the multiple elements including the above-mentioned storage unit, analysis unit, selection unit, and presentation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the storage unit stores the conversation history in the storage 50 of the robot 414 or the storage 32 of the data processing device 12. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the stored conversation history using a generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and selects an appropriate topic based on the analysis result. The presentation unit is realized, for example, by the control unit 46A of the robot 414, and presents the selected topic to the user. The conversion unit is realized, for example, by the control unit 46A of the robot 414, and converts voice data into text data. The reaction analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the user's reaction in real time. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0170] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0171] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0172] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0173] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0174] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0175] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0176] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0177] 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.

[0178] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0179] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0180] 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.

[0181] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0182] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0183] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0184] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0185] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0186] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0187] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0188] (Appendix 1) A storage unit for storing a conversation history; an analysis unit that analyzes the conversation history stored by the storage unit; a selection unit that selects a topic based on the result of the analysis by the analysis unit; A presentation unit that presents the topic selected by the selection unit to a user. A system characterized by: (Appendix 2) Equipped with a conversion unit that converts conversation history into text data 2. The system of claim 1, (Appendix 3) Equipped with a reaction analysis section that analyzes user reactions in real time and analyzes the next conversation 2. The system of claim 1, (Appendix 4) The storage unit includes: Analyze user sentiment and adjust the frequency of saving conversations based on the analyzed user sentiment 2. The system of claim 1, (Appendix 5) The storage unit includes: When saving, prioritize saving based on the importance of the conversation 2. The system of claim 1, (Appendix 6) The storage unit includes: When saving, change the way you save depending on the conversation category 2. The system of claim 1, (Appendix 7) The storage unit includes: Infer user emotions and select conversations to store based on the estimated user emotions. 2. The system of claim 1, (Appendix 8) The storage unit includes: When saving, prioritize saving the most relevant conversations based on the user's geographic location 2. The system of claim 1, (Appendix 9) The storage unit includes: At the time of storage, we analyze your social media activity and store the most relevant conversations. 2. The system of claim 1, (Appendix 10) The analysis unit is Analyze user emotions and adjust the accuracy of the analysis based on the analyzed user emotions 2. The system of claim 1, (Appendix 11) The analysis unit is During analysis, adjust the accuracy of the analysis based on the content of the conversation 2. The system of claim 1, (Appendix 12) The analysis unit is During analysis, the analysis algorithm changes depending on the conversation category. 2. The system of claim 1, (Appendix 13) The analysis unit is Analyze user sentiment and determine analysis priorities based on the analyzed user sentiment 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, determine the order of analysis based on when the conversations were submitted 2. The system of claim 1, (Appendix 15) The analysis unit is During parsing, order of parsing is determined based on conversation relevance 2. The system of claim 1, (Appendix 16) The selection unit is Analyze user sentiment and prioritize topics based on the analyzed user sentiment 2. The system of claim 1, (Appendix 17) The selection unit is During selection, improve selection accuracy based on conversation correlation 2. The system of claim 1, (Appendix 18) The selection unit is When selecting a conversation, the selection is based on the attribute information of the person submitting the conversation. 2. The system of claim 1, (Appendix 19) The selection unit is Analyze user sentiment and adjust the display method of selected topics based on the analyzed user sentiment. 2. The system of claim 1, (Appendix 20) The selection unit is When making selections, the selection will be based on the geographic distribution of conversations. 2. The system of claim 1, (Appendix 21) The selection unit is When selecting, improve the accuracy of the selection based on the related literature of the conversation 2. The system of claim 1, (Appendix 22) The presentation unit is Analyze user's emotions and adjust presentation style based on the analyzed user's emotions 2. The system of claim 1, (Appendix 23) The presentation unit is At presentation time, adjust the level of detail of the presentation based on the importance of the topic 2. The system of claim 1, (Appendix 24) The presentation unit is At the time of presentation, the presentation algorithm changes depending on the topic category. 2. The system of claim 1, (Appendix 25) The presentation unit is Analyze user's emotions and adjust presentation length based on the analyzed user's emotions 2. The system of claim 1, (Appendix 26) The presentation unit is During presentation, determine the order of presentation based on when topics were submitted 2. The system of claim 1, (Appendix 27) The presentation unit is During presentation, determine the order of presentation based on topical relevance 2. The system of claim 1, (Appendix 28) The conversion unit is Analyze user sentiment and adjust the method of converting text data based on the analyzed user sentiment. 3. The system of claim 2, (Appendix 29) The conversion unit is When converting, adjust conversion accuracy based on the content of the conversation 3. The system of claim 2, (Appendix 30) The conversion unit is Analyze user sentiment and prioritize conversions based on the analyzed user sentiment 3. The system of claim 2, (Appendix 31) The conversion unit is During conversion, determine the order of conversion based on when the conversations were submitted 3. The system of claim 2, (Appendix 32) The reaction analysis unit includes: Analyze user emotions and adjust the reaction analysis method based on the analyzed user emotions. 4. The system of claim 3. (Appendix 33) The reaction analysis unit includes: When analyzing reactions, the most suitable analysis method is selected based on the user's past reaction history. 4. The system of claim 3. (Appendix 34) The reaction analysis unit includes: Analyze user sentiment and determine priority of reaction analysis based on the analyzed user sentiment. 4. The system of claim 3. (Appendix 35) The reaction analysis unit includes: When analyzing reactions, the optimal analysis method is selected based on the user's device information. 4. The system of claim 3. [Explanation of symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A storage unit for storing a conversation history; an analysis unit that analyzes the conversation history stored by the storage unit; a selection unit that selects a topic based on the result of the analysis by the analysis unit; A presentation unit that presents the topic selected by the selection unit to a user. A system characterized by:

2. The presentation unit is Adjust the level of detail presented based on the importance of the topic 2. The system of claim 1 .

3. Equipped with a reaction analysis section that analyzes user reactions in real time and analyzes the next conversation 2. The system of claim 1 .

4. The storage unit includes: Analyze user sentiment and adjust the frequency of saving conversations based on the analyzed user sentiment 2. The system of claim 1 .

5. The storage unit includes: When saving, prioritize saving based on the importance of the conversation 2. The system of claim 1 .

6. The storage unit includes: When saving, change the way you save depending on the conversation category 2. The system of claim 1 .

7. The storage unit includes: Infer user emotions and select conversations to store based on the estimated user emotions.

2. The system of claim 1 .

8. The storage unit includes: When saving, prioritize saving the most relevant conversations based on the user's geographic location 2. The system of claim 1 .

9. The storage unit includes: At the time of storage, we analyze your social media activity and store the most relevant conversations.

2. The system of claim 1 .

Images