System

Abstract

An object of the system according to the embodiment is to prevent sleepiness during driving for a long time by providing a conversation based on the interest and concern of the driver.SOLUTION: A system includes a registration unit, a storage unit, a provision unit, a database unit, a response unit, and a conversation management unit. The registration unit registers a driver's interest and concern. The storage unit stores the information registered by the registration unit. The providing unit provides a topic based on the information stored in the storage unit. The database unit stores data related to the topic provided by the providing unit. The response unit answers the driver's question based on the topic provided by the providing unit. The conversation management unit manages the conversation with the driver by the response unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately provide means for effectively preventing driver drowsiness during long driving periods, and there is room for improvement.

[0005] The system according to the embodiment aims to prevent drowsiness during long driving periods by providing conversations based on the driver's interests and concerns. [Means for solving the problem]

[0006] The system according to the embodiment includes a registration unit, a storage unit, a providing unit, a database unit, a response unit, and a conversation management unit. The registration unit registers the interests and concerns of the driver. The storage unit stores the information registered by the registration unit. The providing unit provides topics based on the information stored in the storage unit. The database unit stores data related to the topics provided by the providing unit. The response unit answers questions from the driver based on the topics provided by the providing unit. The conversation management unit manages conversations with the driver via the response unit. [Effects of the Invention]

[0007] The system according to the embodiment can prevent drowsiness during long driving periods by providing conversations based on the driver's interests and concerns. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A high-performance AI car navigation system according to an embodiment of the present invention provides topics based on the driver's interests and encourages conversation, preventing the driver from becoming drowsy and allowing the driver to continue enjoying their drive. For example, the system can register the driver's interests in advance, and then use that information to provide topics and encourage conversation while the driver is driving. This allows the driver to continue enjoying their drive without feeling drowsy. For example, if the driver is a soccer fan, the system can provide topics about the team's latest news and game results. Also, if the driver is heading to a travel destination, the system can provide topics about the destination's attractions and tourist information. Furthermore, the AI ​​car navigation system can continue to engage in conversation with the driver. For example, if the driver asks, "When is the next game?", the AI ​​car navigation system can answer that question. Also, if the driver asks, "What restaurants are recommended at this travel destination?", the AI ​​car navigation system can also answer that question. This allows the high-performance AI car navigation system to prevent the driver from becoming drowsy and continue enjoying their drive. For example, even if the driver becomes drowsy during a long drive, they can avoid drowsiness by enjoying a conversation with the AI ​​car navigation system. Furthermore, by enjoying conversations about topics that interest the driver, the drive becomes more enjoyable.

[0029] A high-performance AI car navigation system according to an embodiment includes a registration unit, a storage unit, a providing unit, a database unit, a response unit, and a conversation management unit. The registration unit registers the driver's interests. For example, the driver can input information about their favorite sports teams, hobbies, travel destinations, etc. The storage unit saves the information registered by the registration unit. For example, if the driver is a soccer fan, the storage unit saves the team's latest information and game results. The provision unit provides topics based on the information saved in the storage unit. For example, if the driver is a soccer fan, the provision unit saves the team's latest information and game results. The database unit saves data related to the topics provided by the provision unit. For example, the database unit saves a history of the provided topics and uses them for future conversations. The response unit answers the driver's questions based on the topics provided by the provision unit. For example, if the driver asks, "When is the next game?", the response unit can answer the question. The conversation management unit manages the conversation with the driver via the response unit. For example, the conversation management unit manages the progress of the conversation with the driver to ensure a smooth conversation. As a result, the high-performance AI car navigation system according to the embodiment can provide topics based on the driver's interests and keep the conversation going, preventing the driver from getting drowsy and allowing them to continue enjoying their drive.

[0030] The registration unit analyzes the driver's past history of interests and selects the optimal registration method. For example, the registration unit analyzes patterns of interests and concerns registered in the past and suggests the most frequently used method. The registration unit can also preferentially suggest the driver's preferred registration method (voice, text, etc.) based on the past history. The registration unit can also suggest a registration method suitable for a specific time period based on the past history. This makes it possible to suggest the optimal registration method based on the past history. The analysis of the history may be performed, for example, using AI or without using AI.

[0031] When registering interests, the registration unit filters the interests based on the driver's current living situation and areas of interest. The registration unit suggests related interests based on, for example, the driver's current occupation and hobbies. The registration unit can also filter appropriate interests based on the driver's family structure and lifestyle. The registration unit can also suggest related interests based on the driver's current health condition and fitness level. This makes it possible to suggest appropriate interests according to the driver's current situation. The filtering process may be performed using, for example, AI or without AI.

[0032] When registering interests and concerns, the registration unit selects an appropriate registration means according to the driver's input method. For example, if the driver prefers voice input, the registration unit registers interests and concerns using voice recognition technology. Furthermore, if the driver prefers text input, the registration unit can provide a simple text input interface. Furthermore, if the driver prefers image input, the registration unit can register interests and concerns using image recognition technology. This makes it possible to provide the optimal registration means according to the driver's input method. The selection of the input method may be performed using, for example, AI or without AI.

[0033] When registering interests and concerns, the registration unit prioritizes registering highly relevant information taking into account the driver's geographical location information. For example, if the driver is in a specific area, the registration unit prioritizes registering interests and concerns related to that area. Furthermore, if the driver is traveling, the registration unit can prioritize registering tourist information and sights at the travel destination. Furthermore, if the driver is commuting to work, the registration unit can prioritize registering interests and concerns related to the commuting route. This makes it possible to prioritize registering highly relevant information based on the driver's geographical location information. The acquisition of geographical location information and the selection of highly relevant information may be performed, for example, using AI or without AI.

[0034] When registering interests, the registration unit analyzes the driver's social media activity and registers related information. The registration unit may, for example, register interests based on the accounts the driver follows on social media. The registration unit may also analyze the content of the driver's social media posts and register related interests. The registration unit may also register related interests based on the activities of the driver's friends on social media. This makes it possible to register related information based on the driver's social media activity. The analysis of social media activity may be performed, for example, using AI or without AI.

[0035] The registration unit customizes the registration method by reflecting the driver's past feedback when registering interests. The registration unit, for example, suggests the optimal registration method based on feedback provided by the driver in the past. The registration unit can also preferentially suggest a specific registration method based on the driver's past feedback. The registration unit can also analyze the driver's past feedback and customize the registration method. This makes it possible to customize the registration method based on the driver's past feedback. The analysis and reflection of feedback may be performed, for example, using AI or may be performed without using AI.

[0036] The storage unit optimizes the storage algorithm by referring to previously stored data when storing data. For example, the storage unit analyzes previously stored data and selects an optimal storage algorithm. The storage unit can also extract specific patterns from previously stored data and optimize the storage algorithm. The storage unit can also adjust parameters of the storage algorithm based on the previously stored data. This makes it possible to optimize the storage algorithm based on the previously stored data. Optimization of the storage algorithm may be performed using, for example, AI or without using AI.

[0037] The storage unit updates the stored data by reflecting the driver's feedback when storing the data. The storage unit updates the stored data, for example, based on the feedback provided by the driver. The storage unit can also prioritize storing specific data based on the driver's feedback. The storage unit can also analyze the driver's feedback and optimize the stored data. This makes it possible to update the stored data based on the driver's feedback. The feedback can be reflected, for example, using AI or without using AI.

[0038] The storage unit analyzes fluctuations in the driver's interests and adjusts the update frequency of the stored data when storing the data. For example, if the driver's interests and concerns change frequently, the storage unit increases the update frequency of the stored data. In addition, if the driver's interests and concerns are stable, the storage unit can also decrease the update frequency of the stored data. In addition, the storage unit can analyze the pattern of fluctuations in the driver's interests and concerns and set an optimal update frequency. This makes it possible to adjust the update frequency of the stored data based on fluctuations in the driver's interests and concerns. The analysis of fluctuations in interests and concerns may be performed, for example, using AI or without using AI.

[0039] The storage unit weights the stored data based on the registration time of the interests and concerns when storing the data. For example, the storage unit prioritizes storing recently registered interests and concerns. The storage unit can also prioritize storing interests and concerns that have been registered over a long period of time. The storage unit can also adjust the weighting of the stored data based on the registration time. This allows the stored data to be weighted based on the registration time of the interests and concerns. The weighting adjustment may be performed using, for example, AI or without AI.

[0040] The storage unit integrates information from different data sources to enrich the stored data when storing the data. For example, the storage unit integrates information from social media to enrich the stored data. The storage unit can also integrate information from news sites to enrich the stored data. The storage unit can also integrate information from the driver's past search history to enrich the stored data. In this way, the stored data can be enriched by integrating information from different data sources. The integration of data sources may be performed using AI, for example, or may be performed without using AI.

[0041] When providing a topic, the providing unit adjusts the level of detail to be provided based on the importance of the topic. For example, in the case of an important topic, the providing unit provides detailed information. In addition, in the case of a less important topic, the providing unit can also provide concise information. In addition, the providing unit can adjust the level of detail to be provided based on the importance of the topic. In this way, the level of detail to be provided can be adjusted based on the importance of the topic. The adjustment of the level of detail to be provided may be performed, for example, using AI or may be performed without using AI.

[0042] When providing a topic, the providing unit applies an appropriate providing algorithm depending on the category of the topic. For example, in the case of a sports-related topic, the providing unit applies an algorithm that provides the latest game results and player information. In addition, in the case of a travel-related topic, the providing unit can also apply an algorithm that provides tourist spot and restaurant information. In addition, in the case of an entertainment-related topic, the providing unit can also apply an algorithm that provides the latest information on movies and music. In this way, it is possible to apply the optimal providing algorithm depending on the category of the topic. The application of the providing algorithm may be performed using, for example, AI, or may be performed without using AI.

[0043] When providing a topic, the providing unit improves the accuracy of the topic provision by referring to the driver's past provision results. The providing unit, for example, analyzes reactions to topics provided in the past to improve the accuracy of the topic provision. The providing unit can also preferentially provide topics that the driver prefers based on the past provision results. The providing unit can also optimize the provision algorithm based on the past provision results. This makes it possible to improve the accuracy of the topic provision based on the driver's past provision results. The improvement in the accuracy of the topic provision may be performed, for example, using AI or without using AI.

[0044] When providing a topic, the providing unit determines the priority of the topic based on the time of submission. For example, the providing unit provides the most recent topic with priority. The providing unit can also postpone topics that have been submitted earlier. The providing unit can also adjust the priority of the topic based on the time of submission. This makes it possible to determine the priority of the topic based on the time of submission. The determination of the priority of the topic may be performed using AI, for example, or may be performed without using AI.

[0045] The provision unit adjusts the order of topics provided based on the relevance of the topics when providing the topics. For example, the provision unit prioritizes providing a topic that is most relevant to the driver's interests and concerns. The provision unit can also prioritize providing a topic that is relevant to the driver's current situation. The provision unit can also prioritize providing a topic that is highly relevant based on the driver's past responses. This makes it possible to adjust the order of topics provided based on the relevance of the topics. The adjustment of the order of topics provided may be performed using AI, for example, or may be performed without using AI.

[0046] When providing a topic, the providing unit adjusts the use of technical terms in the provided topic depending on the driver's level of expertise. For example, if the driver has technical expertise, the providing unit provides a topic that uses a lot of technical terms. Furthermore, if the driver does not have technical expertise, the providing unit can also provide a topic that explains the topic in simple terms. Furthermore, the providing unit can adjust the use of technical terms in accordance with the driver's level of expertise. In this way, the use of technical terms in the provided topic can be adjusted depending on the driver's level of expertise. The adjustment of the use of technical terms may be performed, for example, using AI or may be performed without using AI.

[0047] When updating the database, the database unit optimizes the update algorithm by referring to past data. For example, the database unit analyzes data stored in the past and selects an optimal update algorithm. The database unit can also extract specific patterns from the past data and optimize the update algorithm. The database unit can also adjust the parameters of the update algorithm based on the past data. This makes it possible to optimize the update algorithm based on the past data. Optimization of the update algorithm may be performed using, for example, AI or without using AI.

[0048] When updating the database, the database unit updates the data by reflecting the driver's feedback. The database unit updates the data based on, for example, the feedback provided by the driver. The database unit can also prioritize updating specific data based on the driver's feedback. The database unit can also analyze the driver's feedback and optimize the data. This makes it possible to update the data based on the driver's feedback. The feedback may be reflected using, for example, AI or without using AI.

[0049] When updating the database, the database unit analyzes fluctuations in the driver's interests and adjusts the data update frequency. For example, if the driver's interests and concerns change frequently, the database unit increases the data update frequency. In addition, if the driver's interests and concerns remain stable, the database unit can also decrease the data update frequency. In addition, the database unit can analyze the pattern of fluctuations in the driver's interests and concerns and set an optimal update frequency. This makes it possible to adjust the data update frequency based on fluctuations in the driver's interests and concerns. The analysis of fluctuations in interests and concerns may be performed, for example, using AI or without using AI.

[0050] When updating the database, the database unit integrates information from different data sources to enrich the data. For example, the database unit integrates information from social media to enrich the data. The database unit can also integrate information from news sites to enrich the data. The database unit can also integrate information from the driver's past search history to enrich the data. In this way, the data can be enriched by integrating information from different data sources. The integration of data sources may be performed, for example, using AI or without using AI.

[0051] When updating the database, the database unit takes into consideration the driver's geographical location information and prioritizes updating highly relevant data. For example, when the driver is in a specific area, the database unit prioritizes updating data related to that area. Furthermore, when the driver is traveling, the database unit can also prioritize updating tourist information and attractions for the travel destination. Furthermore, when the driver is commuting to work, the database unit can also prioritize updating data related to the commuting route. This makes it possible to prioritize updating highly relevant data based on the driver's geographical location information. The acquisition of geographical location information and the selection of highly relevant data may be performed, for example, using AI or without using AI.

[0052] When responding, the response unit adjusts the level of detail of the response based on the importance of the question. For example, the response unit provides a detailed response in the case of an important question. The response unit can also provide a concise response in the case of a less important question. The response unit can also adjust the level of detail of the response based on the importance of the question. This makes it possible to adjust the level of detail of the response based on the importance of the question. The adjustment of the level of detail of the response may be performed, for example, using AI or may be performed without using AI.

[0053] When responding, the response unit applies different response algorithms depending on the category of the question. For example, in the case of a sports-related question, the response unit applies an algorithm that provides the latest game results and player information. In addition, in the case of a travel-related question, the response unit can apply an algorithm that provides tourist spot and restaurant information. In addition, in the case of an entertainment-related question, the response unit can apply an algorithm that provides the latest information on movies and music. In this way, it is possible to apply the optimal response algorithm depending on the category of the question. The application of the response algorithm may be performed using, for example, AI or without using AI.

[0054] When responding, the response unit improves the accuracy of the response by referring to the driver's past response results. The response unit, for example, analyzes reactions to responses provided in the past to improve the accuracy of the response. The response unit can also preferentially provide a response method preferred by the driver based on the past response results. The response unit can also optimize a response algorithm based on the past response results. This makes it possible to improve the accuracy of the response based on the driver's past response results. The improvement in response accuracy may be performed, for example, using AI or without using AI.

[0055] When responding, the response unit determines the priority of the responses based on the time of submission of the question. For example, the response unit prioritizes responses to the most recent questions. The response unit can also postpone questions that have been submitted earlier. The response unit can also adjust the priority of the responses based on the time of submission. This makes it possible to determine the priority of the responses based on the time of submission of the questions. The determination of the priority of the responses may be performed using, for example, AI or without using AI.

[0056] The response unit adjusts the order of responses based on the relevance of the questions when responding. For example, the response unit prioritizes responses to questions that are most relevant to the driver's interests and concerns. The response unit can also prioritize responses to questions that are relevant to the driver's current situation. The response unit can also prioritize responses to highly relevant questions based on the driver's past responses. This makes it possible to adjust the order of responses based on the relevance of the questions. Adjustment of the order of responses may be performed, for example, using AI or without using AI.

[0057] When responding, the response unit adjusts the use of technical terms in the response according to the driver's level of expertise. For example, if the driver has technical expertise, the response unit provides a response that uses a lot of technical terms. Also, if the driver does not have technical expertise, the response unit can provide a response that explains in simple terms. Also, the response unit can adjust the use of technical terms according to the driver's level of expertise. In this way, the use of technical terms in the response can be adjusted according to the driver's level of expertise. The adjustment of the use of technical terms may be performed, for example, using AI or may be performed without using AI.

[0058] The conversation management unit optimizes the conversation algorithm by referring to past conversation history during conversation management. For example, the conversation management unit analyzes the past conversation history and selects the optimal conversation algorithm. The conversation management unit can also extract specific patterns from the past conversation history and optimize the conversation algorithm. The conversation management unit can also adjust the parameters of the conversation algorithm based on the past conversation history. This makes it possible to optimize the conversation algorithm based on the past conversation history. Optimization of the conversation algorithm may be performed, for example, using AI or without using AI.

[0059] The conversation management unit updates the progress of the conversation by reflecting the driver's feedback during conversation management. The conversation management unit updates the progress of the conversation based on, for example, feedback provided by the driver. The conversation management unit can also prioritize the progress of a specific conversation pattern based on the driver's feedback. The conversation management unit can also analyze the driver's feedback and optimize the progress of the conversation. This makes it possible to update the progress of the conversation based on the driver's feedback. Reflecting the feedback may be performed using AI, for example, or may be performed without using AI.

[0060] The conversation management unit analyzes fluctuations in the driver's interests and adjusts the frequency of conversation progression during conversation management. For example, if the driver's interests and concerns change frequently, the conversation management unit increases the frequency of conversation progression. In addition, the conversation management unit can also decrease the frequency of conversation progression if the driver's interests and concerns are stable. The conversation management unit can also analyze fluctuation patterns in the driver's interests and set an optimal frequency of progression. This makes it possible to adjust the frequency of conversation progression based on fluctuations in the driver's interests and concerns. The analysis of fluctuations in interests and concerns may be performed, for example, using AI or without using AI.

[0061] The conversation management unit prioritizes highly relevant conversations during conversation management, taking into account the driver's geographical location information. For example, when the driver is in a specific area, the conversation management unit prioritizes topics related to that area. Furthermore, when the driver is traveling, the conversation management unit can prioritize topics related to tourist information and attractions at the travel destination. Furthermore, when the driver is commuting to work, the conversation management unit can prioritize topics related to the commuting route. This makes it possible to prioritize highly relevant conversations based on the driver's geographical location information. The acquisition of geographical location information and the selection of highly relevant conversations may be performed, for example, using AI or without AI.

[0062] During conversation management, the conversation management unit analyzes the driver's social media activities and advances related conversations. For example, the conversation management unit advances conversations based on the accounts the driver follows on social media. The conversation management unit can also analyze the content of the driver's social media posts and advance related topics. The conversation management unit can also advance related topics by referring to the activities of the driver's friends on social media. In this way, related conversations can advance based on the driver's social media activities. The analysis of social media activities may be performed using, for example, AI or without AI.

[0063] During conversation management, the conversation management unit customizes the conversation progression method by reflecting the driver's past feedback. The conversation management unit, for example, suggests an optimal conversation progression method based on feedback provided by the driver in the past. The conversation management unit can also prioritize a specific conversation pattern based on the driver's past feedback. The conversation management unit can also analyze the driver's past feedback and customize the conversation progression method. This makes it possible to customize the conversation progression method based on the driver's past feedback. Reflecting the feedback may be performed, for example, using AI or without using AI.

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

[0065] The providing unit can also adjust the level of detail provided based on the importance of the topic when providing the topic. For example, detailed information can be provided for an important topic. Also, brief information can be provided for a less important topic. Furthermore, the level of detail provided can be adjusted based on the importance of the topic. This makes it possible to adjust the level of detail provided based on the importance of the topic.

[0066] The storage unit can also optimize the storage algorithm by referring to previously stored data when storing data. For example, the storage unit can analyze previously stored data and select an optimal storage algorithm. It can also extract specific patterns from previously stored data and optimize the storage algorithm. It can also adjust parameters of the storage algorithm based on previously stored data. This makes it possible to optimize the storage algorithm based on previously stored data.

[0067] When responding, the response unit can also adjust the level of detail of the response based on the importance of the question. For example, if the question is important, a detailed response can be provided. Alternatively, if the question is not very important, a brief response can be provided. Furthermore, the response unit can also adjust the level of detail of the response based on the importance of the question. This makes it possible to adjust the level of detail of the response based on the importance of the question.

[0068] The conversation management unit can also optimize the conversation algorithm by referring to past conversation history during conversation management. For example, it can analyze past conversation history and select the optimal conversation algorithm. It can also extract specific patterns from past conversation history and optimize the conversation algorithm. Furthermore, it can adjust the parameters of the conversation algorithm based on the past conversation history. This makes it possible to optimize the conversation algorithm based on the past conversation history.

[0069] When updating the database, the database unit can also integrate information from different data sources to enrich the data. For example, the database unit can integrate information from social media to enrich the data. It can also integrate information from news sites to enrich the data. It can also integrate information from the driver's past search history to enrich the data. This makes it possible to integrate information from different data sources to enrich the data.

[0070] The processing flow of the first embodiment will be briefly explained below.

[0071] Step 1: The registration unit registers the driver's interests. For example, the driver can enter information about their favorite sports teams, hobbies, travel destinations, etc. Step 2: The storage unit stores the information registered by the registration unit. For example, if the driver is a soccer team fan, the storage unit stores the latest information about the team, game results, etc. Step 3: The providing unit provides topics based on the information stored in the storage unit. For example, if the driver is a soccer team fan, the providing unit provides topics about the team's latest news and game results. Step 4: The database unit stores data related to the topics provided by the providing unit. For example, the database unit stores a history of the topics provided and uses this information for future conversations. Step 5: The responding unit answers the driver's question based on the topic provided by the providing unit. For example, if the driver asks, "When is the next game?", the responding unit can answer the question. Step 6: The conversation management unit manages the conversation with the driver through the response unit. For example, the conversation management unit manages the progress of the conversation with the driver to ensure a smooth conversation.

[0072] (Example 2) A high-performance AI car navigation system according to an embodiment of the present invention provides topics based on the driver's interests and encourages conversation, preventing the driver from becoming drowsy and allowing the driver to continue enjoying their drive. For example, the system can register the driver's interests in advance, and then use that information to provide topics and encourage conversation while the driver is driving. This allows the driver to continue enjoying their drive without feeling drowsy. For example, if the driver is a soccer fan, the system can provide topics about the team's latest news and game results. Also, if the driver is heading to a travel destination, the system can provide topics about the destination's attractions and tourist information. Furthermore, the AI ​​car navigation system can continue to engage in conversation with the driver. For example, if the driver asks, "When is the next game?", the AI ​​car navigation system can answer that question. Also, if the driver asks, "What restaurants are recommended at this travel destination?", the AI ​​car navigation system can also answer that question. This allows the high-performance AI car navigation system to prevent the driver from becoming drowsy and continue enjoying their drive. For example, even if the driver becomes drowsy during a long drive, they can avoid drowsiness by enjoying a conversation with the AI ​​car navigation system. Furthermore, by enjoying conversations about topics that interest the driver, the drive becomes more enjoyable.

[0073] A high-performance AI car navigation system according to an embodiment includes a registration unit, a storage unit, a providing unit, a database unit, a response unit, and a conversation management unit. The registration unit registers the driver's interests. For example, the driver can input information about their favorite sports teams, hobbies, travel destinations, etc. The storage unit saves the information registered by the registration unit. For example, if the driver is a soccer fan, the storage unit saves the team's latest information and game results. The provision unit provides topics based on the information saved in the storage unit. For example, if the driver is a soccer fan, the provision unit saves the team's latest information and game results. The database unit saves data related to the topics provided by the provision unit. For example, the database unit saves a history of the provided topics and uses them for future conversations. The response unit answers the driver's questions based on the topics provided by the provision unit. For example, if the driver asks, "When is the next game?", the response unit can answer the question. The conversation management unit manages the conversation with the driver via the response unit. For example, the conversation management unit manages the progress of the conversation with the driver to ensure a smooth conversation. As a result, the high-performance AI car navigation system according to the embodiment can provide topics based on the driver's interests and keep the conversation going, preventing the driver from getting drowsy and allowing them to continue enjoying their drive.

[0074] The registration unit estimates the driver's emotions and adjusts the timing of registering interests and concerns based on the estimated driver's emotions. For example, if the driver is relaxed, the registration unit prompts the driver to register detailed interests and concerns. If the driver is feeling stressed, the registration unit can also register interests and concerns with a simple question. If the driver is in a hurry, the registration unit can also set a reminder to enter details later. This allows interests and concerns to be registered at the optimal time depending on the driver's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the registration unit may be performed using, for example, AI, or without AI.

[0075] The registration unit analyzes the driver's past history of interests and selects the optimal registration method. For example, the registration unit analyzes patterns of interests and concerns registered in the past and suggests the most frequently used method. The registration unit can also preferentially suggest the driver's preferred registration method (voice, text, etc.) based on the past history. The registration unit can also suggest a registration method suitable for a specific time period based on the past history. This makes it possible to suggest the optimal registration method based on the past history. The analysis of the history may be performed, for example, using AI or without using AI.

[0076] When registering interests, the registration unit filters the interests based on the driver's current living situation and areas of interest. The registration unit suggests related interests based on, for example, the driver's current occupation and hobbies. The registration unit can also filter appropriate interests based on the driver's family structure and lifestyle. The registration unit can also suggest related interests based on the driver's current health condition and fitness level. This makes it possible to suggest appropriate interests according to the driver's current situation. The filtering process may be performed using, for example, AI or without AI.

[0077] When registering interests and concerns, the registration unit selects an appropriate registration means according to the driver's input method. For example, if the driver prefers voice input, the registration unit registers interests and concerns using voice recognition technology. Furthermore, if the driver prefers text input, the registration unit can provide a simple text input interface. Furthermore, if the driver prefers image input, the registration unit can register interests and concerns using image recognition technology. This makes it possible to provide the optimal registration means according to the driver's input method. The selection of the input method may be performed using, for example, AI or without AI.

[0078] The registration unit estimates the driver's emotions and determines the priority of the interests to be registered based on the estimated driver's emotions. For example, if the driver is excited, the registration unit may prioritize entertainment-related interests. Furthermore, if the driver is relaxed, the registration unit may prioritize hobbies and relaxation-related interests. Furthermore, if the driver is stressed, the registration unit may prioritize stress relief-related interests. This allows the prioritization of interests based on the driver's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the registration unit may be performed using, for example, AI, or without AI.

[0079] When registering interests and concerns, the registration unit prioritizes registering highly relevant information taking into account the driver's geographical location information. For example, if the driver is in a specific area, the registration unit prioritizes registering interests and concerns related to that area. Furthermore, if the driver is traveling, the registration unit can prioritize registering tourist information and sights at the travel destination. Furthermore, if the driver is commuting to work, the registration unit can prioritize registering interests and concerns related to the commuting route. This makes it possible to prioritize registering highly relevant information based on the driver's geographical location information. The acquisition of geographical location information and the selection of highly relevant information may be performed, for example, using AI or without AI.

[0080] When registering interests, the registration unit analyzes the driver's social media activity and registers related information. The registration unit may, for example, register interests based on the accounts the driver follows on social media. The registration unit may also analyze the content of the driver's social media posts and register related interests. The registration unit may also register related interests based on the activities of the driver's friends on social media. This makes it possible to register related information based on the driver's social media activity. The analysis of social media activity may be performed, for example, using AI or without AI.

[0081] The registration unit customizes the registration method by reflecting the driver's past feedback when registering interests. The registration unit, for example, suggests the optimal registration method based on feedback provided by the driver in the past. The registration unit can also preferentially suggest a specific registration method based on the driver's past feedback. The registration unit can also analyze the driver's past feedback and customize the registration method. This makes it possible to customize the registration method based on the driver's past feedback. The analysis and reflection of feedback may be performed, for example, using AI or may be performed without using AI.

[0082] The storage unit estimates the driver's emotions and selects information to be stored based on the estimated driver's emotions. For example, if the driver is relaxed, the storage unit may preferentially store information related to relaxation. Furthermore, if the driver is excited, the storage unit may preferentially store information related to entertainment. Furthermore, if the driver is stressed, the storage unit may preferentially store information related to stress relief. This makes it possible to select information to be stored based on the driver's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or without using AI.

[0083] The storage unit optimizes the storage algorithm by referring to previously stored data when storing data. For example, the storage unit analyzes previously stored data and selects an optimal storage algorithm. The storage unit can also extract specific patterns from previously stored data and optimize the storage algorithm. The storage unit can also adjust parameters of the storage algorithm based on the previously stored data. This makes it possible to optimize the storage algorithm based on the previously stored data. Optimization of the storage algorithm may be performed using, for example, AI or without using AI.

[0084] The storage unit updates the stored data by reflecting the driver's feedback when storing the data. The storage unit updates the stored data, for example, based on the feedback provided by the driver. The storage unit can also prioritize storing specific data based on the driver's feedback. The storage unit can also analyze the driver's feedback and optimize the stored data. This makes it possible to update the stored data based on the driver's feedback. The feedback can be reflected, for example, using AI or without using AI.

[0085] The storage unit analyzes fluctuations in the driver's interests and adjusts the update frequency of the stored data when storing the data. For example, if the driver's interests and concerns change frequently, the storage unit increases the update frequency of the stored data. In addition, if the driver's interests and concerns are stable, the storage unit can also decrease the update frequency of the stored data. In addition, the storage unit can analyze the pattern of fluctuations in the driver's interests and concerns and set an optimal update frequency. This makes it possible to adjust the update frequency of the stored data based on fluctuations in the driver's interests and concerns. The analysis of fluctuations in interests and concerns may be performed, for example, using AI or without using AI.

[0086] The storage unit estimates the driver's emotions and adjusts the frequency of storage based on the estimated driver's emotions. For example, the storage unit reduces the frequency of storage when the driver is relaxed. The storage unit can also increase the frequency of storage when the driver is excited. The storage unit can also adjust the frequency of storage when the driver is stressed. This makes it possible to adjust the frequency of storage based on the driver's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the storage unit may be performed, for example, using AI or without using AI.

[0087] The storage unit weights the stored data based on the registration time of the interests and concerns when storing the data. For example, the storage unit prioritizes storing recently registered interests and concerns. The storage unit can also prioritize storing interests and concerns that have been registered over a long period of time. The storage unit can also adjust the weighting of the stored data based on the registration time. This allows the stored data to be weighted based on the registration time of the interests and concerns. The weighting adjustment may be performed using, for example, AI or without AI.

[0088] The storage unit integrates information from different data sources to enrich the stored data when storing the data. For example, the storage unit integrates information from social media to enrich the stored data. The storage unit can also integrate information from news sites to enrich the stored data. The storage unit can also integrate information from the driver's past search history to enrich the stored data. In this way, the stored data can be enriched by integrating information from different data sources. The integration of data sources may be performed using AI, for example, or may be performed without using AI.

[0089] The provision unit estimates the driver's emotions and adjusts the topic provision method based on the estimated driver's emotions. For example, if the driver is relaxed, the provision unit provides the topic at a leisurely pace. Furthermore, if the driver is excited, the provision unit can provide the topic in an energetic tone. Furthermore, if the driver is stressed, the provision unit can provide the topic in a calm tone. This makes it possible to adjust the topic provision method based on the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the provision unit may be performed, for example, using AI, or may be performed without using AI.

[0090] When providing a topic, the providing unit adjusts the level of detail to be provided based on the importance of the topic. For example, in the case of an important topic, the providing unit provides detailed information. In addition, in the case of a less important topic, the providing unit can also provide concise information. In addition, the providing unit can adjust the level of detail to be provided based on the importance of the topic. In this way, the level of detail to be provided can be adjusted based on the importance of the topic. The adjustment of the level of detail to be provided may be performed, for example, using AI or may be performed without using AI.

[0091] When providing a topic, the providing unit applies an appropriate providing algorithm depending on the category of the topic. For example, in the case of a sports-related topic, the providing unit applies an algorithm that provides the latest game results and player information. In addition, in the case of a travel-related topic, the providing unit can also apply an algorithm that provides tourist spot and restaurant information. In addition, in the case of an entertainment-related topic, the providing unit can also apply an algorithm that provides the latest information on movies and music. In this way, it is possible to apply the optimal providing algorithm depending on the category of the topic. The application of the providing algorithm may be performed using, for example, AI, or may be performed without using AI.

[0092] When providing a topic, the providing unit improves the accuracy of the topic provision by referring to the driver's past provision results. The providing unit, for example, analyzes reactions to topics provided in the past to improve the accuracy of the topic provision. The providing unit can also preferentially provide topics that the driver prefers based on the past provision results. The providing unit can also optimize the provision algorithm based on the past provision results. This makes it possible to improve the accuracy of the topic provision based on the driver's past provision results. The improvement in the accuracy of the topic provision may be performed, for example, using AI or without using AI.

[0093] The providing unit estimates the driver's emotions and adjusts the length of the topic based on the estimated driver's emotions. For example, if the driver is relaxed, the providing unit provides a longer topic. Furthermore, if the driver is in a hurry, the providing unit can also provide a shorter topic. Furthermore, if the driver is excited, the providing unit can also provide a topic of appropriate length. This makes it possible to adjust the length of the topic based on the driver's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI.

[0094] When providing a topic, the providing unit determines the priority of the topic based on the time of submission. For example, the providing unit provides the most recent topic with priority. The providing unit can also postpone topics that have been submitted earlier. The providing unit can also adjust the priority of the topic based on the time of submission. This makes it possible to determine the priority of the topic based on the time of submission. The determination of the priority of the topic may be performed using AI, for example, or may be performed without using AI.

[0095] The provision unit adjusts the order of topics provided based on the relevance of the topics when providing the topics. For example, the provision unit prioritizes providing a topic that is most relevant to the driver's interests and concerns. The provision unit can also prioritize providing a topic that is relevant to the driver's current situation. The provision unit can also prioritize providing a topic that is highly relevant based on the driver's past responses. This makes it possible to adjust the order of topics provided based on the relevance of the topics. The adjustment of the order of topics provided may be performed using AI, for example, or may be performed without using AI.

[0096] When providing a topic, the providing unit adjusts the use of technical terms in the provided topic depending on the driver's level of expertise. For example, if the driver has technical expertise, the providing unit provides a topic that uses a lot of technical terms. Furthermore, if the driver does not have technical expertise, the providing unit can also provide a topic that explains the topic in simple terms. Furthermore, the providing unit can adjust the use of technical terms in accordance with the driver's level of expertise. In this way, the use of technical terms in the provided topic can be adjusted depending on the driver's level of expertise. The adjustment of the use of technical terms may be performed, for example, using AI or may be performed without using AI.

[0097] The database unit estimates the driver's emotions and adjusts the update frequency of the database based on the estimated driver's emotions. For example, the database unit reduces the update frequency of the database when the driver is relaxed. The database unit can also increase the update frequency of the database when the driver is excited. The database unit can also adjust the update frequency of the database when the driver is stressed. This makes it possible to adjust the update frequency of the database based on the driver's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the database unit may be performed, for example, using AI or without using AI.

[0098] When updating the database, the database unit optimizes the update algorithm by referring to past data. For example, the database unit analyzes data stored in the past and selects an optimal update algorithm. The database unit can also extract specific patterns from the past data and optimize the update algorithm. The database unit can also adjust the parameters of the update algorithm based on the past data. This makes it possible to optimize the update algorithm based on the past data. Optimization of the update algorithm may be performed using, for example, AI or without using AI.

[0099] When updating the database, the database unit updates the data by reflecting the driver's feedback. The database unit updates the data based on, for example, the feedback provided by the driver. The database unit can also prioritize updating specific data based on the driver's feedback. The database unit can also analyze the driver's feedback and optimize the data. This makes it possible to update the data based on the driver's feedback. The feedback may be reflected using, for example, AI or without using AI.

[0100] When updating the database, the database unit analyzes fluctuations in the driver's interests and adjusts the data update frequency. For example, if the driver's interests and concerns change frequently, the database unit increases the data update frequency. In addition, if the driver's interests and concerns remain stable, the database unit can also decrease the data update frequency. In addition, the database unit can analyze the pattern of fluctuations in the driver's interests and concerns and set an optimal update frequency. This makes it possible to adjust the data update frequency based on fluctuations in the driver's interests and concerns. The analysis of fluctuations in interests and concerns may be performed, for example, using AI or without using AI.

[0101] The database unit estimates the driver's emotion and adjusts the structure of the database based on the estimated driver's emotion. For example, the database unit simplifies the structure of the database when the driver is relaxed. The database unit can also complicate the structure of the database when the driver is excited. The database unit can also adjust the structure of the database when the driver is stressed. This makes it possible to adjust the structure of the database based on the driver's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the database unit may be performed, for example, using AI, or may be performed without using AI.

[0102] When updating the database, the database unit integrates information from different data sources to enrich the data. For example, the database unit integrates information from social media to enrich the data. The database unit can also integrate information from news sites to enrich the data. The database unit can also integrate information from the driver's past search history to enrich the data. In this way, the data can be enriched by integrating information from different data sources. The integration of data sources may be performed, for example, using AI or without using AI.

[0103] When updating the database, the database unit takes into consideration the driver's geographical location information and prioritizes updating highly relevant data. For example, when the driver is in a specific area, the database unit prioritizes updating data related to that area. Furthermore, when the driver is traveling, the database unit can also prioritize updating tourist information and attractions for the travel destination. Furthermore, when the driver is commuting to work, the database unit can also prioritize updating data related to the commuting route. This makes it possible to prioritize updating highly relevant data based on the driver's geographical location information. The acquisition of geographical location information and the selection of highly relevant data may be performed, for example, using AI or without using AI.

[0104] The response unit estimates the driver's emotions and adjusts the way the response is expressed based on the estimated driver's emotions. For example, if the driver is relaxed, the response unit responds in a relaxed tone. If the driver is excited, the response unit can also respond in an energetic tone. If the driver is stressed, the response unit can also respond in a calm tone. This makes it possible to adjust the way the response is expressed based on the driver's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the response unit may be performed, for example, using AI or without using AI.

[0105] When responding, the response unit adjusts the level of detail of the response based on the importance of the question. For example, the response unit provides a detailed response in the case of an important question. The response unit can also provide a concise response in the case of a less important question. The response unit can also adjust the level of detail of the response based on the importance of the question. This makes it possible to adjust the level of detail of the response based on the importance of the question. The adjustment of the level of detail of the response may be performed, for example, using AI or may be performed without using AI.

[0106] When responding, the response unit applies different response algorithms depending on the category of the question. For example, in the case of a sports-related question, the response unit applies an algorithm that provides the latest game results and player information. In addition, in the case of a travel-related question, the response unit can apply an algorithm that provides tourist spot and restaurant information. In addition, in the case of an entertainment-related question, the response unit can apply an algorithm that provides the latest information on movies and music. In this way, it is possible to apply the optimal response algorithm depending on the category of the question. The application of the response algorithm may be performed using, for example, AI or without using AI.

[0107] When responding, the response unit improves the accuracy of the response by referring to the driver's past response results. The response unit, for example, analyzes reactions to responses provided in the past to improve the accuracy of the response. The response unit can also preferentially provide a response method preferred by the driver based on the past response results. The response unit can also optimize a response algorithm based on the past response results. This makes it possible to improve the accuracy of the response based on the driver's past response results. The improvement in response accuracy may be performed, for example, using AI or without using AI.

[0108] The response unit estimates the driver's emotion and adjusts the length of the response based on the estimated driver's emotion. For example, the response unit provides a longer response when the driver is relaxed. The response unit can also provide a shorter response when the driver is in a hurry. The response unit can also provide a response of appropriate length when the driver is excited. This makes it possible to adjust the length of the response based on the driver's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the response unit may be performed, for example, using AI or without using AI.

[0109] When responding, the response unit determines the priority of the responses based on the time of submission of the question. For example, the response unit prioritizes responses to the most recent questions. The response unit can also postpone questions that have been submitted earlier. The response unit can also adjust the priority of the responses based on the time of submission. This makes it possible to determine the priority of the responses based on the time of submission of the questions. The determination of the priority of the responses may be performed using, for example, AI or without using AI.

[0110] The response unit adjusts the order of responses based on the relevance of the questions when responding. For example, the response unit prioritizes responses to questions that are most relevant to the driver's interests and concerns. The response unit can also prioritize responses to questions that are relevant to the driver's current situation. The response unit can also prioritize responses to highly relevant questions based on the driver's past responses. This makes it possible to adjust the order of responses based on the relevance of the questions. Adjustment of the order of responses may be performed, for example, using AI or without using AI.

[0111] When responding, the response unit adjusts the use of technical terms in the response according to the driver's level of expertise. For example, if the driver has technical expertise, the response unit provides a response that uses a lot of technical terms. Also, if the driver does not have technical expertise, the response unit can provide a response that explains in simple terms. Also, the response unit can adjust the use of technical terms according to the driver's level of expertise. In this way, the use of technical terms in the response can be adjusted according to the driver's level of expertise. The adjustment of the use of technical terms may be performed, for example, using AI or may be performed without using AI.

[0112] The conversation management unit estimates the driver's emotions and adjusts the way the conversation proceeds based on the estimated driver's emotions. For example, if the driver is relaxed, the conversation management unit may proceed with the conversation at a leisurely pace. If the driver is excited, the conversation management unit may also proceed with the conversation in an energetic tone. If the driver is stressed, the conversation management unit may also proceed with the conversation in a calm tone. This makes it possible to adjust the way the conversation proceeds based on the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the conversation management unit may be performed, for example, using AI or without using AI.

[0113] The conversation management unit optimizes the conversation algorithm by referring to past conversation history during conversation management. For example, the conversation management unit analyzes the past conversation history and selects the optimal conversation algorithm. The conversation management unit can also extract specific patterns from the past conversation history and optimize the conversation algorithm. The conversation management unit can also adjust the parameters of the conversation algorithm based on the past conversation history. This makes it possible to optimize the conversation algorithm based on the past conversation history. Optimization of the conversation algorithm may be performed, for example, using AI or without using AI.

[0114] The conversation management unit updates the progress of the conversation by reflecting the driver's feedback during conversation management. The conversation management unit updates the progress of the conversation based on, for example, feedback provided by the driver. The conversation management unit can also prioritize the progress of a specific conversation pattern based on the driver's feedback. The conversation management unit can also analyze the driver's feedback and optimize the progress of the conversation. This makes it possible to update the progress of the conversation based on the driver's feedback. Reflecting the feedback may be performed using AI, for example, or may be performed without using AI.

[0115] The conversation management unit analyzes fluctuations in the driver's interests and adjusts the frequency of conversation progression during conversation management. For example, if the driver's interests and concerns change frequently, the conversation management unit increases the frequency of conversation progression. In addition, the conversation management unit can also decrease the frequency of conversation progression if the driver's interests and concerns are stable. The conversation management unit can also analyze fluctuation patterns in the driver's interests and set an optimal frequency of progression. This makes it possible to adjust the frequency of conversation progression based on fluctuations in the driver's interests and concerns. The analysis of fluctuations in interests and concerns may be performed, for example, using AI or without using AI.

[0116] The conversation management unit estimates the driver's emotions and determines the priority of the conversation based on the estimated driver's emotions. For example, if the driver is relaxed, the conversation management unit prioritizes relaxing topics. Furthermore, if the driver is excited, the conversation management unit can prioritize energetic topics. Furthermore, if the driver is stressed, the conversation management unit can prioritize topics related to stress relief. This makes it possible to determine the priority of the conversation based on the driver's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the conversation management unit may be performed, for example, using AI, or may be performed without using AI.

[0117] The conversation management unit prioritizes highly relevant conversations during conversation management, taking into account the driver's geographical location information. For example, when the driver is in a specific area, the conversation management unit prioritizes topics related to that area. Furthermore, when the driver is traveling, the conversation management unit can prioritize topics related to tourist information and attractions at the travel destination. Furthermore, when the driver is commuting to work, the conversation management unit can prioritize topics related to the commuting route. This makes it possible to prioritize highly relevant conversations based on the driver's geographical location information. The acquisition of geographical location information and the selection of highly relevant conversations may be performed, for example, using AI or without AI.

[0118] During conversation management, the conversation management unit analyzes the driver's social media activities and advances related conversations. For example, the conversation management unit advances conversations based on the accounts the driver follows on social media. The conversation management unit can also analyze the content of the driver's social media posts and advance related topics. The conversation management unit can also advance related topics by referring to the activities of the driver's friends on social media. In this way, related conversations can advance based on the driver's social media activities. The analysis of social media activities may be performed using, for example, AI or without AI.

[0119] During conversation management, the conversation management unit customizes the conversation progression method by reflecting the driver's past feedback. The conversation management unit, for example, suggests an optimal conversation progression method based on feedback provided by the driver in the past. The conversation management unit can also prioritize a specific conversation pattern based on the driver's past feedback. The conversation management unit can also analyze the driver's past feedback and customize the conversation progression method. This makes it possible to customize the conversation progression method based on the driver's past feedback. Reflecting the feedback may be performed, for example, using AI or without using AI. === Hard Collateral 1-1 === For example, each of the multiple elements including the registration unit, storage unit, provision unit, database unit, response unit, and conversation management unit is realized in at least one of the smart device 14 and the data processing device 12. For example, the registration unit can register the driver's interests and concerns via the control unit 46A of the smart device 14. The storage unit can store information registered by the specific processing unit 290 of the data processing device 12. The provision unit can provide topics based on the information stored by the specific processing unit 290 of the data processing device 12. The database unit can store data related to topics provided by the database 24 of the data processing device 12. The response unit can answer the driver's questions via the specific processing unit 290 of the data processing device 12. The conversation management unit can manage conversations with the driver via the control unit 46A of the smart device 14. === Hard Collateral 1-2 === For example, each of the multiple elements including the registration unit, storage unit, provision unit, database unit, response unit, and conversation management unit is realized in at least one of the smart glasses 214 and the data processing device 12. For example, the registration unit can register the driver's interests and concerns via the control unit 46A of the smart glasses 214. The storage unit can store information registered by the specific processing unit 290 of the data processing device 12. The provision unit can provide topics based on the information stored by the specific processing unit 290 of the data processing device 12. The database unit can store data related to topics provided by the database 24 of the data processing device 12. The response unit can answer the driver's questions via the specific processing unit 290 of the data processing device 12. The conversation management unit can manage conversations with the driver via the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === For example, each of the multiple elements including the registration unit, storage unit, provision unit, database unit, response unit, and conversation management unit is realized in at least one of the headset type terminal 314 and the data processing device 12. For example, the registration unit can register the interests and concerns of the driver via the control unit 46A of the headset type terminal 314. The storage unit can store information registered by the specific processing unit 290 of the data processing device 12. The provision unit can provide topics based on the information stored by the specific processing unit 290 of the data processing device 12. The database unit can store data related to the topics provided by the database 24 of the data processing device 12. The response unit can answer the driver's questions via the specific processing unit 290 of the data processing device 12. The conversation management unit can manage conversations with the driver via the control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === For example, each of a plurality of elements including a registration unit, a storage unit, a provision unit, a database unit, a response unit, and a conversation management unit is realized in at least one of the robot 414 and the data processing device 12. For example, the registration unit can register the interests and concerns of the driver via the control unit 46A of the robot 414. The storage unit can store information registered by the specific processing unit 290 of the data processing device 12. The provision unit can provide topics based on the information stored by the specific processing unit 290 of the data processing device 12. The database unit can store data on topics provided by the database 24 of the data processing device 12. The response unit can answer questions from the driver via the specific processing unit 290 of the data processing device 12. The conversation management unit can manage conversations with the driver via the control unit 46A of the robot 414.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The provision unit can also estimate the driver's emotions and adjust the way in which topics are provided based on the estimated driver's emotions. For example, if the driver is relaxed, the provision unit can provide topics at a leisurely pace. If the driver is excited, the provision unit can provide topics in an energetic tone. Furthermore, if the driver is stressed, the provision unit can provide topics in a calm tone. In this way, the way in which topics are provided can be adjusted based on the driver's emotions.

[0122] The storage unit can also estimate the driver's emotions and select information to be stored based on the estimated driver's emotions. For example, if the driver is relaxed, information related to relaxation can be preferentially stored. Also, if the driver is excited, information related to entertainment can be preferentially stored. Furthermore, if the driver is stressed, information related to stress relief can be preferentially stored. In this way, information to be stored can be selected based on the driver's emotions.

[0123] The response unit can also estimate the driver's emotions and adjust the way the response is expressed based on the estimated driver's emotions. For example, if the driver is relaxed, the response unit can respond in a relaxed tone. If the driver is excited, the response unit can respond in an energetic tone. Furthermore, if the driver is stressed, the response unit can respond in a calm tone. In this way, the way the response is expressed can be adjusted based on the driver's emotions.

[0124] The conversation management unit can also estimate the driver's emotions and adjust the way the conversation proceeds based on the estimated driver's emotions. For example, if the driver is relaxed, the conversation can proceed at a leisurely pace. If the driver is excited, the conversation can proceed in an energetic tone. Furthermore, if the driver is stressed, the conversation can proceed in a calm tone. In this way, the way the conversation proceeds can be adjusted based on the driver's emotions.

[0125] The database unit can also estimate the driver's emotions and adjust the database update frequency based on the estimated driver's emotions. For example, if the driver is relaxed, the database update frequency can be reduced. Also, if the driver is excited, the database update frequency can be increased. Furthermore, if the driver is stressed, the database update frequency can be adjusted. In this way, the database update frequency can be adjusted based on the driver's emotions.

[0126] The providing unit can also adjust the level of detail provided based on the importance of the topic when providing the topic. For example, detailed information can be provided for an important topic. Also, brief information can be provided for a less important topic. Furthermore, the level of detail provided can be adjusted based on the importance of the topic. This makes it possible to adjust the level of detail provided based on the importance of the topic.

[0127] The storage unit can also optimize the storage algorithm by referring to previously stored data when storing data. For example, the storage unit can analyze previously stored data and select an optimal storage algorithm. It can also extract specific patterns from previously stored data and optimize the storage algorithm. It can also adjust parameters of the storage algorithm based on previously stored data. This makes it possible to optimize the storage algorithm based on previously stored data.

[0128] When responding, the response unit can also adjust the level of detail of the response based on the importance of the question. For example, if the question is important, a detailed response can be provided. Alternatively, if the question is not very important, a brief response can be provided. Furthermore, the response unit can also adjust the level of detail of the response based on the importance of the question. This makes it possible to adjust the level of detail of the response based on the importance of the question.

[0129] The conversation management unit can also optimize the conversation algorithm by referring to past conversation history during conversation management. For example, it can analyze past conversation history and select the optimal conversation algorithm. It can also extract specific patterns from past conversation history and optimize the conversation algorithm. Furthermore, it can adjust the parameters of the conversation algorithm based on the past conversation history. This makes it possible to optimize the conversation algorithm based on the past conversation history.

[0130] When updating the database, the database unit can also integrate information from different data sources to enrich the data. For example, the database unit can integrate information from social media to enrich the data. It can also integrate information from news sites to enrich the data. It can also integrate information from the driver's past search history to enrich the data. This makes it possible to integrate information from different data sources to enrich the data.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The registration unit registers the driver's interests. For example, the driver can enter information about their favorite sports teams, hobbies, travel destinations, etc. Step 2: The storage unit stores the information registered by the registration unit. For example, if the driver is a soccer team fan, the storage unit stores the latest information about the team, game results, etc. Step 3: The providing unit provides topics based on the information stored in the storage unit. For example, if the driver is a soccer team fan, the providing unit provides topics about the team's latest news and game results. Step 4: The database unit stores data related to the topics provided by the providing unit. For example, the database unit stores a history of the topics provided and uses this information for future conversations. Step 5: The responding unit answers the driver's question based on the topic provided by the providing unit. For example, if the driver asks, "When is the next game?", the responding unit can answer the question. Step 6: The conversation management unit manages the conversation with the driver through the response unit. For example, the conversation management unit manages the progress of the conversation with the driver to ensure a smooth conversation.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 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.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] 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.

[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 audio according to instructions from the processor 46.

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

[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 carried out in a secure state.

[0144] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 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.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] 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.

[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 audio according to instructions from the processor 46.

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

[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 carried out in a secure state.

[0160] 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.

[0161] 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.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] 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.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0177] 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.

[0178] 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.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0189] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0193] 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.

[0194] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0195] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0196] 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.

[0197] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0198] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0199] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0202] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0204] [Explanation of symbols]

[0205] 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 registration unit for registering the interests and concerns of the driver; a storage unit that stores the information registered by the registration unit; a providing unit that provides topics based on the information stored in the storage unit; a database unit for storing data relating to the topics provided by the providing unit; a response unit that answers questions from the driver based on the topics provided by the provision unit; a conversation management unit that manages a conversation with the driver by the response unit; A system characterized by:

2. The registration unit Estimate the driver's emotions and adjust the timing of registering interests based on the estimated driver's emotions.

2. The system of claim 1.

3. The registration unit Analyze the driver's past interests and select the appropriate registration method 2. The system of claim 1.

4. The registration unit When registering interests, filtering is performed based on the driver's current life situation and areas of interest.

2. The system of claim 1.

5. The registration unit When registering interests, select the appropriate registration method depending on the driver's input method 2. The system of claim 1.

6. The registration unit The driver's emotions are estimated, and the priority of the interests to be registered is determined based on the estimated driver's emotions.

2. The system of claim 1.

7. The registration unit When registering interests, the driver's geographic location is taken into account to prioritize the most relevant information.

2. The system of claim 1.

8. The registration unit When registering interests, analyze the driver's social media activity and register relevant information 2. The system of claim 1.

Images