system

Abstract

The system according to the embodiment aims to reduce the burden on bus drivers and achieve efficient operation. [Solution] The system according to the embodiment includes a reception unit, a generation unit, an analysis unit, an announcement unit, an acquisition unit, and an adjustment unit. The reception unit receives questions from passengers. The generation unit generates answers based on the questions received by the reception unit. The analysis unit analyzes camera footage inside the bus. The announcement unit makes warning announcements based on the results of the analysis by the analysis unit. The acquisition unit acquires GPS data. The announcement unit announces the next bus stop based on the data acquired by the acquisition unit. The acquisition unit acquires temperature sensor data. The adjustment unit adjusts the air conditioner settings based on the data acquired by the acquisition unit.

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 technology has the problem that bus drivers are burdened with tasks other than driving, making it difficult to operate efficiently.

[0005] The system according to the embodiment aims to reduce the burden on bus drivers and achieve efficient operation. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, an analysis unit, an announcement unit, an acquisition unit, and an adjustment unit. The reception unit receives questions from passengers. The generation unit generates answers based on the questions received by the reception unit. The analysis unit analyzes camera footage inside the bus. The announcement unit makes warning announcements based on the results of the analysis by the analysis unit. The acquisition unit acquires GPS data. The announcement unit announces the next bus stop based on the data acquired by the acquisition unit. The acquisition unit acquires temperature sensor data. The adjustment unit adjusts the air conditioner settings based on the data acquired by the acquisition unit. [Effects of the Invention]

[0007] The system according to the embodiment can reduce the burden on bus drivers and realize efficient operation. [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 bus driver task automation system according to an embodiment of the present invention utilizes a generation AI to automate the tasks of bus drivers. This system automates tasks such as providing bus destination and route guidance, making in-vehicle warning announcements, confirming stop stations and announcing the next bus stop, and adjusting the temperature inside the bus. For example, for bus destination and route guidance, the generation AI explains the destination and route to passengers in real time. Next, for in-vehicle warning announcements, the generation AI analyzes camera footage inside the bus, detects people standing or engaging in dangerous behavior, and makes appropriate warning announcements. For stop station confirmation and next bus stop announcements, the generation AI determines the bus's current location based on GPS data and automatically announces the next bus stop. For in-vehicle temperature control, the generation AI analyzes temperature sensor data and automatically adjusts the air conditioning settings to maintain passenger comfort. In this way, by utilizing a generation AI, the bus driver task automation system can automate the tasks of bus drivers and provide passengers with a more comfortable and safer service. This allows the bus driver task automation system to automate the tasks of bus drivers and provide passengers with a more comfortable and safer service.

[0029] A bus driver task automation system according to an embodiment includes a reception unit, a generation unit, an analysis unit, an announcement unit, an acquisition unit, and an adjustment unit. The reception unit receives questions from passengers. Questions from passengers may be in text format or audio format, but are not limited to these examples. For example, when a passenger asks about a bus destination or route, the reception unit can receive the question in text format. The reception unit can also receive questions in audio format. The generation unit uses a generation AI to generate an answer based on the question received by the reception unit. The generation AI generates an answer to the question using, for example, a text generation AI (e.g., LLM). The generation unit can also generate an answer in audio format using the generation AI. For example, the generation AI generates an appropriate answer to a passenger's question and outputs it in audio format. The analysis unit analyzes camera footage inside the bus to detect people standing or people performing dangerous actions. The analysis unit analyzes camera footage inside the bus using, for example, an image analysis algorithm. For example, the analysis unit detects people who are standing and identifies people who are performing dangerous actions. The announcement unit makes a warning announcement based on the results of the analysis by the analysis unit. The announcement unit warns people who are standing or performing dangerous actions, for example, by using an audio announcement. The announcement unit can also warn people by using a display announcement. The acquisition unit acquires GPS data. The acquisition unit acquires GPS data, for example, to determine the current location of the bus. The acquisition unit acquires GPS data such as location information and speed information. The announcement unit announces the next bus stop based on the data acquired by the acquisition unit. The announcement unit notifies passengers of the next bus stop, for example, by using an audio announcement. The announcement unit can also notify passengers of the next bus stop by using a display announcement. The acquisition unit acquires temperature sensor data. The acquisition unit acquires temperature sensor data, for example, to determine the temperature inside the bus. The acquisition unit acquires temperature sensor data, for example, such as the temperature unit and acquisition frequency. The adjustment unit adjusts the settings of the air conditioner based on the data acquired by the acquisition unit. The adjustment unit adjusts the temperature setting of the air conditioner based on temperature sensor data, for example.The adjustment unit adjusts air conditioner settings such as temperature setting, air volume setting, etc. In this way, the bus driver task automation system according to the embodiment can automate the tasks of bus drivers and provide passengers with more comfortable and safer services.

[0030] The reception unit can analyze the passenger's past question history and select an appropriate reception method. For example, the reception unit can automatically display questions that the passenger has frequently asked in the past as candidates. The reception unit can also preferentially suggest question formats (voice, text, etc.) that the passenger has used in the past. The reception unit can also predict and suggest questions that are frequently asked in a specific time period based on the passenger's past question history. This makes it possible to provide the optimal question reception method based on the passenger's past question history. The analysis of the question history may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the passenger's past question data into the generation AI and have the generation AI analyze the question history.

[0031] The reception unit can perform filtering based on the passenger's current situation and areas of interest when receiving a question. For example, if the passenger is at a tourist spot, the reception unit can prioritize receiving questions about sightseeing. Furthermore, if the passenger is commuting, the reception unit can also prioritize receiving questions about traffic information. Furthermore, if the passenger is at an event venue, the reception unit can also prioritize receiving questions about the event. This makes it possible to receive questions according to the passenger's current situation and areas of interest. Filtering of the current situation and areas of interest may be performed using, for example, AI or without AI. For example, the reception unit can input the passenger's location information and area of ​​interest data to the generation AI and have the generation AI perform filtering.

[0032] When accepting questions, the reception unit can prioritize accepting highly relevant questions by taking into account the passenger's geographical location information. For example, if the passenger is in a specific tourist attraction, the reception unit can prioritize accepting questions related to the tourist attraction. Furthermore, if the passenger is near a specific bus stop, the reception unit can prioritize accepting questions related to the bus stop. Furthermore, if the passenger is at a specific event venue, the reception unit can prioritize accepting questions related to the event. This makes it possible to accept questions based on the passenger's geographical location information. Consideration of the geographical location information may be performed using, for example, AI or without AI. For example, the reception unit can input the passenger's location information data into the generation AI and cause the generation AI to perform filtering to prioritize accepting highly relevant questions.

[0033] When accepting a question, the reception unit can analyze the passenger's social media activity and accept related questions. For example, if a passenger mentions a specific event on social media, the reception unit can prioritize accepting questions related to the event. Furthermore, if a passenger mentions a specific tourist destination on social media, the reception unit can prioritize accepting questions related to the tourist destination. Furthermore, if a passenger mentions specific traffic information on social media, the reception unit can prioritize accepting questions related to the traffic information. This makes it possible to accept questions based on the passenger's social media activity. The analysis of social media activity may be performed using, for example, AI or without AI. For example, the reception unit can input the passenger's social media data into the generation AI and cause the generation AI to perform filtering to prioritize accepting related questions.

[0034] When generating an answer, the generation unit can adjust the level of detail of the answer based on the importance of the question. For example, the generation unit generates a detailed answer for an important question. The generation unit can also generate a concise answer for a general question. The generation unit can also quickly generate an answer for a question with a high degree of urgency. This makes it possible to provide an appropriate level of detail of the answer according to the importance of the question. The evaluation of the importance of the question may be performed, for example, using AI or without using AI. For example, the generation unit can input question importance data to the generation AI and cause the generation AI to perform filtering to adjust the level of detail of the answer.

[0035] When generating an answer, the generation unit can apply different generation algorithms depending on the category of the question. For example, the generation unit can apply a generation algorithm specialized for tourist information to a question about tourism. The generation unit can also apply a generation algorithm specialized for traffic information to a question about traffic information. The generation unit can also apply a generation algorithm specialized for event information to a question about an event. This makes it possible to apply an appropriate generation algorithm depending on the category of the question. Classification of question categories may be performed using, for example, AI or without AI. For example, the generation unit can input question category data into the generation AI and cause the generation AI to perform filtering to select an appropriate generation algorithm.

[0036] When generating answers, the generation unit can determine the priority of answers based on the time when the question was submitted. For example, the generation unit can prioritize generating answers for recently submitted questions. The generation unit can also postpone generating answers for questions submitted in the past. The generation unit can also quickly generate answers for questions with high urgency. This makes it possible to provide appropriate answer priorities according to the time when the question was submitted. The evaluation of the time when the question was submitted may be performed, for example, using AI or without using AI. For example, the generation unit can input data on the time when the question was submitted to the generation AI and cause the generation AI to perform filtering to determine the priority of the answers.

[0037] The generation unit can adjust the order of answers based on the relevance of the questions when generating answers. For example, the generation unit can generate answers preferentially for highly relevant questions. The generation unit can also postpone generating answers for less relevant questions. The generation unit can also adjust the order of answers according to the category of the question. This makes it possible to provide an appropriate answer order according to the relevance of the questions. The evaluation of the relevance of questions may be performed, for example, using AI or without using AI. For example, the generation unit can input question relevance data to the generation AI and cause the generation AI to perform filtering to adjust the order of answers.

[0038] During analysis, the analysis unit can improve the accuracy of the analysis based on the interrelationships within the bus. For example, the analysis unit analyzes the movements of passengers within the bus to determine the positions of those who are standing and those who are sitting. The analysis unit can also analyze camera footage within the bus to measure the distance between passengers. The analysis unit can also analyze audio data within the bus to determine the content of conversations between passengers. This makes it possible to improve the accuracy of the analysis by taking into account the interrelationships within the bus. The analysis of the interrelationships within the bus may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can input camera footage data within the bus into a generation AI and cause the generation AI to analyze the interrelationships.

[0039] During analysis, the analysis unit can perform analysis based on passenger attribute information. The analysis unit performs appropriate analysis by taking into account, for example, the passenger's age and gender. The analysis unit can also perform appropriate analysis by taking into account the passenger's past behavior history. The analysis unit can also perform appropriate analysis by taking into account the passenger's current situation (standing, sitting, etc.). This enables appropriate analysis based on passenger attribute information. The analysis of passenger attribute information may be performed using, for example, AI or without AI. For example, the analysis unit can input passenger attribute information data to the generation AI and cause the generation AI to perform analysis based on the attribute information.

[0040] During the analysis, the analysis unit can perform the analysis based on the geographical distribution within the bus. For example, the analysis unit analyzes the location information of passengers on the bus to understand the congestion situation. The analysis unit can also analyze camera footage inside the bus to understand passenger movement patterns. The analysis unit can also analyze GPS data inside the bus to understand the passenger boarding and disembarking locations. This enables appropriate analysis based on the geographical distribution within the bus. The analysis of the geographical distribution may be performed, for example, using AI or without using AI. For example, the analysis unit can input location information data within the bus to the generation AI and cause the generation AI to perform an analysis of the geographical distribution.

[0041] The analysis unit can improve the accuracy of the analysis by referring to related literature during the analysis. The analysis unit can, for example, compare the analysis results with related literature to improve the accuracy. The analysis unit can also improve the accuracy of the analysis by referring to data from related literature during the analysis. The analysis unit can also improve the accuracy of the analysis by comparing the analysis results with related literature. This makes it possible to improve the accuracy of the analysis by referring to related literature. The reference to related literature can be performed, for example, using AI or without using AI. For example, the analysis unit can input related literature data into the generation AI and cause the generation AI to perform filtering to improve the accuracy of the analysis.

[0042] The announcement unit can adjust the level of detail of the announcement based on the importance of the analysis result when making the announcement. For example, the announcement unit can make a detailed announcement for important analysis results. The announcement unit can also make a concise announcement for general analysis results. The announcement unit can also make a quick announcement for analysis results with high urgency. This makes it possible to provide an appropriate level of detail in the announcement depending on the importance of the analysis result. The evaluation of the importance of the analysis result may be performed, for example, using AI or without using AI. For example, the announcement unit can input importance data of the analysis result to the generation AI and cause the generation AI to perform filtering to adjust the level of detail in the announcement.

[0043] The announcement unit can apply different announcement algorithms depending on the category of the analysis results when making an announcement. For example, the announcement unit can apply an announcement algorithm specialized for safety information to analysis results related to safety. The announcement unit can also apply an announcement algorithm specialized for traffic information to analysis results related to traffic information. The announcement unit can also apply an announcement algorithm specialized for event information to analysis results related to event information. This makes it possible to apply an appropriate announcement algorithm depending on the category of the analysis results. The classification of the analysis results into categories may be performed, for example, using AI or without using AI. For example, the announcement unit can input category data of the analysis results to the generation AI and cause the generation AI to perform filtering to select an appropriate announcement algorithm.

[0044] When making an announcement, the announcement unit can determine the priority of the announcement based on the submission time of the analysis results. For example, the announcement unit can prioritize announcements for recently analyzed results. The announcement unit can also postpone announcements for results analyzed in the past. The announcement unit can also quickly announce analysis results that require urgent attention. This makes it possible to provide appropriate announcement priorities according to the submission time of the analysis results. The evaluation of the submission time of the analysis results may be performed, for example, using AI or without using AI. For example, the announcement unit can input data on the submission time of the analysis results into the generation AI and cause the generation AI to perform filtering to determine the priority of the announcements.

[0045] The announcement unit can adjust the order of announcements based on the relevance of the analysis results when making announcements. For example, the announcement unit prioritizes announcements for highly relevant analysis results. The announcement unit can also postpone announcements for less relevant analysis results. The announcement unit can also adjust the order of announcements according to the category of the analysis results. This makes it possible to provide an appropriate announcement order according to the relevance of the analysis results. The evaluation of the relevance of the analysis results may be performed, for example, using AI or without using AI. For example, the announcement unit can input relevance data of the analysis results to the generation AI and cause the generation AI to perform filtering to adjust the order of announcements.

[0046] The acquisition unit can analyze past GPS data and select an optimal acquisition method. The acquisition unit can, for example, set an optimal acquisition interval based on the past GPS data. The acquisition unit can also analyze the past GPS data and select an acquisition method that avoids congestion. The acquisition unit can also select the most efficient acquisition method based on the past GPS data. This makes it possible to provide an optimal acquisition method based on the past GPS data. The analysis of the past GPS data can be performed, for example, using AI or without using AI. For example, the acquisition unit can input the past GPS data into the generation AI and cause the generation AI to perform filtering to select the optimal acquisition method.

[0047] The acquisition unit can perform filtering based on current traffic conditions and weather information when acquiring GPS data. The acquisition unit can set an optimal acquisition timing based on, for example, current traffic congestion information. The acquisition unit can also select an optimal acquisition method based on current weather information. The acquisition unit can also select an acquisition method for proposing a detour route based on current road construction information. This makes it possible to acquire appropriate GPS data based on current traffic conditions and weather information. Filtering of traffic conditions and weather information may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input traffic condition data and weather information data to the generation AI and cause the generation AI to perform filtering.

[0048] When acquiring GPS data, the acquisition unit can prioritize acquiring highly relevant data by taking geographical location information into consideration. For example, if a passenger is at a specific tourist attraction, the acquisition unit can prioritize acquiring GPS data related to the tourist attraction. Furthermore, if a passenger is near a specific bus stop, the acquisition unit can prioritize acquiring GPS data related to the bus stop. Furthermore, if a passenger is at a specific event venue, the acquisition unit can prioritize acquiring GPS data related to the event. This makes it possible to acquire appropriate GPS data based on geographical location information. Consideration of geographical location information may be performed, for example, using AI or without using AI. For example, the acquisition unit can input geographical location information data to the generation AI and cause the generation AI to perform filtering to prioritize acquiring highly relevant data.

[0049] The acquisition unit can analyze social media activity when acquiring GPS data and acquire related data. For example, if a passenger mentions a specific event on social media, the acquisition unit can prioritize acquiring GPS data related to the event. Furthermore, if a passenger mentions a specific tourist destination on social media, the acquisition unit can prioritize acquiring GPS data related to the tourist destination. Furthermore, if a passenger mentions specific traffic information on social media, the acquisition unit can prioritize acquiring GPS data related to the traffic information. This enables appropriate GPS data acquisition based on social media activity. The analysis of social media activity may be performed using, for example, AI or without AI. For example, the acquisition unit can input social media data into the generation AI and cause the generation AI to perform filtering to prioritize acquiring related data.

[0050] The acquisition unit can analyze past temperature sensor data and select an optimal acquisition method. The acquisition unit can, for example, set an optimal acquisition interval based on the past temperature sensor data. The acquisition unit can also analyze the past temperature sensor data and select an acquisition method for maintaining comfort. The acquisition unit can also select the most efficient acquisition method based on the past temperature sensor data. This makes it possible to provide an optimal acquisition method based on the past temperature sensor data. The analysis of the past temperature sensor data can be performed, for example, using AI or without using AI. For example, the acquisition unit can input the past temperature sensor data to the generation AI and cause the generation AI to perform filtering to select the optimal acquisition method.

[0051] When acquiring temperature sensor data, the acquisition unit can filter the data based on current weather information and the number of passengers on the bus. The acquisition unit can, for example, set an optimal acquisition timing based on the current weather information. The acquisition unit can also select an optimal acquisition method based on the number of passengers on the bus. The acquisition unit can also select an acquisition method for maintaining comfort based on the current weather information and number of passengers. This makes it possible to acquire appropriate temperature sensor data based on the current weather information and number of passengers on the bus. Filtering of the weather information and number of passengers may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input weather information data and passenger number data to a generation AI and have the generation AI perform filtering.

[0052] When acquiring temperature sensor data, the acquisition unit can prioritize acquiring highly relevant data by taking geographical location information into consideration. For example, if a passenger is at a specific tourist attraction, the acquisition unit prioritizes acquiring temperature sensor data related to the tourist attraction. Furthermore, if a passenger is near a specific bus stop, the acquisition unit can prioritize acquiring temperature sensor data related to the bus stop. Furthermore, if a passenger is at a specific event venue, the acquisition unit can prioritize acquiring temperature sensor data related to the event. This makes it possible to acquire appropriate temperature sensor data based on geographical location information. Consideration of geographical location information may be performed, for example, using AI or without using AI. For example, the acquisition unit can input geographical location information data to the generation AI and cause the generation AI to perform filtering to prioritize acquiring highly relevant data.

[0053] The acquisition unit can analyze social media activity when acquiring temperature sensor data and acquire related data. For example, if a passenger mentions a specific event on social media, the acquisition unit can prioritize acquiring temperature sensor data related to the event. Furthermore, if a passenger mentions a specific tourist destination on social media, the acquisition unit can prioritize acquiring temperature sensor data related to the tourist destination. Furthermore, if a passenger mentions specific traffic information on social media, the acquisition unit can prioritize acquiring temperature sensor data related to the traffic information. This enables appropriate temperature sensor data to be acquired based on social media activity. The analysis of social media activity may be performed, for example, using AI or without AI. For example, the acquisition unit can input social media data into the generation AI and cause the generation AI to perform filtering to prioritize acquiring related data.

[0054] The adjustment unit can analyze past temperature sensor data and select optimal air conditioner setting methods. The adjustment unit can, for example, select optimal air conditioner settings based on past temperature sensor data. The adjustment unit can also analyze past temperature sensor data and select air conditioner settings that maintain comfort. The adjustment unit can also select the most efficient air conditioner settings based on past temperature sensor data. This makes it possible to provide optimal air conditioner setting methods based on past temperature sensor data. The analysis of past temperature sensor data can be performed, for example, using AI or without using AI. For example, the adjustment unit can input past temperature sensor data into a generation AI and cause the generation AI to perform filtering to select optimal air conditioner setting methods.

[0055] The adjustment unit can adjust the air conditioner settings based on current weather information and the number of passengers on the bus. The adjustment unit, for example, sets the optimal air conditioner settings based on the current weather information. The adjustment unit can also set the optimal air conditioner settings based on the number of passengers on the bus. The adjustment unit can also set the air conditioner settings to maintain comfort based on the current weather information and number of passengers. This enables appropriate air conditioner settings based on the current weather information and number of passengers on the bus. Consideration of the weather information and the number of passengers may be performed, for example, using AI or without using AI. For example, the adjustment unit inputs weather information data and passenger number data into the generation AI and causes the generation AI to adjust the air conditioner settings.

[0056] The adjustment unit can select optimal settings by taking geographical location information into consideration when setting the air conditioner. For example, if a passenger is in a specific tourist attraction, the adjustment unit selects air conditioner settings appropriate for that tourist attraction. Furthermore, if a passenger is near a specific bus stop, the adjustment unit can select air conditioner settings appropriate for that bus stop. Furthermore, if a passenger is at a specific event venue, the adjustment unit can select air conditioner settings appropriate for that event. This enables appropriate air conditioner settings based on geographical location information. Consideration of geographical location information may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input geographical location information data into the generation AI and cause the generation AI to perform filtering to select optimal air conditioner settings.

[0057] The adjustment unit can analyze social media activity and suggest related settings when setting the air conditioner. For example, if a passenger mentions a specific event on social media, the adjustment unit can suggest air conditioner settings appropriate for the event. Furthermore, if a passenger mentions a specific tourist destination on social media, the adjustment unit can suggest air conditioner settings appropriate for the tourist destination. Furthermore, if a passenger mentions specific traffic information on social media, the adjustment unit can suggest air conditioner settings appropriate for the traffic information. This enables appropriate air conditioner settings based on social media activity. The analysis of social media activity may be performed, for example, using AI or without AI. For example, the adjustment unit can input social media data into the generation AI and cause the generation AI to perform filtering to suggest related settings.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The reception unit can also monitor the passenger's health condition and adjust the method of receiving questions based on the passenger's health condition. For example, if a passenger is tired, a simple and quick method of receiving questions can be provided. Also, if a passenger complains of feeling unwell, health-related questions can be given priority. Furthermore, if a passenger is relaxed, an interface for receiving detailed questions can be provided. This makes it possible to provide an appropriate method of receiving questions according to the passenger's health condition.

[0060] The reception unit can analyze passengers' past question history and select an appropriate reception method. For example, it can automatically display questions that passengers have frequently asked in the past as candidates. It can also prioritize and suggest question formats (voice, text, etc.) that passengers have used in the past. Furthermore, it can predict and suggest questions that are frequently asked during specific time periods based on passengers' past question history. This makes it possible to provide the optimal question reception method based on passengers' past question history.

[0061] When accepting questions, the acceptance unit can filter the questions based on the passenger's current situation and areas of interest. For example, if the passenger is at a tourist spot, questions about sightseeing can be accepted with priority. Also, if the passenger is commuting, questions about traffic information can be accepted with priority. Furthermore, if the passenger is at an event venue, questions about the event can be accepted with priority. This makes it possible to accept questions according to the passenger's current situation and areas of interest.

[0062] When accepting questions, the acceptance unit can prioritize accepting highly relevant questions by taking into account the passenger's geographical location information. For example, if a passenger is at a specific tourist spot, questions about that tourist spot can be accepted with priority. Also, if a passenger is near a specific bus stop, questions about that bus stop can be accepted with priority. Furthermore, if a passenger is at a specific event venue, questions about that event can be accepted with priority. This makes it possible to accept questions based on the passenger's geographical location information.

[0063] When accepting questions, the reception unit can analyze the passenger's social media activity and accept relevant questions. For example, if a passenger mentions a specific event on social media, questions about that event can be accepted with priority. Also, if a passenger mentions a specific tourist destination on social media, questions about that tourist destination can be accepted with priority. Furthermore, if a passenger mentions specific traffic information on social media, questions about that traffic information can be accepted with priority. This makes it possible to accept questions based on the passenger's social media activity.

[0064] When generating an answer, the generator can adjust the level of detail of the answer based on the importance of the question. For example, a detailed answer can be generated for an important question. A concise answer can also be generated for a general question. Furthermore, an answer can be generated quickly for a question with a high degree of urgency. This makes it possible to provide an answer with an appropriate level of detail according to the importance of the question.

[0065] When generating an answer, the generator can apply different generation algorithms depending on the category of the question. For example, a generation algorithm specialized for tourist information can be applied to a question about sightseeing. Also, a generation algorithm specialized for traffic information can be applied to a question about traffic information. Furthermore, a generation algorithm specialized for event information can be applied to a question about an event. This allows the appropriate generation algorithm to be applied depending on the category of the question.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The reception unit accepts questions from passengers. Questions from passengers can be in text format or voice format. For example, if a passenger asks about the bus destination or route, the question can be accepted in text format. Questions can also be accepted in voice format. Step 2: The generation unit uses a generation AI to generate an answer based on the question received by the reception unit. The generation AI generates an answer to the question using a text generation AI (e.g., LLM). The generation unit can also generate an answer in audio format using the generation AI. For example, the generation AI generates an appropriate answer to the passenger's question and outputs it in audio format. Step 3: The analysis unit analyzes the camera footage inside the bus to detect people standing or engaging in dangerous behavior.The analysis unit uses an image analysis algorithm to analyze the camera footage inside the bus to detect people standing and identify people engaging in dangerous behavior. Step 4: The announcement unit issues a warning announcement based on the results of the analysis by the analysis unit. The announcement unit uses audio announcements to warn people who are standing or performing dangerous actions. It can also use visual announcements to warn people. Step 5: The acquisition unit acquires GPS data The acquisition unit acquires GPS data such as position information and speed information to determine the current location of the bus. Step 6: The announcement unit announces the next bus stop based on the data acquired by the acquisition unit. The announcement unit notifies passengers of the next bus stop using a voice announcement. It can also notify passengers of the next bus stop using a display announcement. Step 7: The acquisition unit acquires data from the temperature sensor. The acquisition unit acquires data from the temperature sensor to grasp the temperature inside the bus. For example, the temperature sensor data such as the unit of temperature and acquisition frequency is acquired. Step 8: The adjustment unit adjusts the settings of the air conditioner based on the data acquired by the acquisition unit. The adjustment unit adjusts the temperature settings of the air conditioner based on the temperature sensor data. For example, the adjustment unit adjusts the settings of the air conditioner, such as the temperature setting and the air volume setting.

[0068] (Example 2) A bus driver task automation system according to an embodiment of the present invention utilizes a generation AI to automate the tasks of bus drivers. This system automates tasks such as providing bus destination and route guidance, making in-vehicle warning announcements, confirming stop stations and announcing the next bus stop, and adjusting the temperature inside the bus. For example, for bus destination and route guidance, the generation AI explains the destination and route to passengers in real time. Next, for in-vehicle warning announcements, the generation AI analyzes camera footage inside the bus, detects people standing or engaging in dangerous behavior, and makes appropriate warning announcements. For stop station confirmation and next bus stop announcements, the generation AI determines the bus's current location based on GPS data and automatically announces the next bus stop. For in-vehicle temperature control, the generation AI analyzes temperature sensor data and automatically adjusts the air conditioning settings to maintain passenger comfort. In this way, by utilizing a generation AI, the bus driver task automation system can automate the tasks of bus drivers and provide passengers with a more comfortable and safer service. This allows the bus driver task automation system to automate the tasks of bus drivers and provide passengers with a more comfortable and safer service.

[0069] A bus driver task automation system according to an embodiment includes a reception unit, a generation unit, an analysis unit, an announcement unit, an acquisition unit, and an adjustment unit. The reception unit receives questions from passengers. Questions from passengers may be in text format or audio format, but are not limited to these examples. For example, when a passenger asks about a bus destination or route, the reception unit can receive the question in text format. The reception unit can also receive questions in audio format. The generation unit uses a generation AI to generate an answer based on the question received by the reception unit. The generation AI generates an answer to the question using, for example, a text generation AI (e.g., LLM). The generation unit can also generate an answer in audio format using the generation AI. For example, the generation AI generates an appropriate answer to a passenger's question and outputs it in audio format. The analysis unit analyzes camera footage inside the bus to detect people standing or people performing dangerous actions. The analysis unit analyzes camera footage inside the bus using, for example, an image analysis algorithm. For example, the analysis unit detects people who are standing and identifies people who are performing dangerous actions. The announcement unit makes a warning announcement based on the results of the analysis by the analysis unit. The announcement unit warns people who are standing or performing dangerous actions, for example, by using an audio announcement. The announcement unit can also warn people by using a display announcement. The acquisition unit acquires GPS data. The acquisition unit acquires GPS data, for example, to determine the current location of the bus. The acquisition unit acquires GPS data such as location information and speed information. The announcement unit announces the next bus stop based on the data acquired by the acquisition unit. The announcement unit notifies passengers of the next bus stop, for example, by using an audio announcement. The announcement unit can also notify passengers of the next bus stop by using a display announcement. The acquisition unit acquires temperature sensor data. The acquisition unit acquires temperature sensor data, for example, to determine the temperature inside the bus. The acquisition unit acquires temperature sensor data, for example, such as the temperature unit and acquisition frequency. The adjustment unit adjusts the settings of the air conditioner based on the data acquired by the acquisition unit. The adjustment unit adjusts the temperature setting of the air conditioner based on temperature sensor data, for example.The adjustment unit adjusts air conditioner settings such as temperature setting, air volume setting, etc. In this way, the bus driver task automation system according to the embodiment can automate the tasks of bus drivers and provide passengers with more comfortable and safer services.

[0070] The reception unit can estimate the passenger's emotions and adjust the way questions are accepted based on the estimated passenger emotions. For example, if the passenger is feeling anxious, the reception unit can provide an interface that accepts questions in a gentle tone. Furthermore, if the passenger is in a hurry, the reception unit can provide a concise and quick way to accept questions. Furthermore, if the passenger is relaxed, the reception unit can provide an interface that accepts detailed questions. This makes it possible to provide an appropriate way to accept questions according to the passenger's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, 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 reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input passenger emotion data into the generation AI and have the generation AI execute emotion estimation.

[0071] The reception unit can analyze the passenger's past question history and select an appropriate reception method. For example, the reception unit can automatically display questions that the passenger has frequently asked in the past as candidates. The reception unit can also preferentially suggest question formats (voice, text, etc.) that the passenger has used in the past. The reception unit can also predict and suggest questions that are frequently asked in a specific time period based on the passenger's past question history. This makes it possible to provide the optimal question reception method based on the passenger's past question history. The analysis of the question history may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the passenger's past question data into the generation AI and have the generation AI analyze the question history.

[0072] The reception unit can perform filtering based on the passenger's current situation and areas of interest when receiving a question. For example, if the passenger is at a tourist spot, the reception unit can prioritize receiving questions about sightseeing. Furthermore, if the passenger is commuting, the reception unit can also prioritize receiving questions about traffic information. Furthermore, if the passenger is at an event venue, the reception unit can also prioritize receiving questions about the event. This makes it possible to receive questions according to the passenger's current situation and areas of interest. Filtering of the current situation and areas of interest may be performed using, for example, AI or without AI. For example, the reception unit can input the passenger's location information and area of ​​interest data to the generation AI and have the generation AI perform filtering.

[0073] The reception unit can estimate the passenger's emotions and determine the priority of questions to be received based on the estimated passenger's emotions. For example, if the passenger is feeling anxious, the reception unit can prioritize urgent questions. Furthermore, if the passenger is relaxed, the reception unit can prioritize detailed questions. Furthermore, if the passenger is in a hurry, the reception unit can prioritize concise questions. This allows the priority of questions to be determined according to the passenger's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 these examples. Some or all of the above-described processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input passenger emotion data into the generation AI and have the generation AI perform emotion estimation.

[0074] When accepting questions, the reception unit can prioritize accepting highly relevant questions by taking into account the passenger's geographical location information. For example, if the passenger is in a specific tourist attraction, the reception unit can prioritize accepting questions related to the tourist attraction. Furthermore, if the passenger is near a specific bus stop, the reception unit can prioritize accepting questions related to the bus stop. Furthermore, if the passenger is at a specific event venue, the reception unit can prioritize accepting questions related to the event. This makes it possible to accept questions based on the passenger's geographical location information. Consideration of the geographical location information may be performed using, for example, AI or without AI. For example, the reception unit can input the passenger's location information data into the generation AI and cause the generation AI to perform filtering to prioritize accepting highly relevant questions.

[0075] When accepting a question, the reception unit can analyze the passenger's social media activity and accept related questions. For example, if a passenger mentions a specific event on social media, the reception unit can prioritize accepting questions related to the event. Furthermore, if a passenger mentions a specific tourist destination on social media, the reception unit can prioritize accepting questions related to the tourist destination. Furthermore, if a passenger mentions specific traffic information on social media, the reception unit can prioritize accepting questions related to the traffic information. This makes it possible to accept questions based on the passenger's social media activity. The analysis of social media activity may be performed using, for example, AI or without AI. For example, the reception unit can input the passenger's social media data into the generation AI and cause the generation AI to perform filtering to prioritize accepting related questions.

[0076] The generation unit can estimate the passenger's emotions and adjust the way the answer is expressed based on the estimated passenger's emotions. For example, if the passenger is feeling anxious, the generation unit can generate an answer in a gentle tone. If the passenger is relaxed, the generation unit can also generate an answer with detailed information. If the passenger is in a hurry, the generation unit can also generate a concise and quick answer. This makes it possible to provide an appropriate answer expression method according to the passenger's emotions. Emotion estimation is realized 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 generation unit can be performed using AI, for example, or without AI. For example, the generation unit can input passenger emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0077] When generating an answer, the generation unit can adjust the level of detail of the answer based on the importance of the question. For example, the generation unit generates a detailed answer for an important question. The generation unit can also generate a concise answer for a general question. The generation unit can also quickly generate an answer for a question with a high degree of urgency. This makes it possible to provide an appropriate level of detail of the answer according to the importance of the question. The evaluation of the importance of the question may be performed, for example, using AI or without using AI. For example, the generation unit can input question importance data to the generation AI and cause the generation AI to perform filtering to adjust the level of detail of the answer.

[0078] When generating an answer, the generation unit can apply different generation algorithms depending on the category of the question. For example, the generation unit can apply a generation algorithm specialized for tourist information to a question about tourism. The generation unit can also apply a generation algorithm specialized for traffic information to a question about traffic information. The generation unit can also apply a generation algorithm specialized for event information to a question about an event. This makes it possible to apply an appropriate generation algorithm depending on the category of the question. Classification of question categories may be performed using, for example, AI or without AI. For example, the generation unit can input question category data into the generation AI and cause the generation AI to perform filtering to select an appropriate generation algorithm.

[0079] The generation unit can estimate the passenger's emotions and adjust the length of the response based on the estimated passenger's emotions. For example, if the passenger is feeling anxious, the generation unit can generate a short, to-the-point response. If the passenger is relaxed, the generation unit can generate a longer response with detailed explanations. If the passenger is in a hurry, the generation unit can generate a concise, quick response. This allows the response length to be appropriate for the passenger's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, an AI, or without an AI. For example, the generation unit can input passenger emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0080] When generating answers, the generation unit can determine the priority of answers based on the time when the question was submitted. For example, the generation unit can prioritize generating answers for recently submitted questions. The generation unit can also postpone generating answers for questions submitted in the past. The generation unit can also quickly generate answers for questions with high urgency. This makes it possible to provide appropriate answer priorities according to the time when the question was submitted. The evaluation of the time when the question was submitted may be performed, for example, using AI or without using AI. For example, the generation unit can input data on the time when the question was submitted to the generation AI and cause the generation AI to perform filtering to determine the priority of the answers.

[0081] The generation unit can adjust the order of answers based on the relevance of the questions when generating answers. For example, the generation unit can generate answers preferentially for highly relevant questions. The generation unit can also postpone generating answers for less relevant questions. The generation unit can also adjust the order of answers according to the category of the question. This makes it possible to provide an appropriate answer order according to the relevance of the questions. The evaluation of the relevance of questions may be performed, for example, using AI or without using AI. For example, the generation unit can input question relevance data to the generation AI and cause the generation AI to perform filtering to adjust the order of answers.

[0082] The analysis unit can estimate passenger emotions and adjust analysis standards based on the estimated passenger emotions. For example, if a passenger feels anxious, the analysis unit can perform a detailed analysis and provide information that provides a sense of security. Furthermore, if a passenger is relaxed, the analysis unit can perform a concise analysis and provide the minimum necessary information. Furthermore, if a passenger is in a hurry, the analysis unit can perform a quick analysis and provide information that focuses on the main points. This allows for providing appropriate analysis standards according to the passenger emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 these examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input passenger emotion data into the generation AI and have the generation AI perform emotion estimation.

[0083] During analysis, the analysis unit can improve the accuracy of the analysis based on the interrelationships within the bus. For example, the analysis unit analyzes the movements of passengers within the bus to determine the positions of those who are standing and those who are sitting. The analysis unit can also analyze camera footage within the bus to measure the distance between passengers. The analysis unit can also analyze audio data within the bus to determine the content of conversations between passengers. This makes it possible to improve the accuracy of the analysis by taking into account the interrelationships within the bus. The analysis of the interrelationships within the bus may be performed, for example, using AI or may be performed without using AI. For example, the analysis unit can input camera footage data within the bus into a generation AI and cause the generation AI to analyze the interrelationships.

[0084] During analysis, the analysis unit can perform analysis based on passenger attribute information. The analysis unit performs appropriate analysis by taking into account, for example, the passenger's age and gender. The analysis unit can also perform appropriate analysis by taking into account the passenger's past behavior history. The analysis unit can also perform appropriate analysis by taking into account the passenger's current situation (standing, sitting, etc.). This enables appropriate analysis based on passenger attribute information. The analysis of passenger attribute information may be performed using, for example, AI or without AI. For example, the analysis unit can input passenger attribute information data to the generation AI and cause the generation AI to perform analysis based on the attribute information.

[0085] The analysis unit can estimate the passenger's emotions and adjust the display order of the analysis results based on the estimated passenger's emotions. For example, if the passenger is feeling anxious, the analysis unit can prioritize displaying information that gives a sense of security. Furthermore, if the passenger is relaxed, the analysis unit can prioritize displaying detailed information. Furthermore, if the passenger is in a hurry, the analysis unit can prioritize displaying information that focuses on the main points. This makes it possible to provide an appropriate display order of the analysis results according to the passenger's emotions. Emotion estimation is realized using an emotion estimation function, for example, using 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-mentioned processing in the analysis unit may be performed using an AI, for example, or without an AI. For example, the analysis unit can input passenger's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0086] During the analysis, the analysis unit can perform the analysis based on the geographical distribution within the bus. For example, the analysis unit analyzes the location information of passengers on the bus to understand the congestion situation. The analysis unit can also analyze camera footage inside the bus to understand passenger movement patterns. The analysis unit can also analyze GPS data inside the bus to understand the passenger boarding and disembarking locations. This enables appropriate analysis based on the geographical distribution within the bus. The analysis of the geographical distribution may be performed, for example, using AI or without using AI. For example, the analysis unit can input location information data within the bus to the generation AI and cause the generation AI to perform an analysis of the geographical distribution.

[0087] The analysis unit can improve the accuracy of the analysis by referring to related literature during the analysis. The analysis unit can, for example, compare the analysis results with related literature to improve the accuracy. The analysis unit can also improve the accuracy of the analysis by referring to data from related literature during the analysis. The analysis unit can also improve the accuracy of the analysis by comparing the analysis results with related literature. This makes it possible to improve the accuracy of the analysis by referring to related literature. The reference to related literature can be performed, for example, using AI or without using AI. For example, the analysis unit can input related literature data into the generation AI and cause the generation AI to perform filtering to improve the accuracy of the analysis.

[0088] The announcement unit can estimate passenger emotions and adjust the way the announcement is made based on the estimated passenger emotions. For example, if a passenger is feeling anxious, the announcement unit can make an announcement in a gentle tone. If a passenger is relaxed, the announcement unit can also make an announcement with detailed information. If a passenger is in a hurry, the announcement unit can also make a concise and quick announcement. This makes it possible to provide an appropriate announcement expression method according to the passenger emotions. Emotion estimation is realized using an emotion estimation function, for example, 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-mentioned processing in the announcement unit can be performed using AI, for example, or without AI. For example, the announcement unit can input passenger emotion data into the generation AI and have the generation AI perform emotion estimation.

[0089] The announcement unit can adjust the level of detail of the announcement based on the importance of the analysis result when making the announcement. For example, the announcement unit can make a detailed announcement for important analysis results. The announcement unit can also make a concise announcement for general analysis results. The announcement unit can also make a quick announcement for analysis results with high urgency. This makes it possible to provide an appropriate level of detail in the announcement depending on the importance of the analysis result. The evaluation of the importance of the analysis result may be performed, for example, using AI or without using AI. For example, the announcement unit can input importance data of the analysis result to the generation AI and cause the generation AI to perform filtering to adjust the level of detail in the announcement.

[0090] The announcement unit can apply different announcement algorithms depending on the category of the analysis results when making an announcement. For example, the announcement unit can apply an announcement algorithm specialized for safety information to analysis results related to safety. The announcement unit can also apply an announcement algorithm specialized for traffic information to analysis results related to traffic information. The announcement unit can also apply an announcement algorithm specialized for event information to analysis results related to event information. This makes it possible to apply an appropriate announcement algorithm depending on the category of the analysis results. The classification of the analysis results into categories may be performed, for example, using AI or without using AI. For example, the announcement unit can input category data of the analysis results to the generation AI and cause the generation AI to perform filtering to select an appropriate announcement algorithm.

[0091] The announcement unit can estimate passenger emotions and adjust the length of announcements based on the estimated passenger emotions. For example, if a passenger is feeling anxious, the announcement unit can make a short, to-the-point announcement. If a passenger is feeling relaxed, the announcement unit can make a longer announcement with detailed explanations. If a passenger is in a hurry, the announcement unit can make a concise, quick announcement. This allows the announcement length to be adjusted appropriately according to the passenger's emotions. The emotion estimation is achieved using an emotion estimation function, for example, 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 these examples. Some or all of the above-described processing in the announcement unit can be performed using AI, or without AI. For example, the announcement unit can input passenger emotion data into the generation AI and have the generation AI perform emotion estimation.

[0092] When making an announcement, the announcement unit can determine the priority of the announcement based on the submission time of the analysis results. For example, the announcement unit can prioritize announcements for recently analyzed results. The announcement unit can also postpone announcements for results analyzed in the past. The announcement unit can also quickly announce analysis results that require urgent attention. This makes it possible to provide appropriate announcement priorities according to the submission time of the analysis results. The evaluation of the submission time of the analysis results may be performed, for example, using AI or without using AI. For example, the announcement unit can input data on the submission time of the analysis results into the generation AI and cause the generation AI to perform filtering to determine the priority of the announcements.

[0093] The announcement unit can adjust the order of announcements based on the relevance of the analysis results when making announcements. For example, the announcement unit prioritizes announcements for highly relevant analysis results. The announcement unit can also postpone announcements for less relevant analysis results. The announcement unit can also adjust the order of announcements according to the category of the analysis results. This makes it possible to provide an appropriate announcement order according to the relevance of the analysis results. The evaluation of the relevance of the analysis results may be performed, for example, using AI or without using AI. For example, the announcement unit can input relevance data of the analysis results to the generation AI and cause the generation AI to perform filtering to adjust the order of announcements.

[0094] The acquisition unit can estimate the passenger's emotions and adjust the timing of acquiring GPS data based on the estimated passenger's emotions. For example, if the passenger is feeling anxious, the acquisition unit can frequently acquire GPS data to determine the passenger's current location. Furthermore, if the passenger is relaxed, the acquisition unit can acquire GPS data at appropriate intervals. Furthermore, if the passenger is in a hurry, the acquisition unit can quickly acquire GPS data and suggest an optimal route. This makes it possible to provide an appropriate timing for acquiring GPS data according to the passenger's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, 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 acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input the passenger's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0095] The acquisition unit can analyze past GPS data and select an optimal acquisition method. The acquisition unit can, for example, set an optimal acquisition interval based on the past GPS data. The acquisition unit can also analyze the past GPS data and select an acquisition method that avoids congestion. The acquisition unit can also select the most efficient acquisition method based on the past GPS data. This makes it possible to provide an optimal acquisition method based on the past GPS data. The analysis of the past GPS data can be performed, for example, using AI or without using AI. For example, the acquisition unit can input the past GPS data into the generation AI and cause the generation AI to perform filtering to select the optimal acquisition method.

[0096] The acquisition unit can perform filtering based on current traffic conditions and weather information when acquiring GPS data. The acquisition unit can set an optimal acquisition timing based on, for example, current traffic congestion information. The acquisition unit can also select an optimal acquisition method based on current weather information. The acquisition unit can also select an acquisition method for proposing a detour route based on current road construction information. This makes it possible to acquire appropriate GPS data based on current traffic conditions and weather information. Filtering of traffic conditions and weather information may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input traffic condition data and weather information data to the generation AI and cause the generation AI to perform filtering.

[0097] The acquisition unit can estimate the passenger's emotions and determine the priority of GPS data to be acquired based on the estimated passenger's emotions. For example, if the passenger is feeling anxious, the acquisition unit can prioritize acquiring important GPS data. Furthermore, if the passenger is relaxed, the acquisition unit can prioritize acquiring detailed GPS data. Furthermore, if the passenger is in a hurry, the acquisition unit can prioritize acquiring GPS data that can be acquired quickly. This allows appropriate GPS data prioritization to be provided according to the passenger's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, 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 acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input passenger's emotion data to the generation AI and cause the generation AI to estimate the emotion.

[0098] When acquiring GPS data, the acquisition unit can prioritize acquiring highly relevant data by taking geographical location information into consideration. For example, if a passenger is at a specific tourist attraction, the acquisition unit can prioritize acquiring GPS data related to the tourist attraction. Furthermore, if a passenger is near a specific bus stop, the acquisition unit can prioritize acquiring GPS data related to the bus stop. Furthermore, if a passenger is at a specific event venue, the acquisition unit can prioritize acquiring GPS data related to the event. This makes it possible to acquire appropriate GPS data based on geographical location information. Consideration of geographical location information may be performed, for example, using AI or without using AI. For example, the acquisition unit can input geographical location information data to the generation AI and cause the generation AI to perform filtering to prioritize acquiring highly relevant data.

[0099] The acquisition unit can analyze social media activity when acquiring GPS data and acquire related data. For example, if a passenger mentions a specific event on social media, the acquisition unit can prioritize acquiring GPS data related to the event. Furthermore, if a passenger mentions a specific tourist destination on social media, the acquisition unit can prioritize acquiring GPS data related to the tourist destination. Furthermore, if a passenger mentions specific traffic information on social media, the acquisition unit can prioritize acquiring GPS data related to the traffic information. This enables appropriate GPS data acquisition based on social media activity. The analysis of social media activity may be performed using, for example, AI or without AI. For example, the acquisition unit can input social media data into the generation AI and cause the generation AI to perform filtering to prioritize acquiring related data.

[0100] The acquisition unit can estimate the passenger's emotions and adjust the timing of acquiring temperature sensor data based on the estimated passenger emotions. For example, if the passenger feels anxious, the acquisition unit can frequently acquire temperature sensor data to maintain comfort. Furthermore, if the passenger is relaxed, the acquisition unit can also acquire temperature sensor data at appropriate intervals. Furthermore, if the passenger is in a hurry, the acquisition unit can quickly acquire temperature sensor data and suggest an optimal temperature. This makes it possible to provide an appropriate timing for acquiring temperature sensor data according to the passenger's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, 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 acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input passenger emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0101] The acquisition unit can analyze past temperature sensor data and select an optimal acquisition method. The acquisition unit can, for example, set an optimal acquisition interval based on the past temperature sensor data. The acquisition unit can also analyze the past temperature sensor data and select an acquisition method for maintaining comfort. The acquisition unit can also select the most efficient acquisition method based on the past temperature sensor data. This makes it possible to provide an optimal acquisition method based on the past temperature sensor data. The analysis of the past temperature sensor data can be performed, for example, using AI or without using AI. For example, the acquisition unit can input the past temperature sensor data to the generation AI and cause the generation AI to perform filtering to select the optimal acquisition method.

[0102] When acquiring temperature sensor data, the acquisition unit can filter the data based on current weather information and the number of passengers on the bus. The acquisition unit can, for example, set an optimal acquisition timing based on the current weather information. The acquisition unit can also select an optimal acquisition method based on the number of passengers on the bus. The acquisition unit can also select an acquisition method for maintaining comfort based on the current weather information and number of passengers. This makes it possible to acquire appropriate temperature sensor data based on the current weather information and number of passengers on the bus. Filtering of the weather information and number of passengers may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input weather information data and passenger number data to a generation AI and have the generation AI perform filtering.

[0103] The acquisition unit can estimate the passenger's emotions and determine the priority of the temperature sensor data to be acquired based on the estimated passenger's emotions. For example, if the passenger is feeling anxious, the acquisition unit can prioritize acquiring important temperature sensor data. Furthermore, if the passenger is relaxed, the acquisition unit can prioritize acquiring detailed temperature sensor data. Furthermore, if the passenger is in a hurry, the acquisition unit can prioritize acquiring temperature sensor data that can be acquired quickly. This allows appropriate prioritization of temperature sensor data according to the passenger's emotions to be provided. The emotion estimation is realized using an emotion estimation function, for example, 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 acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input passenger's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0104] When acquiring temperature sensor data, the acquisition unit can prioritize acquiring highly relevant data by taking geographical location information into consideration. For example, if a passenger is at a specific tourist attraction, the acquisition unit prioritizes acquiring temperature sensor data related to the tourist attraction. Furthermore, if a passenger is near a specific bus stop, the acquisition unit can prioritize acquiring temperature sensor data related to the bus stop. Furthermore, if a passenger is at a specific event venue, the acquisition unit can prioritize acquiring temperature sensor data related to the event. This makes it possible to acquire appropriate temperature sensor data based on geographical location information. Consideration of geographical location information may be performed, for example, using AI or without using AI. For example, the acquisition unit can input geographical location information data to the generation AI and cause the generation AI to perform filtering to prioritize acquiring highly relevant data.

[0105] The acquisition unit can analyze social media activity when acquiring temperature sensor data and acquire related data. For example, if a passenger mentions a specific event on social media, the acquisition unit can prioritize acquiring temperature sensor data related to the event. Furthermore, if a passenger mentions a specific tourist destination on social media, the acquisition unit can prioritize acquiring temperature sensor data related to the tourist destination. Furthermore, if a passenger mentions specific traffic information on social media, the acquisition unit can prioritize acquiring temperature sensor data related to the traffic information. This enables appropriate temperature sensor data to be acquired based on social media activity. The analysis of social media activity may be performed, for example, using AI or without AI. For example, the acquisition unit can input social media data into the generation AI and cause the generation AI to perform filtering to prioritize acquiring related data.

[0106] The adjustment unit can estimate the passenger's emotions and adjust the air conditioning settings based on the estimated passenger emotions. For example, if the passenger feels anxious, the adjustment unit can set the temperature to a comfortable level. If the passenger feels relaxed, the adjustment unit can also set the temperature to a moderate level. If the passenger is in a hurry, the adjustment unit can quickly set the temperature to a comfortable level. This makes it possible to provide appropriate air conditioning settings according to the passenger's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 these examples. Some or all of the above-mentioned processing in the adjustment unit may be performed using an AI, for example, or without using an AI. For example, the adjustment unit can input passenger emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0107] The adjustment unit can analyze past temperature sensor data and select optimal air conditioner setting methods. The adjustment unit can, for example, select optimal air conditioner settings based on past temperature sensor data. The adjustment unit can also analyze past temperature sensor data and select air conditioner settings that maintain comfort. The adjustment unit can also select the most efficient air conditioner settings based on past temperature sensor data. This makes it possible to provide optimal air conditioner setting methods based on past temperature sensor data. The analysis of past temperature sensor data can be performed, for example, using AI or without using AI. For example, the adjustment unit can input past temperature sensor data into a generation AI and cause the generation AI to perform filtering to select optimal air conditioner setting methods.

[0108] The adjustment unit can adjust the air conditioner settings based on current weather information and the number of passengers on the bus. The adjustment unit, for example, sets the optimal air conditioner settings based on the current weather information. The adjustment unit can also set the optimal air conditioner settings based on the number of passengers on the bus. The adjustment unit can also set the air conditioner settings to maintain comfort based on the current weather information and number of passengers. This enables appropriate air conditioner settings based on the current weather information and number of passengers on the bus. Consideration of the weather information and the number of passengers may be performed, for example, using AI or without using AI. For example, the adjustment unit inputs weather information data and passenger number data into the generation AI and causes the generation AI to adjust the air conditioner settings.

[0109] The adjustment unit can estimate the passenger's emotions and determine the air conditioner setting priority based on the estimated passenger's emotions. For example, if the passenger is feeling anxious, the adjustment unit can prioritize setting a comfortable temperature. Also, if the passenger is relaxed, the adjustment unit can prioritize setting a moderate temperature. Also, if the passenger is in a hurry, the adjustment unit can quickly prioritize setting a comfortable temperature. This makes it possible to provide appropriate air conditioner setting priority according to the passenger's emotions. Emotion estimation is realized using an emotion estimation function, for example, 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-mentioned processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input passenger emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0110] The adjustment unit can select optimal settings by taking geographical location information into consideration when setting the air conditioner. For example, if a passenger is in a specific tourist attraction, the adjustment unit selects air conditioner settings appropriate for that tourist attraction. Furthermore, if a passenger is near a specific bus stop, the adjustment unit can select air conditioner settings appropriate for that bus stop. Furthermore, if a passenger is at a specific event venue, the adjustment unit can select air conditioner settings appropriate for that event. This enables appropriate air conditioner settings based on geographical location information. Consideration of geographical location information may be performed, for example, using AI or may be performed without using AI. For example, the adjustment unit can input geographical location information data into the generation AI and cause the generation AI to perform filtering to select optimal air conditioner settings.

[0111] The adjustment unit can analyze social media activity and suggest related settings when setting the air conditioner. For example, if a passenger mentions a specific event on social media, the adjustment unit can suggest air conditioner settings appropriate for the event. Furthermore, if a passenger mentions a specific tourist destination on social media, the adjustment unit can suggest air conditioner settings appropriate for the tourist destination. Furthermore, if a passenger mentions specific traffic information on social media, the adjustment unit can suggest air conditioner settings appropriate for the traffic information. This enables appropriate air conditioner settings based on social media activity. The analysis of social media activity may be performed, for example, using AI or without AI. For example, the adjustment unit can input social media data into the generation AI and cause the generation AI to perform filtering to suggest related settings. === Hard Collateral 1-1 === Each of the multiple elements, including the reception unit, generation unit, analysis unit, announcement unit, acquisition unit, and adjustment unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives questions from passengers in text or voice format. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates answers to the questions using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes camera footage inside the bus to detect people standing or performing dangerous actions. The announcement unit is realized by the output device 40 of the smart device 14 and makes audio or visual announcements based on the analysis results. The acquisition unit is realized by the specific processing unit 290 of the data processing device 12 and acquires GPS data and temperature sensor data. The adjustment unit is realized by the specific processing unit 290 of the data processing device 12 and adjusts air conditioner settings based on the acquired data. === Hard Collateral 1-2 === Each of the multiple elements, including the reception unit, generation unit, analysis unit, announcement unit, acquisition unit, and adjustment unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives questions from passengers in audio format. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates answers to the questions using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes camera footage inside the bus to detect people standing or performing dangerous actions. The announcement unit is realized by the speaker 240 of the smart glasses 214 and makes audio announcements based on the analysis results. The acquisition unit is realized by the specific processing unit 290 of the data processing device 12 and acquires GPS data and temperature sensor data. The adjustment unit is realized by the specific processing unit 290 of the data processing device 12 and adjusts air conditioner settings based on the acquired data. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, analysis unit, announcement unit, acquisition unit, and adjustment unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the headset-type terminal 314 and receives questions from passengers in audio format. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates answers to the questions using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes camera footage inside the bus to detect people standing or performing dangerous actions. The announcement unit is realized by the speaker 240 of the headset-type terminal 314 and makes audio announcements based on the analysis results. The acquisition unit is realized by the specific processing unit 290 of the data processing device 12 and acquires GPS data and temperature sensor data. The adjustment unit is realized by the specific processing unit 290 of the data processing device 12 and adjusts air conditioner settings based on the acquired data. === Hard Collateral 1-4 === Each of the multiple elements, including the reception unit, generation unit, analysis unit, announcement unit, acquisition unit, and adjustment unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 of the robot 414 and receives questions from passengers in audio format. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates answers to the questions using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes camera footage inside the bus to detect people standing or performing dangerous actions. The announcement unit is realized by the speaker 240 of the robot 414 and makes audio announcements based on the analysis results. The acquisition unit is realized by the specific processing unit 290 of the data processing device 12 and acquires GPS data and temperature sensor data. The adjustment unit is realized by the specific processing unit 290 of the data processing device 12 and adjusts air conditioner settings based on the acquired data.

[0112] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0113] The reception unit can also monitor the passenger's health condition and adjust the method of receiving questions based on the passenger's health condition. For example, if a passenger is tired, a simple and quick method of receiving questions can be provided. Also, if a passenger complains of feeling unwell, health-related questions can be given priority. Furthermore, if a passenger is relaxed, an interface for receiving detailed questions can be provided. This makes it possible to provide an appropriate method of receiving questions according to the passenger's health condition.

[0114] The reception unit can estimate the passenger's emotions and adjust the method for receiving questions based on the estimated emotions. For example, if the passenger is feeling anxious, an interface that receives questions in a gentle tone can be provided. If the passenger is in a hurry, a simple and quick method for receiving questions can be provided. Furthermore, if the passenger is relaxed, an interface that receives detailed questions can be provided. In this way, an appropriate method for receiving questions can be provided according to the passenger's emotions.

[0115] The reception unit can analyze passengers' past question history and select an appropriate reception method. For example, it can automatically display questions that passengers have frequently asked in the past as candidates. It can also prioritize and suggest question formats (voice, text, etc.) that passengers have used in the past. Furthermore, it can predict and suggest questions that are frequently asked during specific time periods based on passengers' past question history. This makes it possible to provide the optimal question reception method based on passengers' past question history.

[0116] When accepting questions, the acceptance unit can filter the questions based on the passenger's current situation and areas of interest. For example, if the passenger is at a tourist spot, questions about sightseeing can be accepted with priority. Also, if the passenger is commuting, questions about traffic information can be accepted with priority. Furthermore, if the passenger is at an event venue, questions about the event can be accepted with priority. This makes it possible to accept questions according to the passenger's current situation and areas of interest.

[0117] The reception unit can estimate the emotions of passengers and determine the priority of questions to be received based on the estimated emotions. For example, if a passenger feels anxious, it can prioritize urgent questions. Also, if a passenger feels relaxed, it can prioritize detailed questions. Furthermore, if a passenger is in a hurry, it can prioritize brief questions. In this way, it is possible to determine the priority of questions according to the emotions of passengers.

[0118] When accepting questions, the acceptance unit can prioritize accepting highly relevant questions by taking into account the passenger's geographical location information. For example, if a passenger is at a specific tourist spot, questions about that tourist spot can be accepted with priority. Also, if a passenger is near a specific bus stop, questions about that bus stop can be accepted with priority. Furthermore, if a passenger is at a specific event venue, questions about that event can be accepted with priority. This makes it possible to accept questions based on the passenger's geographical location information.

[0119] When accepting questions, the reception unit can analyze the passenger's social media activity and accept relevant questions. For example, if a passenger mentions a specific event on social media, questions about that event can be accepted with priority. Also, if a passenger mentions a specific tourist destination on social media, questions about that tourist destination can be accepted with priority. Furthermore, if a passenger mentions specific traffic information on social media, questions about that traffic information can be accepted with priority. This makes it possible to accept questions based on the passenger's social media activity.

[0120] The generation unit can estimate the passenger's emotions and adjust the way the answer is expressed based on the estimated emotions. For example, if the passenger is feeling anxious, the generation unit can generate an answer in a gentle tone. If the passenger is relaxed, the generation unit can generate an answer that includes detailed information. Furthermore, if the passenger is in a hurry, the generation unit can generate a concise and quick answer. This makes it possible to provide an appropriate way of expressing an answer according to the passenger's emotions.

[0121] When generating an answer, the generator can adjust the level of detail of the answer based on the importance of the question. For example, a detailed answer can be generated for an important question. A concise answer can also be generated for a general question. Furthermore, an answer can be generated quickly for a question with a high degree of urgency. This makes it possible to provide an answer with an appropriate level of detail according to the importance of the question.

[0122] When generating an answer, the generator can apply different generation algorithms depending on the category of the question. For example, a generation algorithm specialized for tourist information can be applied to a question about sightseeing. Also, a generation algorithm specialized for traffic information can be applied to a question about traffic information. Furthermore, a generation algorithm specialized for event information can be applied to a question about an event. This allows the appropriate generation algorithm to be applied depending on the category of the question.

[0123] The processing flow of the second embodiment will be briefly explained below.

[0124] Step 1: The reception unit accepts questions from passengers. Questions from passengers can be in text format or voice format. For example, if a passenger asks about the bus destination or route, the question can be accepted in text format. Questions can also be accepted in voice format. Step 2: The generation unit uses a generation AI to generate an answer based on the question received by the reception unit. The generation AI generates an answer to the question using a text generation AI (e.g., LLM). The generation unit can also generate an answer in audio format using the generation AI. For example, the generation AI generates an appropriate answer to the passenger's question and outputs it in audio format. Step 3: The analysis unit analyzes the camera footage inside the bus to detect people standing or engaging in dangerous behavior.The analysis unit uses an image analysis algorithm to analyze the camera footage inside the bus to detect people standing and identify people engaging in dangerous behavior. Step 4: The announcement unit issues a warning announcement based on the results of the analysis by the analysis unit. The announcement unit uses audio announcements to warn people who are standing or performing dangerous actions. It can also use visual announcements to warn people. Step 5: The acquisition unit acquires GPS data The acquisition unit acquires GPS data such as position information and speed information to determine the current location of the bus. Step 6: The announcement unit announces the next bus stop based on the data acquired by the acquisition unit. The announcement unit notifies passengers of the next bus stop using a voice announcement. It can also notify passengers of the next bus stop using a display announcement. Step 7: The acquisition unit acquires data from the temperature sensor. The acquisition unit acquires data from the temperature sensor to grasp the temperature inside the bus. For example, the temperature sensor data such as the unit of temperature and acquisition frequency is acquired. Step 8: The adjustment unit adjusts the settings of the air conditioner based on the data acquired by the acquisition unit. The adjustment unit adjusts the temperature settings of the air conditioner based on the temperature sensor data. For example, the adjustment unit adjusts the settings of the air conditioner, such as the temperature setting and the air volume setting.

[0125] 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.

[0126] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0127] 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.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0130] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0143] 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.

[0144] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0145] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0159] 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.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0162] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0176] 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.

[0177] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] [Explanation of symbols]

[0197] 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 reception desk to receive questions from passengers; a generator that generates an answer based on the question received by the receiver; an analysis unit that analyzes the camera footage inside the bus; an announcement unit that issues a warning announcement based on the results of the analysis by the analysis unit; an acquisition unit for acquiring GPS data; an announcing unit that announces the next bus stop based on the data acquired by the acquiring unit; an acquisition unit that acquires data from the temperature sensor; an adjustment unit that adjusts the settings of the air conditioner based on the data acquired by the acquisition unit. A system characterized by:

2. The reception unit Estimate passenger emotions and adjust how questions are received based on the estimated emotions.

2. The system of claim 1.

3. The reception unit Analyze passengers' past question history and select the appropriate reception method 2. The system of claim 1.

4. The reception unit Filtering questions based on the passenger's current situation and interests 2. The system of claim 1.

5. The reception unit Estimate passenger emotions and prioritize questions based on the estimated emotions 2. The system of claim 1.

6. The reception unit Prioritize relevant questions based on the passenger's geographic location when asking questions 2. The system of claim 1.

7. The reception unit When receiving a question, analyze passengers' social media activity and ask relevant questions 2. The system of claim 1.

8. The generation unit Infer passenger sentiment and adjust response language based on the estimated passenger sentiment 2. The system of claim 1.

Images