system

Abstract

The system according to this embodiment aims to enable tourists to gain a deeper understanding of local culture and history and to overcome language barriers. [Solution] The system according to the embodiment comprises an acquisition unit, a generation unit, a response unit, and a multilingual support unit. The acquisition unit acquires the location information of tourists. The generation unit generates a character based on the location information acquired by the acquisition unit. The response unit has the character generated by the generation unit respond to the tourist's questions. The multilingual support unit provides the information provided by the response unit in multiple languages.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , , , ,

[0001] The technology of this disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the information provided for tourists to deeply understand the local culture and history is insufficient and there is a language barrier.

[0005] The system according to the embodiment aims to enable tourists to deeply understand the local culture and history and overcome the language barrier. [[ID=四十]]

Means for Solving the Problems

[0006] It should be noted that in the translation of the patent number, "特開2022-180282号公報" is translated as "Japanese Patent Application Laid-Open No. 2022-180282". If there are more specific requirements for patent number translation, it can be adjusted according to the actual situation. Also, some of the tags like , , etc. seem to have some incorrect digits in the original text, but they are translated as-is as per the requirement.The system according to this embodiment comprises an acquisition unit, a generation unit, a response unit, and a multilingual support unit. The acquisition unit acquires the location information of tourists. The generation unit generates a character based on the location information acquired by the acquisition unit. The response unit has the character generated by the generation unit respond to the tourist's questions. The multilingual support unit provides the information provided by the response unit in multiple languages. [Effects of the Invention]

[0007] The system according to this embodiment can enable tourists to gain a deeper understanding of the local culture and history, and overcome language barriers. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The pilgrimage tour system according to an embodiment of the present invention is a system that uses generative AI to allow anime and manga characters to interact with tourists in real time. This system enables tourists to participate in the tour using devices such as smartphones and tablets. The system acquires the tourist's location information and guides them on the pilgrimage tour based on their current location. Furthermore, when a tourist inputs a question, the generative AI responds interactively to that question. This system is also multilingual, providing guidance and responses in the language selected by the tourist. As a result, tourists can enjoy the pilgrimage tour with anime and manga characters and gain a deeper understanding of the local culture and history. For example, when a tourist arrives at a specific tourist spot, the generative AI displays an anime or manga character associated with that spot, and the character explains the history and culture of that spot. If a tourist asks, "What is the history of this place?", the generative AI will explain the history of the place in detail. In addition, multilingual support allows foreign tourists to participate in the tour without feeling a language barrier. As a result, the pilgrimage tour system can provide tourists with real-time guidance.

[0029] The pilgrimage tour system according to this embodiment comprises an acquisition unit, a generation unit, a response unit, and a multilingual support unit. The acquisition unit acquires the location information of tourists. The tourist's location information includes, but is not limited to, GPS, Wi-Fi, beacons, etc. The acquisition unit can, for example, acquire GPS information from the tourist's device. The generation unit uses a generation AI to generate anime or manga characters based on the location information acquired by the acquisition unit. The generation unit generates, for example, anime or manga characters based on the tourist's current location. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. The response unit has the characters generated by the generation unit respond to the tourist's questions. The response unit analyzes the tourist's questions, for example, and the generation AI generates an appropriate answer. Some or all of the above processing in the response unit may be performed using, for example, AI, or not using AI. The multilingual support unit provides the information provided by the response unit in multiple languages. The multilingual support unit, for example, provides guidance and responses in the language selected by the tourist. This allows the pilgrimage tour system according to this embodiment to provide real-time guidance to tourists.

[0030] The acquisition unit can acquire GPS information from the tourist's device. GPS information includes, but is not limited to, the type of device and the frequency of location information updates. The acquisition unit acquires GPS information from the tourist's device, for example. The tourist's device includes smartphones, tablets, wearable devices, etc. The acquisition unit acquires GPS information from the tourist's device in real time and identifies the tourist's current location. This makes it possible to provide real-time guidance by obtaining accurate location information from the tourist's device. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the GPS information acquired from the tourist's device into a generating AI and have the generating AI perform location information analysis.

[0031] The generation unit can generate anime or manga characters based on the tourist's current location. For example, the generation unit generates anime or manga characters based on the tourist's current location. The generation unit uses a generation AI to generate characters related to the tourist's current location. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, when a tourist arrives at a specific tourist spot, the generation unit generates anime or manga characters related to that spot. The generation unit can also use a generation AI to generate the appearance and movements of characters based on the tourist's current location. This enables more realistic guidance by generating characters that correspond to the tourist's current location. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the tourist's current location information into the generation AI and have the generation AI perform character generation.

[0032] The response unit can analyze questions from tourists, and a generative AI can generate answers. For example, the response unit can analyze questions from tourists, and the generative AI can generate appropriate answers. The response unit uses the generative AI to respond interactively to tourists' questions. The generative AI is, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. For example, if a tourist asks, "What is the history of this place?", the generative AI will explain the history of the place in detail. The response unit can also use the generative AI to generate appropriate answers to tourists' questions. This enables interactive guidance by generating appropriate answers to tourists' questions. Some or all of the above processing in the response unit may be performed using AI, for example, or not using AI. For example, the response unit can input a tourist's question into the generative AI and have the generative AI generate the answer.

[0033] The multilingual support unit can provide guidance and responses in the language selected by the tourist. For example, the multilingual support unit provides guidance and responses in the language selected by the tourist. The multilingual support unit uses generative AI to provide guidance and responses in the language selected by the tourist. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the tourist selects English, the multilingual support unit will provide guidance and responses in English. The multilingual support unit can also generate the content of guidance and responses based on the language selected by the tourist. This allows foreign tourists to participate in the tour without feeling a language barrier through multilingual support. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the language information selected by the tourist into the generative AI and have the generative AI generate guidance and responses.

[0034] The acquisition unit can analyze a tourist's past visit history and select a method for acquiring location information. For example, the acquisition unit analyzes a tourist's past visit history and selects a method for acquiring location information. The acquisition unit uses a generation AI to analyze a tourist's past visit history. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the acquisition unit analyzes patterns of places the tourist has visited in the past and prioritizes acquiring location information of places the tourist is likely to visit next. The acquisition unit can also analyze the length of stay at places the tourist has visited in the past and acquire detailed location information of places where the tourist stays for a long time. The acquisition unit can also analyze the travel routes of places the tourist has visited in the past and select an efficient method for acquiring location information. This makes it possible to acquire location information efficiently by analyzing past visit history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the tourist's past visit history data into a generation AI and have the generation AI select a method for acquiring location information.

[0035] The acquisition unit can filter location information based on the tourist's current interests and preferences when acquiring it. For example, the acquisition unit can filter location information based on the tourist's current interests and preferences when acquiring it. The acquisition unit uses a generative AI to estimate the tourist's interests and preferences. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the tourist is interested in anime, the acquisition unit will prioritize acquiring location information of anime-related spots. If the tourist is interested in history, the acquisition unit can also prioritize acquiring location information of historical spots. If the tourist is interested in food, the acquisition unit can also prioritize acquiring location information of restaurants. This makes it possible to provide more personalized guidance by acquiring location information that matches the tourist's interests and preferences. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input tourist interest data into a generative AI and have the generative AI perform location information filtering.

[0036] The acquisition unit can select an acquisition method when acquiring location information, taking into account the remaining battery level of the tourist's device. For example, the acquisition unit selects an acquisition method when acquiring location information, taking into account the remaining battery level of the tourist's device. The acquisition unit estimates the remaining battery level of the tourist's device using a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the device's battery level is low, the acquisition unit reduces the frequency of location information acquisition to conserve battery power. If the device's battery level is sufficient, the acquisition unit can also acquire location information frequently to provide detailed guidance. If the device's battery level is moderate, the acquisition unit can also balance battery consumption with the frequency of location information acquisition. This makes it possible to provide appropriate guidance while conserving battery power by taking the device's battery level into consideration. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the tourist's device's battery level data into the generation AI and have the generation AI select the location information acquisition method.

[0037] The acquisition unit can analyze a tourist's social media activity and acquire relevant location information when acquiring location information. For example, the acquisition unit analyzes a tourist's social media activity and acquires relevant location information when acquiring location information. The acquisition unit analyzes a tourist's social media activity using a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the acquisition unit prioritizes acquiring location information of places where the tourist has checked in on social media. The acquisition unit can also acquire location information of places in photos shared by the tourist on social media. The acquisition unit can also acquire location information of places recommended by accounts that the tourist follows on social media. In this way, by analyzing social media activity, location information tailored to the tourist's interests can be acquired. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the tourist's social media activity data into a generative AI and have the generative AI perform the acquisition of location information.

[0038] The generation unit can adjust the level of detail of characters based on the tourist's past visit history when generating characters. For example, the generation unit adjusts the level of detail of characters based on the tourist's past visit history when generating characters. The generation unit analyzes the tourist's past visit history using a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the generation unit provides detailed information about characters related to places the tourist has visited in the past. The generation unit can also provide basic information about characters related to places the tourist is visiting for the first time. The generation unit can also provide detailed background information about characters related to places the tourist frequently visits. This allows for more personalized guidance by adjusting the level of detail of characters based on past visit history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the tourist's past visit history data into the generation AI and have the generation AI perform the adjustment of the level of detail of the characters.

[0039] The generation unit can apply different generation algorithms to characters depending on the characteristics of the tourist's current location. For example, the generation unit can apply different generation algorithms depending on the characteristics of the tourist's current location when generating characters. The generation unit uses a generation AI to analyze the characteristics of the tourist's current location. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the tourist is in an urban area, the generation unit can apply an algorithm to generate characters related to cities. If the tourist is in a place with a lot of nature, the generation unit can also apply an algorithm to generate characters related to nature. If the tourist is in a historical place, the generation unit can also apply an algorithm to generate characters related to history. This makes it possible to provide more realistic guidance by generating characters that are appropriate to the characteristics of the current location. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the tourist's current location information into the generation AI and have the generation AI execute the application of the generation algorithm.

[0040] The generation unit can determine the generation priority based on the performance of the tourist's device when generating characters. For example, the generation unit determines the generation priority based on the performance of the tourist's device when generating characters. The generation unit uses a generation AI to evaluate the performance of the tourist's device. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if a high-performance device is used, the generation unit will prioritize generating detailed characters. If a low-performance device is used, the generation unit may also prioritize generating basic characters. If a medium-performance device is used, the generation unit may also generate balanced characters. This allows for the provision of an optimal experience by generating characters according to the device's performance. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input the tourist's device performance data into the generation AI and have the generation AI determine the generation priority.

[0041] The generation unit can generate characters by referencing the viewer's history of anime and manga relevant to the tourist. For example, the generation unit can generate characters by referencing the viewer's history of anime and manga relevant to the tourist. The generation unit analyzes the tourist's viewing history using a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the generation unit can prioritize generating characters from anime the tourist has watched. The generation unit can also prioritize generating characters from manga the tourist has read. The generation unit can also combine characters from anime and manga the tourist has watched. This enables more personalized guidance by generating characters based on viewing history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the tourist's viewing history data into the generation AI and have the generation AI perform character generation.

[0042] The response unit can adjust the level of detail in a response based on the tourist's past question history when generating a response. For example, the response unit can adjust the level of detail in a response based on the tourist's past question history when generating a response. The response unit analyzes the tourist's question history using a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the response unit provides a detailed response if the tourist has asked a detailed question in the past. The response unit can also provide a concise response if the tourist has asked a concise question in the past. The response unit can also provide a detailed response related to a specific topic if the tourist has asked a question about that topic in the past. This allows for more appropriate guidance by adjusting the level of detail in the response based on past question history. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the tourist's question history data into a generation AI and have the generation AI perform the adjustment of the level of detail in the response.

[0043] The response unit can apply different response algorithms depending on the tourist's current interests and preferences when generating responses. For example, the response unit applies different response algorithms depending on the tourist's current interests and preferences when generating responses. The response unit uses a generative AI to estimate the tourist's interests and preferences. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the tourist shows interest in anime, the response unit applies an anime-related response algorithm. If the tourist shows interest in history, the response unit can also apply a history-related response algorithm. If the tourist shows interest in food, the response unit can also apply a food-related response algorithm. This allows for more personalized guidance by applying a response algorithm tailored to the tourist's interests and preferences. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input tourist interest data into a generative AI and have the generative AI perform the application of response algorithms.

[0044] The response unit can determine the priority of responses based on the communication status of the tourist's device when generating responses. For example, the response unit determines the priority of responses based on the communication status of the tourist's device when generating responses. The response unit uses a generation AI to evaluate the communication status of the tourist's device. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the response unit may prioritize providing detailed responses when the communication status is good. The response unit may also prioritize providing concise responses when the communication status is unstable. The response unit may also prioritize providing text-based responses when the communication status is poor. This allows for more appropriate guidance by determining the priority of responses according to the device's communication status. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the tourist's device communication status data into the generation AI and have the generation AI determine the priority of responses.

[0045] The response unit can generate responses by referencing the tourist's knowledge of relevant anime and manga. For example, the response unit can generate responses by referencing the tourist's knowledge of relevant anime and manga. The response unit analyzes the tourist's knowledge using a generative AI. The generative AI is, but is not limited to, text-generating AI (e.g., LLM) or multimodal-generating AI. For example, the response unit generates responses based on the tourist's knowledge of anime they have watched. The response unit can also generate responses based on the tourist's knowledge of manga they have read. The response unit can also generate responses by combining knowledge of anime and manga the tourist has watched. This allows for more personalized responses by referencing relevant anime and manga knowledge. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the tourist's knowledge data into a generative AI and have the generative AI perform the response generation.

[0046] The multilingual support unit can select the optimal language based on the tourist's past language selection history when providing multilingual support. For example, the multilingual support unit selects the optimal language based on the tourist's past language selection history when providing multilingual support. The multilingual support unit analyzes the tourist's language selection history using a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The multilingual support unit can, for example, prioritize displaying languages ​​previously selected by the tourist. The multilingual support unit can also automatically select languages ​​frequently used by tourists. If a tourist selects a specific language, the multilingual support unit can provide guidance and responses in that language. This enables more appropriate guidance by selecting the optimal language based on past language selection history. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the tourist's language selection history data into a generative AI and have the generative AI perform the selection of the optimal language.

[0047] The multilingual support unit can apply different translation algorithms depending on the tourist's current language proficiency when providing multilingual support. For example, the multilingual support unit applies different translation algorithms depending on the tourist's current language proficiency when providing multilingual support. The multilingual support unit uses generative AI to evaluate the tourist's language proficiency. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the multilingual support unit applies a detailed translation algorithm if the tourist speaks the language fluently. If the tourist has basic language skills, the multilingual support unit may also apply a concise translation algorithm. If the tourist has beginner-level language skills, the multilingual support unit may also apply a translation algorithm that uses simple expressions. This allows for more appropriate guidance by applying a translation algorithm tailored to the tourist's language proficiency. Some or all of the above-described processes in the multilingual support unit may be performed using AI, or not. For example, the multilingual support unit can input the tourist's language proficiency data into a generative AI and have the generative AI apply the translation algorithm.

[0048] The multilingual support unit can select the optimal language when providing multilingual support, taking into account the language settings of the tourist's device. For example, the multilingual support unit selects the optimal language when providing multilingual support, taking into account the language settings of the tourist's device. The multilingual support unit uses generative AI to evaluate the language settings of the tourist's device. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the multilingual support unit automatically sets the language of guidance and responses based on the language settings of the tourist's device. If the tourist uses multiple languages, the multilingual support unit can also prioritize the language settings of the device. If the tourist selects a specific language, the multilingual support unit can provide guidance and responses in that language. This allows for more appropriate guidance by selecting the optimal language based on the device's language settings. Some or all of the above processing in the multilingual support unit may be performed using AI, or not. For example, the multilingual support unit can input the language setting data of the tourist's device into the generative AI and have the generative AI select the optimal language.

[0049] The multilingual support unit can perform translations by referencing language versions of anime and manga relevant to the tourist during multilingual support. For example, the multilingual support unit can perform translations by referencing language versions of anime and manga relevant to the tourist during multilingual support. The multilingual support unit analyzes the tourist's viewing history using generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the multilingual support unit performs translations based on language versions of anime watched by the tourist. The multilingual support unit can also perform translations based on language versions of manga read by the tourist. The multilingual support unit can also perform translations by combining language versions of anime and manga watched by the tourist. This allows for more appropriate translations by referencing language versions of relevant anime and manga. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the tourist's viewing history data into the generative AI and have the generative AI perform the translation.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The acquisition unit can acquire not only location information from tourists' devices but also health data from tourists. For example, it can acquire data such as the tourist's heart rate, steps taken, and body temperature, and adjust the sightseeing route based on this data. If the tourist is tired, it can suggest rest stops. Conversely, if the tourist is in good health, it can suggest a more active sightseeing route. This allows for the provision of an optimal sightseeing experience tailored to the tourist's health condition.

[0052] The generation unit can consider a tourist's past visit history when generating characters based on their current location. For example, it can prioritize generating characters related to places the tourist has visited in the past. Furthermore, if a tourist prefers a particular character, that character can be displayed more frequently. It can also suggest new, relevant characters based on information about places the tourist has visited in the past. This enables personalized character generation based on the tourist's past visit history.

[0053] The response unit can consider the tourist's current interests and preferences when generating responses to their questions. For example, if a tourist is interested in anime, it can prioritize providing anime-related information. If a tourist is interested in history, it can provide detailed historical information. Furthermore, if a tourist is interested in food, it can provide information about local restaurants and specialty dishes. This enables responses tailored to the tourist's interests and preferences.

[0054] The multilingual support section can adjust the level of detail in translations according to the tourist's language proficiency. For example, if the tourist speaks the language fluently, a detailed translation can be provided. If the tourist has basic language skills, a concise translation can be provided. Furthermore, if the tourist has beginner-level language skills, a translation using simple expressions can be provided. This ensures that the optimal translation is tailored to the tourist's language proficiency.

[0055] The acquisition unit can adjust the frequency of location information acquisition considering the battery level of the tourist's device. For example, if the device's battery level is low, the frequency of location information acquisition can be reduced to conserve battery power. Conversely, if the device's battery level is sufficient, location information can be acquired frequently to provide detailed guidance. Furthermore, if the device's battery level is moderate, a balance can be struck between battery consumption and the frequency of location information acquisition. This enables optimal guidance tailored to the device's battery level.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The acquisition unit acquires the tourist's location information. This tourist location information includes GPS, Wi-Fi, beacons, etc. For example, GPS information can be acquired from the tourist's device. Step 2: The generation unit uses a generation AI to generate anime or manga characters based on the location information acquired by the acquisition unit. For example, it generates characters based on the current location of tourists. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The response unit uses characters generated by the generation unit to respond to tourists' questions. For example, the generation AI analyzes the tourist's question and generates an appropriate answer. Processing in the response unit may or may not be performed using AI. Step 4: The multilingual support unit provides information in multiple languages, including the language selected by the response unit. For example, it provides guidance and responses in the language chosen by the tourist.

[0058] (Example of form 2) The pilgrimage tour system according to an embodiment of the present invention is a system that uses generative AI to allow anime and manga characters to interact with tourists in real time. This system enables tourists to participate in the tour using devices such as smartphones and tablets. The system acquires the tourist's location information and guides them on the pilgrimage tour based on their current location. Furthermore, when a tourist inputs a question, the generative AI responds interactively to that question. This system is also multilingual, providing guidance and responses in the language selected by the tourist. As a result, tourists can enjoy the pilgrimage tour with anime and manga characters and gain a deeper understanding of the local culture and history. For example, when a tourist arrives at a specific tourist spot, the generative AI displays an anime or manga character associated with that spot, and the character explains the history and culture of that spot. If a tourist asks, "What is the history of this place?", the generative AI will explain the history of the place in detail. In addition, multilingual support allows foreign tourists to participate in the tour without feeling a language barrier. As a result, the pilgrimage tour system can provide tourists with real-time guidance.

[0059] The pilgrimage tour system according to this embodiment comprises an acquisition unit, a generation unit, a response unit, and a multilingual support unit. The acquisition unit acquires the location information of tourists. The tourist's location information includes, but is not limited to, GPS, Wi-Fi, beacons, etc. The acquisition unit can, for example, acquire GPS information from the tourist's device. The generation unit uses a generation AI to generate anime or manga characters based on the location information acquired by the acquisition unit. The generation unit generates, for example, anime or manga characters based on the tourist's current location. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. The response unit has the characters generated by the generation unit respond to the tourist's questions. The response unit analyzes the tourist's questions, for example, and the generation AI generates an appropriate answer. Some or all of the above processing in the response unit may be performed using, for example, AI, or not using AI. The multilingual support unit provides the information provided by the response unit in multiple languages. The multilingual support unit, for example, provides guidance and responses in the language selected by the tourist. This allows the pilgrimage tour system according to this embodiment to provide real-time guidance to tourists.

[0060] The acquisition unit can acquire GPS information from the tourist's device. GPS information includes, but is not limited to, the type of device and the frequency of location information updates. The acquisition unit acquires GPS information from the tourist's device, for example. The tourist's device includes smartphones, tablets, wearable devices, etc. The acquisition unit acquires GPS information from the tourist's device in real time and identifies the tourist's current location. This makes it possible to provide real-time guidance by obtaining accurate location information from the tourist's device. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the GPS information acquired from the tourist's device into a generating AI and have the generating AI perform location information analysis.

[0061] The generation unit can generate anime or manga characters based on the tourist's current location. For example, the generation unit generates anime or manga characters based on the tourist's current location. The generation unit uses a generation AI to generate characters related to the tourist's current location. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, when a tourist arrives at a specific tourist spot, the generation unit generates anime or manga characters related to that spot. The generation unit can also use a generation AI to generate the appearance and movements of characters based on the tourist's current location. This enables more realistic guidance by generating characters that correspond to the tourist's current location. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the tourist's current location information into the generation AI and have the generation AI perform character generation.

[0062] The response unit can analyze questions from tourists, and a generative AI can generate answers. For example, the response unit can analyze questions from tourists, and the generative AI can generate appropriate answers. The response unit uses the generative AI to respond interactively to tourists' questions. The generative AI is, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. For example, if a tourist asks, "What is the history of this place?", the generative AI will explain the history of the place in detail. The response unit can also use the generative AI to generate appropriate answers to tourists' questions. This enables interactive guidance by generating appropriate answers to tourists' questions. Some or all of the above processing in the response unit may be performed using AI, for example, or not using AI. For example, the response unit can input a tourist's question into the generative AI and have the generative AI generate the answer.

[0063] The multilingual support unit can provide guidance and responses in the language selected by the tourist. For example, the multilingual support unit provides guidance and responses in the language selected by the tourist. The multilingual support unit uses generative AI to provide guidance and responses in the language selected by the tourist. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the tourist selects English, the multilingual support unit will provide guidance and responses in English. The multilingual support unit can also generate the content of guidance and responses based on the language selected by the tourist. This allows foreign tourists to participate in the tour without feeling a language barrier through multilingual support. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the language information selected by the tourist into the generative AI and have the generative AI generate guidance and responses.

[0064] The acquisition unit can estimate the tourist's emotions and adjust the timing of location information acquisition based on the estimated emotions. The acquisition unit estimates the tourist's emotions using a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the tourist is excited, the acquisition unit can acquire location information more frequently to enhance real-time guidance. If the tourist is relaxed, the acquisition unit can reduce the frequency of location information acquisition to conserve battery power. If the tourist is tired, the acquisition unit can increase the intervals between location information acquisitions to minimize information acquisition during breaks. This allows for more appropriate guidance by adjusting the timing of location information acquisition according to the tourist's emotions. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input tourist emotion data into a generative AI and have the generative AI adjust the timing of location information acquisition.

[0065] The acquisition unit can analyze a tourist's past visit history and select a method for acquiring location information. For example, the acquisition unit analyzes a tourist's past visit history and selects a method for acquiring location information. The acquisition unit uses a generation AI to analyze a tourist's past visit history. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the acquisition unit analyzes patterns of places the tourist has visited in the past and prioritizes acquiring location information of places the tourist is likely to visit next. The acquisition unit can also analyze the length of stay at places the tourist has visited in the past and acquire detailed location information of places where the tourist stays for a long time. The acquisition unit can also analyze the travel routes of places the tourist has visited in the past and select an efficient method for acquiring location information. This makes it possible to acquire location information efficiently by analyzing past visit history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the tourist's past visit history data into a generation AI and have the generation AI select a method for acquiring location information.

[0066] The acquisition unit can filter location information based on the tourist's current interests and preferences when acquiring it. For example, the acquisition unit can filter location information based on the tourist's current interests and preferences when acquiring it. The acquisition unit uses a generative AI to estimate the tourist's interests and preferences. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the tourist is interested in anime, the acquisition unit will prioritize acquiring location information of anime-related spots. If the tourist is interested in history, the acquisition unit can also prioritize acquiring location information of historical spots. If the tourist is interested in food, the acquisition unit can also prioritize acquiring location information of restaurants. This makes it possible to provide more personalized guidance by acquiring location information that matches the tourist's interests and preferences. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input tourist interest data into a generative AI and have the generative AI perform location information filtering.

[0067] The acquisition unit can estimate the tourist's emotions and determine the priority of location information to acquire based on the estimated emotions. The acquisition unit estimates the tourist's emotions using a generative AI. The generative AI is, but is not limited to, a text generative AI (e.g., LLM) or a multimodal generative AI. For example, if the tourist is excited, the acquisition unit will prioritize acquiring location information of popular tourist spots. If the tourist is relaxed, the acquisition unit may also prioritize acquiring location information of quiet places or places with abundant nature. If the tourist is tired, the acquisition unit may also prioritize acquiring location information of places where they can rest. This allows for more appropriate guidance by prioritizing location information according to the tourist's emotions. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input tourist emotion data into a generative AI and have the generative AI perform the determination of location information priorities.

[0068] The acquisition unit can select an acquisition method when acquiring location information, taking into account the remaining battery level of the tourist's device. For example, the acquisition unit selects an acquisition method when acquiring location information, taking into account the remaining battery level of the tourist's device. The acquisition unit estimates the remaining battery level of the tourist's device using a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the device's battery level is low, the acquisition unit reduces the frequency of location information acquisition to conserve battery power. If the device's battery level is sufficient, the acquisition unit can also acquire location information frequently to provide detailed guidance. If the device's battery level is moderate, the acquisition unit can also balance battery consumption with the frequency of location information acquisition. This makes it possible to provide appropriate guidance while conserving battery power by taking the device's battery level into consideration. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the tourist's device's battery level data into the generation AI and have the generation AI select the location information acquisition method.

[0069] The acquisition unit can analyze a tourist's social media activity and acquire relevant location information when acquiring location information. For example, the acquisition unit analyzes a tourist's social media activity and acquires relevant location information when acquiring location information. The acquisition unit analyzes a tourist's social media activity using a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, the acquisition unit prioritizes acquiring location information of places where the tourist has checked in on social media. The acquisition unit can also acquire location information of places in photos shared by the tourist on social media. The acquisition unit can also acquire location information of places recommended by accounts that the tourist follows on social media. In this way, by analyzing social media activity, location information tailored to the tourist's interests can be acquired. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the tourist's social media activity data into a generative AI and have the generative AI perform the acquisition of location information.

[0070] The generation unit can estimate the emotions of tourists and adjust the character's expression based on the estimated emotions. For example, the generation unit estimates the emotions of tourists and adjusts the character's expression based on the estimated emotions. The generation unit estimates the emotions of tourists using a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the tourist is excited, the generation unit makes the character's facial expressions and movements more lively. If the tourist is relaxed, the generation unit can also make the character's facial expressions and movements calmer. If the tourist is tired, the generation unit can also make the character's facial expressions and movements more subdued. By adjusting the character's expression according to the tourist's emotions, a more realistic experience can be provided. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input tourist emotion data into a generation AI and have the generation AI adjust the character's expression.

[0071] The generation unit can adjust the level of detail of characters based on the tourist's past visit history when generating characters. For example, the generation unit adjusts the level of detail of characters based on the tourist's past visit history when generating characters. The generation unit analyzes the tourist's past visit history using a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the generation unit provides detailed information about characters related to places the tourist has visited in the past. The generation unit can also provide basic information about characters related to places the tourist is visiting for the first time. The generation unit can also provide detailed background information about characters related to places the tourist frequently visits. This allows for more personalized guidance by adjusting the level of detail of characters based on past visit history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the tourist's past visit history data into the generation AI and have the generation AI perform the adjustment of the level of detail of the characters.

[0072] The generation unit can apply different generation algorithms to characters depending on the characteristics of the tourist's current location. For example, the generation unit can apply different generation algorithms depending on the characteristics of the tourist's current location when generating characters. The generation unit uses a generation AI to analyze the characteristics of the tourist's current location. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the tourist is in an urban area, the generation unit can apply an algorithm to generate characters related to cities. If the tourist is in a place with a lot of nature, the generation unit can also apply an algorithm to generate characters related to nature. If the tourist is in a historical place, the generation unit can also apply an algorithm to generate characters related to history. This makes it possible to provide more realistic guidance by generating characters that are appropriate to the characteristics of the current location. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the tourist's current location information into the generation AI and have the generation AI execute the application of the generation algorithm.

[0073] The generation unit can estimate the emotions of tourists and adjust the character's actions based on the estimated emotions. The generation unit estimates the emotions of tourists using a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if the tourist is excited, the generation unit makes the character's actions more lively. If the tourist is relaxed, the generation unit may also make the character's actions calmer. If the tourist is tired, the generation unit may also make the character's actions more subdued. By adjusting the character's actions according to the tourist's emotions, a more realistic experience can be provided. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input tourist emotion data into a generation AI and have the generation AI perform the adjustment of the character's actions.

[0074] The generation unit can determine the generation priority based on the performance of the tourist's device when generating characters. For example, the generation unit determines the generation priority based on the performance of the tourist's device when generating characters. The generation unit uses a generation AI to evaluate the performance of the tourist's device. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. For example, if a high-performance device is used, the generation unit will prioritize generating detailed characters. If a low-performance device is used, the generation unit may also prioritize generating basic characters. If a medium-performance device is used, the generation unit may also generate balanced characters. This allows for the provision of an optimal experience by generating characters according to the device's performance. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input the tourist's device performance data into the generation AI and have the generation AI determine the generation priority.

[0075] The generation unit can generate characters by referencing the viewer's history of anime and manga relevant to the tourist. For example, the generation unit can generate characters by referencing the viewer's history of anime and manga relevant to the tourist. The generation unit analyzes the tourist's viewing history using a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the generation unit can prioritize generating characters from anime the tourist has watched. The generation unit can also prioritize generating characters from manga the tourist has read. The generation unit can also combine characters from anime and manga the tourist has watched. This enables more personalized guidance by generating characters based on viewing history. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the tourist's viewing history data into the generation AI and have the generation AI perform character generation.

[0076] The response unit can estimate the tourist's emotions and adjust the expression of its response based on the estimated emotions. The response unit estimates the tourist's emotions using a generative AI. The generative AI is, but is not limited to, a text-generating AI (e.g., LLM) or a multimodal-generating AI. For example, if the tourist is excited, the response unit will make the expression lively and energetic. If the tourist is relaxed, the response unit may also make the expression calm and composed. If the tourist is tired, the response unit may also make the expression reserved and concise. By adjusting the expression of the response according to the tourist's emotions, more appropriate guidance becomes possible. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input tourist emotion data into a generative AI and have the generative AI adjust the expression of the response.

[0077] The response unit can adjust the level of detail in a response based on the tourist's past question history when generating a response. For example, the response unit can adjust the level of detail in a response based on the tourist's past question history when generating a response. The response unit analyzes the tourist's question history using a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the response unit provides a detailed response if the tourist has asked a detailed question in the past. The response unit can also provide a concise response if the tourist has asked a concise question in the past. The response unit can also provide a detailed response related to a specific topic if the tourist has asked a question about that topic in the past. This allows for more appropriate guidance by adjusting the level of detail in the response based on past question history. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the tourist's question history data into a generation AI and have the generation AI perform the adjustment of the level of detail in the response.

[0078] The response unit can apply different response algorithms depending on the tourist's current interests and preferences when generating responses. For example, the response unit applies different response algorithms depending on the tourist's current interests and preferences when generating responses. The response unit uses a generative AI to estimate the tourist's interests and preferences. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if the tourist shows interest in anime, the response unit applies an anime-related response algorithm. If the tourist shows interest in history, the response unit can also apply a history-related response algorithm. If the tourist shows interest in food, the response unit can also apply a food-related response algorithm. This allows for more personalized guidance by applying a response algorithm tailored to the tourist's interests and preferences. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input tourist interest data into a generative AI and have the generative AI perform the application of response algorithms.

[0079] The response unit can estimate the tourist's emotions and adjust the length of the response based on the estimated emotions. The response unit estimates the tourist's emotions using generative AI. The generative AI is, but is not limited to, text-generating AI (e.g., LLM) or multimodal-generating AI. For example, if the tourist is excited, the response unit can shorten the response to get to the point. If the tourist is relaxed, the response unit can also lengthen the response to provide more detailed information. If the tourist is tired, the response unit can also shorten the response to be concise. By adjusting the length of the response according to the tourist's emotions, more appropriate guidance becomes possible. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input tourist emotion data into the generative AI and have the generative AI adjust the length of the response.

[0080] The response unit can determine the priority of responses based on the communication status of the tourist's device when generating responses. For example, the response unit determines the priority of responses based on the communication status of the tourist's device when generating responses. The response unit uses a generation AI to evaluate the communication status of the tourist's device. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the response unit may prioritize providing detailed responses when the communication status is good. The response unit may also prioritize providing concise responses when the communication status is unstable. The response unit may also prioritize providing text-based responses when the communication status is poor. This allows for more appropriate guidance by determining the priority of responses according to the device's communication status. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the tourist's device communication status data into the generation AI and have the generation AI determine the priority of responses.

[0081] The response unit can generate responses by referencing the tourist's knowledge of relevant anime and manga. For example, the response unit can generate responses by referencing the tourist's knowledge of relevant anime and manga. The response unit analyzes the tourist's knowledge using a generative AI. The generative AI is, but is not limited to, text-generating AI (e.g., LLM) or multimodal-generating AI. For example, the response unit generates responses based on the tourist's knowledge of anime they have watched. The response unit can also generate responses based on the tourist's knowledge of manga they have read. The response unit can also generate responses by combining knowledge of anime and manga the tourist has watched. This allows for more personalized responses by referencing relevant anime and manga knowledge. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the tourist's knowledge data into a generative AI and have the generative AI perform the response generation.

[0082] The multilingual support unit can estimate the emotions of tourists and adjust the multilingual expression based on the estimated emotions. The multilingual support unit estimates the emotions of tourists using generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, if a tourist is excited, the multilingual support unit will provide a lively and energetic expression. If a tourist is relaxed, the multilingual support unit may also provide a calm and soothing expression. If a tourist is tired, the multilingual support unit may also provide a reserved and concise expression. By adjusting the multilingual expression according to the emotions of tourists, more appropriate guidance becomes possible. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input tourist emotion data into a generating AI and have the AI ​​adjust the multilingual expression methods.

[0083] The multilingual support unit can select the optimal language based on the tourist's past language selection history when providing multilingual support. For example, the multilingual support unit selects the optimal language based on the tourist's past language selection history when providing multilingual support. The multilingual support unit analyzes the tourist's language selection history using a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The multilingual support unit can, for example, prioritize displaying languages ​​previously selected by the tourist. The multilingual support unit can also automatically select languages ​​frequently used by tourists. If a tourist selects a specific language, the multilingual support unit can provide guidance and responses in that language. This enables more appropriate guidance by selecting the optimal language based on past language selection history. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the tourist's language selection history data into a generative AI and have the generative AI perform the selection of the optimal language.

[0084] The multilingual support unit can apply different translation algorithms depending on the tourist's current language proficiency when providing multilingual support. For example, the multilingual support unit applies different translation algorithms depending on the tourist's current language proficiency when providing multilingual support. The multilingual support unit uses generative AI to evaluate the tourist's language proficiency. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the multilingual support unit applies a detailed translation algorithm if the tourist speaks the language fluently. If the tourist has basic language skills, the multilingual support unit may also apply a concise translation algorithm. If the tourist has beginner-level language skills, the multilingual support unit may also apply a translation algorithm that uses simple expressions. This allows for more appropriate guidance by applying a translation algorithm tailored to the tourist's language proficiency. Some or all of the above-described processes in the multilingual support unit may be performed using AI, or not. For example, the multilingual support unit can input the tourist's language proficiency data into a generative AI and have the generative AI apply the translation algorithm.

[0085] The multilingual support unit can estimate the emotions of tourists and determine the priority of multilingual support based on the estimated emotions. The multilingual support unit estimates the emotions of tourists using generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The multilingual support unit provides rapid multilingual support if the tourist is excited. The multilingual support unit can also provide detailed multilingual support if the tourist is relaxed. The multilingual support unit can also provide concise multilingual support if the tourist is tired. This allows for more appropriate guidance by determining the priority of multilingual support according to the emotions of tourists. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input tourist emotion data into the generative AI and have the generative AI perform the determination of the priority of multilingual support.

[0086] The multilingual support unit can select the optimal language when providing multilingual support, taking into account the language settings of the tourist's device. For example, the multilingual support unit selects the optimal language when providing multilingual support, taking into account the language settings of the tourist's device. The multilingual support unit uses generative AI to evaluate the language settings of the tourist's device. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the multilingual support unit automatically sets the language of guidance and responses based on the language settings of the tourist's device. If the tourist uses multiple languages, the multilingual support unit can also prioritize the language settings of the device. If the tourist selects a specific language, the multilingual support unit can provide guidance and responses in that language. This allows for more appropriate guidance by selecting the optimal language based on the device's language settings. Some or all of the above processing in the multilingual support unit may be performed using AI, or not. For example, the multilingual support unit can input the language setting data of the tourist's device into the generative AI and have the generative AI select the optimal language.

[0087] The multilingual support unit can perform translations by referencing language versions of anime and manga relevant to the tourist during multilingual support. For example, the multilingual support unit can perform translations by referencing language versions of anime and manga relevant to the tourist during multilingual support. The multilingual support unit analyzes the tourist's viewing history using generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the multilingual support unit performs translations based on language versions of anime watched by the tourist. The multilingual support unit can also perform translations based on language versions of manga read by the tourist. The multilingual support unit can also perform translations by combining language versions of anime and manga watched by the tourist. This allows for more appropriate translations by referencing language versions of relevant anime and manga. Some or all of the above processing in the multilingual support unit may be performed using AI, for example, or without AI. For example, the multilingual support unit can input the tourist's viewing history data into the generative AI and have the generative AI perform the translation. === Hard Collateral 1-1 === Each of the multiple elements described above, including the acquisition unit, generation unit, response unit, and multilingual support unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the acquisition unit acquires the tourist's location information using the GPS function of the smart device 14. The generation unit generates a character using a generation AI via the specific processing unit 290 of the data processing unit 12. The response unit responds to the tourist's questions via the control unit 46A of the smart device 14. The multilingual support unit provides guidance and responses in multiple languages ​​via the specific processing unit 290 of the data processing unit 12. === Hard Collateral 1-2 === Each of the multiple elements described above, including the acquisition unit, generation unit, response unit, and multilingual support unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit acquires the tourist's location information using the GPS function of the smart glasses 214. The generation unit generates a character using a generation AI via the specific processing unit 290 of the data processing unit 12. The response unit responds to the tourist's questions via the control unit 46A of the smart glasses 214. The multilingual support unit provides guidance and responses in multiple languages ​​via the specific processing unit 290 of the data processing unit 12. === Hard Collateral 1-3 === Each of the multiple elements described above, including the acquisition unit, generation unit, response unit, and multilingual support unit, is implemented, for example, in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit acquires the tourist's location information using the GPS function of the headset terminal 314. The generation unit generates a character using a generation AI via the specific processing unit 290 of the data processing unit 12. The response unit responds to the tourist's questions via the control unit 46A of the headset terminal 314. The multilingual support unit provides guidance and responses in multiple languages ​​via the specific processing unit 290 of the data processing unit 12. === Hard Collateral 1-4 === Each of the multiple elements described above, including the acquisition unit, generation unit, response unit, and multilingual support unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit acquires the location information of tourists using the GPS function of the robot 414. The generation unit generates characters using a generation AI by the specific processing unit 290 of the data processing unit 12. The response unit responds to the tourists' questions by the control unit 46A of the robot 414. The multilingual support unit provides guidance and responses in multiple languages ​​by the specific processing unit 290 of the data processing unit 12.

[0088] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0089] The acquisition unit can acquire not only location information from tourists' devices but also health data from tourists. For example, it can acquire data such as the tourist's heart rate, steps taken, and body temperature, and adjust the sightseeing route based on this data. If the tourist is tired, it can suggest rest stops. Conversely, if the tourist is in good health, it can suggest a more active sightseeing route. This allows for the provision of an optimal sightseeing experience tailored to the tourist's health condition.

[0090] The generation unit can consider a tourist's past visit history when generating characters based on their current location. For example, it can prioritize generating characters related to places the tourist has visited in the past. Furthermore, if a tourist prefers a particular character, that character can be displayed more frequently. It can also suggest new, relevant characters based on information about places the tourist has visited in the past. This enables personalized character generation based on the tourist's past visit history.

[0091] The response unit can consider the tourist's current interests and preferences when generating responses to their questions. For example, if a tourist is interested in anime, it can prioritize providing anime-related information. If a tourist is interested in history, it can provide detailed historical information. Furthermore, if a tourist is interested in food, it can provide information about local restaurants and specialty dishes. This enables responses tailored to the tourist's interests and preferences.

[0092] The multilingual support section can adjust the level of detail in translations according to the tourist's language proficiency. For example, if the tourist speaks the language fluently, a detailed translation can be provided. If the tourist has basic language skills, a concise translation can be provided. Furthermore, if the tourist has beginner-level language skills, a translation using simple expressions can be provided. This ensures that the optimal translation is tailored to the tourist's language proficiency.

[0093] The acquisition unit can adjust the frequency of location information acquisition considering the battery level of the tourist's device. For example, if the device's battery level is low, the frequency of location information acquisition can be reduced to conserve battery power. Conversely, if the device's battery level is sufficient, location information can be acquired frequently to provide detailed guidance. Furthermore, if the device's battery level is moderate, a balance can be struck between battery consumption and the frequency of location information acquisition. This enables optimal guidance tailored to the device's battery level.

[0094] The acquisition unit can estimate the tourist's emotions and adjust the timing of location information acquisition based on the estimated emotions. For example, if the tourist is excited, location information can be acquired more frequently to enhance real-time guidance. Conversely, if the tourist is relaxed, the frequency of location information acquisition can be reduced to conserve battery power. Furthermore, if the tourist is tired, location information can be acquired at longer intervals to minimize information acquisition during rest periods. This enables optimal guidance tailored to the tourist's emotions.

[0095] The generation unit can estimate the emotions of tourists and adjust the character's expression based on those estimated emotions. For example, if a tourist is excited, the character's facial expressions and movements can be made more lively. If a tourist is relaxed, the character's facial expressions and movements can be made calmer. Furthermore, if a tourist is tired, the character's facial expressions and movements can be made more subdued. This makes it possible to express the character in a way that matches the tourist's emotions.

[0096] The response unit can estimate the tourist's emotions and adjust the expression of its response based on those emotions. For example, if the tourist is excited, the response can be lively and energetic. If the tourist is relaxed, the response can be calm and composed. Furthermore, if the tourist is tired, the response can be reserved and concise. This allows for a response style that is appropriate to the tourist's emotions.

[0097] The multilingual support unit can estimate the emotions of tourists and adjust the multilingual expressions based on those estimates. For example, if a tourist is excited, it can provide lively and energetic expressions. If a tourist is relaxed, it can provide calm and soothing expressions. Furthermore, if a tourist is tired, it can provide restrained and concise expressions. This enables multilingual expressions that are tailored to the emotions of tourists.

[0098] The response unit can estimate the tourist's emotions and adjust the length of the response based on the estimated emotions. For example, if the tourist is excited, the response can be shortened to get straight to the point. If the tourist is relaxed, the response can be lengthened to provide more detailed information. Furthermore, if the tourist is tired, the response can be shortened to be concise. This allows for response lengths that are appropriate to the tourist's emotions.

[0099] The following briefly describes the processing flow for example form 2.

[0100] Step 1: The acquisition unit acquires the tourist's location information. This tourist location information includes GPS, Wi-Fi, beacons, etc. For example, GPS information can be acquired from the tourist's device. Step 2: The generation unit uses a generation AI to generate anime or manga characters based on the location information acquired by the acquisition unit. For example, it generates characters based on the current location of tourists. The generation AI includes text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The response unit uses characters generated by the generation unit to respond to tourists' questions. For example, the generation AI analyzes the tourist's question and generates an appropriate answer. Processing in the response unit may or may not be performed using AI. Step 4: The multilingual support unit provides information in multiple languages, including the language selected by the response unit. For example, it provides guidance and responses in the language chosen by the tourist.

[0101] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0102] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0103] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0104] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0105] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0106] As shown in Figure 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.

[0107] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0108] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0109] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0111] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0112] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0113] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0114] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0115] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0117] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0119] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0120] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0121] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0122] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

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

[0124] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0127] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0128] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0129] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0130] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0131] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0135] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

[0137] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0138] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

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

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0145] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0146] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0147] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0148] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0150] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, 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 specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0152] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0153] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0154] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0155] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0156] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0157] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0158] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0159] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0160] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0161] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0162] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0163] 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.

[0164] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0165] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0166] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0167] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0168] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0169] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0170] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0171] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0172] [Explanation of Symbols]

[0173] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A unit that acquires the location information of tourists, A generation unit generates a character based on the position information acquired by the acquisition unit, The character generated by the generation unit responds to questions from tourists, The system includes a multilingual support unit that provides information provided by the response unit in multiple languages. A system characterized by the following features.

2. The acquisition unit is, Obtain GPS information from tourists' devices. The system according to feature 1.

3. The generating unit is Generate anime and manga characters based on the tourist's current location. The system according to feature 1.

4. The response unit is The system analyzes questions from tourists, and a generative AI generates answers. The system according to feature 1.

5. The aforementioned multilingual support unit is The system provides guidance and responses in the language selected by the tourist. The system according to feature 1.

6. The acquisition unit is, The system estimates the status of tourists and adjusts the timing of location data acquisition based on the estimated status of tourists. The system according to feature 1.

7. The acquisition unit is, Analyze tourists' past visit history to select a method for acquiring location information. The system according to feature 1.

8. The acquisition unit is, When acquiring location information, filtering is performed based on the tourist's current interests and concerns. The system according to feature 1.

9. The acquisition unit is, The system estimates the sentiment of tourists and prioritizes the location information to be acquired based on the estimated sentiment. The system according to feature 1.

10. The acquisition unit is, When acquiring location information, the acquisition method is selected considering the remaining battery level of the tourist's device. The system according to feature 1.

Images