System

Abstract

An object of a system according to an embodiment is to provide rich content using a generation AI model customized for each business operator.SOLUTION: A system includes a generation AI model creation unit, a customization unit, and a rich content provision unit. The generated AI model creation unit creates a generated AI model. The customization unit customizes the generated AI model created by the generated AI model creation unit for each business operator. The rich content providing unit provides rich content of at least one of a video or an image using the generation AI model customized by the customization unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies are not sufficient for creating generative AI models customized for each business and providing rich content, and there is room for improvement.

[0005] The system according to the embodiment aims to provide rich content using a generative AI model customized for each business operator. [Means for solving the problem]

[0006] A system according to an embodiment includes a generative AI model creation unit, a customization unit, and a rich content providing unit. The generative AI model creation unit creates a generative AI model. The customization unit customizes the generative AI model created by the generative AI model creation unit for each business operator. The rich content providing unit provides at least one rich content of video or image using the generative AI model customized by the customization unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide rich content using a generative AI model customized for each business operator. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The tourism industry automation system according to an embodiment of the present invention uses generative AI to achieve multilingual support and automate customer service in the tourism industry. This tourism industry automation system customizes the generative AI for each business, enabling it to respond to tourists from Europe, the United States, Asia, and other countries without bothering employees. This allows the tourism industry automation system to improve labor productivity and increase customer satisfaction by providing explanations using rich content such as videos and images.

[0029] A tourism industry automation system according to an embodiment includes a generative AI model creation unit, a customization unit, and a rich content provision unit. The generative AI model creation unit creates a generative AI model. For example, the generative AI model creation unit creates a text generation model. The generative AI model creation unit can also create an image generation model. The generative AI model creation unit can also create a voice generation model. The customization unit customizes the generative AI model created by the generative AI model creation unit for each business operator. For example, the customization unit adjusts parameters according to the needs of the business operator. The customization unit can also add specific functions. The customization unit can also create a generative AI model that includes information about specific tourist destinations and facilities. The rich content provision unit provides at least one rich content of videos or images using the generative AI model customized by the customization unit. For example, the rich content provision unit provides a video introducing a tourist destination. The rich content provision unit can also provide maps and photos. The rich content provision unit can also provide interactive content. As a result, the tourism industry automation system according to the embodiment uses a generation AI to achieve multilingual support and automate customer service in the tourism industry, thereby improving labor productivity and customer satisfaction. For example, when a tourist asks for information about a tourist spot, the generation AI automatically generates an answer and provides it to the tourist. This allows employees to focus on other tasks. In addition, the generation AI provides introductory videos, maps, photos, etc. of tourist spots, allowing tourists to get a more concrete image of the spot.

[0030] The generative AI model creation unit can learn regional slang and dialects to achieve more natural conversations. For example, the generative AI model creation unit can learn regional slang and dialects to make conversations with tourists more natural. For example, New York-specific slang is used for tourists in New York. The generative AI model creation unit also learns regional linguistic expressions to provide tourists with conversations that are familiar to them. For example, Kansai dialect is used for tourists in the Kansai region. The generative AI model creation unit also uses a generative AI model that has learned slang and dialects to facilitate communication with tourists. For example, London-specific expressions are used for tourists in London. In this way, by learning regional slang and dialects, conversations with tourists can be made more natural.

[0031] The generative AI model creation unit can learn the tourist's past question history and provide answers that meet individual needs. The generative AI model creation unit, for example, provides answers that meet individual needs by learning the tourist's past question history. For example, a tourist who has previously asked about restaurant information can be provided with the latest restaurant information. The generative AI model creation unit also provides information that meets the tourist's interests and concerns based on the question history. For example, a tourist who has previously shown interest in historical tourist spots can be provided with related new tourist spot information. The generative AI model creation unit also provides more personalized services using a generative AI model that has learned the tourist's question history. For example, a tourist who has previously asked about shopping information can be suggested the latest shopping spots. In this way, by learning the tourist's past question history, it is possible to provide answers that meet individual needs.

[0032] The generative AI model creation unit can also be applied to service industries other than the tourism industry to achieve multilingual support. For example, the generative AI model creation unit applies the generative AI model to a restaurant to provide multilingual menu descriptions. For example, menu details are explained in English, Chinese, and Japanese. The generative AI model creation unit also introduces the generative AI model to a retail store to provide multilingual product descriptions. For example, product features are explained in French, Spanish, and German. The generative AI model creation unit also applies the generative AI model to the hotel industry to provide multilingual check-in and check-out procedures. For example, the procedures are explained in Italian, Korean, and Russian. This allows multilingual support to be achieved by applying the generative AI model to service industries other than the tourism industry.

[0033] The generative AI model creation unit can automate reservations or ticket purchases for tourist attractions. The generative AI model creation unit, for example, automates the reservation procedure for tourist attractions. For example, when a tourist enters the desired date and time and number of people, the generative AI automatically completes the reservation. The generative AI model creation unit also automates the ticket purchase procedure using the generative AI model and provides multilingual guidance to tourists. For example, it provides guidance on the ticket purchase procedure in English, French, and Chinese. The generative AI model creation unit also centrally manages reservations and ticket purchases for tourist attractions using the generative AI model, providing tourists with prompt service. For example, it automatically purchases tickets for the tourist attraction desired by the tourist and sends a confirmation email. In this way, automating reservations and ticket purchases for tourist attractions makes it possible to provide tourists with prompt service.

[0034] The generative AI model creation unit can analyze tourist behavior patterns and propose optimal sightseeing routes. For example, the generative AI in the generative AI model creation unit analyzes tourist behavior patterns and proposes optimal sightseeing routes. For example, it generates efficient sightseeing routes based on tourists' interests and length of stay. The generative AI model creation unit also builds a system that proposes optimal sightseeing routes based on tourists' past behavior data. For example, it analyzes the places tourists have visited and the length of their stay and proposes the next place they should visit. The generative AI in the generative AI model creation unit also monitors tourist behavior in real time and dynamically adjusts the optimal sightseeing route. For example, it changes the route taking into account the congestion situation at tourist spots and weather information. This allows the system to propose optimal sightseeing routes by analyzing tourist behavior patterns, thereby reducing the burden on employees.

[0035] The generative AI model creation unit can collect tourist feedback in real time and automatically suggest improvements to services. The generative AI model creation unit, for example, builds a system in which the generative AI collects tourist feedback in real time and automatically suggests improvements to services. For example, it analyzes tourist ratings and comments and identifies areas for improvement. The generative AI model creation unit also uses the generative AI to make service improvement suggestions based on tourist feedback data. For example, it analyzes points of dissatisfaction that tourists have and proposes specific improvement measures. The generative AI model creation unit also uses the generative AI to automatically suggest improvements to services based on feedback collected in real time. For example, it proposes new services that reflect tourist opinions. In this way, the quality of services can be improved by collecting tourist feedback in real time and automatically suggesting improvements to services.

[0036] The generative AI model creation unit can automate the management of tourists' luggage and the tracking of lost items. For example, the generative AI model creation unit uses generative AI to build a system that automates the management of tourists' luggage. For example, it tracks the location information of luggage in real time and notifies tourists. The generative AI model creation unit also automates the tracking of lost items using generative AI, providing tourists with a quick response. For example, when the characteristics of a lost item are entered, the generative AI automatically starts tracking. The generative AI model creation unit also centrally manages luggage management and tracking of lost items using generative AI, providing tourists with a sense of security. For example, if luggage is lost, it automatically issues an alert and starts tracking. In this way, automating the management of tourists' luggage and the tracking of lost items can provide tourists with a sense of security.

[0037] The generative AI model creation unit can monitor the health status of tourists and provide them with necessary medical information. For example, the generative AI model creation unit uses a generative AI to build a system that monitors the health status of tourists in real time. For example, it measures the tourist's body temperature and heart rate and notifies them if any abnormalities are found. The generative AI model creation unit also monitors the health status and provides the necessary medical information via the generative AI. For example, if a tourist complains of feeling unwell, it guides the tourist to nearby medical facilities. The generative AI model creation unit also analyzes the tourist's health data and provides preventive medical information. For example, if a tourist is tired, it sends a message encouraging them to take a break. In this way, the safety of tourists can be ensured by monitoring their health status and providing them with the necessary medical information.

[0038] The rich content providing unit can analyze tourists' interests and provide individually customized rich content. For example, the generation AI in the rich content providing unit analyzes tourists' interests and provides individually customized rich content. For example, a tourist who is interested in history is provided with a video introducing historical tourist spots. The rich content providing unit also builds a system that generates rich content according to the interests of tourists based on the tourists' past behavior data. For example, a tourist who has previously visited an art museum is provided with a video introducing the museum. The rich content providing unit also monitors tourists' interests in real time using the generation AI and provides individually customized rich content. For example, if a tourist shows interest in nature, a video of natural scenery is provided. In this way, by analyzing tourists' interests and providing individually customized rich content, tourist satisfaction can be increased.

[0039] The rich content providing unit can provide rich content related to the current location based on the tourist's real-time location information. In the rich content providing unit, for example, a generation AI analyzes the tourist's real-time location information and provides rich content related to the current location. For example, if the tourist is at a specific tourist spot, a video introducing the tourist spot is provided. The rich content providing unit also builds a system in which a generation AI generates related rich content based on the tourist's location information. For example, if the tourist is at a museum, a video introducing the exhibits is provided. The rich content providing unit also monitors the tourist's location information in real time and provides rich content related to the current location. For example, if the tourist is at a park, a video introducing the park's history and highlights is provided. In this way, tourist satisfaction can be increased by providing rich content related to the current location based on the tourist's real-time location information.

[0040] The rich content providing unit can automatically generate and provide rich content related to the history or culture of a tourist destination. The rich content providing unit, for example, uses a generation AI to build a system that automatically generates rich content related to the history or culture of a tourist destination. For example, it generates videos introducing the historical background of a tourist destination. The rich content providing unit also automatically generates rich content related to the culture of a tourist destination using the generation AI and provides it to tourists. For example, it generates videos introducing traditional festivals and events. The rich content providing unit also uses the generation AI to analyze information related to the history and culture of a tourist destination and automatically generate rich content. For example, it generates videos introducing important events and people at the tourist destination. In this way, the automatic generation and provision of rich content related to the history and culture of a tourist destination can deepen tourists' understanding.

[0041] The rich content providing unit can analyze photos and videos taken by tourists and suggest related rich content. The rich content providing unit, for example, builds a system in which a generation AI analyzes photos and videos taken by tourists and suggests related rich content. For example, a video introducing the history and highlights of a location is provided based on photos taken by tourists. The rich content providing unit also analyzes photos and videos taken by tourists and a generation AI generates related rich content. For example, a video providing detailed information about buildings photographed by tourists is generated. The rich content providing unit also analyzes photos and videos taken by tourists in real time and suggests related rich content. For example, a video introducing the natural environment, flora and fauna of a location is provided based on scenery photographed by tourists. In this way, tourist satisfaction can be increased by analyzing photos and videos taken by tourists and suggesting related rich content.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The tourism automation system can further include a health management unit that monitors the health status of tourists. For example, it can measure a tourist's body temperature and heart rate in real time, and if an abnormality is detected, it can guide the tourist to a nearby medical facility. The health management unit can also provide preventive advice based on the tourist's health data. For example, if a tourist appears tired, it can send a message encouraging them to take a break. The health management unit can also build a system that monitors the tourist's health status and provides necessary medical information. This makes it possible to ensure the safety of tourists by monitoring their health status and providing them with necessary medical information.

[0044] The tourism industry automation system can further include a behavior analysis unit that analyzes tourist behavior patterns. For example, it can propose optimal sightseeing routes based on the tourist's interests and length of stay. The behavior analysis unit can also suggest the next place to visit based on the tourist's past behavior data. For example, it can analyze the places the tourist has visited and the length of their stay and suggest the next tourist spot to visit. The behavior analysis unit can also monitor tourist behavior in real time and dynamically adjust routes taking into account the congestion situation at tourist spots and weather information. In this way, by analyzing tourist behavior patterns, it is possible to propose optimal sightseeing routes and increase tourist satisfaction.

[0045] The tourism industry automation system can further include a feedback collection unit that collects tourist feedback in real time. For example, it can analyze tourist ratings and comments to identify areas for improvement in the service. The feedback collection unit can also make suggestions for service improvements based on tourist feedback data. For example, it can analyze areas where tourists are dissatisfied and propose specific measures for improvement. The feedback collection unit can also propose new services based on the feedback collected in real time. In this way, the quality of services can be improved by collecting tourist feedback in real time and automatically proposing areas for service improvement.

[0046] The tourism industry automation system can further include a luggage management unit that automates the management of tourists' luggage and the tracking of lost items. For example, the location information of luggage can be tracked in real time and notified to tourists. The luggage management unit can also automate the tracking of lost items to provide tourists with a quick response. For example, when the characteristics of the lost item are entered, the system automatically starts tracking. The luggage management unit can also automatically issue an alert and start tracking when luggage is lost. In this way, automating the management of tourists' luggage and the tracking of lost items can provide tourists with a sense of security.

[0047] The tourism industry automation system can further include a location information interlocking unit that provides rich content related to a tourist's current location based on the tourist's real-time location information. For example, the generation AI analyzes the tourist's real-time location information and provides rich content related to the tourist's current location. For example, if the tourist is at a specific tourist attraction, a video introducing the tourist attraction is provided. The location information interlocking unit can also be used to construct a system in which the generation AI generates related rich content based on the tourist's location information. For example, if the tourist is at a museum, a video introducing the exhibits is provided. The location information interlocking unit can also enable the generation AI to monitor the tourist's location information in real time and provide rich content related to the tourist's current location. This can increase tourist satisfaction by providing rich content related to the tourist's current location based on the tourist's real-time location information.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The generative AI model creation unit creates a generative AI model. For example, the generative AI model creation unit can create a text generation model, an image generation model, or a voice generation model. Step 2: The customization unit customizes the generative AI model created by the generative AI model creation unit for each business. For example, the customization unit can adjust parameters according to the needs of the business, add specific functions, or create a generative AI model that includes information on specific tourist spots and facilities. Step 3: The rich content providing unit provides at least one rich content of a video or an image using the generative AI model customized by the customization unit. For example, the rich content providing unit can provide an introductory video, map, photo, or interactive content of a tourist attraction.

[0050] (Example 2) The tourism industry automation system according to an embodiment of the present invention uses generative AI to achieve multilingual support and automate customer service in the tourism industry. This tourism industry automation system customizes the generative AI for each business, enabling it to respond to tourists from Europe, the United States, Asia, and other countries without bothering employees. This allows the tourism industry automation system to improve labor productivity and increase customer satisfaction by providing explanations using rich content such as videos and images.

[0051] A tourism industry automation system according to an embodiment includes a generative AI model creation unit, a customization unit, and a rich content provision unit. The generative AI model creation unit creates a generative AI model. For example, the generative AI model creation unit creates a text generation model. The generative AI model creation unit can also create an image generation model. The generative AI model creation unit can also create a voice generation model. The customization unit customizes the generative AI model created by the generative AI model creation unit for each business operator. For example, the customization unit adjusts parameters according to the needs of the business operator. The customization unit can also add specific functions. The customization unit can also create a generative AI model that includes information about specific tourist destinations and facilities. The rich content provision unit provides at least one rich content of videos or images using the generative AI model customized by the customization unit. For example, the rich content provision unit provides a video introducing a tourist destination. The rich content provision unit can also provide maps and photos. The rich content provision unit can also provide interactive content. As a result, the tourism industry automation system according to the embodiment uses a generation AI to achieve multilingual support and automate customer service in the tourism industry, thereby improving labor productivity and customer satisfaction. For example, when a tourist asks for information about a tourist spot, the generation AI automatically generates an answer and provides it to the tourist. This allows employees to focus on other tasks. In addition, the generation AI provides introductory videos, maps, photos, etc. of tourist spots, allowing tourists to get a more concrete image of the spot.

[0052] The generative AI model creation unit can estimate the emotions of tourists and generate optimal language expressions corresponding to those emotions. The generative AI model creation unit, for example, incorporates an emotion estimation function and analyzes the emotional state of tourists in real time. For example, if a tourist is excited, it generates more casual and friendly language expressions. The generative AI model creation unit also uses the emotion estimation function to select language expressions corresponding to the tourist's emotions. For example, if a tourist is feeling anxious, it generates polite language expressions that give a sense of security. The generative AI model creation unit also builds a system that generates optimal language expressions based on tourist emotion data. For example, if a tourist is happy, it generates expressions that make use of positive words. This makes it possible to increase customer satisfaction by generating optimal language expressions corresponding to the tourist's emotions.

[0053] The generative AI model creation unit can learn regional slang and dialects to achieve more natural conversations. For example, the generative AI model creation unit can learn regional slang and dialects to make conversations with tourists more natural. For example, New York-specific slang is used for tourists in New York. The generative AI model creation unit also learns regional linguistic expressions to provide tourists with conversations that are familiar to them. For example, Kansai dialect is used for tourists in the Kansai region. The generative AI model creation unit also uses a generative AI model that has learned slang and dialects to facilitate communication with tourists. For example, London-specific expressions are used for tourists in London. In this way, by learning regional slang and dialects, conversations with tourists can be made more natural.

[0054] The generative AI model creation unit can learn the tourist's past question history and provide answers that meet individual needs. The generative AI model creation unit, for example, provides answers that meet individual needs by learning the tourist's past question history. For example, a tourist who has previously asked about restaurant information can be provided with the latest restaurant information. The generative AI model creation unit also provides information that meets the tourist's interests and concerns based on the question history. For example, a tourist who has previously shown interest in historical tourist spots can be provided with related new tourist spot information. The generative AI model creation unit also provides more personalized services using a generative AI model that has learned the tourist's question history. For example, a tourist who has previously asked about shopping information can be suggested the latest shopping spots. In this way, by learning the tourist's past question history, it is possible to provide answers that meet individual needs.

[0055] The generative AI model creation unit can also be applied to service industries other than the tourism industry to achieve multilingual support. For example, the generative AI model creation unit applies the generative AI model to a restaurant to provide multilingual menu descriptions. For example, menu details are explained in English, Chinese, and Japanese. The generative AI model creation unit also introduces the generative AI model to a retail store to provide multilingual product descriptions. For example, product features are explained in French, Spanish, and German. The generative AI model creation unit also applies the generative AI model to the hotel industry to provide multilingual check-in and check-out procedures. For example, the procedures are explained in Italian, Korean, and Russian. This allows multilingual support to be achieved by applying the generative AI model to service industries other than the tourism industry.

[0056] The generative AI model creation unit can automate reservations or ticket purchases for tourist attractions. The generative AI model creation unit, for example, automates the reservation procedure for tourist attractions. For example, when a tourist enters the desired date and time and number of people, the generative AI automatically completes the reservation. The generative AI model creation unit also automates the ticket purchase procedure using the generative AI model and provides multilingual guidance to tourists. For example, it provides guidance on the ticket purchase procedure in English, French, and Chinese. The generative AI model creation unit also centrally manages reservations and ticket purchases for tourist attractions using the generative AI model, providing tourists with prompt service. For example, it automatically purchases tickets for the tourist attraction desired by the tourist and sends a confirmation email. In this way, automating reservations and ticket purchases for tourist attractions makes it possible to provide tourists with prompt service.

[0057] The generative AI model creation unit can propose sightseeing plans that correspond to the tourist's emotions. For example, the generative AI model creation unit uses an emotion estimation function to analyze the tourist's emotional state and propose the optimal sightseeing plan. For example, if the tourist wants to relax, it will propose quiet tourist spots. The generative AI model creation unit also generates sightseeing plans that correspond to the tourist's emotions based on the tourist's emotional data. For example, if the tourist is excited, it will propose active tourist spots. The generative AI model creation unit also uses the emotion estimation function to propose sightseeing plans that correspond to the tourist's emotions in real time. For example, if the tourist is tired, it will propose tourist spots where they can relax. In this way, by proposing sightseeing plans that correspond to the tourist's emotions, customer satisfaction can be increased.

[0058] The generative AI model creation unit can estimate the emotions of tourists and suggest relaxation methods according to their emotions. For example, the generative AI model creation unit analyzes the emotions of tourists in real time and suggests relaxation methods to reduce stress. For example, if a tourist is nervous, it suggests deep breathing or meditation. The generative AI model creation unit also suggests customized relaxation methods based on the tourist's emotional data. For example, if a tourist is tired, it suggests a massage or hot spring. The generative AI model creation unit also uses the emotion estimation function to measure the tourist's stress level and suggest appropriate relaxation methods. For example, if a tourist is feeling anxious, it suggests relaxing music. In this way, by suggesting relaxation methods according to the tourist's emotions, it is possible to reduce the tourist's stress.

[0059] The generative AI model creation unit can analyze tourist behavior patterns and propose optimal sightseeing routes. For example, the generative AI in the generative AI model creation unit analyzes tourist behavior patterns and proposes optimal sightseeing routes. For example, it generates efficient sightseeing routes based on tourists' interests and length of stay. The generative AI model creation unit also builds a system that proposes optimal sightseeing routes based on tourists' past behavior data. For example, it analyzes the places tourists have visited and the length of their stay and proposes the next place they should visit. The generative AI in the generative AI model creation unit also monitors tourist behavior in real time and dynamically adjusts the optimal sightseeing route. For example, it changes the route taking into account the congestion situation at tourist spots and weather information. This allows the system to propose optimal sightseeing routes by analyzing tourist behavior patterns, thereby reducing the burden on employees.

[0060] The generative AI model creation unit can collect tourist feedback in real time and automatically suggest improvements to services. The generative AI model creation unit, for example, builds a system in which the generative AI collects tourist feedback in real time and automatically suggests improvements to services. For example, it analyzes tourist ratings and comments and identifies areas for improvement. The generative AI model creation unit also uses the generative AI to make service improvement suggestions based on tourist feedback data. For example, it analyzes points of dissatisfaction that tourists have and proposes specific improvement measures. The generative AI model creation unit also uses the generative AI to automatically suggest improvements to services based on feedback collected in real time. For example, it proposes new services that reflect tourist opinions. In this way, the quality of services can be improved by collecting tourist feedback in real time and automatically suggesting improvements to services.

[0061] The generative AI model creation unit can automate the management of tourists' luggage and the tracking of lost items. For example, the generative AI model creation unit uses generative AI to build a system that automates the management of tourists' luggage. For example, it tracks the location information of luggage in real time and notifies tourists. The generative AI model creation unit also automates the tracking of lost items using generative AI, providing tourists with a quick response. For example, when the characteristics of a lost item are entered, the generative AI automatically starts tracking. The generative AI model creation unit also centrally manages luggage management and tracking of lost items using generative AI, providing tourists with a sense of security. For example, if luggage is lost, it automatically issues an alert and starts tracking. In this way, automating the management of tourists' luggage and the tracking of lost items can provide tourists with a sense of security.

[0062] The generative AI model creation unit can monitor the health status of tourists and provide them with necessary medical information. For example, the generative AI model creation unit uses a generative AI to build a system that monitors the health status of tourists in real time. For example, it measures the tourist's body temperature and heart rate and notifies them if any abnormalities are found. The generative AI model creation unit also monitors the health status and provides the necessary medical information via the generative AI. For example, if a tourist complains of feeling unwell, it guides the tourist to nearby medical facilities. The generative AI model creation unit also analyzes the tourist's health data and provides preventive medical information. For example, if a tourist is tired, it sends a message encouraging them to take a break. In this way, the safety of tourists can be ensured by monitoring their health status and providing them with the necessary medical information.

[0063] The generative AI model creation unit can suggest refreshment spots according to the tourist's emotions. For example, the generative AI model creation unit uses an emotion estimation function to analyze the tourist's emotional state and suggest the most suitable refreshment spot. For example, if the tourist is tired, it will suggest a quiet park. The generative AI model creation unit also customizes and suggests refreshment spots based on the tourist's emotional data. For example, if the tourist is feeling stressed, it will suggest a relaxing cafe. The generative AI model creation unit also uses the emotion estimation function to suggest refreshment spots that match the tourist's emotions in real time. For example, if the tourist is excited, it will suggest an active attraction. In this way, by suggesting refreshment spots that match the tourist's emotions, it is possible to increase tourist satisfaction.

[0064] The rich content providing unit can estimate the emotions of tourists and provide rich content that corresponds to their emotions. For example, the rich content providing unit uses a generation AI to analyze the emotions of tourists in real time and provide rich content that corresponds to their emotions. For example, if a tourist wants to relax, a quiet landscape video is provided. The rich content providing unit also customizes and provides rich content based on the tourist's emotion data. For example, if a tourist is excited, a video of an active attraction is provided. The rich content providing unit also uses the emotion estimation function to provide rich content that matches the tourist's emotions in real time. For example, if a tourist is tired, relaxing music is provided. In this way, by providing rich content that corresponds to the tourist's emotions, tourist satisfaction can be increased.

[0065] The rich content providing unit can analyze tourists' interests and provide individually customized rich content. For example, the generation AI in the rich content providing unit analyzes tourists' interests and provides individually customized rich content. For example, a tourist who is interested in history is provided with a video introducing historical tourist spots. The rich content providing unit also builds a system that generates rich content according to the interests of tourists based on the tourists' past behavior data. For example, a tourist who has previously visited an art museum is provided with a video introducing the museum. The rich content providing unit also monitors tourists' interests in real time using the generation AI and provides individually customized rich content. For example, if a tourist shows interest in nature, a video of natural scenery is provided. In this way, by analyzing tourists' interests and providing individually customized rich content, tourist satisfaction can be increased.

[0066] The rich content providing unit can provide rich content related to the current location based on the tourist's real-time location information. In the rich content providing unit, for example, a generation AI analyzes the tourist's real-time location information and provides rich content related to the current location. For example, if the tourist is at a specific tourist spot, a video introducing the tourist spot is provided. The rich content providing unit also builds a system in which a generation AI generates related rich content based on the tourist's location information. For example, if the tourist is at a museum, a video introducing the exhibits is provided. The rich content providing unit also monitors the tourist's location information in real time and provides rich content related to the current location. For example, if the tourist is at a park, a video introducing the park's history and highlights is provided. In this way, tourist satisfaction can be increased by providing rich content related to the current location based on the tourist's real-time location information.

[0067] The rich content providing unit can automatically generate and provide rich content related to the history or culture of a tourist destination. The rich content providing unit, for example, uses a generation AI to build a system that automatically generates rich content related to the history or culture of a tourist destination. For example, it generates videos introducing the historical background of a tourist destination. The rich content providing unit also automatically generates rich content related to the culture of a tourist destination using the generation AI and provides it to tourists. For example, it generates videos introducing traditional festivals and events. The rich content providing unit also uses the generation AI to analyze information related to the history and culture of a tourist destination and automatically generate rich content. For example, it generates videos introducing important events and people at the tourist destination. In this way, the automatic generation and provision of rich content related to the history and culture of a tourist destination can deepen tourists' understanding.

[0068] The rich content providing unit can analyze photos and videos taken by tourists and suggest related rich content. The rich content providing unit, for example, builds a system in which a generation AI analyzes photos and videos taken by tourists and suggests related rich content. For example, a video introducing the history and highlights of a location is provided based on photos taken by tourists. The rich content providing unit also analyzes photos and videos taken by tourists and a generation AI generates related rich content. For example, a video providing detailed information about buildings photographed by tourists is generated. The rich content providing unit also analyzes photos and videos taken by tourists in real time and suggests related rich content. For example, a video introducing the natural environment, flora and fauna of a location is provided based on scenery photographed by tourists. In this way, tourist satisfaction can be increased by analyzing photos and videos taken by tourists and suggesting related rich content.

[0069] The rich content providing unit can generate and provide rich content in real time according to the emotions of tourists. The rich content providing unit uses, for example, an emotion estimation function to analyze the emotional state of tourists and generate rich content in real time according to the emotions. For example, if a tourist wants to relax, it generates a quiet landscape video. The rich content providing unit also customizes rich content based on the tourist's emotion data and provides it in real time. For example, if a tourist is excited, it generates an active attraction video. The rich content providing unit also uses the emotion estimation function to build a system that generates and provides rich content in real time according to the tourist's emotions. For example, if a tourist is tired, it generates relaxing music. In this way, by generating and providing rich content in real time according to the tourist's emotions, tourist satisfaction can be increased.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The tourism automation system can further include a health management unit that monitors the health status of tourists. For example, it can measure a tourist's body temperature and heart rate in real time, and if an abnormality is detected, it can guide the tourist to a nearby medical facility. The health management unit can also provide preventive advice based on the tourist's health data. For example, if a tourist appears tired, it can send a message encouraging them to take a break. The health management unit can also build a system that monitors the tourist's health status and provides necessary medical information. This makes it possible to ensure the safety of tourists by monitoring their health status and providing them with necessary medical information.

[0072] The tourism industry automation system can further include a behavior analysis unit that analyzes tourist behavior patterns. For example, it can propose optimal sightseeing routes based on the tourist's interests and length of stay. The behavior analysis unit can also suggest the next place to visit based on the tourist's past behavior data. For example, it can analyze the places the tourist has visited and the length of their stay and suggest the next tourist spot to visit. The behavior analysis unit can also monitor tourist behavior in real time and dynamically adjust routes taking into account the congestion situation at tourist spots and weather information. In this way, by analyzing tourist behavior patterns, it is possible to propose optimal sightseeing routes and increase tourist satisfaction.

[0073] The tourism industry automation system can further include a feedback collection unit that collects tourist feedback in real time. For example, it can analyze tourist ratings and comments to identify areas for improvement in the service. The feedback collection unit can also make suggestions for service improvements based on tourist feedback data. For example, it can analyze areas where tourists are dissatisfied and propose specific measures for improvement. The feedback collection unit can also propose new services based on the feedback collected in real time. In this way, the quality of services can be improved by collecting tourist feedback in real time and automatically proposing areas for service improvement.

[0074] The tourism industry automation system can further include a luggage management unit that automates the management of tourists' luggage and the tracking of lost items. For example, the location information of luggage can be tracked in real time and notified to tourists. The luggage management unit can also automate the tracking of lost items to provide tourists with a quick response. For example, when the characteristics of the lost item are entered, the system automatically starts tracking. The luggage management unit can also automatically issue an alert and start tracking when luggage is lost. In this way, automating the management of tourists' luggage and the tracking of lost items can provide tourists with a sense of security.

[0075] The tourism industry automation system can further include a refreshment suggestion unit that suggests refreshment spots according to the tourist's emotions. For example, an emotion estimation function can be used to analyze the tourist's emotional state and suggest the most suitable refreshment spot. For example, if the tourist is tired, a quiet park can be suggested. The refreshment suggestion unit can also customize and suggest refreshment spots based on the tourist's emotional data. For example, if the tourist is feeling stressed, a relaxing cafe can be suggested. The refreshment suggestion unit can also suggest refreshment spots that match the tourist's emotions in real time. This makes it possible to increase tourist satisfaction by suggesting refreshment spots that match the tourist's emotions.

[0076] The tourism industry automation system can further include a rich content providing unit that provides rich content according to the tourist's emotions. For example, an emotion estimation function can be used to analyze the tourist's emotional state and provide rich content according to the emotion. For example, if the tourist wants to relax, a quiet landscape video can be provided. The rich content providing unit can also customize and provide rich content based on the tourist's emotional data. For example, if the tourist is excited, an active attraction video can be provided. The rich content providing unit can also provide rich content that matches the tourist's emotions in real time. This makes it possible to increase tourist satisfaction by providing rich content that matches the tourist's emotions.

[0077] The tourism industry automation system can further include a tour plan proposal unit that proposes tour plans according to the tourist's emotions. For example, an emotion estimation function can be used to analyze the tourist's emotional state and propose the optimal tour plan. For example, if the tourist wants to relax, quiet tourist destinations can be proposed. The tour plan proposal unit can also generate tour plans according to the tourist's emotions based on the tourist's emotional data. For example, if the tourist is excited, active tourist destinations can be proposed. The tour plan proposal unit can also propose tour plans according to the tourist's emotions in real time. This makes it possible to increase tourist satisfaction by proposing tour plans according to the tourist's emotions.

[0078] The tourism industry automation system can further include a relaxation suggestion unit that suggests relaxation methods according to the tourist's emotions. For example, the emotion estimation function can be used to analyze the tourist's emotional state and suggest relaxation methods to reduce stress. For example, if the tourist is nervous, deep breathing or meditation can be suggested. The relaxation suggestion unit can also suggest customized relaxation methods based on the tourist's emotional data. For example, if the tourist is tired, a massage or hot spring bath can be suggested. The relaxation suggestion unit can also measure the tourist's stress level and suggest appropriate relaxation methods. In this way, tourists' stress can be reduced by suggesting relaxation methods according to their emotions.

[0079] The tourism industry automation system can further include a rich content generation unit that generates and provides rich content in real time according to the emotions of tourists. For example, an emotion estimation function can be used to analyze the emotional state of tourists and generate rich content in real time according to their emotions. For example, if a tourist wants to relax, a quiet landscape video can be generated. The rich content generation unit can also customize rich content based on the tourist's emotional data and provide it in real time. For example, if a tourist is excited, an active attraction video can be generated. The rich content generation unit can also build a system that generates and provides rich content in real time according to the tourist's emotions. This makes it possible to increase tourist satisfaction by generating and providing rich content in real time according to the tourist's emotions.

[0080] The tourism industry automation system can further include a location information interlocking unit that provides rich content related to a tourist's current location based on the tourist's real-time location information. For example, the generation AI analyzes the tourist's real-time location information and provides rich content related to the tourist's current location. For example, if the tourist is at a specific tourist attraction, a video introducing the tourist attraction is provided. The location information interlocking unit can also be used to construct a system in which the generation AI generates related rich content based on the tourist's location information. For example, if the tourist is at a museum, a video introducing the exhibits is provided. The location information interlocking unit can also enable the generation AI to monitor the tourist's location information in real time and provide rich content related to the tourist's current location. This can increase tourist satisfaction by providing rich content related to the tourist's current location based on the tourist's real-time location information.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The generative AI model creation unit creates a generative AI model. For example, the generative AI model creation unit can create a text generation model, an image generation model, or a voice generation model. Step 2: The customization unit customizes the generative AI model created by the generative AI model creation unit for each business. For example, the customization unit can adjust parameters according to the needs of the business, add specific functions, or create a generative AI model that includes information on specific tourist spots and facilities. Step 3: The rich content providing unit provides at least one rich content of a video or an image using the generative AI model customized by the customization unit. For example, the rich content providing unit can provide an introductory video, map, photo, or interactive content of a tourist attraction.

[0083] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0089] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0090] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0093] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0094] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0097] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0111] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0124] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0133] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0134] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0135] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0136] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0137] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0138] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0139] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0140] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0141] 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.

[0142] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0143] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0144] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0145] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0146] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0147] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0148] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0149] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0150] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a generative AI model creation unit that creates a generative AI model; a customization unit that customizes the generative AI model created by the generative AI model creation unit for each business operator; a rich content providing unit that provides at least one rich content of a video or an image using the generative AI model customized by the customization unit. A system characterized by:

2. The generative AI model creation unit Estimate the tourist's emotions and generate the optimal language expression according to those emotions 2. The system of claim 1.

3. The generative AI model creation unit Learn regional slang and dialects to enable more natural conversation 2. The system of claim 1.

4. The generative AI model creation unit Learns tourists' past question history and provides answers tailored to their individual needs 2. The system of claim 1.

5. The generative AI model creation unit It can be applied to service industries other than tourism, realizing multilingual support 2. The system of claim 1.

Images